Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: omni_training_less_than_5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# omni_training_less_than_5
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the omni_training_less_than_5 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8705
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.7356        | 0.8696 | 200  | 0.8250          |
+| 0.2754        | 1.7391 | 400  | 0.8717          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.8704994916915894,
+    "eval_runtime": 1.2229,
+    "eval_samples_per_second": 15.537,
+    "eval_steps_per_second": 4.089,
+    "total_flos": 2556217393152.0,
+    "train_loss": 0.679824001374452,
+    "train_runtime": 538.1176,
+    "train_samples_per_second": 6.839,
+    "train_steps_per_second": 0.855
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.8704994916915894,
+    "eval_runtime": 1.2229,
+    "eval_samples_per_second": 15.537,
+    "eval_steps_per_second": 4.089
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d281e9de5f6675f2521c5f066062162ab0da9088a4562beefb6ab6bf6bed5815
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e7cc40a1d9ddf53cd46d8d39d13e6fc2d155f91975cfad9fe98447d41edfed
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2556217393152.0,
+    "train_loss": 0.679824001374452,
+    "train_runtime": 538.1176,
+    "train_samples_per_second": 6.839,
+    "train_steps_per_second": 0.855
+}

trainer_log.jsonl

@@ -0,0 +1,463 @@
+{"current_steps": 1, "total_steps": 460, "loss": 1.1079, "lr": 9.999883393595949e-06, "epoch": 0.004347826086956522, "percentage": 0.22, "elapsed_time": "0:00:02", "remaining_time": "0:19:09"}
+{"current_steps": 2, "total_steps": 460, "loss": 1.0206, "lr": 9.999533579822611e-06, "epoch": 0.008695652173913044, "percentage": 0.43, "elapsed_time": "0:00:05", "remaining_time": "0:20:32"}
+{"current_steps": 3, "total_steps": 460, "loss": 0.8925, "lr": 9.9989505749962e-06, "epoch": 0.013043478260869565, "percentage": 0.65, "elapsed_time": "0:00:06", "remaining_time": "0:16:28"}
+{"current_steps": 4, "total_steps": 460, "loss": 0.8343, "lr": 9.998134406309555e-06, "epoch": 0.017391304347826087, "percentage": 0.87, "elapsed_time": "0:00:07", "remaining_time": "0:14:25"}
+{"current_steps": 5, "total_steps": 460, "loss": 0.6931, "lr": 9.99708511183087e-06, "epoch": 0.021739130434782608, "percentage": 1.09, "elapsed_time": "0:00:08", "remaining_time": "0:13:18"}
+{"current_steps": 6, "total_steps": 460, "loss": 0.8249, "lr": 9.995802740501933e-06, "epoch": 0.02608695652173913, "percentage": 1.3, "elapsed_time": "0:00:09", "remaining_time": "0:12:27"}
+{"current_steps": 7, "total_steps": 460, "loss": 0.8491, "lr": 9.994287352135826e-06, "epoch": 0.030434782608695653, "percentage": 1.52, "elapsed_time": "0:00:10", "remaining_time": "0:11:49"}
+{"current_steps": 8, "total_steps": 460, "loss": 0.7867, "lr": 9.99253901741414e-06, "epoch": 0.034782608695652174, "percentage": 1.74, "elapsed_time": "0:00:12", "remaining_time": "0:11:22"}
+{"current_steps": 9, "total_steps": 460, "loss": 0.559, "lr": 9.99055781788369e-06, "epoch": 0.0391304347826087, "percentage": 1.96, "elapsed_time": "0:00:13", "remaining_time": "0:10:59"}
+{"current_steps": 10, "total_steps": 460, "loss": 0.8831, "lr": 9.988343845952697e-06, "epoch": 0.043478260869565216, "percentage": 2.17, "elapsed_time": "0:00:14", "remaining_time": "0:10:40"}
+{"current_steps": 11, "total_steps": 460, "loss": 0.7416, "lr": 9.985897204886481e-06, "epoch": 0.04782608695652174, "percentage": 2.39, "elapsed_time": "0:00:15", "remaining_time": "0:10:28"}
+{"current_steps": 12, "total_steps": 460, "loss": 0.7885, "lr": 9.983218008802648e-06, "epoch": 0.05217391304347826, "percentage": 2.61, "elapsed_time": "0:00:16", "remaining_time": "0:10:15"}
+{"current_steps": 13, "total_steps": 460, "loss": 0.8622, "lr": 9.98030638266577e-06, "epoch": 0.05652173913043478, "percentage": 2.83, "elapsed_time": "0:00:17", "remaining_time": "0:10:04"}
+{"current_steps": 14, "total_steps": 460, "loss": 0.7362, "lr": 9.977162462281544e-06, "epoch": 0.06086956521739131, "percentage": 3.04, "elapsed_time": "0:00:18", "remaining_time": "0:09:55"}
+{"current_steps": 15, "total_steps": 460, "loss": 0.7865, "lr": 9.973786394290475e-06, "epoch": 0.06521739130434782, "percentage": 3.26, "elapsed_time": "0:00:19", "remaining_time": "0:09:46"}
+{"current_steps": 16, "total_steps": 460, "loss": 0.7807, "lr": 9.970178336161018e-06, "epoch": 0.06956521739130435, "percentage": 3.48, "elapsed_time": "0:00:20", "remaining_time": "0:09:39"}
+{"current_steps": 17, "total_steps": 460, "loss": 0.945, "lr": 9.96633845618225e-06, "epoch": 0.07391304347826087, "percentage": 3.7, "elapsed_time": "0:00:21", "remaining_time": "0:09:32"}
+{"current_steps": 18, "total_steps": 460, "loss": 0.5839, "lr": 9.962266933456008e-06, "epoch": 0.0782608695652174, "percentage": 3.91, "elapsed_time": "0:00:23", "remaining_time": "0:09:28"}
+{"current_steps": 19, "total_steps": 460, "loss": 0.8982, "lr": 9.957963957888542e-06, "epoch": 0.08260869565217391, "percentage": 4.13, "elapsed_time": "0:00:24", "remaining_time": "0:09:22"}
+{"current_steps": 20, "total_steps": 460, "loss": 0.7377, "lr": 9.953429730181653e-06, "epoch": 0.08695652173913043, "percentage": 4.35, "elapsed_time": "0:00:25", "remaining_time": "0:09:17"}
+{"current_steps": 21, "total_steps": 460, "loss": 0.8799, "lr": 9.94866446182334e-06, "epoch": 0.09130434782608696, "percentage": 4.57, "elapsed_time": "0:00:26", "remaining_time": "0:09:12"}
+{"current_steps": 22, "total_steps": 460, "loss": 0.9303, "lr": 9.943668375077926e-06, "epoch": 0.09565217391304348, "percentage": 4.78, "elapsed_time": "0:00:27", "remaining_time": "0:09:07"}
+{"current_steps": 23, "total_steps": 460, "loss": 0.9712, "lr": 9.938441702975689e-06, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:00:28", "remaining_time": "0:09:03"}
+{"current_steps": 24, "total_steps": 460, "loss": 0.9881, "lr": 9.932984689302012e-06, "epoch": 0.10434782608695652, "percentage": 5.22, "elapsed_time": "0:00:29", "remaining_time": "0:08:59"}
+{"current_steps": 25, "total_steps": 460, "loss": 0.7804, "lr": 9.927297588585984e-06, "epoch": 0.10869565217391304, "percentage": 5.43, "elapsed_time": "0:00:30", "remaining_time": "0:08:55"}
+{"current_steps": 26, "total_steps": 460, "loss": 0.692, "lr": 9.921380666088558e-06, "epoch": 0.11304347826086956, "percentage": 5.65, "elapsed_time": "0:00:31", "remaining_time": "0:08:52"}
+{"current_steps": 27, "total_steps": 460, "loss": 0.9255, "lr": 9.915234197790153e-06, "epoch": 0.11739130434782609, "percentage": 5.87, "elapsed_time": "0:00:32", "remaining_time": "0:08:48"}
+{"current_steps": 28, "total_steps": 460, "loss": 0.9835, "lr": 9.908858470377793e-06, "epoch": 0.12173913043478261, "percentage": 6.09, "elapsed_time": "0:00:34", "remaining_time": "0:08:45"}
+{"current_steps": 29, "total_steps": 460, "loss": 0.6559, "lr": 9.902253781231741e-06, "epoch": 0.12608695652173912, "percentage": 6.3, "elapsed_time": "0:00:35", "remaining_time": "0:08:43"}
+{"current_steps": 30, "total_steps": 460, "loss": 0.8773, "lr": 9.895420438411616e-06, "epoch": 0.13043478260869565, "percentage": 6.52, "elapsed_time": "0:00:36", "remaining_time": "0:08:40"}
+{"current_steps": 31, "total_steps": 460, "loss": 0.763, "lr": 9.88835876064203e-06, "epoch": 0.13478260869565217, "percentage": 6.74, "elapsed_time": "0:00:37", "remaining_time": "0:08:37"}
+{"current_steps": 32, "total_steps": 460, "loss": 0.8204, "lr": 9.881069077297724e-06, "epoch": 0.1391304347826087, "percentage": 6.96, "elapsed_time": "0:00:38", "remaining_time": "0:08:36"}
+{"current_steps": 33, "total_steps": 460, "loss": 0.7933, "lr": 9.873551728388203e-06, "epoch": 0.14347826086956522, "percentage": 7.17, "elapsed_time": "0:00:39", "remaining_time": "0:08:33"}
+{"current_steps": 34, "total_steps": 460, "loss": 0.8324, "lr": 9.865807064541878e-06, "epoch": 0.14782608695652175, "percentage": 7.39, "elapsed_time": "0:00:40", "remaining_time": "0:08:30"}
+{"current_steps": 35, "total_steps": 460, "loss": 1.1247, "lr": 9.857835446989708e-06, "epoch": 0.15217391304347827, "percentage": 7.61, "elapsed_time": "0:00:41", "remaining_time": "0:08:28"}
+{"current_steps": 36, "total_steps": 460, "loss": 0.5466, "lr": 9.849637247548356e-06, "epoch": 0.1565217391304348, "percentage": 7.83, "elapsed_time": "0:00:42", "remaining_time": "0:08:26"}
+{"current_steps": 37, "total_steps": 460, "loss": 0.9061, "lr": 9.841212848602848e-06, "epoch": 0.1608695652173913, "percentage": 8.04, "elapsed_time": "0:00:44", "remaining_time": "0:08:23"}
+{"current_steps": 38, "total_steps": 460, "loss": 0.8046, "lr": 9.832562643088724e-06, "epoch": 0.16521739130434782, "percentage": 8.26, "elapsed_time": "0:00:45", "remaining_time": "0:08:21"}
+{"current_steps": 39, "total_steps": 460, "loss": 0.866, "lr": 9.823687034473734e-06, "epoch": 0.16956521739130434, "percentage": 8.48, "elapsed_time": "0:00:46", "remaining_time": "0:08:19"}
+{"current_steps": 40, "total_steps": 460, "loss": 1.0917, "lr": 9.814586436738998e-06, "epoch": 0.17391304347826086, "percentage": 8.7, "elapsed_time": "0:00:47", "remaining_time": "0:08:16"}
+{"current_steps": 41, "total_steps": 460, "loss": 0.8076, "lr": 9.805261274359705e-06, "epoch": 0.1782608695652174, "percentage": 8.91, "elapsed_time": "0:00:48", "remaining_time": "0:08:14"}
+{"current_steps": 42, "total_steps": 460, "loss": 0.8976, "lr": 9.795711982285317e-06, "epoch": 0.1826086956521739, "percentage": 9.13, "elapsed_time": "0:00:49", "remaining_time": "0:08:12"}
+{"current_steps": 43, "total_steps": 460, "loss": 0.8099, "lr": 9.785939005919279e-06, "epoch": 0.18695652173913044, "percentage": 9.35, "elapsed_time": "0:00:50", "remaining_time": "0:08:10"}
+{"current_steps": 44, "total_steps": 460, "loss": 0.7528, "lr": 9.775942801098241e-06, "epoch": 0.19130434782608696, "percentage": 9.57, "elapsed_time": "0:00:51", "remaining_time": "0:08:08"}
+{"current_steps": 45, "total_steps": 460, "loss": 0.8897, "lr": 9.765723834070805e-06, "epoch": 0.1956521739130435, "percentage": 9.78, "elapsed_time": "0:00:52", "remaining_time": "0:08:06"}
+{"current_steps": 46, "total_steps": 460, "loss": 0.6911, "lr": 9.755282581475769e-06, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:00:53", "remaining_time": "0:08:05"}
+{"current_steps": 47, "total_steps": 460, "loss": 0.9875, "lr": 9.7446195303199e-06, "epoch": 0.20434782608695654, "percentage": 10.22, "elapsed_time": "0:00:54", "remaining_time": "0:08:03"}
+{"current_steps": 48, "total_steps": 460, "loss": 0.5668, "lr": 9.733735177955219e-06, "epoch": 0.20869565217391303, "percentage": 10.43, "elapsed_time": "0:00:56", "remaining_time": "0:08:01"}
+{"current_steps": 49, "total_steps": 460, "loss": 0.8334, "lr": 9.722630032055804e-06, "epoch": 0.21304347826086956, "percentage": 10.65, "elapsed_time": "0:00:57", "remaining_time": "0:07:59"}
+{"current_steps": 50, "total_steps": 460, "loss": 0.8011, "lr": 9.711304610594104e-06, "epoch": 0.21739130434782608, "percentage": 10.87, "elapsed_time": "0:00:58", "remaining_time": "0:07:57"}
+{"current_steps": 51, "total_steps": 460, "loss": 0.6684, "lr": 9.699759441816788e-06, "epoch": 0.2217391304347826, "percentage": 11.09, "elapsed_time": "0:00:59", "remaining_time": "0:07:57"}
+{"current_steps": 52, "total_steps": 460, "loss": 0.8834, "lr": 9.687995064220102e-06, "epoch": 0.22608695652173913, "percentage": 11.3, "elapsed_time": "0:01:00", "remaining_time": "0:07:55"}
+{"current_steps": 53, "total_steps": 460, "loss": 0.6965, "lr": 9.676012026524755e-06, "epoch": 0.23043478260869565, "percentage": 11.52, "elapsed_time": "0:01:01", "remaining_time": "0:07:53"}
+{"current_steps": 54, "total_steps": 460, "loss": 0.938, "lr": 9.66381088765032e-06, "epoch": 0.23478260869565218, "percentage": 11.74, "elapsed_time": "0:01:02", "remaining_time": "0:07:51"}
+{"current_steps": 55, "total_steps": 460, "loss": 1.0933, "lr": 9.651392216689167e-06, "epoch": 0.2391304347826087, "percentage": 11.96, "elapsed_time": "0:01:03", "remaining_time": "0:07:50"}
+{"current_steps": 56, "total_steps": 460, "loss": 0.6742, "lr": 9.638756592879923e-06, "epoch": 0.24347826086956523, "percentage": 12.17, "elapsed_time": "0:01:04", "remaining_time": "0:07:48"}
+{"current_steps": 57, "total_steps": 460, "loss": 0.7107, "lr": 9.625904605580452e-06, "epoch": 0.24782608695652175, "percentage": 12.39, "elapsed_time": "0:01:06", "remaining_time": "0:07:47"}
+{"current_steps": 58, "total_steps": 460, "loss": 0.8229, "lr": 9.61283685424036e-06, "epoch": 0.25217391304347825, "percentage": 12.61, "elapsed_time": "0:01:07", "remaining_time": "0:07:45"}
+{"current_steps": 59, "total_steps": 460, "loss": 0.6858, "lr": 9.599553948373047e-06, "epoch": 0.2565217391304348, "percentage": 12.83, "elapsed_time": "0:01:08", "remaining_time": "0:07:43"}
+{"current_steps": 60, "total_steps": 460, "loss": 0.8061, "lr": 9.586056507527266e-06, "epoch": 0.2608695652173913, "percentage": 13.04, "elapsed_time": "0:01:09", "remaining_time": "0:07:42"}
+{"current_steps": 61, "total_steps": 460, "loss": 0.8282, "lr": 9.572345161258235e-06, "epoch": 0.26521739130434785, "percentage": 13.26, "elapsed_time": "0:01:10", "remaining_time": "0:07:40"}
+{"current_steps": 62, "total_steps": 460, "loss": 0.8382, "lr": 9.558420549098269e-06, "epoch": 0.26956521739130435, "percentage": 13.48, "elapsed_time": "0:01:11", "remaining_time": "0:07:39"}
+{"current_steps": 63, "total_steps": 460, "loss": 0.7024, "lr": 9.544283320526943e-06, "epoch": 0.27391304347826084, "percentage": 13.7, "elapsed_time": "0:01:12", "remaining_time": "0:07:37"}
+{"current_steps": 64, "total_steps": 460, "loss": 0.6702, "lr": 9.529934134940819e-06, "epoch": 0.2782608695652174, "percentage": 13.91, "elapsed_time": "0:01:13", "remaining_time": "0:07:36"}
+{"current_steps": 65, "total_steps": 460, "loss": 0.8201, "lr": 9.515373661622665e-06, "epoch": 0.2826086956521739, "percentage": 14.13, "elapsed_time": "0:01:14", "remaining_time": "0:07:35"}
+{"current_steps": 66, "total_steps": 460, "loss": 0.6873, "lr": 9.500602579710256e-06, "epoch": 0.28695652173913044, "percentage": 14.35, "elapsed_time": "0:01:16", "remaining_time": "0:07:33"}
+{"current_steps": 67, "total_steps": 460, "loss": 0.667, "lr": 9.48562157816469e-06, "epoch": 0.29130434782608694, "percentage": 14.57, "elapsed_time": "0:01:17", "remaining_time": "0:07:32"}
+{"current_steps": 68, "total_steps": 460, "loss": 0.8051, "lr": 9.470431355738257e-06, "epoch": 0.2956521739130435, "percentage": 14.78, "elapsed_time": "0:01:18", "remaining_time": "0:07:30"}
+{"current_steps": 69, "total_steps": 460, "loss": 1.0722, "lr": 9.45503262094184e-06, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "0:01:19", "remaining_time": "0:07:29"}
+{"current_steps": 70, "total_steps": 460, "loss": 0.7878, "lr": 9.439426092011877e-06, "epoch": 0.30434782608695654, "percentage": 15.22, "elapsed_time": "0:01:20", "remaining_time": "0:07:27"}
+{"current_steps": 71, "total_steps": 460, "loss": 0.9254, "lr": 9.423612496876856e-06, "epoch": 0.30869565217391304, "percentage": 15.43, "elapsed_time": "0:01:21", "remaining_time": "0:07:26"}
+{"current_steps": 72, "total_steps": 460, "loss": 0.6889, "lr": 9.407592573123359e-06, "epoch": 0.3130434782608696, "percentage": 15.65, "elapsed_time": "0:01:22", "remaining_time": "0:07:24"}
+{"current_steps": 73, "total_steps": 460, "loss": 0.9096, "lr": 9.39136706796167e-06, "epoch": 0.3173913043478261, "percentage": 15.87, "elapsed_time": "0:01:23", "remaining_time": "0:07:23"}
+{"current_steps": 74, "total_steps": 460, "loss": 1.0758, "lr": 9.374936738190913e-06, "epoch": 0.3217391304347826, "percentage": 16.09, "elapsed_time": "0:01:24", "remaining_time": "0:07:22"}
+{"current_steps": 75, "total_steps": 460, "loss": 0.9975, "lr": 9.358302350163758e-06, "epoch": 0.32608695652173914, "percentage": 16.3, "elapsed_time": "0:01:25", "remaining_time": "0:07:20"}
+{"current_steps": 76, "total_steps": 460, "loss": 0.815, "lr": 9.341464679750669e-06, "epoch": 0.33043478260869563, "percentage": 16.52, "elapsed_time": "0:01:26", "remaining_time": "0:07:19"}
+{"current_steps": 77, "total_steps": 460, "loss": 0.7434, "lr": 9.32442451230373e-06, "epoch": 0.3347826086956522, "percentage": 16.74, "elapsed_time": "0:01:28", "remaining_time": "0:07:17"}
+{"current_steps": 78, "total_steps": 460, "loss": 0.9034, "lr": 9.307182642620001e-06, "epoch": 0.3391304347826087, "percentage": 16.96, "elapsed_time": "0:01:29", "remaining_time": "0:07:16"}
+{"current_steps": 79, "total_steps": 460, "loss": 0.78, "lr": 9.289739874904448e-06, "epoch": 0.34347826086956523, "percentage": 17.17, "elapsed_time": "0:01:30", "remaining_time": "0:07:14"}
+{"current_steps": 80, "total_steps": 460, "loss": 0.6927, "lr": 9.272097022732444e-06, "epoch": 0.34782608695652173, "percentage": 17.39, "elapsed_time": "0:01:31", "remaining_time": "0:07:13"}
+{"current_steps": 81, "total_steps": 460, "loss": 0.6882, "lr": 9.254254909011805e-06, "epoch": 0.3521739130434783, "percentage": 17.61, "elapsed_time": "0:01:32", "remaining_time": "0:07:12"}
+{"current_steps": 82, "total_steps": 460, "loss": 0.7601, "lr": 9.236214365944418e-06, "epoch": 0.3565217391304348, "percentage": 17.83, "elapsed_time": "0:01:33", "remaining_time": "0:07:10"}
+{"current_steps": 83, "total_steps": 460, "loss": 0.8002, "lr": 9.217976234987429e-06, "epoch": 0.36086956521739133, "percentage": 18.04, "elapsed_time": "0:01:34", "remaining_time": "0:07:09"}
+{"current_steps": 84, "total_steps": 460, "loss": 0.9108, "lr": 9.199541366813984e-06, "epoch": 0.3652173913043478, "percentage": 18.26, "elapsed_time": "0:01:35", "remaining_time": "0:07:08"}
+{"current_steps": 85, "total_steps": 460, "loss": 0.9495, "lr": 9.180910621273555e-06, "epoch": 0.3695652173913043, "percentage": 18.48, "elapsed_time": "0:01:36", "remaining_time": "0:07:06"}
+{"current_steps": 86, "total_steps": 460, "loss": 0.796, "lr": 9.16208486735184e-06, "epoch": 0.3739130434782609, "percentage": 18.7, "elapsed_time": "0:01:38", "remaining_time": "0:07:07"}
+{"current_steps": 87, "total_steps": 460, "loss": 0.9202, "lr": 9.14306498313023e-06, "epoch": 0.3782608695652174, "percentage": 18.91, "elapsed_time": "0:01:39", "remaining_time": "0:07:06"}
+{"current_steps": 88, "total_steps": 460, "loss": 0.868, "lr": 9.123851855744842e-06, "epoch": 0.3826086956521739, "percentage": 19.13, "elapsed_time": "0:01:40", "remaining_time": "0:07:05"}
+{"current_steps": 89, "total_steps": 460, "loss": 0.8633, "lr": 9.10444638134516e-06, "epoch": 0.3869565217391304, "percentage": 19.35, "elapsed_time": "0:01:41", "remaining_time": "0:07:04"}
+{"current_steps": 90, "total_steps": 460, "loss": 0.4639, "lr": 9.08484946505221e-06, "epoch": 0.391304347826087, "percentage": 19.57, "elapsed_time": "0:01:42", "remaining_time": "0:07:02"}
+{"current_steps": 91, "total_steps": 460, "loss": 1.0704, "lr": 9.065062020916376e-06, "epoch": 0.39565217391304347, "percentage": 19.78, "elapsed_time": "0:01:43", "remaining_time": "0:07:01"}
+{"current_steps": 92, "total_steps": 460, "loss": 0.7493, "lr": 9.045084971874738e-06, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:01:45", "remaining_time": "0:07:00"}
+{"current_steps": 93, "total_steps": 460, "loss": 0.6936, "lr": 9.024919249708034e-06, "epoch": 0.4043478260869565, "percentage": 20.22, "elapsed_time": "0:01:46", "remaining_time": "0:06:58"}
+{"current_steps": 94, "total_steps": 460, "loss": 1.2122, "lr": 9.004565794997209e-06, "epoch": 0.40869565217391307, "percentage": 20.43, "elapsed_time": "0:01:47", "remaining_time": "0:06:57"}
+{"current_steps": 95, "total_steps": 460, "loss": 0.8132, "lr": 8.984025557079523e-06, "epoch": 0.41304347826086957, "percentage": 20.65, "elapsed_time": "0:01:48", "remaining_time": "0:06:55"}
+{"current_steps": 96, "total_steps": 460, "loss": 0.8736, "lr": 8.963299494004292e-06, "epoch": 0.41739130434782606, "percentage": 20.87, "elapsed_time": "0:01:49", "remaining_time": "0:06:54"}
+{"current_steps": 97, "total_steps": 460, "loss": 0.8824, "lr": 8.942388572488188e-06, "epoch": 0.4217391304347826, "percentage": 21.09, "elapsed_time": "0:01:50", "remaining_time": "0:06:53"}
+{"current_steps": 98, "total_steps": 460, "loss": 0.959, "lr": 8.921293767870157e-06, "epoch": 0.4260869565217391, "percentage": 21.3, "elapsed_time": "0:01:51", "remaining_time": "0:06:52"}
+{"current_steps": 99, "total_steps": 460, "loss": 0.9751, "lr": 8.900016064065923e-06, "epoch": 0.43043478260869567, "percentage": 21.52, "elapsed_time": "0:01:52", "remaining_time": "0:06:51"}
+{"current_steps": 100, "total_steps": 460, "loss": 0.734, "lr": 8.8785564535221e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:01:53", "remaining_time": "0:06:50"}
+{"current_steps": 101, "total_steps": 460, "loss": 0.9944, "lr": 8.85691593716989e-06, "epoch": 0.4391304347826087, "percentage": 21.96, "elapsed_time": "0:01:55", "remaining_time": "0:06:48"}
+{"current_steps": 102, "total_steps": 460, "loss": 0.8144, "lr": 8.835095524378413e-06, "epoch": 0.4434782608695652, "percentage": 22.17, "elapsed_time": "0:01:56", "remaining_time": "0:06:47"}
+{"current_steps": 103, "total_steps": 460, "loss": 1.1465, "lr": 8.81309623290762e-06, "epoch": 0.44782608695652176, "percentage": 22.39, "elapsed_time": "0:01:57", "remaining_time": "0:06:46"}
+{"current_steps": 104, "total_steps": 460, "loss": 0.5616, "lr": 8.790919088860815e-06, "epoch": 0.45217391304347826, "percentage": 22.61, "elapsed_time": "0:01:58", "remaining_time": "0:06:44"}
+{"current_steps": 105, "total_steps": 460, "loss": 1.0732, "lr": 8.768565126636806e-06, "epoch": 0.45652173913043476, "percentage": 22.83, "elapsed_time": "0:01:59", "remaining_time": "0:06:43"}
+{"current_steps": 106, "total_steps": 460, "loss": 0.8622, "lr": 8.746035388881655e-06, "epoch": 0.4608695652173913, "percentage": 23.04, "elapsed_time": "0:02:00", "remaining_time": "0:06:42"}
+{"current_steps": 107, "total_steps": 460, "loss": 0.9579, "lr": 8.723330926440045e-06, "epoch": 0.4652173913043478, "percentage": 23.26, "elapsed_time": "0:02:01", "remaining_time": "0:06:41"}
+{"current_steps": 108, "total_steps": 460, "loss": 0.8125, "lr": 8.70045279830626e-06, "epoch": 0.46956521739130436, "percentage": 23.48, "elapsed_time": "0:02:02", "remaining_time": "0:06:39"}
+{"current_steps": 109, "total_steps": 460, "loss": 0.5519, "lr": 8.677402071574806e-06, "epoch": 0.47391304347826085, "percentage": 23.7, "elapsed_time": "0:02:03", "remaining_time": "0:06:38"}
+{"current_steps": 110, "total_steps": 460, "loss": 0.5283, "lr": 8.65417982139062e-06, "epoch": 0.4782608695652174, "percentage": 23.91, "elapsed_time": "0:02:04", "remaining_time": "0:06:37"}
+{"current_steps": 111, "total_steps": 460, "loss": 0.652, "lr": 8.630787130898943e-06, "epoch": 0.4826086956521739, "percentage": 24.13, "elapsed_time": "0:02:05", "remaining_time": "0:06:36"}
+{"current_steps": 112, "total_steps": 460, "loss": 0.6831, "lr": 8.60722509119478e-06, "epoch": 0.48695652173913045, "percentage": 24.35, "elapsed_time": "0:02:07", "remaining_time": "0:06:35"}
+{"current_steps": 113, "total_steps": 460, "loss": 0.8531, "lr": 8.583494801272018e-06, "epoch": 0.49130434782608695, "percentage": 24.57, "elapsed_time": "0:02:08", "remaining_time": "0:06:33"}
+{"current_steps": 114, "total_steps": 460, "loss": 0.6959, "lr": 8.559597367972168e-06, "epoch": 0.4956521739130435, "percentage": 24.78, "elapsed_time": "0:02:09", "remaining_time": "0:06:32"}
+{"current_steps": 115, "total_steps": 460, "loss": 0.7375, "lr": 8.535533905932739e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:02:10", "remaining_time": "0:06:31"}
+{"current_steps": 116, "total_steps": 460, "loss": 0.8875, "lr": 8.511305537535238e-06, "epoch": 0.5043478260869565, "percentage": 25.22, "elapsed_time": "0:02:11", "remaining_time": "0:06:30"}
+{"current_steps": 117, "total_steps": 460, "loss": 0.593, "lr": 8.48691339285283e-06, "epoch": 0.508695652173913, "percentage": 25.43, "elapsed_time": "0:02:12", "remaining_time": "0:06:28"}
+{"current_steps": 118, "total_steps": 460, "loss": 0.7789, "lr": 8.462358609597629e-06, "epoch": 0.5130434782608696, "percentage": 25.65, "elapsed_time": "0:02:13", "remaining_time": "0:06:27"}
+{"current_steps": 119, "total_steps": 460, "loss": 0.9247, "lr": 8.437642333067626e-06, "epoch": 0.5173913043478261, "percentage": 25.87, "elapsed_time": "0:02:14", "remaining_time": "0:06:26"}
+{"current_steps": 120, "total_steps": 460, "loss": 0.9483, "lr": 8.412765716093273e-06, "epoch": 0.5217391304347826, "percentage": 26.09, "elapsed_time": "0:02:15", "remaining_time": "0:06:24"}
+{"current_steps": 121, "total_steps": 460, "loss": 0.7953, "lr": 8.387729918983706e-06, "epoch": 0.5260869565217391, "percentage": 26.3, "elapsed_time": "0:02:16", "remaining_time": "0:06:23"}
+{"current_steps": 122, "total_steps": 460, "loss": 0.9418, "lr": 8.362536109472637e-06, "epoch": 0.5304347826086957, "percentage": 26.52, "elapsed_time": "0:02:18", "remaining_time": "0:06:22"}
+{"current_steps": 123, "total_steps": 460, "loss": 1.0663, "lr": 8.33718546266388e-06, "epoch": 0.5347826086956522, "percentage": 26.74, "elapsed_time": "0:02:19", "remaining_time": "0:06:21"}
+{"current_steps": 124, "total_steps": 460, "loss": 0.7193, "lr": 8.31167916097654e-06, "epoch": 0.5391304347826087, "percentage": 26.96, "elapsed_time": "0:02:20", "remaining_time": "0:06:20"}
+{"current_steps": 125, "total_steps": 460, "loss": 0.8919, "lr": 8.286018394089864e-06, "epoch": 0.5434782608695652, "percentage": 27.17, "elapsed_time": "0:02:21", "remaining_time": "0:06:18"}
+{"current_steps": 126, "total_steps": 460, "loss": 0.9262, "lr": 8.260204358887753e-06, "epoch": 0.5478260869565217, "percentage": 27.39, "elapsed_time": "0:02:22", "remaining_time": "0:06:17"}
+{"current_steps": 127, "total_steps": 460, "loss": 0.6884, "lr": 8.234238259402936e-06, "epoch": 0.5521739130434783, "percentage": 27.61, "elapsed_time": "0:02:23", "remaining_time": "0:06:16"}
+{"current_steps": 128, "total_steps": 460, "loss": 0.976, "lr": 8.208121306760806e-06, "epoch": 0.5565217391304348, "percentage": 27.83, "elapsed_time": "0:02:24", "remaining_time": "0:06:15"}
+{"current_steps": 129, "total_steps": 460, "loss": 0.9472, "lr": 8.181854719122938e-06, "epoch": 0.5608695652173913, "percentage": 28.04, "elapsed_time": "0:02:25", "remaining_time": "0:06:13"}
+{"current_steps": 130, "total_steps": 460, "loss": 1.205, "lr": 8.155439721630265e-06, "epoch": 0.5652173913043478, "percentage": 28.26, "elapsed_time": "0:02:26", "remaining_time": "0:06:12"}
+{"current_steps": 131, "total_steps": 460, "loss": 0.7917, "lr": 8.128877546345932e-06, "epoch": 0.5695652173913044, "percentage": 28.48, "elapsed_time": "0:02:27", "remaining_time": "0:06:11"}
+{"current_steps": 132, "total_steps": 460, "loss": 0.6568, "lr": 8.102169432197842e-06, "epoch": 0.5739130434782609, "percentage": 28.7, "elapsed_time": "0:02:29", "remaining_time": "0:06:10"}
+{"current_steps": 133, "total_steps": 460, "loss": 0.7244, "lr": 8.075316624920848e-06, "epoch": 0.5782608695652174, "percentage": 28.91, "elapsed_time": "0:02:30", "remaining_time": "0:06:09"}
+{"current_steps": 134, "total_steps": 460, "loss": 0.8697, "lr": 8.048320376998675e-06, "epoch": 0.5826086956521739, "percentage": 29.13, "elapsed_time": "0:02:31", "remaining_time": "0:06:07"}
+{"current_steps": 135, "total_steps": 460, "loss": 0.7617, "lr": 8.021181947605474e-06, "epoch": 0.5869565217391305, "percentage": 29.35, "elapsed_time": "0:02:32", "remaining_time": "0:06:06"}
+{"current_steps": 136, "total_steps": 460, "loss": 0.79, "lr": 7.993902602547113e-06, "epoch": 0.591304347826087, "percentage": 29.57, "elapsed_time": "0:02:33", "remaining_time": "0:06:05"}
+{"current_steps": 137, "total_steps": 460, "loss": 0.9127, "lr": 7.966483614202127e-06, "epoch": 0.5956521739130435, "percentage": 29.78, "elapsed_time": "0:02:34", "remaining_time": "0:06:04"}
+{"current_steps": 138, "total_steps": 460, "loss": 0.6109, "lr": 7.938926261462366e-06, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:02:35", "remaining_time": "0:06:02"}
+{"current_steps": 139, "total_steps": 460, "loss": 0.7885, "lr": 7.911231829673356e-06, "epoch": 0.6043478260869565, "percentage": 30.22, "elapsed_time": "0:02:36", "remaining_time": "0:06:01"}
+{"current_steps": 140, "total_steps": 460, "loss": 0.6665, "lr": 7.883401610574338e-06, "epoch": 0.6086956521739131, "percentage": 30.43, "elapsed_time": "0:02:37", "remaining_time": "0:06:00"}
+{"current_steps": 141, "total_steps": 460, "loss": 0.8652, "lr": 7.855436902238018e-06, "epoch": 0.6130434782608696, "percentage": 30.65, "elapsed_time": "0:02:38", "remaining_time": "0:05:59"}
+{"current_steps": 142, "total_steps": 460, "loss": 0.8522, "lr": 7.82733900901003e-06, "epoch": 0.6173913043478261, "percentage": 30.87, "elapsed_time": "0:02:40", "remaining_time": "0:05:58"}
+{"current_steps": 143, "total_steps": 460, "loss": 0.9895, "lr": 7.799109241448091e-06, "epoch": 0.6217391304347826, "percentage": 31.09, "elapsed_time": "0:02:41", "remaining_time": "0:05:57"}
+{"current_steps": 144, "total_steps": 460, "loss": 1.1143, "lr": 7.770748916260875e-06, "epoch": 0.6260869565217392, "percentage": 31.3, "elapsed_time": "0:02:42", "remaining_time": "0:05:55"}
+{"current_steps": 145, "total_steps": 460, "loss": 0.7515, "lr": 7.742259356246594e-06, "epoch": 0.6304347826086957, "percentage": 31.52, "elapsed_time": "0:02:43", "remaining_time": "0:05:54"}
+{"current_steps": 146, "total_steps": 460, "loss": 1.019, "lr": 7.71364189023131e-06, "epoch": 0.6347826086956522, "percentage": 31.74, "elapsed_time": "0:02:44", "remaining_time": "0:05:53"}
+{"current_steps": 147, "total_steps": 460, "loss": 0.7827, "lr": 7.68489785300694e-06, "epoch": 0.6391304347826087, "percentage": 31.96, "elapsed_time": "0:02:45", "remaining_time": "0:05:52"}
+{"current_steps": 148, "total_steps": 460, "loss": 0.881, "lr": 7.656028585269017e-06, "epoch": 0.6434782608695652, "percentage": 32.17, "elapsed_time": "0:02:46", "remaining_time": "0:05:51"}
+{"current_steps": 149, "total_steps": 460, "loss": 0.83, "lr": 7.627035433554138e-06, "epoch": 0.6478260869565218, "percentage": 32.39, "elapsed_time": "0:02:47", "remaining_time": "0:05:49"}
+{"current_steps": 150, "total_steps": 460, "loss": 0.731, "lr": 7.597919750177168e-06, "epoch": 0.6521739130434783, "percentage": 32.61, "elapsed_time": "0:02:48", "remaining_time": "0:05:48"}
+{"current_steps": 151, "total_steps": 460, "loss": 0.7652, "lr": 7.5686828931681646e-06, "epoch": 0.6565217391304348, "percentage": 32.83, "elapsed_time": "0:02:50", "remaining_time": "0:05:47"}
+{"current_steps": 152, "total_steps": 460, "loss": 0.7775, "lr": 7.539326226209032e-06, "epoch": 0.6608695652173913, "percentage": 33.04, "elapsed_time": "0:02:51", "remaining_time": "0:05:46"}
+{"current_steps": 153, "total_steps": 460, "loss": 0.8261, "lr": 7.509851118569915e-06, "epoch": 0.6652173913043479, "percentage": 33.26, "elapsed_time": "0:02:52", "remaining_time": "0:05:45"}
+{"current_steps": 154, "total_steps": 460, "loss": 0.9438, "lr": 7.4802589450453415e-06, "epoch": 0.6695652173913044, "percentage": 33.48, "elapsed_time": "0:02:53", "remaining_time": "0:05:44"}
+{"current_steps": 155, "total_steps": 460, "loss": 0.7168, "lr": 7.450551085890087e-06, "epoch": 0.6739130434782609, "percentage": 33.7, "elapsed_time": "0:02:54", "remaining_time": "0:05:43"}
+{"current_steps": 156, "total_steps": 460, "loss": 0.7393, "lr": 7.420728926754803e-06, "epoch": 0.6782608695652174, "percentage": 33.91, "elapsed_time": "0:02:55", "remaining_time": "0:05:41"}
+{"current_steps": 157, "total_steps": 460, "loss": 0.6084, "lr": 7.390793858621386e-06, "epoch": 0.6826086956521739, "percentage": 34.13, "elapsed_time": "0:02:56", "remaining_time": "0:05:40"}
+{"current_steps": 158, "total_steps": 460, "loss": 0.9321, "lr": 7.360747277738094e-06, "epoch": 0.6869565217391305, "percentage": 34.35, "elapsed_time": "0:02:57", "remaining_time": "0:05:39"}
+{"current_steps": 159, "total_steps": 460, "loss": 0.8209, "lr": 7.330590585554428e-06, "epoch": 0.691304347826087, "percentage": 34.57, "elapsed_time": "0:02:58", "remaining_time": "0:05:38"}
+{"current_steps": 160, "total_steps": 460, "loss": 0.7925, "lr": 7.300325188655762e-06, "epoch": 0.6956521739130435, "percentage": 34.78, "elapsed_time": "0:02:59", "remaining_time": "0:05:37"}
+{"current_steps": 161, "total_steps": 460, "loss": 0.9974, "lr": 7.269952498697734e-06, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "0:03:01", "remaining_time": "0:05:36"}
+{"current_steps": 162, "total_steps": 460, "loss": 1.091, "lr": 7.2394739323404105e-06, "epoch": 0.7043478260869566, "percentage": 35.22, "elapsed_time": "0:03:02", "remaining_time": "0:05:35"}
+{"current_steps": 163, "total_steps": 460, "loss": 1.1279, "lr": 7.208890911182198e-06, "epoch": 0.7086956521739131, "percentage": 35.43, "elapsed_time": "0:03:03", "remaining_time": "0:05:33"}
+{"current_steps": 164, "total_steps": 460, "loss": 0.8294, "lr": 7.178204861693546e-06, "epoch": 0.7130434782608696, "percentage": 35.65, "elapsed_time": "0:03:04", "remaining_time": "0:05:32"}
+{"current_steps": 165, "total_steps": 460, "loss": 1.0741, "lr": 7.147417215150411e-06, "epoch": 0.717391304347826, "percentage": 35.87, "elapsed_time": "0:03:05", "remaining_time": "0:05:31"}
+{"current_steps": 166, "total_steps": 460, "loss": 0.614, "lr": 7.116529407567489e-06, "epoch": 0.7217391304347827, "percentage": 36.09, "elapsed_time": "0:03:06", "remaining_time": "0:05:30"}
+{"current_steps": 167, "total_steps": 460, "loss": 0.7525, "lr": 7.085542879631253e-06, "epoch": 0.7260869565217392, "percentage": 36.3, "elapsed_time": "0:03:07", "remaining_time": "0:05:29"}
+{"current_steps": 168, "total_steps": 460, "loss": 0.9964, "lr": 7.054459076632742e-06, "epoch": 0.7304347826086957, "percentage": 36.52, "elapsed_time": "0:03:08", "remaining_time": "0:05:27"}
+{"current_steps": 169, "total_steps": 460, "loss": 0.7518, "lr": 7.0232794484001495e-06, "epoch": 0.7347826086956522, "percentage": 36.74, "elapsed_time": "0:03:09", "remaining_time": "0:05:26"}
+{"current_steps": 170, "total_steps": 460, "loss": 0.7821, "lr": 6.9920054492312086e-06, "epoch": 0.7391304347826086, "percentage": 36.96, "elapsed_time": "0:03:10", "remaining_time": "0:05:25"}
+{"current_steps": 171, "total_steps": 460, "loss": 1.1481, "lr": 6.960638537825352e-06, "epoch": 0.7434782608695653, "percentage": 37.17, "elapsed_time": "0:03:11", "remaining_time": "0:05:24"}
+{"current_steps": 172, "total_steps": 460, "loss": 0.7234, "lr": 6.9291801772156775e-06, "epoch": 0.7478260869565218, "percentage": 37.39, "elapsed_time": "0:03:13", "remaining_time": "0:05:23"}
+{"current_steps": 173, "total_steps": 460, "loss": 0.7835, "lr": 6.89763183470071e-06, "epoch": 0.7521739130434782, "percentage": 37.61, "elapsed_time": "0:03:14", "remaining_time": "0:05:22"}
+{"current_steps": 174, "total_steps": 460, "loss": 0.8836, "lr": 6.865994981775958e-06, "epoch": 0.7565217391304347, "percentage": 37.83, "elapsed_time": "0:03:15", "remaining_time": "0:05:20"}
+{"current_steps": 175, "total_steps": 460, "loss": 0.9207, "lr": 6.834271094065284e-06, "epoch": 0.7608695652173914, "percentage": 38.04, "elapsed_time": "0:03:16", "remaining_time": "0:05:19"}
+{"current_steps": 176, "total_steps": 460, "loss": 0.8593, "lr": 6.802461651252073e-06, "epoch": 0.7652173913043478, "percentage": 38.26, "elapsed_time": "0:03:17", "remaining_time": "0:05:18"}
+{"current_steps": 177, "total_steps": 460, "loss": 0.9054, "lr": 6.770568137010226e-06, "epoch": 0.7695652173913043, "percentage": 38.48, "elapsed_time": "0:03:18", "remaining_time": "0:05:17"}
+{"current_steps": 178, "total_steps": 460, "loss": 0.8688, "lr": 6.738592038934946e-06, "epoch": 0.7739130434782608, "percentage": 38.7, "elapsed_time": "0:03:19", "remaining_time": "0:05:16"}
+{"current_steps": 179, "total_steps": 460, "loss": 0.8779, "lr": 6.706534848473353e-06, "epoch": 0.7782608695652173, "percentage": 38.91, "elapsed_time": "0:03:20", "remaining_time": "0:05:14"}
+{"current_steps": 180, "total_steps": 460, "loss": 0.8055, "lr": 6.674398060854931e-06, "epoch": 0.782608695652174, "percentage": 39.13, "elapsed_time": "0:03:21", "remaining_time": "0:05:13"}
+{"current_steps": 181, "total_steps": 460, "loss": 0.7101, "lr": 6.642183175021779e-06, "epoch": 0.7869565217391304, "percentage": 39.35, "elapsed_time": "0:03:22", "remaining_time": "0:05:12"}
+{"current_steps": 182, "total_steps": 460, "loss": 0.7036, "lr": 6.609891693558692e-06, "epoch": 0.7913043478260869, "percentage": 39.57, "elapsed_time": "0:03:23", "remaining_time": "0:05:11"}
+{"current_steps": 183, "total_steps": 460, "loss": 0.8071, "lr": 6.5775251226230855e-06, "epoch": 0.7956521739130434, "percentage": 39.78, "elapsed_time": "0:03:25", "remaining_time": "0:05:10"}
+{"current_steps": 184, "total_steps": 460, "loss": 0.826, "lr": 6.545084971874738e-06, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:03:26", "remaining_time": "0:05:09"}
+{"current_steps": 185, "total_steps": 460, "loss": 1.1722, "lr": 6.51257275440538e-06, "epoch": 0.8043478260869565, "percentage": 40.22, "elapsed_time": "0:03:27", "remaining_time": "0:05:08"}
+{"current_steps": 186, "total_steps": 460, "loss": 0.7167, "lr": 6.479989986668118e-06, "epoch": 0.808695652173913, "percentage": 40.43, "elapsed_time": "0:03:28", "remaining_time": "0:05:06"}
+{"current_steps": 187, "total_steps": 460, "loss": 0.9436, "lr": 6.447338188406705e-06, "epoch": 0.8130434782608695, "percentage": 40.65, "elapsed_time": "0:03:29", "remaining_time": "0:05:05"}
+{"current_steps": 188, "total_steps": 460, "loss": 0.7366, "lr": 6.41461888258465e-06, "epoch": 0.8173913043478261, "percentage": 40.87, "elapsed_time": "0:03:30", "remaining_time": "0:05:04"}
+{"current_steps": 189, "total_steps": 460, "loss": 0.8666, "lr": 6.3818335953141955e-06, "epoch": 0.8217391304347826, "percentage": 41.09, "elapsed_time": "0:03:31", "remaining_time": "0:05:03"}
+{"current_steps": 190, "total_steps": 460, "loss": 0.8697, "lr": 6.348983855785122e-06, "epoch": 0.8260869565217391, "percentage": 41.3, "elapsed_time": "0:03:32", "remaining_time": "0:05:02"}
+{"current_steps": 191, "total_steps": 460, "loss": 0.6411, "lr": 6.31607119619343e-06, "epoch": 0.8304347826086956, "percentage": 41.52, "elapsed_time": "0:03:33", "remaining_time": "0:05:01"}
+{"current_steps": 192, "total_steps": 460, "loss": 0.8285, "lr": 6.283097151669869e-06, "epoch": 0.8347826086956521, "percentage": 41.74, "elapsed_time": "0:03:34", "remaining_time": "0:05:00"}
+{"current_steps": 193, "total_steps": 460, "loss": 0.7585, "lr": 6.250063260208345e-06, "epoch": 0.8391304347826087, "percentage": 41.96, "elapsed_time": "0:03:36", "remaining_time": "0:04:58"}
+{"current_steps": 194, "total_steps": 460, "loss": 0.8291, "lr": 6.216971062594179e-06, "epoch": 0.8434782608695652, "percentage": 42.17, "elapsed_time": "0:03:37", "remaining_time": "0:04:57"}
+{"current_steps": 195, "total_steps": 460, "loss": 0.8107, "lr": 6.183822102332234e-06, "epoch": 0.8478260869565217, "percentage": 42.39, "elapsed_time": "0:03:38", "remaining_time": "0:04:56"}
+{"current_steps": 196, "total_steps": 460, "loss": 0.9379, "lr": 6.1506179255749335e-06, "epoch": 0.8521739130434782, "percentage": 42.61, "elapsed_time": "0:03:39", "remaining_time": "0:04:55"}
+{"current_steps": 197, "total_steps": 460, "loss": 0.6765, "lr": 6.1173600810501355e-06, "epoch": 0.8565217391304348, "percentage": 42.83, "elapsed_time": "0:03:40", "remaining_time": "0:04:54"}
+{"current_steps": 198, "total_steps": 460, "loss": 0.8658, "lr": 6.084050119988905e-06, "epoch": 0.8608695652173913, "percentage": 43.04, "elapsed_time": "0:03:41", "remaining_time": "0:04:53"}
+{"current_steps": 199, "total_steps": 460, "loss": 0.9007, "lr": 6.050689596053151e-06, "epoch": 0.8652173913043478, "percentage": 43.26, "elapsed_time": "0:03:42", "remaining_time": "0:04:52"}
+{"current_steps": 200, "total_steps": 460, "loss": 0.7356, "lr": 6.0172800652631706e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:03:44", "remaining_time": "0:04:51"}
+{"current_steps": 200, "total_steps": 460, "eval_loss": 0.825007438659668, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:03:45", "remaining_time": "0:04:52"}
+{"current_steps": 201, "total_steps": 460, "loss": 0.6462, "lr": 5.983823085925059e-06, "epoch": 0.8739130434782608, "percentage": 43.7, "elapsed_time": "0:03:46", "remaining_time": "0:04:51"}
+{"current_steps": 202, "total_steps": 460, "loss": 0.6327, "lr": 5.950320218558037e-06, "epoch": 0.8782608695652174, "percentage": 43.91, "elapsed_time": "0:03:47", "remaining_time": "0:04:50"}
+{"current_steps": 203, "total_steps": 460, "loss": 0.8199, "lr": 5.916773025821662e-06, "epoch": 0.8826086956521739, "percentage": 44.13, "elapsed_time": "0:03:48", "remaining_time": "0:04:49"}
+{"current_steps": 204, "total_steps": 460, "loss": 0.654, "lr": 5.883183072442938e-06, "epoch": 0.8869565217391304, "percentage": 44.35, "elapsed_time": "0:03:49", "remaining_time": "0:04:48"}
+{"current_steps": 205, "total_steps": 460, "loss": 0.8819, "lr": 5.849551925143334e-06, "epoch": 0.8913043478260869, "percentage": 44.57, "elapsed_time": "0:03:50", "remaining_time": "0:04:46"}
+{"current_steps": 206, "total_steps": 460, "loss": 0.8065, "lr": 5.815881152565712e-06, "epoch": 0.8956521739130435, "percentage": 44.78, "elapsed_time": "0:03:51", "remaining_time": "0:04:45"}
+{"current_steps": 207, "total_steps": 460, "loss": 1.0186, "lr": 5.782172325201155e-06, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "0:03:52", "remaining_time": "0:04:44"}
+{"current_steps": 208, "total_steps": 460, "loss": 0.6512, "lr": 5.7484270153157215e-06, "epoch": 0.9043478260869565, "percentage": 45.22, "elapsed_time": "0:03:53", "remaining_time": "0:04:43"}
+{"current_steps": 209, "total_steps": 460, "loss": 1.0551, "lr": 5.714646796877108e-06, "epoch": 0.908695652173913, "percentage": 45.43, "elapsed_time": "0:03:55", "remaining_time": "0:04:42"}
+{"current_steps": 210, "total_steps": 460, "loss": 0.8123, "lr": 5.680833245481234e-06, "epoch": 0.9130434782608695, "percentage": 45.65, "elapsed_time": "0:03:56", "remaining_time": "0:04:41"}
+{"current_steps": 211, "total_steps": 460, "loss": 0.7966, "lr": 5.646987938278753e-06, "epoch": 0.9173913043478261, "percentage": 45.87, "elapsed_time": "0:03:57", "remaining_time": "0:04:39"}
+{"current_steps": 212, "total_steps": 460, "loss": 0.8161, "lr": 5.613112453901493e-06, "epoch": 0.9217391304347826, "percentage": 46.09, "elapsed_time": "0:03:58", "remaining_time": "0:04:38"}
+{"current_steps": 213, "total_steps": 460, "loss": 0.8341, "lr": 5.579208372388822e-06, "epoch": 0.9260869565217391, "percentage": 46.3, "elapsed_time": "0:03:59", "remaining_time": "0:04:37"}
+{"current_steps": 214, "total_steps": 460, "loss": 0.7814, "lr": 5.5452772751139496e-06, "epoch": 0.9304347826086956, "percentage": 46.52, "elapsed_time": "0:04:00", "remaining_time": "0:04:36"}
+{"current_steps": 215, "total_steps": 460, "loss": 0.7195, "lr": 5.511320744710171e-06, "epoch": 0.9347826086956522, "percentage": 46.74, "elapsed_time": "0:04:01", "remaining_time": "0:04:35"}
+{"current_steps": 216, "total_steps": 460, "loss": 0.9754, "lr": 5.477340364997051e-06, "epoch": 0.9391304347826087, "percentage": 46.96, "elapsed_time": "0:04:02", "remaining_time": "0:04:34"}
+{"current_steps": 217, "total_steps": 460, "loss": 0.9599, "lr": 5.443337720906542e-06, "epoch": 0.9434782608695652, "percentage": 47.17, "elapsed_time": "0:04:03", "remaining_time": "0:04:32"}
+{"current_steps": 218, "total_steps": 460, "loss": 0.7041, "lr": 5.409314398409067e-06, "epoch": 0.9478260869565217, "percentage": 47.39, "elapsed_time": "0:04:05", "remaining_time": "0:04:32"}
+{"current_steps": 219, "total_steps": 460, "loss": 0.6793, "lr": 5.375271984439541e-06, "epoch": 0.9521739130434783, "percentage": 47.61, "elapsed_time": "0:04:06", "remaining_time": "0:04:30"}
+{"current_steps": 220, "total_steps": 460, "loss": 0.8546, "lr": 5.341212066823356e-06, "epoch": 0.9565217391304348, "percentage": 47.83, "elapsed_time": "0:04:07", "remaining_time": "0:04:29"}
+{"current_steps": 221, "total_steps": 460, "loss": 0.6732, "lr": 5.307136234202318e-06, "epoch": 0.9608695652173913, "percentage": 48.04, "elapsed_time": "0:04:08", "remaining_time": "0:04:28"}
+{"current_steps": 222, "total_steps": 460, "loss": 1.0779, "lr": 5.27304607596055e-06, "epoch": 0.9652173913043478, "percentage": 48.26, "elapsed_time": "0:04:09", "remaining_time": "0:04:27"}
+{"current_steps": 223, "total_steps": 460, "loss": 0.6516, "lr": 5.238943182150361e-06, "epoch": 0.9695652173913043, "percentage": 48.48, "elapsed_time": "0:04:10", "remaining_time": "0:04:26"}
+{"current_steps": 224, "total_steps": 460, "loss": 0.709, "lr": 5.204829143418072e-06, "epoch": 0.9739130434782609, "percentage": 48.7, "elapsed_time": "0:04:11", "remaining_time": "0:04:25"}
+{"current_steps": 225, "total_steps": 460, "loss": 0.753, "lr": 5.17070555092984e-06, "epoch": 0.9782608695652174, "percentage": 48.91, "elapsed_time": "0:04:12", "remaining_time": "0:04:23"}
+{"current_steps": 226, "total_steps": 460, "loss": 1.0238, "lr": 5.136573996297431e-06, "epoch": 0.9826086956521739, "percentage": 49.13, "elapsed_time": "0:04:13", "remaining_time": "0:04:22"}
+{"current_steps": 227, "total_steps": 460, "loss": 0.9125, "lr": 5.102436071503983e-06, "epoch": 0.9869565217391304, "percentage": 49.35, "elapsed_time": "0:04:14", "remaining_time": "0:04:21"}
+{"current_steps": 228, "total_steps": 460, "loss": 0.8642, "lr": 5.068293368829755e-06, "epoch": 0.991304347826087, "percentage": 49.57, "elapsed_time": "0:04:16", "remaining_time": "0:04:20"}
+{"current_steps": 229, "total_steps": 460, "loss": 0.8394, "lr": 5.034147480777867e-06, "epoch": 0.9956521739130435, "percentage": 49.78, "elapsed_time": "0:04:17", "remaining_time": "0:04:19"}
+{"current_steps": 230, "total_steps": 460, "loss": 0.9067, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:04:18", "remaining_time": "0:04:18"}
+{"current_steps": 231, "total_steps": 460, "loss": 0.7034, "lr": 4.965852519222135e-06, "epoch": 1.0043478260869565, "percentage": 50.22, "elapsed_time": "0:04:19", "remaining_time": "0:04:17"}
+{"current_steps": 232, "total_steps": 460, "loss": 0.6254, "lr": 4.931706631170246e-06, "epoch": 1.008695652173913, "percentage": 50.43, "elapsed_time": "0:04:20", "remaining_time": "0:04:15"}
+{"current_steps": 233, "total_steps": 460, "loss": 0.4885, "lr": 4.89756392849602e-06, "epoch": 1.0130434782608695, "percentage": 50.65, "elapsed_time": "0:04:21", "remaining_time": "0:04:14"}
+{"current_steps": 234, "total_steps": 460, "loss": 0.7407, "lr": 4.863426003702572e-06, "epoch": 1.017391304347826, "percentage": 50.87, "elapsed_time": "0:04:22", "remaining_time": "0:04:13"}
+{"current_steps": 235, "total_steps": 460, "loss": 0.6666, "lr": 4.829294449070161e-06, "epoch": 1.0217391304347827, "percentage": 51.09, "elapsed_time": "0:04:23", "remaining_time": "0:04:12"}
+{"current_steps": 236, "total_steps": 460, "loss": 0.6291, "lr": 4.795170856581929e-06, "epoch": 1.0260869565217392, "percentage": 51.3, "elapsed_time": "0:04:24", "remaining_time": "0:04:11"}
+{"current_steps": 237, "total_steps": 460, "loss": 0.5469, "lr": 4.7610568178496405e-06, "epoch": 1.0304347826086957, "percentage": 51.52, "elapsed_time": "0:04:25", "remaining_time": "0:04:10"}
+{"current_steps": 238, "total_steps": 460, "loss": 0.4352, "lr": 4.7269539240394505e-06, "epoch": 1.0347826086956522, "percentage": 51.74, "elapsed_time": "0:04:27", "remaining_time": "0:04:09"}
+{"current_steps": 239, "total_steps": 460, "loss": 0.5481, "lr": 4.692863765797683e-06, "epoch": 1.0391304347826087, "percentage": 51.96, "elapsed_time": "0:04:28", "remaining_time": "0:04:07"}
+{"current_steps": 240, "total_steps": 460, "loss": 0.6503, "lr": 4.6587879331766465e-06, "epoch": 1.0434782608695652, "percentage": 52.17, "elapsed_time": "0:04:29", "remaining_time": "0:04:06"}
+{"current_steps": 241, "total_steps": 460, "loss": 0.6356, "lr": 4.624728015560461e-06, "epoch": 1.0478260869565217, "percentage": 52.39, "elapsed_time": "0:04:30", "remaining_time": "0:04:05"}
+{"current_steps": 242, "total_steps": 460, "loss": 0.4898, "lr": 4.5906856015909365e-06, "epoch": 1.0521739130434782, "percentage": 52.61, "elapsed_time": "0:04:31", "remaining_time": "0:04:04"}
+{"current_steps": 243, "total_steps": 460, "loss": 0.5339, "lr": 4.556662279093461e-06, "epoch": 1.0565217391304347, "percentage": 52.83, "elapsed_time": "0:04:32", "remaining_time": "0:04:03"}
+{"current_steps": 244, "total_steps": 460, "loss": 0.7113, "lr": 4.52265963500295e-06, "epoch": 1.0608695652173914, "percentage": 53.04, "elapsed_time": "0:04:33", "remaining_time": "0:04:02"}
+{"current_steps": 245, "total_steps": 460, "loss": 0.6041, "lr": 4.488679255289829e-06, "epoch": 1.065217391304348, "percentage": 53.26, "elapsed_time": "0:04:34", "remaining_time": "0:04:01"}
+{"current_steps": 246, "total_steps": 460, "loss": 0.4484, "lr": 4.454722724886051e-06, "epoch": 1.0695652173913044, "percentage": 53.48, "elapsed_time": "0:04:35", "remaining_time": "0:03:59"}
+{"current_steps": 247, "total_steps": 460, "loss": 0.4856, "lr": 4.4207916276111795e-06, "epoch": 1.0739130434782609, "percentage": 53.7, "elapsed_time": "0:04:36", "remaining_time": "0:03:58"}
+{"current_steps": 248, "total_steps": 460, "loss": 0.5426, "lr": 4.386887546098509e-06, "epoch": 1.0782608695652174, "percentage": 53.91, "elapsed_time": "0:04:37", "remaining_time": "0:03:57"}
+{"current_steps": 249, "total_steps": 460, "loss": 0.4695, "lr": 4.353012061721249e-06, "epoch": 1.0826086956521739, "percentage": 54.13, "elapsed_time": "0:04:39", "remaining_time": "0:03:56"}
+{"current_steps": 250, "total_steps": 460, "loss": 0.3785, "lr": 4.319166754518768e-06, "epoch": 1.0869565217391304, "percentage": 54.35, "elapsed_time": "0:04:40", "remaining_time": "0:03:55"}
+{"current_steps": 251, "total_steps": 460, "loss": 0.3999, "lr": 4.285353203122894e-06, "epoch": 1.0913043478260869, "percentage": 54.57, "elapsed_time": "0:04:41", "remaining_time": "0:03:54"}
+{"current_steps": 252, "total_steps": 460, "loss": 0.7579, "lr": 4.251572984684281e-06, "epoch": 1.0956521739130434, "percentage": 54.78, "elapsed_time": "0:04:42", "remaining_time": "0:03:53"}
+{"current_steps": 253, "total_steps": 460, "loss": 0.6067, "lr": 4.217827674798845e-06, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "0:04:43", "remaining_time": "0:03:51"}
+{"current_steps": 254, "total_steps": 460, "loss": 0.485, "lr": 4.18411884743429e-06, "epoch": 1.1043478260869566, "percentage": 55.22, "elapsed_time": "0:04:44", "remaining_time": "0:03:50"}
+{"current_steps": 255, "total_steps": 460, "loss": 0.5005, "lr": 4.150448074856667e-06, "epoch": 1.108695652173913, "percentage": 55.43, "elapsed_time": "0:04:45", "remaining_time": "0:03:49"}
+{"current_steps": 256, "total_steps": 460, "loss": 0.4883, "lr": 4.116816927557063e-06, "epoch": 1.1130434782608696, "percentage": 55.65, "elapsed_time": "0:04:46", "remaining_time": "0:03:48"}
+{"current_steps": 257, "total_steps": 460, "loss": 0.3788, "lr": 4.083226974178339e-06, "epoch": 1.117391304347826, "percentage": 55.87, "elapsed_time": "0:04:47", "remaining_time": "0:03:47"}
+{"current_steps": 258, "total_steps": 460, "loss": 0.4932, "lr": 4.0496797814419655e-06, "epoch": 1.1217391304347826, "percentage": 56.09, "elapsed_time": "0:04:48", "remaining_time": "0:03:46"}
+{"current_steps": 259, "total_steps": 460, "loss": 0.5368, "lr": 4.016176914074944e-06, "epoch": 1.126086956521739, "percentage": 56.3, "elapsed_time": "0:04:49", "remaining_time": "0:03:45"}
+{"current_steps": 260, "total_steps": 460, "loss": 0.4211, "lr": 3.982719934736832e-06, "epoch": 1.1304347826086956, "percentage": 56.52, "elapsed_time": "0:04:51", "remaining_time": "0:03:43"}
+{"current_steps": 261, "total_steps": 460, "loss": 0.4899, "lr": 3.949310403946849e-06, "epoch": 1.134782608695652, "percentage": 56.74, "elapsed_time": "0:04:52", "remaining_time": "0:03:42"}
+{"current_steps": 262, "total_steps": 460, "loss": 0.4823, "lr": 3.915949880011096e-06, "epoch": 1.1391304347826088, "percentage": 56.96, "elapsed_time": "0:04:53", "remaining_time": "0:03:41"}
+{"current_steps": 263, "total_steps": 460, "loss": 0.5596, "lr": 3.882639918949865e-06, "epoch": 1.1434782608695653, "percentage": 57.17, "elapsed_time": "0:04:54", "remaining_time": "0:03:40"}
+{"current_steps": 264, "total_steps": 460, "loss": 0.423, "lr": 3.849382074425069e-06, "epoch": 1.1478260869565218, "percentage": 57.39, "elapsed_time": "0:04:55", "remaining_time": "0:03:39"}
+{"current_steps": 265, "total_steps": 460, "loss": 0.8296, "lr": 3.816177897667767e-06, "epoch": 1.1521739130434783, "percentage": 57.61, "elapsed_time": "0:04:56", "remaining_time": "0:03:38"}
+{"current_steps": 266, "total_steps": 460, "loss": 0.616, "lr": 3.7830289374058214e-06, "epoch": 1.1565217391304348, "percentage": 57.83, "elapsed_time": "0:04:57", "remaining_time": "0:03:37"}
+{"current_steps": 267, "total_steps": 460, "loss": 0.5357, "lr": 3.749936739791656e-06, "epoch": 1.1608695652173913, "percentage": 58.04, "elapsed_time": "0:04:58", "remaining_time": "0:03:35"}
+{"current_steps": 268, "total_steps": 460, "loss": 0.4663, "lr": 3.7169028483301333e-06, "epoch": 1.1652173913043478, "percentage": 58.26, "elapsed_time": "0:04:59", "remaining_time": "0:03:34"}
+{"current_steps": 269, "total_steps": 460, "loss": 0.3898, "lr": 3.6839288038065736e-06, "epoch": 1.1695652173913043, "percentage": 58.48, "elapsed_time": "0:05:00", "remaining_time": "0:03:33"}
+{"current_steps": 270, "total_steps": 460, "loss": 0.4019, "lr": 3.6510161442148783e-06, "epoch": 1.1739130434782608, "percentage": 58.7, "elapsed_time": "0:05:02", "remaining_time": "0:03:32"}
+{"current_steps": 271, "total_steps": 460, "loss": 0.6163, "lr": 3.6181664046858045e-06, "epoch": 1.1782608695652175, "percentage": 58.91, "elapsed_time": "0:05:03", "remaining_time": "0:03:31"}
+{"current_steps": 272, "total_steps": 460, "loss": 0.6357, "lr": 3.58538111741535e-06, "epoch": 1.182608695652174, "percentage": 59.13, "elapsed_time": "0:05:04", "remaining_time": "0:03:30"}
+{"current_steps": 273, "total_steps": 460, "loss": 0.5377, "lr": 3.5526618115932974e-06, "epoch": 1.1869565217391305, "percentage": 59.35, "elapsed_time": "0:05:05", "remaining_time": "0:03:29"}
+{"current_steps": 274, "total_steps": 460, "loss": 0.7388, "lr": 3.5200100133318836e-06, "epoch": 1.191304347826087, "percentage": 59.57, "elapsed_time": "0:05:06", "remaining_time": "0:03:28"}
+{"current_steps": 275, "total_steps": 460, "loss": 0.3212, "lr": 3.4874272455946217e-06, "epoch": 1.1956521739130435, "percentage": 59.78, "elapsed_time": "0:05:07", "remaining_time": "0:03:26"}
+{"current_steps": 276, "total_steps": 460, "loss": 0.5172, "lr": 3.4549150281252635e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:05:08", "remaining_time": "0:03:25"}
+{"current_steps": 277, "total_steps": 460, "loss": 0.4703, "lr": 3.4224748773769166e-06, "epoch": 1.2043478260869565, "percentage": 60.22, "elapsed_time": "0:05:09", "remaining_time": "0:03:24"}
+{"current_steps": 278, "total_steps": 460, "loss": 0.5399, "lr": 3.39010830644131e-06, "epoch": 1.208695652173913, "percentage": 60.43, "elapsed_time": "0:05:10", "remaining_time": "0:03:23"}
+{"current_steps": 279, "total_steps": 460, "loss": 0.4727, "lr": 3.357816824978222e-06, "epoch": 1.2130434782608694, "percentage": 60.65, "elapsed_time": "0:05:11", "remaining_time": "0:03:22"}
+{"current_steps": 280, "total_steps": 460, "loss": 0.7769, "lr": 3.3256019391450696e-06, "epoch": 1.2173913043478262, "percentage": 60.87, "elapsed_time": "0:05:13", "remaining_time": "0:03:21"}
+{"current_steps": 281, "total_steps": 460, "loss": 0.5781, "lr": 3.2934651515266485e-06, "epoch": 1.2217391304347827, "percentage": 61.09, "elapsed_time": "0:05:14", "remaining_time": "0:03:20"}
+{"current_steps": 282, "total_steps": 460, "loss": 0.6225, "lr": 3.261407961065056e-06, "epoch": 1.2260869565217392, "percentage": 61.3, "elapsed_time": "0:05:15", "remaining_time": "0:03:18"}
+{"current_steps": 283, "total_steps": 460, "loss": 0.5312, "lr": 3.2294318629897746e-06, "epoch": 1.2304347826086957, "percentage": 61.52, "elapsed_time": "0:05:16", "remaining_time": "0:03:17"}
+{"current_steps": 284, "total_steps": 460, "loss": 0.5066, "lr": 3.197538348747927e-06, "epoch": 1.2347826086956522, "percentage": 61.74, "elapsed_time": "0:05:17", "remaining_time": "0:03:16"}
+{"current_steps": 285, "total_steps": 460, "loss": 0.3998, "lr": 3.1657289059347184e-06, "epoch": 1.2391304347826086, "percentage": 61.96, "elapsed_time": "0:05:18", "remaining_time": "0:03:15"}
+{"current_steps": 286, "total_steps": 460, "loss": 0.4784, "lr": 3.1340050182240438e-06, "epoch": 1.2434782608695651, "percentage": 62.17, "elapsed_time": "0:05:19", "remaining_time": "0:03:14"}
+{"current_steps": 287, "total_steps": 460, "loss": 0.6345, "lr": 3.1023681652992925e-06, "epoch": 1.2478260869565219, "percentage": 62.39, "elapsed_time": "0:05:20", "remaining_time": "0:03:13"}
+{"current_steps": 288, "total_steps": 460, "loss": 0.4243, "lr": 3.070819822784323e-06, "epoch": 1.2521739130434781, "percentage": 62.61, "elapsed_time": "0:05:22", "remaining_time": "0:03:12"}
+{"current_steps": 289, "total_steps": 460, "loss": 0.4092, "lr": 3.03936146217465e-06, "epoch": 1.2565217391304349, "percentage": 62.83, "elapsed_time": "0:05:23", "remaining_time": "0:03:11"}
+{"current_steps": 290, "total_steps": 460, "loss": 0.4044, "lr": 3.007994550768793e-06, "epoch": 1.2608695652173914, "percentage": 63.04, "elapsed_time": "0:05:24", "remaining_time": "0:03:10"}
+{"current_steps": 291, "total_steps": 460, "loss": 0.4325, "lr": 2.976720551599852e-06, "epoch": 1.2652173913043478, "percentage": 63.26, "elapsed_time": "0:05:25", "remaining_time": "0:03:08"}
+{"current_steps": 292, "total_steps": 460, "loss": 0.8048, "lr": 2.9455409233672594e-06, "epoch": 1.2695652173913043, "percentage": 63.48, "elapsed_time": "0:05:26", "remaining_time": "0:03:07"}
+{"current_steps": 293, "total_steps": 460, "loss": 0.7234, "lr": 2.914457120368748e-06, "epoch": 1.2739130434782608, "percentage": 63.7, "elapsed_time": "0:05:27", "remaining_time": "0:03:06"}
+{"current_steps": 294, "total_steps": 460, "loss": 0.4799, "lr": 2.883470592432512e-06, "epoch": 1.2782608695652173, "percentage": 63.91, "elapsed_time": "0:05:28", "remaining_time": "0:03:05"}
+{"current_steps": 295, "total_steps": 460, "loss": 0.4406, "lr": 2.8525827848495912e-06, "epoch": 1.2826086956521738, "percentage": 64.13, "elapsed_time": "0:05:30", "remaining_time": "0:03:04"}
+{"current_steps": 296, "total_steps": 460, "loss": 0.5246, "lr": 2.8217951383064546e-06, "epoch": 1.2869565217391306, "percentage": 64.35, "elapsed_time": "0:05:31", "remaining_time": "0:03:03"}
+{"current_steps": 297, "total_steps": 460, "loss": 0.5552, "lr": 2.7911090888178033e-06, "epoch": 1.2913043478260868, "percentage": 64.57, "elapsed_time": "0:05:32", "remaining_time": "0:03:02"}
+{"current_steps": 298, "total_steps": 460, "loss": 0.6207, "lr": 2.760526067659591e-06, "epoch": 1.2956521739130435, "percentage": 64.78, "elapsed_time": "0:05:33", "remaining_time": "0:03:01"}
+{"current_steps": 299, "total_steps": 460, "loss": 0.5759, "lr": 2.7300475013022666e-06, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "0:05:34", "remaining_time": "0:03:00"}
+{"current_steps": 300, "total_steps": 460, "loss": 0.3266, "lr": 2.6996748113442397e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "0:05:35", "remaining_time": "0:02:58"}
+{"current_steps": 301, "total_steps": 460, "loss": 0.5043, "lr": 2.669409414445574e-06, "epoch": 1.308695652173913, "percentage": 65.43, "elapsed_time": "0:05:36", "remaining_time": "0:02:57"}
+{"current_steps": 302, "total_steps": 460, "loss": 0.4729, "lr": 2.6392527222619078e-06, "epoch": 1.3130434782608695, "percentage": 65.65, "elapsed_time": "0:05:37", "remaining_time": "0:02:56"}
+{"current_steps": 303, "total_steps": 460, "loss": 0.5379, "lr": 2.6092061413786158e-06, "epoch": 1.317391304347826, "percentage": 65.87, "elapsed_time": "0:05:38", "remaining_time": "0:02:55"}
+{"current_steps": 304, "total_steps": 460, "loss": 0.6848, "lr": 2.5792710732452e-06, "epoch": 1.3217391304347825, "percentage": 66.09, "elapsed_time": "0:05:39", "remaining_time": "0:02:54"}
+{"current_steps": 305, "total_steps": 460, "loss": 0.3645, "lr": 2.5494489141099155e-06, "epoch": 1.3260869565217392, "percentage": 66.3, "elapsed_time": "0:05:41", "remaining_time": "0:02:53"}
+{"current_steps": 306, "total_steps": 460, "loss": 0.3829, "lr": 2.5197410549546598e-06, "epoch": 1.3304347826086955, "percentage": 66.52, "elapsed_time": "0:05:42", "remaining_time": "0:02:52"}
+{"current_steps": 307, "total_steps": 460, "loss": 0.5438, "lr": 2.4901488814300855e-06, "epoch": 1.3347826086956522, "percentage": 66.74, "elapsed_time": "0:05:43", "remaining_time": "0:02:51"}
+{"current_steps": 308, "total_steps": 460, "loss": 0.3286, "lr": 2.4606737737909696e-06, "epoch": 1.3391304347826087, "percentage": 66.96, "elapsed_time": "0:05:44", "remaining_time": "0:02:49"}
+{"current_steps": 309, "total_steps": 460, "loss": 0.7414, "lr": 2.431317106831836e-06, "epoch": 1.3434782608695652, "percentage": 67.17, "elapsed_time": "0:05:45", "remaining_time": "0:02:48"}
+{"current_steps": 310, "total_steps": 460, "loss": 0.5214, "lr": 2.4020802498228333e-06, "epoch": 1.3478260869565217, "percentage": 67.39, "elapsed_time": "0:05:46", "remaining_time": "0:02:47"}
+{"current_steps": 311, "total_steps": 460, "loss": 0.7109, "lr": 2.3729645664458637e-06, "epoch": 1.3521739130434782, "percentage": 67.61, "elapsed_time": "0:05:47", "remaining_time": "0:02:46"}
+{"current_steps": 312, "total_steps": 460, "loss": 0.4919, "lr": 2.3439714147309845e-06, "epoch": 1.3565217391304347, "percentage": 67.83, "elapsed_time": "0:05:48", "remaining_time": "0:02:45"}
+{"current_steps": 313, "total_steps": 460, "loss": 0.3315, "lr": 2.315102146993061e-06, "epoch": 1.3608695652173912, "percentage": 68.04, "elapsed_time": "0:05:49", "remaining_time": "0:02:44"}
+{"current_steps": 314, "total_steps": 460, "loss": 0.4416, "lr": 2.286358109768693e-06, "epoch": 1.365217391304348, "percentage": 68.26, "elapsed_time": "0:05:50", "remaining_time": "0:02:43"}
+{"current_steps": 315, "total_steps": 460, "loss": 0.4012, "lr": 2.2577406437534055e-06, "epoch": 1.3695652173913042, "percentage": 68.48, "elapsed_time": "0:05:52", "remaining_time": "0:02:42"}
+{"current_steps": 316, "total_steps": 460, "loss": 0.4213, "lr": 2.229251083739127e-06, "epoch": 1.373913043478261, "percentage": 68.7, "elapsed_time": "0:05:53", "remaining_time": "0:02:40"}
+{"current_steps": 317, "total_steps": 460, "loss": 0.6007, "lr": 2.2008907585519094e-06, "epoch": 1.3782608695652174, "percentage": 68.91, "elapsed_time": "0:05:54", "remaining_time": "0:02:39"}
+{"current_steps": 318, "total_steps": 460, "loss": 0.5128, "lr": 2.172660990989971e-06, "epoch": 1.382608695652174, "percentage": 69.13, "elapsed_time": "0:05:55", "remaining_time": "0:02:38"}
+{"current_steps": 319, "total_steps": 460, "loss": 0.6044, "lr": 2.144563097761984e-06, "epoch": 1.3869565217391304, "percentage": 69.35, "elapsed_time": "0:05:56", "remaining_time": "0:02:37"}
+{"current_steps": 320, "total_steps": 460, "loss": 0.5243, "lr": 2.1165983894256647e-06, "epoch": 1.391304347826087, "percentage": 69.57, "elapsed_time": "0:05:57", "remaining_time": "0:02:36"}
+{"current_steps": 321, "total_steps": 460, "loss": 0.6501, "lr": 2.0887681703266453e-06, "epoch": 1.3956521739130434, "percentage": 69.78, "elapsed_time": "0:05:58", "remaining_time": "0:02:35"}
+{"current_steps": 322, "total_steps": 460, "loss": 0.4023, "lr": 2.061073738537635e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "0:05:59", "remaining_time": "0:02:34"}
+{"current_steps": 323, "total_steps": 460, "loss": 0.584, "lr": 2.0335163857978747e-06, "epoch": 1.4043478260869566, "percentage": 70.22, "elapsed_time": "0:06:00", "remaining_time": "0:02:33"}
+{"current_steps": 324, "total_steps": 460, "loss": 0.4691, "lr": 2.0060973974528873e-06, "epoch": 1.4086956521739131, "percentage": 70.43, "elapsed_time": "0:06:01", "remaining_time": "0:02:31"}
+{"current_steps": 325, "total_steps": 460, "loss": 0.3754, "lr": 1.978818052394528e-06, "epoch": 1.4130434782608696, "percentage": 70.65, "elapsed_time": "0:06:02", "remaining_time": "0:02:30"}
+{"current_steps": 326, "total_steps": 460, "loss": 0.3779, "lr": 1.9516796230013275e-06, "epoch": 1.4173913043478261, "percentage": 70.87, "elapsed_time": "0:06:04", "remaining_time": "0:02:29"}
+{"current_steps": 327, "total_steps": 460, "loss": 0.5946, "lr": 1.9246833750791526e-06, "epoch": 1.4217391304347826, "percentage": 71.09, "elapsed_time": "0:06:05", "remaining_time": "0:02:28"}
+{"current_steps": 328, "total_steps": 460, "loss": 0.5896, "lr": 1.8978305678021598e-06, "epoch": 1.4260869565217391, "percentage": 71.3, "elapsed_time": "0:06:06", "remaining_time": "0:02:27"}
+{"current_steps": 329, "total_steps": 460, "loss": 0.4248, "lr": 1.8711224536540678e-06, "epoch": 1.4304347826086956, "percentage": 71.52, "elapsed_time": "0:06:07", "remaining_time": "0:02:26"}
+{"current_steps": 330, "total_steps": 460, "loss": 0.5666, "lr": 1.8445602783697375e-06, "epoch": 1.434782608695652, "percentage": 71.74, "elapsed_time": "0:06:08", "remaining_time": "0:02:25"}
+{"current_steps": 331, "total_steps": 460, "loss": 0.4982, "lr": 1.8181452808770638e-06, "epoch": 1.4391304347826086, "percentage": 71.96, "elapsed_time": "0:06:09", "remaining_time": "0:02:24"}
+{"current_steps": 332, "total_steps": 460, "loss": 0.5396, "lr": 1.7918786932391945e-06, "epoch": 1.4434782608695653, "percentage": 72.17, "elapsed_time": "0:06:10", "remaining_time": "0:02:22"}
+{"current_steps": 333, "total_steps": 460, "loss": 0.679, "lr": 1.765761740597065e-06, "epoch": 1.4478260869565218, "percentage": 72.39, "elapsed_time": "0:06:11", "remaining_time": "0:02:21"}
+{"current_steps": 334, "total_steps": 460, "loss": 0.6588, "lr": 1.739795641112248e-06, "epoch": 1.4521739130434783, "percentage": 72.61, "elapsed_time": "0:06:12", "remaining_time": "0:02:20"}
+{"current_steps": 335, "total_steps": 460, "loss": 0.8358, "lr": 1.7139816059101372e-06, "epoch": 1.4565217391304348, "percentage": 72.83, "elapsed_time": "0:06:14", "remaining_time": "0:02:19"}
+{"current_steps": 336, "total_steps": 460, "loss": 0.5513, "lr": 1.688320839023463e-06, "epoch": 1.4608695652173913, "percentage": 73.04, "elapsed_time": "0:06:15", "remaining_time": "0:02:18"}
+{"current_steps": 337, "total_steps": 460, "loss": 0.5271, "lr": 1.662814537336122e-06, "epoch": 1.4652173913043478, "percentage": 73.26, "elapsed_time": "0:06:16", "remaining_time": "0:02:17"}
+{"current_steps": 338, "total_steps": 460, "loss": 0.5086, "lr": 1.6374638905273643e-06, "epoch": 1.4695652173913043, "percentage": 73.48, "elapsed_time": "0:06:17", "remaining_time": "0:02:16"}
+{"current_steps": 339, "total_steps": 460, "loss": 0.4622, "lr": 1.6122700810162967e-06, "epoch": 1.4739130434782608, "percentage": 73.7, "elapsed_time": "0:06:18", "remaining_time": "0:02:15"}
+{"current_steps": 340, "total_steps": 460, "loss": 0.3739, "lr": 1.5872342839067305e-06, "epoch": 1.4782608695652173, "percentage": 73.91, "elapsed_time": "0:06:19", "remaining_time": "0:02:13"}
+{"current_steps": 341, "total_steps": 460, "loss": 0.631, "lr": 1.5623576669323743e-06, "epoch": 1.482608695652174, "percentage": 74.13, "elapsed_time": "0:06:20", "remaining_time": "0:02:12"}
+{"current_steps": 342, "total_steps": 460, "loss": 0.5104, "lr": 1.5376413904023723e-06, "epoch": 1.4869565217391305, "percentage": 74.35, "elapsed_time": "0:06:21", "remaining_time": "0:02:11"}
+{"current_steps": 343, "total_steps": 460, "loss": 0.5094, "lr": 1.5130866071471717e-06, "epoch": 1.491304347826087, "percentage": 74.57, "elapsed_time": "0:06:22", "remaining_time": "0:02:10"}
+{"current_steps": 344, "total_steps": 460, "loss": 0.3944, "lr": 1.4886944624647647e-06, "epoch": 1.4956521739130435, "percentage": 74.78, "elapsed_time": "0:06:23", "remaining_time": "0:02:09"}
+{"current_steps": 345, "total_steps": 460, "loss": 0.6328, "lr": 1.4644660940672628e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:06:25", "remaining_time": "0:02:08"}
+{"current_steps": 346, "total_steps": 460, "loss": 0.4224, "lr": 1.4404026320278318e-06, "epoch": 1.5043478260869565, "percentage": 75.22, "elapsed_time": "0:06:26", "remaining_time": "0:02:07"}
+{"current_steps": 347, "total_steps": 460, "loss": 0.6405, "lr": 1.4165051987279832e-06, "epoch": 1.508695652173913, "percentage": 75.43, "elapsed_time": "0:06:27", "remaining_time": "0:02:06"}
+{"current_steps": 348, "total_steps": 460, "loss": 0.56, "lr": 1.3927749088052218e-06, "epoch": 1.5130434782608697, "percentage": 75.65, "elapsed_time": "0:06:28", "remaining_time": "0:02:04"}
+{"current_steps": 349, "total_steps": 460, "loss": 0.4332, "lr": 1.3692128691010592e-06, "epoch": 1.517391304347826, "percentage": 75.87, "elapsed_time": "0:06:29", "remaining_time": "0:02:03"}
+{"current_steps": 350, "total_steps": 460, "loss": 0.5717, "lr": 1.3458201786093795e-06, "epoch": 1.5217391304347827, "percentage": 76.09, "elapsed_time": "0:06:30", "remaining_time": "0:02:02"}
+{"current_steps": 351, "total_steps": 460, "loss": 0.3907, "lr": 1.3225979284251955e-06, "epoch": 1.526086956521739, "percentage": 76.3, "elapsed_time": "0:06:31", "remaining_time": "0:02:01"}
+{"current_steps": 352, "total_steps": 460, "loss": 0.5003, "lr": 1.2995472016937405e-06, "epoch": 1.5304347826086957, "percentage": 76.52, "elapsed_time": "0:06:32", "remaining_time": "0:02:00"}
+{"current_steps": 353, "total_steps": 460, "loss": 0.5317, "lr": 1.2766690735599569e-06, "epoch": 1.5347826086956522, "percentage": 76.74, "elapsed_time": "0:06:33", "remaining_time": "0:01:59"}
+{"current_steps": 354, "total_steps": 460, "loss": 0.43, "lr": 1.2539646111183452e-06, "epoch": 1.5391304347826087, "percentage": 76.96, "elapsed_time": "0:06:34", "remaining_time": "0:01:58"}
+{"current_steps": 355, "total_steps": 460, "loss": 0.5412, "lr": 1.2314348733631958e-06, "epoch": 1.5434782608695652, "percentage": 77.17, "elapsed_time": "0:06:35", "remaining_time": "0:01:57"}
+{"current_steps": 356, "total_steps": 460, "loss": 0.3157, "lr": 1.209080911139187e-06, "epoch": 1.5478260869565217, "percentage": 77.39, "elapsed_time": "0:06:37", "remaining_time": "0:01:55"}
+{"current_steps": 357, "total_steps": 460, "loss": 0.4854, "lr": 1.1869037670923817e-06, "epoch": 1.5521739130434784, "percentage": 77.61, "elapsed_time": "0:06:38", "remaining_time": "0:01:54"}
+{"current_steps": 358, "total_steps": 460, "loss": 0.6346, "lr": 1.1649044756215872e-06, "epoch": 1.5565217391304347, "percentage": 77.83, "elapsed_time": "0:06:39", "remaining_time": "0:01:53"}
+{"current_steps": 359, "total_steps": 460, "loss": 0.5448, "lr": 1.1430840628301093e-06, "epoch": 1.5608695652173914, "percentage": 78.04, "elapsed_time": "0:06:40", "remaining_time": "0:01:52"}
+{"current_steps": 360, "total_steps": 460, "loss": 0.568, "lr": 1.1214435464779006e-06, "epoch": 1.5652173913043477, "percentage": 78.26, "elapsed_time": "0:06:41", "remaining_time": "0:01:51"}
+{"current_steps": 361, "total_steps": 460, "loss": 0.7196, "lr": 1.099983935934077e-06, "epoch": 1.5695652173913044, "percentage": 78.48, "elapsed_time": "0:06:42", "remaining_time": "0:01:50"}
+{"current_steps": 362, "total_steps": 460, "loss": 0.6018, "lr": 1.0787062321298441e-06, "epoch": 1.5739130434782609, "percentage": 78.7, "elapsed_time": "0:06:43", "remaining_time": "0:01:49"}
+{"current_steps": 363, "total_steps": 460, "loss": 0.493, "lr": 1.0576114275118132e-06, "epoch": 1.5782608695652174, "percentage": 78.91, "elapsed_time": "0:06:44", "remaining_time": "0:01:48"}
+{"current_steps": 364, "total_steps": 460, "loss": 0.4647, "lr": 1.0367005059957097e-06, "epoch": 1.5826086956521739, "percentage": 79.13, "elapsed_time": "0:06:46", "remaining_time": "0:01:47"}
+{"current_steps": 365, "total_steps": 460, "loss": 0.4877, "lr": 1.0159744429204776e-06, "epoch": 1.5869565217391304, "percentage": 79.35, "elapsed_time": "0:06:47", "remaining_time": "0:01:45"}
+{"current_steps": 366, "total_steps": 460, "loss": 0.7812, "lr": 9.954342050027922e-07, "epoch": 1.591304347826087, "percentage": 79.57, "elapsed_time": "0:06:48", "remaining_time": "0:01:44"}
+{"current_steps": 367, "total_steps": 460, "loss": 0.6274, "lr": 9.75080750291965e-07, "epoch": 1.5956521739130434, "percentage": 79.78, "elapsed_time": "0:06:49", "remaining_time": "0:01:43"}
+{"current_steps": 368, "total_steps": 460, "loss": 0.4421, "lr": 9.549150281252633e-07, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "0:06:50", "remaining_time": "0:01:42"}
+{"current_steps": 369, "total_steps": 460, "loss": 0.5028, "lr": 9.349379790836243e-07, "epoch": 1.6043478260869564, "percentage": 80.22, "elapsed_time": "0:06:51", "remaining_time": "0:01:41"}
+{"current_steps": 370, "total_steps": 460, "loss": 0.5141, "lr": 9.151505349477901e-07, "epoch": 1.608695652173913, "percentage": 80.43, "elapsed_time": "0:06:52", "remaining_time": "0:01:40"}
+{"current_steps": 371, "total_steps": 460, "loss": 0.6085, "lr": 8.955536186548425e-07, "epoch": 1.6130434782608696, "percentage": 80.65, "elapsed_time": "0:06:53", "remaining_time": "0:01:39"}
+{"current_steps": 372, "total_steps": 460, "loss": 0.5389, "lr": 8.761481442551573e-07, "epoch": 1.617391304347826, "percentage": 80.87, "elapsed_time": "0:06:54", "remaining_time": "0:01:38"}
+{"current_steps": 373, "total_steps": 460, "loss": 0.6038, "lr": 8.569350168697705e-07, "epoch": 1.6217391304347826, "percentage": 81.09, "elapsed_time": "0:06:56", "remaining_time": "0:01:37"}
+{"current_steps": 374, "total_steps": 460, "loss": 0.4799, "lr": 8.379151326481588e-07, "epoch": 1.626086956521739, "percentage": 81.3, "elapsed_time": "0:06:57", "remaining_time": "0:01:35"}
+{"current_steps": 375, "total_steps": 460, "loss": 0.6335, "lr": 8.19089378726447e-07, "epoch": 1.6304347826086958, "percentage": 81.52, "elapsed_time": "0:06:58", "remaining_time": "0:01:34"}
+{"current_steps": 376, "total_steps": 460, "loss": 0.3404, "lr": 8.004586331860176e-07, "epoch": 1.634782608695652, "percentage": 81.74, "elapsed_time": "0:06:59", "remaining_time": "0:01:33"}
+{"current_steps": 377, "total_steps": 460, "loss": 0.4203, "lr": 7.820237650125711e-07, "epoch": 1.6391304347826088, "percentage": 81.96, "elapsed_time": "0:07:00", "remaining_time": "0:01:32"}
+{"current_steps": 378, "total_steps": 460, "loss": 0.7531, "lr": 7.637856340555822e-07, "epoch": 1.643478260869565, "percentage": 82.17, "elapsed_time": "0:07:01", "remaining_time": "0:01:31"}
+{"current_steps": 379, "total_steps": 460, "loss": 0.6053, "lr": 7.457450909881969e-07, "epoch": 1.6478260869565218, "percentage": 82.39, "elapsed_time": "0:07:02", "remaining_time": "0:01:30"}
+{"current_steps": 380, "total_steps": 460, "loss": 0.46, "lr": 7.279029772675572e-07, "epoch": 1.6521739130434783, "percentage": 82.61, "elapsed_time": "0:07:03", "remaining_time": "0:01:29"}
+{"current_steps": 381, "total_steps": 460, "loss": 0.3617, "lr": 7.102601250955526e-07, "epoch": 1.6565217391304348, "percentage": 82.83, "elapsed_time": "0:07:04", "remaining_time": "0:01:28"}
+{"current_steps": 382, "total_steps": 460, "loss": 0.739, "lr": 6.928173573800007e-07, "epoch": 1.6608695652173913, "percentage": 83.04, "elapsed_time": "0:07:05", "remaining_time": "0:01:26"}
+{"current_steps": 383, "total_steps": 460, "loss": 0.463, "lr": 6.755754876962711e-07, "epoch": 1.6652173913043478, "percentage": 83.26, "elapsed_time": "0:07:06", "remaining_time": "0:01:25"}
+{"current_steps": 384, "total_steps": 460, "loss": 0.5875, "lr": 6.585353202493322e-07, "epoch": 1.6695652173913045, "percentage": 83.48, "elapsed_time": "0:07:08", "remaining_time": "0:01:24"}
+{"current_steps": 385, "total_steps": 460, "loss": 0.5305, "lr": 6.416976498362432e-07, "epoch": 1.6739130434782608, "percentage": 83.7, "elapsed_time": "0:07:09", "remaining_time": "0:01:23"}
+{"current_steps": 386, "total_steps": 460, "loss": 0.4703, "lr": 6.250632618090868e-07, "epoch": 1.6782608695652175, "percentage": 83.91, "elapsed_time": "0:07:10", "remaining_time": "0:01:22"}
+{"current_steps": 387, "total_steps": 460, "loss": 0.4213, "lr": 6.086329320383311e-07, "epoch": 1.6826086956521737, "percentage": 84.13, "elapsed_time": "0:07:11", "remaining_time": "0:01:21"}
+{"current_steps": 388, "total_steps": 460, "loss": 0.4856, "lr": 5.924074268766422e-07, "epoch": 1.6869565217391305, "percentage": 84.35, "elapsed_time": "0:07:13", "remaining_time": "0:01:20"}
+{"current_steps": 389, "total_steps": 460, "loss": 0.5905, "lr": 5.763875031231464e-07, "epoch": 1.691304347826087, "percentage": 84.57, "elapsed_time": "0:07:14", "remaining_time": "0:01:19"}
+{"current_steps": 390, "total_steps": 460, "loss": 0.4024, "lr": 5.60573907988124e-07, "epoch": 1.6956521739130435, "percentage": 84.78, "elapsed_time": "0:07:15", "remaining_time": "0:01:18"}
+{"current_steps": 391, "total_steps": 460, "loss": 0.5591, "lr": 5.449673790581611e-07, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "0:07:16", "remaining_time": "0:01:16"}
+{"current_steps": 392, "total_steps": 460, "loss": 0.4434, "lr": 5.295686442617442e-07, "epoch": 1.7043478260869565, "percentage": 85.22, "elapsed_time": "0:07:17", "remaining_time": "0:01:15"}
+{"current_steps": 393, "total_steps": 460, "loss": 0.7183, "lr": 5.143784218353104e-07, "epoch": 1.7086956521739132, "percentage": 85.43, "elapsed_time": "0:07:18", "remaining_time": "0:01:14"}
+{"current_steps": 394, "total_steps": 460, "loss": 0.5925, "lr": 4.993974202897456e-07, "epoch": 1.7130434782608694, "percentage": 85.65, "elapsed_time": "0:07:19", "remaining_time": "0:01:13"}
+{"current_steps": 395, "total_steps": 460, "loss": 0.4831, "lr": 4.846263383773364e-07, "epoch": 1.7173913043478262, "percentage": 85.87, "elapsed_time": "0:07:20", "remaining_time": "0:01:12"}
+{"current_steps": 396, "total_steps": 460, "loss": 0.4127, "lr": 4.7006586505918273e-07, "epoch": 1.7217391304347827, "percentage": 86.09, "elapsed_time": "0:07:21", "remaining_time": "0:01:11"}
+{"current_steps": 397, "total_steps": 460, "loss": 0.5253, "lr": 4.557166794730572e-07, "epoch": 1.7260869565217392, "percentage": 86.3, "elapsed_time": "0:07:22", "remaining_time": "0:01:10"}
+{"current_steps": 398, "total_steps": 460, "loss": 0.5074, "lr": 4.4157945090173294e-07, "epoch": 1.7304347826086957, "percentage": 86.52, "elapsed_time": "0:07:24", "remaining_time": "0:01:09"}
+{"current_steps": 399, "total_steps": 460, "loss": 0.5885, "lr": 4.276548387417656e-07, "epoch": 1.7347826086956522, "percentage": 86.74, "elapsed_time": "0:07:25", "remaining_time": "0:01:08"}
+{"current_steps": 400, "total_steps": 460, "loss": 0.2754, "lr": 4.139434924727359e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:07:26", "remaining_time": "0:01:06"}
+{"current_steps": 400, "total_steps": 460, "eval_loss": 0.8716984987258911, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:07:27", "remaining_time": "0:01:07"}
+{"current_steps": 401, "total_steps": 460, "loss": 0.3822, "lr": 4.004460516269554e-07, "epoch": 1.7434782608695651, "percentage": 87.17, "elapsed_time": "0:07:28", "remaining_time": "0:01:05"}
+{"current_steps": 402, "total_steps": 460, "loss": 0.56, "lr": 3.8716314575964197e-07, "epoch": 1.7478260869565219, "percentage": 87.39, "elapsed_time": "0:07:29", "remaining_time": "0:01:04"}
+{"current_steps": 403, "total_steps": 460, "loss": 0.4291, "lr": 3.740953944195497e-07, "epoch": 1.7521739130434781, "percentage": 87.61, "elapsed_time": "0:07:30", "remaining_time": "0:01:03"}
+{"current_steps": 404, "total_steps": 460, "loss": 0.5948, "lr": 3.612434071200771e-07, "epoch": 1.7565217391304349, "percentage": 87.83, "elapsed_time": "0:07:31", "remaining_time": "0:01:02"}
+{"current_steps": 405, "total_steps": 460, "loss": 0.5438, "lr": 3.486077833108342e-07, "epoch": 1.7608695652173914, "percentage": 88.04, "elapsed_time": "0:07:32", "remaining_time": "0:01:01"}
+{"current_steps": 406, "total_steps": 460, "loss": 0.4442, "lr": 3.361891123496824e-07, "epoch": 1.7652173913043478, "percentage": 88.26, "elapsed_time": "0:07:34", "remaining_time": "0:01:00"}
+{"current_steps": 407, "total_steps": 460, "loss": 0.5722, "lr": 3.2398797347524656e-07, "epoch": 1.7695652173913043, "percentage": 88.48, "elapsed_time": "0:07:35", "remaining_time": "0:00:59"}
+{"current_steps": 408, "total_steps": 460, "loss": 0.5971, "lr": 3.1200493577989875e-07, "epoch": 1.7739130434782608, "percentage": 88.7, "elapsed_time": "0:07:36", "remaining_time": "0:00:58"}
+{"current_steps": 409, "total_steps": 460, "loss": 0.8116, "lr": 3.002405581832135e-07, "epoch": 1.7782608695652173, "percentage": 88.91, "elapsed_time": "0:07:37", "remaining_time": "0:00:57"}
+{"current_steps": 410, "total_steps": 460, "loss": 0.6865, "lr": 2.88695389405898e-07, "epoch": 1.7826086956521738, "percentage": 89.13, "elapsed_time": "0:07:38", "remaining_time": "0:00:55"}
+{"current_steps": 411, "total_steps": 460, "loss": 0.5216, "lr": 2.7736996794419767e-07, "epoch": 1.7869565217391306, "percentage": 89.35, "elapsed_time": "0:07:39", "remaining_time": "0:00:54"}
+{"current_steps": 412, "total_steps": 460, "loss": 0.6106, "lr": 2.662648220447811e-07, "epoch": 1.7913043478260868, "percentage": 89.57, "elapsed_time": "0:07:40", "remaining_time": "0:00:53"}
+{"current_steps": 413, "total_steps": 460, "loss": 0.636, "lr": 2.5538046968010097e-07, "epoch": 1.7956521739130435, "percentage": 89.78, "elapsed_time": "0:07:41", "remaining_time": "0:00:52"}
+{"current_steps": 414, "total_steps": 460, "loss": 0.6309, "lr": 2.447174185242324e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "0:07:42", "remaining_time": "0:00:51"}
+{"current_steps": 415, "total_steps": 460, "loss": 0.2978, "lr": 2.3427616592919587e-07, "epoch": 1.8043478260869565, "percentage": 90.22, "elapsed_time": "0:07:43", "remaining_time": "0:00:50"}
+{"current_steps": 416, "total_steps": 460, "loss": 0.3982, "lr": 2.240571989017598e-07, "epoch": 1.808695652173913, "percentage": 90.43, "elapsed_time": "0:07:44", "remaining_time": "0:00:49"}
+{"current_steps": 417, "total_steps": 460, "loss": 0.4452, "lr": 2.1406099408072256e-07, "epoch": 1.8130434782608695, "percentage": 90.65, "elapsed_time": "0:07:46", "remaining_time": "0:00:48"}
+{"current_steps": 418, "total_steps": 460, "loss": 0.5546, "lr": 2.0428801771468388e-07, "epoch": 1.8173913043478263, "percentage": 90.87, "elapsed_time": "0:07:47", "remaining_time": "0:00:46"}
+{"current_steps": 419, "total_steps": 460, "loss": 0.6283, "lr": 1.947387256402966e-07, "epoch": 1.8217391304347825, "percentage": 91.09, "elapsed_time": "0:07:48", "remaining_time": "0:00:45"}
+{"current_steps": 420, "total_steps": 460, "loss": 0.5615, "lr": 1.8541356326100436e-07, "epoch": 1.8260869565217392, "percentage": 91.3, "elapsed_time": "0:07:49", "remaining_time": "0:00:44"}
+{"current_steps": 421, "total_steps": 460, "loss": 0.6423, "lr": 1.7631296552626687e-07, "epoch": 1.8304347826086955, "percentage": 91.52, "elapsed_time": "0:07:50", "remaining_time": "0:00:43"}
+{"current_steps": 422, "total_steps": 460, "loss": 0.413, "lr": 1.6743735691127639e-07, "epoch": 1.8347826086956522, "percentage": 91.74, "elapsed_time": "0:07:51", "remaining_time": "0:00:42"}
+{"current_steps": 423, "total_steps": 460, "loss": 0.5572, "lr": 1.5878715139715395e-07, "epoch": 1.8391304347826087, "percentage": 91.96, "elapsed_time": "0:07:52", "remaining_time": "0:00:41"}
+{"current_steps": 424, "total_steps": 460, "loss": 0.4556, "lr": 1.5036275245164377e-07, "epoch": 1.8434782608695652, "percentage": 92.17, "elapsed_time": "0:07:53", "remaining_time": "0:00:40"}
+{"current_steps": 425, "total_steps": 460, "loss": 0.3541, "lr": 1.4216455301029274e-07, "epoch": 1.8478260869565217, "percentage": 92.39, "elapsed_time": "0:07:54", "remaining_time": "0:00:39"}
+{"current_steps": 426, "total_steps": 460, "loss": 0.4864, "lr": 1.341929354581234e-07, "epoch": 1.8521739130434782, "percentage": 92.61, "elapsed_time": "0:07:55", "remaining_time": "0:00:37"}
+{"current_steps": 427, "total_steps": 460, "loss": 0.4733, "lr": 1.2644827161179763e-07, "epoch": 1.856521739130435, "percentage": 92.83, "elapsed_time": "0:07:57", "remaining_time": "0:00:36"}
+{"current_steps": 428, "total_steps": 460, "loss": 0.4404, "lr": 1.1893092270227724e-07, "epoch": 1.8608695652173912, "percentage": 93.04, "elapsed_time": "0:07:58", "remaining_time": "0:00:35"}
+{"current_steps": 429, "total_steps": 460, "loss": 0.5796, "lr": 1.1164123935797189e-07, "epoch": 1.865217391304348, "percentage": 93.26, "elapsed_time": "0:07:59", "remaining_time": "0:00:34"}
+{"current_steps": 430, "total_steps": 460, "loss": 0.5444, "lr": 1.0457956158838545e-07, "epoch": 1.8695652173913042, "percentage": 93.48, "elapsed_time": "0:08:00", "remaining_time": "0:00:33"}
+{"current_steps": 431, "total_steps": 460, "loss": 0.7298, "lr": 9.774621876825985e-08, "epoch": 1.873913043478261, "percentage": 93.7, "elapsed_time": "0:08:01", "remaining_time": "0:00:32"}
+{"current_steps": 432, "total_steps": 460, "loss": 0.542, "lr": 9.114152962220734e-08, "epoch": 1.8782608695652174, "percentage": 93.91, "elapsed_time": "0:08:02", "remaining_time": "0:00:31"}
+{"current_steps": 433, "total_steps": 460, "loss": 0.6349, "lr": 8.476580220984854e-08, "epoch": 1.882608695652174, "percentage": 94.13, "elapsed_time": "0:08:03", "remaining_time": "0:00:30"}
+{"current_steps": 434, "total_steps": 460, "loss": 0.4515, "lr": 7.861933391144272e-08, "epoch": 1.8869565217391304, "percentage": 94.35, "elapsed_time": "0:08:04", "remaining_time": "0:00:29"}
+{"current_steps": 435, "total_steps": 460, "loss": 0.6042, "lr": 7.270241141401568e-08, "epoch": 1.891304347826087, "percentage": 94.57, "elapsed_time": "0:08:05", "remaining_time": "0:00:27"}
+{"current_steps": 436, "total_steps": 460, "loss": 0.3209, "lr": 6.701531069799039e-08, "epoch": 1.8956521739130436, "percentage": 94.78, "elapsed_time": "0:08:06", "remaining_time": "0:00:26"}
+{"current_steps": 437, "total_steps": 460, "loss": 0.6095, "lr": 6.15582970243117e-08, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "0:08:07", "remaining_time": "0:00:25"}
+{"current_steps": 438, "total_steps": 460, "loss": 0.5979, "lr": 5.633162492207633e-08, "epoch": 1.9043478260869566, "percentage": 95.22, "elapsed_time": "0:08:09", "remaining_time": "0:00:24"}
+{"current_steps": 439, "total_steps": 460, "loss": 0.662, "lr": 5.133553817665948e-08, "epoch": 1.908695652173913, "percentage": 95.43, "elapsed_time": "0:08:10", "remaining_time": "0:00:23"}
+{"current_steps": 440, "total_steps": 460, "loss": 0.5815, "lr": 4.657026981834623e-08, "epoch": 1.9130434782608696, "percentage": 95.65, "elapsed_time": "0:08:11", "remaining_time": "0:00:22"}
+{"current_steps": 441, "total_steps": 460, "loss": 0.3505, "lr": 4.203604211145851e-08, "epoch": 1.9173913043478261, "percentage": 95.87, "elapsed_time": "0:08:12", "remaining_time": "0:00:21"}
+{"current_steps": 442, "total_steps": 460, "loss": 0.4539, "lr": 3.773306654399234e-08, "epoch": 1.9217391304347826, "percentage": 96.09, "elapsed_time": "0:08:13", "remaining_time": "0:00:20"}
+{"current_steps": 443, "total_steps": 460, "loss": 0.5395, "lr": 3.366154381775011e-08, "epoch": 1.9260869565217391, "percentage": 96.3, "elapsed_time": "0:08:14", "remaining_time": "0:00:18"}
+{"current_steps": 444, "total_steps": 460, "loss": 0.5999, "lr": 2.9821663838981994e-08, "epoch": 1.9304347826086956, "percentage": 96.52, "elapsed_time": "0:08:15", "remaining_time": "0:00:17"}
+{"current_steps": 445, "total_steps": 460, "loss": 0.3673, "lr": 2.6213605709525803e-08, "epoch": 1.9347826086956523, "percentage": 96.74, "elapsed_time": "0:08:16", "remaining_time": "0:00:16"}
+{"current_steps": 446, "total_steps": 460, "loss": 0.3699, "lr": 2.283753771845587e-08, "epoch": 1.9391304347826086, "percentage": 96.96, "elapsed_time": "0:08:17", "remaining_time": "0:00:15"}
+{"current_steps": 447, "total_steps": 460, "loss": 0.6307, "lr": 1.969361733423103e-08, "epoch": 1.9434782608695653, "percentage": 97.17, "elapsed_time": "0:08:18", "remaining_time": "0:00:14"}
+{"current_steps": 448, "total_steps": 460, "loss": 0.5428, "lr": 1.6781991197352133e-08, "epoch": 1.9478260869565216, "percentage": 97.39, "elapsed_time": "0:08:19", "remaining_time": "0:00:13"}
+{"current_steps": 449, "total_steps": 460, "loss": 0.4092, "lr": 1.4102795113520307e-08, "epoch": 1.9521739130434783, "percentage": 97.61, "elapsed_time": "0:08:21", "remaining_time": "0:00:12"}
+{"current_steps": 450, "total_steps": 460, "loss": 0.4938, "lr": 1.1656154047303691e-08, "epoch": 1.9565217391304348, "percentage": 97.83, "elapsed_time": "0:08:22", "remaining_time": "0:00:11"}
+{"current_steps": 451, "total_steps": 460, "loss": 0.7239, "lr": 9.442182116309872e-09, "epoch": 1.9608695652173913, "percentage": 98.04, "elapsed_time": "0:08:23", "remaining_time": "0:00:10"}
+{"current_steps": 452, "total_steps": 460, "loss": 0.3265, "lr": 7.460982585860144e-09, "epoch": 1.9652173913043478, "percentage": 98.26, "elapsed_time": "0:08:24", "remaining_time": "0:00:08"}
+{"current_steps": 453, "total_steps": 460, "loss": 0.5066, "lr": 5.712647864176135e-09, "epoch": 1.9695652173913043, "percentage": 98.48, "elapsed_time": "0:08:25", "remaining_time": "0:00:07"}
+{"current_steps": 454, "total_steps": 460, "loss": 0.5468, "lr": 4.197259498067707e-09, "epoch": 1.973913043478261, "percentage": 98.7, "elapsed_time": "0:08:26", "remaining_time": "0:00:06"}
+{"current_steps": 455, "total_steps": 460, "loss": 0.4732, "lr": 2.9148881691298812e-09, "epoch": 1.9782608695652173, "percentage": 98.91, "elapsed_time": "0:08:27", "remaining_time": "0:00:05"}
+{"current_steps": 456, "total_steps": 460, "loss": 0.5222, "lr": 1.865593690446588e-09, "epoch": 1.982608695652174, "percentage": 99.13, "elapsed_time": "0:08:28", "remaining_time": "0:00:04"}
+{"current_steps": 457, "total_steps": 460, "loss": 0.4729, "lr": 1.0494250038006747e-09, "epoch": 1.9869565217391303, "percentage": 99.35, "elapsed_time": "0:08:29", "remaining_time": "0:00:03"}
+{"current_steps": 458, "total_steps": 460, "loss": 0.5507, "lr": 4.664201773896259e-10, "epoch": 1.991304347826087, "percentage": 99.57, "elapsed_time": "0:08:30", "remaining_time": "0:00:02"}
+{"current_steps": 459, "total_steps": 460, "loss": 0.7135, "lr": 1.1660640405308787e-10, "epoch": 1.9956521739130435, "percentage": 99.78, "elapsed_time": "0:08:32", "remaining_time": "0:00:01"}
+{"current_steps": 460, "total_steps": 460, "loss": 0.4461, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:33", "remaining_time": "0:00:00"}
+{"current_steps": 460, "total_steps": 460, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:58", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,3278 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004347826086956522,
+      "grad_norm": 30.10830424636028,
+      "learning_rate": 9.999883393595949e-06,
+      "loss": 1.1079,
+      "step": 1
+    },
+    {
+      "epoch": 0.008695652173913044,
+      "grad_norm": 8.45234959602764,
+      "learning_rate": 9.999533579822611e-06,
+      "loss": 1.0206,
+      "step": 2
+    },
+    {
+      "epoch": 0.013043478260869565,
+      "grad_norm": 12.590663103699724,
+      "learning_rate": 9.9989505749962e-06,
+      "loss": 0.8925,
+      "step": 3
+    },
+    {
+      "epoch": 0.017391304347826087,
+      "grad_norm": 7.5496112069603,
+      "learning_rate": 9.998134406309555e-06,
+      "loss": 0.8343,
+      "step": 4
+    },
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 4.862205369093291,
+      "learning_rate": 9.99708511183087e-06,
+      "loss": 0.6931,
+      "step": 5
+    },
+    {
+      "epoch": 0.02608695652173913,
+      "grad_norm": 5.355958790833682,
+      "learning_rate": 9.995802740501933e-06,
+      "loss": 0.8249,
+      "step": 6
+    },
+    {
+      "epoch": 0.030434782608695653,
+      "grad_norm": 4.813975580629782,
+      "learning_rate": 9.994287352135826e-06,
+      "loss": 0.8491,
+      "step": 7
+    },
+    {
+      "epoch": 0.034782608695652174,
+      "grad_norm": 4.209698696676494,
+      "learning_rate": 9.99253901741414e-06,
+      "loss": 0.7867,
+      "step": 8
+    },
+    {
+      "epoch": 0.0391304347826087,
+      "grad_norm": 5.3082388200901685,
+      "learning_rate": 9.99055781788369e-06,
+      "loss": 0.559,
+      "step": 9
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 4.186725588547987,
+      "learning_rate": 9.988343845952697e-06,
+      "loss": 0.8831,
+      "step": 10
+    },
+    {
+      "epoch": 0.04782608695652174,
+      "grad_norm": 3.6882197290844796,
+      "learning_rate": 9.985897204886481e-06,
+      "loss": 0.7416,
+      "step": 11
+    },
+    {
+      "epoch": 0.05217391304347826,
+      "grad_norm": 4.265123735321938,
+      "learning_rate": 9.983218008802648e-06,
+      "loss": 0.7885,
+      "step": 12
+    },
+    {
+      "epoch": 0.05652173913043478,
+      "grad_norm": 3.9942127849301583,
+      "learning_rate": 9.98030638266577e-06,
+      "loss": 0.8622,
+      "step": 13
+    },
+    {
+      "epoch": 0.06086956521739131,
+      "grad_norm": 3.2098436387002125,
+      "learning_rate": 9.977162462281544e-06,
+      "loss": 0.7362,
+      "step": 14
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 3.732980481277789,
+      "learning_rate": 9.973786394290475e-06,
+      "loss": 0.7865,
+      "step": 15
+    },
+    {
+      "epoch": 0.06956521739130435,
+      "grad_norm": 4.634256740235812,
+      "learning_rate": 9.970178336161018e-06,
+      "loss": 0.7807,
+      "step": 16
+    },
+    {
+      "epoch": 0.07391304347826087,
+      "grad_norm": 3.377746664235735,
+      "learning_rate": 9.96633845618225e-06,
+      "loss": 0.945,
+      "step": 17
+    },
+    {
+      "epoch": 0.0782608695652174,
+      "grad_norm": 3.495299939802682,
+      "learning_rate": 9.962266933456008e-06,
+      "loss": 0.5839,
+      "step": 18
+    },
+    {
+      "epoch": 0.08260869565217391,
+      "grad_norm": 3.7360952184020655,
+      "learning_rate": 9.957963957888542e-06,
+      "loss": 0.8982,
+      "step": 19
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 4.253452751051838,
+      "learning_rate": 9.953429730181653e-06,
+      "loss": 0.7377,
+      "step": 20
+    },
+    {
+      "epoch": 0.09130434782608696,
+      "grad_norm": 4.19176844357134,
+      "learning_rate": 9.94866446182334e-06,
+      "loss": 0.8799,
+      "step": 21
+    },
+    {
+      "epoch": 0.09565217391304348,
+      "grad_norm": 7.890793002340963,
+      "learning_rate": 9.943668375077926e-06,
+      "loss": 0.9303,
+      "step": 22
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.112696318296595,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 0.9712,
+      "step": 23
+    },
+    {
+      "epoch": 0.10434782608695652,
+      "grad_norm": 4.16656380286025,
+      "learning_rate": 9.932984689302012e-06,
+      "loss": 0.9881,
+      "step": 24
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 5.254098871150094,
+      "learning_rate": 9.927297588585984e-06,
+      "loss": 0.7804,
+      "step": 25
+    },
+    {
+      "epoch": 0.11304347826086956,
+      "grad_norm": 4.860475419154404,
+      "learning_rate": 9.921380666088558e-06,
+      "loss": 0.692,
+      "step": 26
+    },
+    {
+      "epoch": 0.11739130434782609,
+      "grad_norm": 4.121016653034456,
+      "learning_rate": 9.915234197790153e-06,
+      "loss": 0.9255,
+      "step": 27
+    },
+    {
+      "epoch": 0.12173913043478261,
+      "grad_norm": 3.5062273892646836,
+      "learning_rate": 9.908858470377793e-06,
+      "loss": 0.9835,
+      "step": 28
+    },
+    {
+      "epoch": 0.12608695652173912,
+      "grad_norm": 3.9902741607607344,
+      "learning_rate": 9.902253781231741e-06,
+      "loss": 0.6559,
+      "step": 29
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 3.72173213984111,
+      "learning_rate": 9.895420438411616e-06,
+      "loss": 0.8773,
+      "step": 30
+    },
+    {
+      "epoch": 0.13478260869565217,
+      "grad_norm": 4.1059197008642485,
+      "learning_rate": 9.88835876064203e-06,
+      "loss": 0.763,
+      "step": 31
+    },
+    {
+      "epoch": 0.1391304347826087,
+      "grad_norm": 3.448061821839538,
+      "learning_rate": 9.881069077297724e-06,
+      "loss": 0.8204,
+      "step": 32
+    },
+    {
+      "epoch": 0.14347826086956522,
+      "grad_norm": 3.5353256397883577,
+      "learning_rate": 9.873551728388203e-06,
+      "loss": 0.7933,
+      "step": 33
+    },
+    {
+      "epoch": 0.14782608695652175,
+      "grad_norm": 4.516883030605288,
+      "learning_rate": 9.865807064541878e-06,
+      "loss": 0.8324,
+      "step": 34
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 4.017654364372926,
+      "learning_rate": 9.857835446989708e-06,
+      "loss": 1.1247,
+      "step": 35
+    },
+    {
+      "epoch": 0.1565217391304348,
+      "grad_norm": 3.9881313932819276,
+      "learning_rate": 9.849637247548356e-06,
+      "loss": 0.5466,
+      "step": 36
+    },
+    {
+      "epoch": 0.1608695652173913,
+      "grad_norm": 4.196181042954896,
+      "learning_rate": 9.841212848602848e-06,
+      "loss": 0.9061,
+      "step": 37
+    },
+    {
+      "epoch": 0.16521739130434782,
+      "grad_norm": 3.971698021758679,
+      "learning_rate": 9.832562643088724e-06,
+      "loss": 0.8046,
+      "step": 38
+    },
+    {
+      "epoch": 0.16956521739130434,
+      "grad_norm": 3.994700871237702,
+      "learning_rate": 9.823687034473734e-06,
+      "loss": 0.866,
+      "step": 39
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 4.300878065609124,
+      "learning_rate": 9.814586436738998e-06,
+      "loss": 1.0917,
+      "step": 40
+    },
+    {
+      "epoch": 0.1782608695652174,
+      "grad_norm": 4.920655306563475,
+      "learning_rate": 9.805261274359705e-06,
+      "loss": 0.8076,
+      "step": 41
+    },
+    {
+      "epoch": 0.1826086956521739,
+      "grad_norm": 3.753606357325065,
+      "learning_rate": 9.795711982285317e-06,
+      "loss": 0.8976,
+      "step": 42
+    },
+    {
+      "epoch": 0.18695652173913044,
+      "grad_norm": 3.2168659658690495,
+      "learning_rate": 9.785939005919279e-06,
+      "loss": 0.8099,
+      "step": 43
+    },
+    {
+      "epoch": 0.19130434782608696,
+      "grad_norm": 3.0870127735418267,
+      "learning_rate": 9.775942801098241e-06,
+      "loss": 0.7528,
+      "step": 44
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 4.360067131834863,
+      "learning_rate": 9.765723834070805e-06,
+      "loss": 0.8897,
+      "step": 45
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.9788089959406663,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 0.6911,
+      "step": 46
+    },
+    {
+      "epoch": 0.20434782608695654,
+      "grad_norm": 4.9444885243270456,
+      "learning_rate": 9.7446195303199e-06,
+      "loss": 0.9875,
+      "step": 47
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 3.0578360199041184,
+      "learning_rate": 9.733735177955219e-06,
+      "loss": 0.5668,
+      "step": 48
+    },
+    {
+      "epoch": 0.21304347826086956,
+      "grad_norm": 3.977296603047938,
+      "learning_rate": 9.722630032055804e-06,
+      "loss": 0.8334,
+      "step": 49
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 2.7972114537424146,
+      "learning_rate": 9.711304610594104e-06,
+      "loss": 0.8011,
+      "step": 50
+    },
+    {
+      "epoch": 0.2217391304347826,
+      "grad_norm": 3.236782797956836,
+      "learning_rate": 9.699759441816788e-06,
+      "loss": 0.6684,
+      "step": 51
+    },
+    {
+      "epoch": 0.22608695652173913,
+      "grad_norm": 4.416621854566764,
+      "learning_rate": 9.687995064220102e-06,
+      "loss": 0.8834,
+      "step": 52
+    },
+    {
+      "epoch": 0.23043478260869565,
+      "grad_norm": 3.3671336274674117,
+      "learning_rate": 9.676012026524755e-06,
+      "loss": 0.6965,
+      "step": 53
+    },
+    {
+      "epoch": 0.23478260869565218,
+      "grad_norm": 3.9913392830992267,
+      "learning_rate": 9.66381088765032e-06,
+      "loss": 0.938,
+      "step": 54
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 3.760436305337915,
+      "learning_rate": 9.651392216689167e-06,
+      "loss": 1.0933,
+      "step": 55
+    },
+    {
+      "epoch": 0.24347826086956523,
+      "grad_norm": 2.7129860608500365,
+      "learning_rate": 9.638756592879923e-06,
+      "loss": 0.6742,
+      "step": 56
+    },
+    {
+      "epoch": 0.24782608695652175,
+      "grad_norm": 3.223448161038934,
+      "learning_rate": 9.625904605580452e-06,
+      "loss": 0.7107,
+      "step": 57
+    },
+    {
+      "epoch": 0.25217391304347825,
+      "grad_norm": 3.5533175943979782,
+      "learning_rate": 9.61283685424036e-06,
+      "loss": 0.8229,
+      "step": 58
+    },
+    {
+      "epoch": 0.2565217391304348,
+      "grad_norm": 4.469619534798299,
+      "learning_rate": 9.599553948373047e-06,
+      "loss": 0.6858,
+      "step": 59
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 3.759555454725975,
+      "learning_rate": 9.586056507527266e-06,
+      "loss": 0.8061,
+      "step": 60
+    },
+    {
+      "epoch": 0.26521739130434785,
+      "grad_norm": 4.237886610909077,
+      "learning_rate": 9.572345161258235e-06,
+      "loss": 0.8282,
+      "step": 61
+    },
+    {
+      "epoch": 0.26956521739130435,
+      "grad_norm": 3.2748103648644546,
+      "learning_rate": 9.558420549098269e-06,
+      "loss": 0.8382,
+      "step": 62
+    },
+    {
+      "epoch": 0.27391304347826084,
+      "grad_norm": 3.610728507102718,
+      "learning_rate": 9.544283320526943e-06,
+      "loss": 0.7024,
+      "step": 63
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 3.0936408893059473,
+      "learning_rate": 9.529934134940819e-06,
+      "loss": 0.6702,
+      "step": 64
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 3.168622390524342,
+      "learning_rate": 9.515373661622665e-06,
+      "loss": 0.8201,
+      "step": 65
+    },
+    {
+      "epoch": 0.28695652173913044,
+      "grad_norm": 4.875869865721861,
+      "learning_rate": 9.500602579710256e-06,
+      "loss": 0.6873,
+      "step": 66
+    },
+    {
+      "epoch": 0.29130434782608694,
+      "grad_norm": 3.194305690371054,
+      "learning_rate": 9.48562157816469e-06,
+      "loss": 0.667,
+      "step": 67
+    },
+    {
+      "epoch": 0.2956521739130435,
+      "grad_norm": 3.3142405160528488,
+      "learning_rate": 9.470431355738257e-06,
+      "loss": 0.8051,
+      "step": 68
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.262816871896188,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 1.0722,
+      "step": 69
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 3.599023595923798,
+      "learning_rate": 9.439426092011877e-06,
+      "loss": 0.7878,
+      "step": 70
+    },
+    {
+      "epoch": 0.30869565217391304,
+      "grad_norm": 5.109580952764362,
+      "learning_rate": 9.423612496876856e-06,
+      "loss": 0.9254,
+      "step": 71
+    },
+    {
+      "epoch": 0.3130434782608696,
+      "grad_norm": 3.948434430815186,
+      "learning_rate": 9.407592573123359e-06,
+      "loss": 0.6889,
+      "step": 72
+    },
+    {
+      "epoch": 0.3173913043478261,
+      "grad_norm": 4.109705050607312,
+      "learning_rate": 9.39136706796167e-06,
+      "loss": 0.9096,
+      "step": 73
+    },
+    {
+      "epoch": 0.3217391304347826,
+      "grad_norm": 4.685155702670585,
+      "learning_rate": 9.374936738190913e-06,
+      "loss": 1.0758,
+      "step": 74
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 3.5583319543828535,
+      "learning_rate": 9.358302350163758e-06,
+      "loss": 0.9975,
+      "step": 75
+    },
+    {
+      "epoch": 0.33043478260869563,
+      "grad_norm": 4.132644653851408,
+      "learning_rate": 9.341464679750669e-06,
+      "loss": 0.815,
+      "step": 76
+    },
+    {
+      "epoch": 0.3347826086956522,
+      "grad_norm": 4.012241097059724,
+      "learning_rate": 9.32442451230373e-06,
+      "loss": 0.7434,
+      "step": 77
+    },
+    {
+      "epoch": 0.3391304347826087,
+      "grad_norm": 4.056336217070605,
+      "learning_rate": 9.307182642620001e-06,
+      "loss": 0.9034,
+      "step": 78
+    },
+    {
+      "epoch": 0.34347826086956523,
+      "grad_norm": 5.018176130315487,
+      "learning_rate": 9.289739874904448e-06,
+      "loss": 0.78,
+      "step": 79
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 4.587214956739399,
+      "learning_rate": 9.272097022732444e-06,
+      "loss": 0.6927,
+      "step": 80
+    },
+    {
+      "epoch": 0.3521739130434783,
+      "grad_norm": 3.3889605410886965,
+      "learning_rate": 9.254254909011805e-06,
+      "loss": 0.6882,
+      "step": 81
+    },
+    {
+      "epoch": 0.3565217391304348,
+      "grad_norm": 4.148693119867694,
+      "learning_rate": 9.236214365944418e-06,
+      "loss": 0.7601,
+      "step": 82
+    },
+    {
+      "epoch": 0.36086956521739133,
+      "grad_norm": 5.706866359933195,
+      "learning_rate": 9.217976234987429e-06,
+      "loss": 0.8002,
+      "step": 83
+    },
+    {
+      "epoch": 0.3652173913043478,
+      "grad_norm": 3.761765555379755,
+      "learning_rate": 9.199541366813984e-06,
+      "loss": 0.9108,
+      "step": 84
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 4.358469235825558,
+      "learning_rate": 9.180910621273555e-06,
+      "loss": 0.9495,
+      "step": 85
+    },
+    {
+      "epoch": 0.3739130434782609,
+      "grad_norm": 5.19380750583511,
+      "learning_rate": 9.16208486735184e-06,
+      "loss": 0.796,
+      "step": 86
+    },
+    {
+      "epoch": 0.3782608695652174,
+      "grad_norm": 4.40504584356501,
+      "learning_rate": 9.14306498313023e-06,
+      "loss": 0.9202,
+      "step": 87
+    },
+    {
+      "epoch": 0.3826086956521739,
+      "grad_norm": 4.154237190106969,
+      "learning_rate": 9.123851855744842e-06,
+      "loss": 0.868,
+      "step": 88
+    },
+    {
+      "epoch": 0.3869565217391304,
+      "grad_norm": 4.649679162473941,
+      "learning_rate": 9.10444638134516e-06,
+      "loss": 0.8633,
+      "step": 89
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 3.659547834041831,
+      "learning_rate": 9.08484946505221e-06,
+      "loss": 0.4639,
+      "step": 90
+    },
+    {
+      "epoch": 0.39565217391304347,
+      "grad_norm": 3.772374253015877,
+      "learning_rate": 9.065062020916376e-06,
+      "loss": 1.0704,
+      "step": 91
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.044411509493095,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.7493,
+      "step": 92
+    },
+    {
+      "epoch": 0.4043478260869565,
+      "grad_norm": 5.291875262805496,
+      "learning_rate": 9.024919249708034e-06,
+      "loss": 0.6936,
+      "step": 93
+    },
+    {
+      "epoch": 0.40869565217391307,
+      "grad_norm": 4.964153371450278,
+      "learning_rate": 9.004565794997209e-06,
+      "loss": 1.2122,
+      "step": 94
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 4.207843872473807,
+      "learning_rate": 8.984025557079523e-06,
+      "loss": 0.8132,
+      "step": 95
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 6.132343241796095,
+      "learning_rate": 8.963299494004292e-06,
+      "loss": 0.8736,
+      "step": 96
+    },
+    {
+      "epoch": 0.4217391304347826,
+      "grad_norm": 2.6269984574966365,
+      "learning_rate": 8.942388572488188e-06,
+      "loss": 0.8824,
+      "step": 97
+    },
+    {
+      "epoch": 0.4260869565217391,
+      "grad_norm": 4.095187049220555,
+      "learning_rate": 8.921293767870157e-06,
+      "loss": 0.959,
+      "step": 98
+    },
+    {
+      "epoch": 0.43043478260869567,
+      "grad_norm": 4.199828959982439,
+      "learning_rate": 8.900016064065923e-06,
+      "loss": 0.9751,
+      "step": 99
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 3.3743148628694457,
+      "learning_rate": 8.8785564535221e-06,
+      "loss": 0.734,
+      "step": 100
+    },
+    {
+      "epoch": 0.4391304347826087,
+      "grad_norm": 7.940326346556448,
+      "learning_rate": 8.85691593716989e-06,
+      "loss": 0.9944,
+      "step": 101
+    },
+    {
+      "epoch": 0.4434782608695652,
+      "grad_norm": 3.7567313163102205,
+      "learning_rate": 8.835095524378413e-06,
+      "loss": 0.8144,
+      "step": 102
+    },
+    {
+      "epoch": 0.44782608695652176,
+      "grad_norm": 5.966995376699713,
+      "learning_rate": 8.81309623290762e-06,
+      "loss": 1.1465,
+      "step": 103
+    },
+    {
+      "epoch": 0.45217391304347826,
+      "grad_norm": 2.6433858040324907,
+      "learning_rate": 8.790919088860815e-06,
+      "loss": 0.5616,
+      "step": 104
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 4.060660371560683,
+      "learning_rate": 8.768565126636806e-06,
+      "loss": 1.0732,
+      "step": 105
+    },
+    {
+      "epoch": 0.4608695652173913,
+      "grad_norm": 4.243491466169052,
+      "learning_rate": 8.746035388881655e-06,
+      "loss": 0.8622,
+      "step": 106
+    },
+    {
+      "epoch": 0.4652173913043478,
+      "grad_norm": 3.9070077494772115,
+      "learning_rate": 8.723330926440045e-06,
+      "loss": 0.9579,
+      "step": 107
+    },
+    {
+      "epoch": 0.46956521739130436,
+      "grad_norm": 3.315573230842983,
+      "learning_rate": 8.70045279830626e-06,
+      "loss": 0.8125,
+      "step": 108
+    },
+    {
+      "epoch": 0.47391304347826085,
+      "grad_norm": 3.418028185224645,
+      "learning_rate": 8.677402071574806e-06,
+      "loss": 0.5519,
+      "step": 109
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 2.3583616451084706,
+      "learning_rate": 8.65417982139062e-06,
+      "loss": 0.5283,
+      "step": 110
+    },
+    {
+      "epoch": 0.4826086956521739,
+      "grad_norm": 3.5720694264768937,
+      "learning_rate": 8.630787130898943e-06,
+      "loss": 0.652,
+      "step": 111
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 3.5329821794242533,
+      "learning_rate": 8.60722509119478e-06,
+      "loss": 0.6831,
+      "step": 112
+    },
+    {
+      "epoch": 0.49130434782608695,
+      "grad_norm": 3.375309035663863,
+      "learning_rate": 8.583494801272018e-06,
+      "loss": 0.8531,
+      "step": 113
+    },
+    {
+      "epoch": 0.4956521739130435,
+      "grad_norm": 3.5989978695462663,
+      "learning_rate": 8.559597367972168e-06,
+      "loss": 0.6959,
+      "step": 114
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.5589265753781603,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.7375,
+      "step": 115
+    },
+    {
+      "epoch": 0.5043478260869565,
+      "grad_norm": 4.346599181980232,
+      "learning_rate": 8.511305537535238e-06,
+      "loss": 0.8875,
+      "step": 116
+    },
+    {
+      "epoch": 0.508695652173913,
+      "grad_norm": 3.387720172084152,
+      "learning_rate": 8.48691339285283e-06,
+      "loss": 0.593,
+      "step": 117
+    },
+    {
+      "epoch": 0.5130434782608696,
+      "grad_norm": 5.311451544282254,
+      "learning_rate": 8.462358609597629e-06,
+      "loss": 0.7789,
+      "step": 118
+    },
+    {
+      "epoch": 0.5173913043478261,
+      "grad_norm": 3.8052363309273147,
+      "learning_rate": 8.437642333067626e-06,
+      "loss": 0.9247,
+      "step": 119
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 3.803654644029343,
+      "learning_rate": 8.412765716093273e-06,
+      "loss": 0.9483,
+      "step": 120
+    },
+    {
+      "epoch": 0.5260869565217391,
+      "grad_norm": 3.120957568605628,
+      "learning_rate": 8.387729918983706e-06,
+      "loss": 0.7953,
+      "step": 121
+    },
+    {
+      "epoch": 0.5304347826086957,
+      "grad_norm": 3.6215649638849317,
+      "learning_rate": 8.362536109472637e-06,
+      "loss": 0.9418,
+      "step": 122
+    },
+    {
+      "epoch": 0.5347826086956522,
+      "grad_norm": 3.769862249632324,
+      "learning_rate": 8.33718546266388e-06,
+      "loss": 1.0663,
+      "step": 123
+    },
+    {
+      "epoch": 0.5391304347826087,
+      "grad_norm": 3.339932901634682,
+      "learning_rate": 8.31167916097654e-06,
+      "loss": 0.7193,
+      "step": 124
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 3.4380458029708603,
+      "learning_rate": 8.286018394089864e-06,
+      "loss": 0.8919,
+      "step": 125
+    },
+    {
+      "epoch": 0.5478260869565217,
+      "grad_norm": 5.277459992809238,
+      "learning_rate": 8.260204358887753e-06,
+      "loss": 0.9262,
+      "step": 126
+    },
+    {
+      "epoch": 0.5521739130434783,
+      "grad_norm": 4.2317096822642615,
+      "learning_rate": 8.234238259402936e-06,
+      "loss": 0.6884,
+      "step": 127
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 4.526808713688422,
+      "learning_rate": 8.208121306760806e-06,
+      "loss": 0.976,
+      "step": 128
+    },
+    {
+      "epoch": 0.5608695652173913,
+      "grad_norm": 5.4246343120836595,
+      "learning_rate": 8.181854719122938e-06,
+      "loss": 0.9472,
+      "step": 129
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 5.84927247067023,
+      "learning_rate": 8.155439721630265e-06,
+      "loss": 1.205,
+      "step": 130
+    },
+    {
+      "epoch": 0.5695652173913044,
+      "grad_norm": 4.573422770218524,
+      "learning_rate": 8.128877546345932e-06,
+      "loss": 0.7917,
+      "step": 131
+    },
+    {
+      "epoch": 0.5739130434782609,
+      "grad_norm": 3.721444294410019,
+      "learning_rate": 8.102169432197842e-06,
+      "loss": 0.6568,
+      "step": 132
+    },
+    {
+      "epoch": 0.5782608695652174,
+      "grad_norm": 4.9417471562139985,
+      "learning_rate": 8.075316624920848e-06,
+      "loss": 0.7244,
+      "step": 133
+    },
+    {
+      "epoch": 0.5826086956521739,
+      "grad_norm": 3.5642397377694577,
+      "learning_rate": 8.048320376998675e-06,
+      "loss": 0.8697,
+      "step": 134
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 3.8198832174635315,
+      "learning_rate": 8.021181947605474e-06,
+      "loss": 0.7617,
+      "step": 135
+    },
+    {
+      "epoch": 0.591304347826087,
+      "grad_norm": 3.481415882832902,
+      "learning_rate": 7.993902602547113e-06,
+      "loss": 0.79,
+      "step": 136
+    },
+    {
+      "epoch": 0.5956521739130435,
+      "grad_norm": 4.510299214820252,
+      "learning_rate": 7.966483614202127e-06,
+      "loss": 0.9127,
+      "step": 137
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.985106774813847,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.6109,
+      "step": 138
+    },
+    {
+      "epoch": 0.6043478260869565,
+      "grad_norm": 3.4432849581794254,
+      "learning_rate": 7.911231829673356e-06,
+      "loss": 0.7885,
+      "step": 139
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 4.31295058606684,
+      "learning_rate": 7.883401610574338e-06,
+      "loss": 0.6665,
+      "step": 140
+    },
+    {
+      "epoch": 0.6130434782608696,
+      "grad_norm": 3.411489887606749,
+      "learning_rate": 7.855436902238018e-06,
+      "loss": 0.8652,
+      "step": 141
+    },
+    {
+      "epoch": 0.6173913043478261,
+      "grad_norm": 2.6161499184487154,
+      "learning_rate": 7.82733900901003e-06,
+      "loss": 0.8522,
+      "step": 142
+    },
+    {
+      "epoch": 0.6217391304347826,
+      "grad_norm": 3.7587252913188074,
+      "learning_rate": 7.799109241448091e-06,
+      "loss": 0.9895,
+      "step": 143
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 4.171495681712704,
+      "learning_rate": 7.770748916260875e-06,
+      "loss": 1.1143,
+      "step": 144
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 4.498205067110739,
+      "learning_rate": 7.742259356246594e-06,
+      "loss": 0.7515,
+      "step": 145
+    },
+    {
+      "epoch": 0.6347826086956522,
+      "grad_norm": 7.042541090075897,
+      "learning_rate": 7.71364189023131e-06,
+      "loss": 1.019,
+      "step": 146
+    },
+    {
+      "epoch": 0.6391304347826087,
+      "grad_norm": 3.4294733121091885,
+      "learning_rate": 7.68489785300694e-06,
+      "loss": 0.7827,
+      "step": 147
+    },
+    {
+      "epoch": 0.6434782608695652,
+      "grad_norm": 5.107734671780975,
+      "learning_rate": 7.656028585269017e-06,
+      "loss": 0.881,
+      "step": 148
+    },
+    {
+      "epoch": 0.6478260869565218,
+      "grad_norm": 3.793430012808144,
+      "learning_rate": 7.627035433554138e-06,
+      "loss": 0.83,
+      "step": 149
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 2.93598624465324,
+      "learning_rate": 7.597919750177168e-06,
+      "loss": 0.731,
+      "step": 150
+    },
+    {
+      "epoch": 0.6565217391304348,
+      "grad_norm": 4.596730503707614,
+      "learning_rate": 7.5686828931681646e-06,
+      "loss": 0.7652,
+      "step": 151
+    },
+    {
+      "epoch": 0.6608695652173913,
+      "grad_norm": 3.6807761395861203,
+      "learning_rate": 7.539326226209032e-06,
+      "loss": 0.7775,
+      "step": 152
+    },
+    {
+      "epoch": 0.6652173913043479,
+      "grad_norm": 3.262665001957235,
+      "learning_rate": 7.509851118569915e-06,
+      "loss": 0.8261,
+      "step": 153
+    },
+    {
+      "epoch": 0.6695652173913044,
+      "grad_norm": 3.754006135747569,
+      "learning_rate": 7.4802589450453415e-06,
+      "loss": 0.9438,
+      "step": 154
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 4.136880641675532,
+      "learning_rate": 7.450551085890087e-06,
+      "loss": 0.7168,
+      "step": 155
+    },
+    {
+      "epoch": 0.6782608695652174,
+      "grad_norm": 4.537082958373421,
+      "learning_rate": 7.420728926754803e-06,
+      "loss": 0.7393,
+      "step": 156
+    },
+    {
+      "epoch": 0.6826086956521739,
+      "grad_norm": 4.709451101592196,
+      "learning_rate": 7.390793858621386e-06,
+      "loss": 0.6084,
+      "step": 157
+    },
+    {
+      "epoch": 0.6869565217391305,
+      "grad_norm": 3.478907976036108,
+      "learning_rate": 7.360747277738094e-06,
+      "loss": 0.9321,
+      "step": 158
+    },
+    {
+      "epoch": 0.691304347826087,
+      "grad_norm": 3.4286921023964356,
+      "learning_rate": 7.330590585554428e-06,
+      "loss": 0.8209,
+      "step": 159
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 4.006094985848452,
+      "learning_rate": 7.300325188655762e-06,
+      "loss": 0.7925,
+      "step": 160
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.7845797221282442,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.9974,
+      "step": 161
+    },
+    {
+      "epoch": 0.7043478260869566,
+      "grad_norm": 3.554993958659687,
+      "learning_rate": 7.2394739323404105e-06,
+      "loss": 1.091,
+      "step": 162
+    },
+    {
+      "epoch": 0.7086956521739131,
+      "grad_norm": 3.360485996421952,
+      "learning_rate": 7.208890911182198e-06,
+      "loss": 1.1279,
+      "step": 163
+    },
+    {
+      "epoch": 0.7130434782608696,
+      "grad_norm": 4.068025031948494,
+      "learning_rate": 7.178204861693546e-06,
+      "loss": 0.8294,
+      "step": 164
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 5.238100324988785,
+      "learning_rate": 7.147417215150411e-06,
+      "loss": 1.0741,
+      "step": 165
+    },
+    {
+      "epoch": 0.7217391304347827,
+      "grad_norm": 3.1428044117390157,
+      "learning_rate": 7.116529407567489e-06,
+      "loss": 0.614,
+      "step": 166
+    },
+    {
+      "epoch": 0.7260869565217392,
+      "grad_norm": 4.913916286363875,
+      "learning_rate": 7.085542879631253e-06,
+      "loss": 0.7525,
+      "step": 167
+    },
+    {
+      "epoch": 0.7304347826086957,
+      "grad_norm": 3.587542818686942,
+      "learning_rate": 7.054459076632742e-06,
+      "loss": 0.9964,
+      "step": 168
+    },
+    {
+      "epoch": 0.7347826086956522,
+      "grad_norm": 4.446156336412497,
+      "learning_rate": 7.0232794484001495e-06,
+      "loss": 0.7518,
+      "step": 169
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 4.1445810778077306,
+      "learning_rate": 6.9920054492312086e-06,
+      "loss": 0.7821,
+      "step": 170
+    },
+    {
+      "epoch": 0.7434782608695653,
+      "grad_norm": 6.5457371594473885,
+      "learning_rate": 6.960638537825352e-06,
+      "loss": 1.1481,
+      "step": 171
+    },
+    {
+      "epoch": 0.7478260869565218,
+      "grad_norm": 3.6216138215097557,
+      "learning_rate": 6.9291801772156775e-06,
+      "loss": 0.7234,
+      "step": 172
+    },
+    {
+      "epoch": 0.7521739130434782,
+      "grad_norm": 3.4588765071154755,
+      "learning_rate": 6.89763183470071e-06,
+      "loss": 0.7835,
+      "step": 173
+    },
+    {
+      "epoch": 0.7565217391304347,
+      "grad_norm": 3.4415204598446167,
+      "learning_rate": 6.865994981775958e-06,
+      "loss": 0.8836,
+      "step": 174
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 4.164177481650729,
+      "learning_rate": 6.834271094065284e-06,
+      "loss": 0.9207,
+      "step": 175
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 4.038475026990704,
+      "learning_rate": 6.802461651252073e-06,
+      "loss": 0.8593,
+      "step": 176
+    },
+    {
+      "epoch": 0.7695652173913043,
+      "grad_norm": 3.468992427141025,
+      "learning_rate": 6.770568137010226e-06,
+      "loss": 0.9054,
+      "step": 177
+    },
+    {
+      "epoch": 0.7739130434782608,
+      "grad_norm": 4.178768224138322,
+      "learning_rate": 6.738592038934946e-06,
+      "loss": 0.8688,
+      "step": 178
+    },
+    {
+      "epoch": 0.7782608695652173,
+      "grad_norm": 4.945467366909143,
+      "learning_rate": 6.706534848473353e-06,
+      "loss": 0.8779,
+      "step": 179
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 4.150398477498481,
+      "learning_rate": 6.674398060854931e-06,
+      "loss": 0.8055,
+      "step": 180
+    },
+    {
+      "epoch": 0.7869565217391304,
+      "grad_norm": 3.911559225842766,
+      "learning_rate": 6.642183175021779e-06,
+      "loss": 0.7101,
+      "step": 181
+    },
+    {
+      "epoch": 0.7913043478260869,
+      "grad_norm": 3.227889892012402,
+      "learning_rate": 6.609891693558692e-06,
+      "loss": 0.7036,
+      "step": 182
+    },
+    {
+      "epoch": 0.7956521739130434,
+      "grad_norm": 3.3323861592761306,
+      "learning_rate": 6.5775251226230855e-06,
+      "loss": 0.8071,
+      "step": 183
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.574513479071914,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.826,
+      "step": 184
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 4.575750771124376,
+      "learning_rate": 6.51257275440538e-06,
+      "loss": 1.1722,
+      "step": 185
+    },
+    {
+      "epoch": 0.808695652173913,
+      "grad_norm": 3.407884861003522,
+      "learning_rate": 6.479989986668118e-06,
+      "loss": 0.7167,
+      "step": 186
+    },
+    {
+      "epoch": 0.8130434782608695,
+      "grad_norm": 4.119129382101472,
+      "learning_rate": 6.447338188406705e-06,
+      "loss": 0.9436,
+      "step": 187
+    },
+    {
+      "epoch": 0.8173913043478261,
+      "grad_norm": 2.888021714493982,
+      "learning_rate": 6.41461888258465e-06,
+      "loss": 0.7366,
+      "step": 188
+    },
+    {
+      "epoch": 0.8217391304347826,
+      "grad_norm": 3.853996538195132,
+      "learning_rate": 6.3818335953141955e-06,
+      "loss": 0.8666,
+      "step": 189
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 3.7044180394270647,
+      "learning_rate": 6.348983855785122e-06,
+      "loss": 0.8697,
+      "step": 190
+    },
+    {
+      "epoch": 0.8304347826086956,
+      "grad_norm": 4.285097504630087,
+      "learning_rate": 6.31607119619343e-06,
+      "loss": 0.6411,
+      "step": 191
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 4.274714148494339,
+      "learning_rate": 6.283097151669869e-06,
+      "loss": 0.8285,
+      "step": 192
+    },
+    {
+      "epoch": 0.8391304347826087,
+      "grad_norm": 4.403460887604329,
+      "learning_rate": 6.250063260208345e-06,
+      "loss": 0.7585,
+      "step": 193
+    },
+    {
+      "epoch": 0.8434782608695652,
+      "grad_norm": 3.9513628543555877,
+      "learning_rate": 6.216971062594179e-06,
+      "loss": 0.8291,
+      "step": 194
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 5.202803286054048,
+      "learning_rate": 6.183822102332234e-06,
+      "loss": 0.8107,
+      "step": 195
+    },
+    {
+      "epoch": 0.8521739130434782,
+      "grad_norm": 3.4198047041657187,
+      "learning_rate": 6.1506179255749335e-06,
+      "loss": 0.9379,
+      "step": 196
+    },
+    {
+      "epoch": 0.8565217391304348,
+      "grad_norm": 3.0362881676390265,
+      "learning_rate": 6.1173600810501355e-06,
+      "loss": 0.6765,
+      "step": 197
+    },
+    {
+      "epoch": 0.8608695652173913,
+      "grad_norm": 3.154366355290239,
+      "learning_rate": 6.084050119988905e-06,
+      "loss": 0.8658,
+      "step": 198
+    },
+    {
+      "epoch": 0.8652173913043478,
+      "grad_norm": 5.054661820553674,
+      "learning_rate": 6.050689596053151e-06,
+      "loss": 0.9007,
+      "step": 199
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 2.738655053566571,
+      "learning_rate": 6.0172800652631706e-06,
+      "loss": 0.7356,
+      "step": 200
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "eval_loss": 0.825007438659668,
+      "eval_runtime": 1.2203,
+      "eval_samples_per_second": 15.571,
+      "eval_steps_per_second": 4.098,
+      "step": 200
+    },
+    {
+      "epoch": 0.8739130434782608,
+      "grad_norm": 3.5083994205280145,
+      "learning_rate": 5.983823085925059e-06,
+      "loss": 0.6462,
+      "step": 201
+    },
+    {
+      "epoch": 0.8782608695652174,
+      "grad_norm": 3.824457588570473,
+      "learning_rate": 5.950320218558037e-06,
+      "loss": 0.6327,
+      "step": 202
+    },
+    {
+      "epoch": 0.8826086956521739,
+      "grad_norm": 4.165824391035445,
+      "learning_rate": 5.916773025821662e-06,
+      "loss": 0.8199,
+      "step": 203
+    },
+    {
+      "epoch": 0.8869565217391304,
+      "grad_norm": 3.3820570905655614,
+      "learning_rate": 5.883183072442938e-06,
+      "loss": 0.654,
+      "step": 204
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 4.3684348308636425,
+      "learning_rate": 5.849551925143334e-06,
+      "loss": 0.8819,
+      "step": 205
+    },
+    {
+      "epoch": 0.8956521739130435,
+      "grad_norm": 3.458483498590032,
+      "learning_rate": 5.815881152565712e-06,
+      "loss": 0.8065,
+      "step": 206
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.3805910702179647,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 1.0186,
+      "step": 207
+    },
+    {
+      "epoch": 0.9043478260869565,
+      "grad_norm": 3.8013431956793924,
+      "learning_rate": 5.7484270153157215e-06,
+      "loss": 0.6512,
+      "step": 208
+    },
+    {
+      "epoch": 0.908695652173913,
+      "grad_norm": 4.393091604713644,
+      "learning_rate": 5.714646796877108e-06,
+      "loss": 1.0551,
+      "step": 209
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 3.0657867889766854,
+      "learning_rate": 5.680833245481234e-06,
+      "loss": 0.8123,
+      "step": 210
+    },
+    {
+      "epoch": 0.9173913043478261,
+      "grad_norm": 4.968276591046584,
+      "learning_rate": 5.646987938278753e-06,
+      "loss": 0.7966,
+      "step": 211
+    },
+    {
+      "epoch": 0.9217391304347826,
+      "grad_norm": 4.010276803924688,
+      "learning_rate": 5.613112453901493e-06,
+      "loss": 0.8161,
+      "step": 212
+    },
+    {
+      "epoch": 0.9260869565217391,
+      "grad_norm": 3.404075079967763,
+      "learning_rate": 5.579208372388822e-06,
+      "loss": 0.8341,
+      "step": 213
+    },
+    {
+      "epoch": 0.9304347826086956,
+      "grad_norm": 4.2830181812234684,
+      "learning_rate": 5.5452772751139496e-06,
+      "loss": 0.7814,
+      "step": 214
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 3.3609431787385544,
+      "learning_rate": 5.511320744710171e-06,
+      "loss": 0.7195,
+      "step": 215
+    },
+    {
+      "epoch": 0.9391304347826087,
+      "grad_norm": 4.496810291115776,
+      "learning_rate": 5.477340364997051e-06,
+      "loss": 0.9754,
+      "step": 216
+    },
+    {
+      "epoch": 0.9434782608695652,
+      "grad_norm": 5.552749375587317,
+      "learning_rate": 5.443337720906542e-06,
+      "loss": 0.9599,
+      "step": 217
+    },
+    {
+      "epoch": 0.9478260869565217,
+      "grad_norm": 2.923863761066833,
+      "learning_rate": 5.409314398409067e-06,
+      "loss": 0.7041,
+      "step": 218
+    },
+    {
+      "epoch": 0.9521739130434783,
+      "grad_norm": 3.7061647650339355,
+      "learning_rate": 5.375271984439541e-06,
+      "loss": 0.6793,
+      "step": 219
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 6.101090552344163,
+      "learning_rate": 5.341212066823356e-06,
+      "loss": 0.8546,
+      "step": 220
+    },
+    {
+      "epoch": 0.9608695652173913,
+      "grad_norm": 3.96750395410377,
+      "learning_rate": 5.307136234202318e-06,
+      "loss": 0.6732,
+      "step": 221
+    },
+    {
+      "epoch": 0.9652173913043478,
+      "grad_norm": 4.528462960181897,
+      "learning_rate": 5.27304607596055e-06,
+      "loss": 1.0779,
+      "step": 222
+    },
+    {
+      "epoch": 0.9695652173913043,
+      "grad_norm": 3.7443235175746805,
+      "learning_rate": 5.238943182150361e-06,
+      "loss": 0.6516,
+      "step": 223
+    },
+    {
+      "epoch": 0.9739130434782609,
+      "grad_norm": 5.394984365821971,
+      "learning_rate": 5.204829143418072e-06,
+      "loss": 0.709,
+      "step": 224
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 3.678247988171025,
+      "learning_rate": 5.17070555092984e-06,
+      "loss": 0.753,
+      "step": 225
+    },
+    {
+      "epoch": 0.9826086956521739,
+      "grad_norm": 4.6791048093273675,
+      "learning_rate": 5.136573996297431e-06,
+      "loss": 1.0238,
+      "step": 226
+    },
+    {
+      "epoch": 0.9869565217391304,
+      "grad_norm": 5.143148587456582,
+      "learning_rate": 5.102436071503983e-06,
+      "loss": 0.9125,
+      "step": 227
+    },
+    {
+      "epoch": 0.991304347826087,
+      "grad_norm": 2.2412926753259597,
+      "learning_rate": 5.068293368829755e-06,
+      "loss": 0.8642,
+      "step": 228
+    },
+    {
+      "epoch": 0.9956521739130435,
+      "grad_norm": 4.942145964692695,
+      "learning_rate": 5.034147480777867e-06,
+      "loss": 0.8394,
+      "step": 229
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.9753321703674143,
+      "learning_rate": 5e-06,
+      "loss": 0.9067,
+      "step": 230
+    },
+    {
+      "epoch": 1.0043478260869565,
+      "grad_norm": 4.2945289583949915,
+      "learning_rate": 4.965852519222135e-06,
+      "loss": 0.7034,
+      "step": 231
+    },
+    {
+      "epoch": 1.008695652173913,
+      "grad_norm": 3.009740756628107,
+      "learning_rate": 4.931706631170246e-06,
+      "loss": 0.6254,
+      "step": 232
+    },
+    {
+      "epoch": 1.0130434782608695,
+      "grad_norm": 3.656846296061854,
+      "learning_rate": 4.89756392849602e-06,
+      "loss": 0.4885,
+      "step": 233
+    },
+    {
+      "epoch": 1.017391304347826,
+      "grad_norm": 4.485100058642041,
+      "learning_rate": 4.863426003702572e-06,
+      "loss": 0.7407,
+      "step": 234
+    },
+    {
+      "epoch": 1.0217391304347827,
+      "grad_norm": 3.0577381177794174,
+      "learning_rate": 4.829294449070161e-06,
+      "loss": 0.6666,
+      "step": 235
+    },
+    {
+      "epoch": 1.0260869565217392,
+      "grad_norm": 3.101255830757204,
+      "learning_rate": 4.795170856581929e-06,
+      "loss": 0.6291,
+      "step": 236
+    },
+    {
+      "epoch": 1.0304347826086957,
+      "grad_norm": 2.4284538991912075,
+      "learning_rate": 4.7610568178496405e-06,
+      "loss": 0.5469,
+      "step": 237
+    },
+    {
+      "epoch": 1.0347826086956522,
+      "grad_norm": 2.927431656629591,
+      "learning_rate": 4.7269539240394505e-06,
+      "loss": 0.4352,
+      "step": 238
+    },
+    {
+      "epoch": 1.0391304347826087,
+      "grad_norm": 2.58940571881285,
+      "learning_rate": 4.692863765797683e-06,
+      "loss": 0.5481,
+      "step": 239
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 2.781029232453596,
+      "learning_rate": 4.6587879331766465e-06,
+      "loss": 0.6503,
+      "step": 240
+    },
+    {
+      "epoch": 1.0478260869565217,
+      "grad_norm": 2.6957972463902893,
+      "learning_rate": 4.624728015560461e-06,
+      "loss": 0.6356,
+      "step": 241
+    },
+    {
+      "epoch": 1.0521739130434782,
+      "grad_norm": 4.28124421456519,
+      "learning_rate": 4.5906856015909365e-06,
+      "loss": 0.4898,
+      "step": 242
+    },
+    {
+      "epoch": 1.0565217391304347,
+      "grad_norm": 2.9643501252854163,
+      "learning_rate": 4.556662279093461e-06,
+      "loss": 0.5339,
+      "step": 243
+    },
+    {
+      "epoch": 1.0608695652173914,
+      "grad_norm": 3.8524672927440946,
+      "learning_rate": 4.52265963500295e-06,
+      "loss": 0.7113,
+      "step": 244
+    },
+    {
+      "epoch": 1.065217391304348,
+      "grad_norm": 3.4202593539885635,
+      "learning_rate": 4.488679255289829e-06,
+      "loss": 0.6041,
+      "step": 245
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "grad_norm": 3.8134083559576277,
+      "learning_rate": 4.454722724886051e-06,
+      "loss": 0.4484,
+      "step": 246
+    },
+    {
+      "epoch": 1.0739130434782609,
+      "grad_norm": 3.331059450346738,
+      "learning_rate": 4.4207916276111795e-06,
+      "loss": 0.4856,
+      "step": 247
+    },
+    {
+      "epoch": 1.0782608695652174,
+      "grad_norm": 3.823406666773115,
+      "learning_rate": 4.386887546098509e-06,
+      "loss": 0.5426,
+      "step": 248
+    },
+    {
+      "epoch": 1.0826086956521739,
+      "grad_norm": 4.6180569791107,
+      "learning_rate": 4.353012061721249e-06,
+      "loss": 0.4695,
+      "step": 249
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 3.6666571715510474,
+      "learning_rate": 4.319166754518768e-06,
+      "loss": 0.3785,
+      "step": 250
+    },
+    {
+      "epoch": 1.0913043478260869,
+      "grad_norm": 2.9634895325655766,
+      "learning_rate": 4.285353203122894e-06,
+      "loss": 0.3999,
+      "step": 251
+    },
+    {
+      "epoch": 1.0956521739130434,
+      "grad_norm": 4.482488004555733,
+      "learning_rate": 4.251572984684281e-06,
+      "loss": 0.7579,
+      "step": 252
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.845918550477848,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.6067,
+      "step": 253
+    },
+    {
+      "epoch": 1.1043478260869566,
+      "grad_norm": 3.6986408697041444,
+      "learning_rate": 4.18411884743429e-06,
+      "loss": 0.485,
+      "step": 254
+    },
+    {
+      "epoch": 1.108695652173913,
+      "grad_norm": 3.509551929199139,
+      "learning_rate": 4.150448074856667e-06,
+      "loss": 0.5005,
+      "step": 255
+    },
+    {
+      "epoch": 1.1130434782608696,
+      "grad_norm": 4.267669168225376,
+      "learning_rate": 4.116816927557063e-06,
+      "loss": 0.4883,
+      "step": 256
+    },
+    {
+      "epoch": 1.117391304347826,
+      "grad_norm": 3.774832262855488,
+      "learning_rate": 4.083226974178339e-06,
+      "loss": 0.3788,
+      "step": 257
+    },
+    {
+      "epoch": 1.1217391304347826,
+      "grad_norm": 3.5227515786871697,
+      "learning_rate": 4.0496797814419655e-06,
+      "loss": 0.4932,
+      "step": 258
+    },
+    {
+      "epoch": 1.126086956521739,
+      "grad_norm": 4.360078037660404,
+      "learning_rate": 4.016176914074944e-06,
+      "loss": 0.5368,
+      "step": 259
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 4.6746791628195545,
+      "learning_rate": 3.982719934736832e-06,
+      "loss": 0.4211,
+      "step": 260
+    },
+    {
+      "epoch": 1.134782608695652,
+      "grad_norm": 2.7321352215986323,
+      "learning_rate": 3.949310403946849e-06,
+      "loss": 0.4899,
+      "step": 261
+    },
+    {
+      "epoch": 1.1391304347826088,
+      "grad_norm": 3.5754406942915806,
+      "learning_rate": 3.915949880011096e-06,
+      "loss": 0.4823,
+      "step": 262
+    },
+    {
+      "epoch": 1.1434782608695653,
+      "grad_norm": 3.6733528041970613,
+      "learning_rate": 3.882639918949865e-06,
+      "loss": 0.5596,
+      "step": 263
+    },
+    {
+      "epoch": 1.1478260869565218,
+      "grad_norm": 2.9305256648457387,
+      "learning_rate": 3.849382074425069e-06,
+      "loss": 0.423,
+      "step": 264
+    },
+    {
+      "epoch": 1.1521739130434783,
+      "grad_norm": 3.9637419933724143,
+      "learning_rate": 3.816177897667767e-06,
+      "loss": 0.8296,
+      "step": 265
+    },
+    {
+      "epoch": 1.1565217391304348,
+      "grad_norm": 6.6811186783510506,
+      "learning_rate": 3.7830289374058214e-06,
+      "loss": 0.616,
+      "step": 266
+    },
+    {
+      "epoch": 1.1608695652173913,
+      "grad_norm": 6.288600124931218,
+      "learning_rate": 3.749936739791656e-06,
+      "loss": 0.5357,
+      "step": 267
+    },
+    {
+      "epoch": 1.1652173913043478,
+      "grad_norm": 3.8918231976142885,
+      "learning_rate": 3.7169028483301333e-06,
+      "loss": 0.4663,
+      "step": 268
+    },
+    {
+      "epoch": 1.1695652173913043,
+      "grad_norm": 3.354158738300337,
+      "learning_rate": 3.6839288038065736e-06,
+      "loss": 0.3898,
+      "step": 269
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 3.3417809268425582,
+      "learning_rate": 3.6510161442148783e-06,
+      "loss": 0.4019,
+      "step": 270
+    },
+    {
+      "epoch": 1.1782608695652175,
+      "grad_norm": 5.117755201256695,
+      "learning_rate": 3.6181664046858045e-06,
+      "loss": 0.6163,
+      "step": 271
+    },
+    {
+      "epoch": 1.182608695652174,
+      "grad_norm": 4.567775279483126,
+      "learning_rate": 3.58538111741535e-06,
+      "loss": 0.6357,
+      "step": 272
+    },
+    {
+      "epoch": 1.1869565217391305,
+      "grad_norm": 5.6456639800107045,
+      "learning_rate": 3.5526618115932974e-06,
+      "loss": 0.5377,
+      "step": 273
+    },
+    {
+      "epoch": 1.191304347826087,
+      "grad_norm": 3.7964931148403984,
+      "learning_rate": 3.5200100133318836e-06,
+      "loss": 0.7388,
+      "step": 274
+    },
+    {
+      "epoch": 1.1956521739130435,
+      "grad_norm": 4.480294572542451,
+      "learning_rate": 3.4874272455946217e-06,
+      "loss": 0.3212,
+      "step": 275
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.467143996076006,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.5172,
+      "step": 276
+    },
+    {
+      "epoch": 1.2043478260869565,
+      "grad_norm": 2.7472548893281776,
+      "learning_rate": 3.4224748773769166e-06,
+      "loss": 0.4703,
+      "step": 277
+    },
+    {
+      "epoch": 1.208695652173913,
+      "grad_norm": 2.930570037247241,
+      "learning_rate": 3.39010830644131e-06,
+      "loss": 0.5399,
+      "step": 278
+    },
+    {
+      "epoch": 1.2130434782608694,
+      "grad_norm": 5.422324007097856,
+      "learning_rate": 3.357816824978222e-06,
+      "loss": 0.4727,
+      "step": 279
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 4.756301690088914,
+      "learning_rate": 3.3256019391450696e-06,
+      "loss": 0.7769,
+      "step": 280
+    },
+    {
+      "epoch": 1.2217391304347827,
+      "grad_norm": 3.6105329586336117,
+      "learning_rate": 3.2934651515266485e-06,
+      "loss": 0.5781,
+      "step": 281
+    },
+    {
+      "epoch": 1.2260869565217392,
+      "grad_norm": 6.656045007547206,
+      "learning_rate": 3.261407961065056e-06,
+      "loss": 0.6225,
+      "step": 282
+    },
+    {
+      "epoch": 1.2304347826086957,
+      "grad_norm": 4.715320102324048,
+      "learning_rate": 3.2294318629897746e-06,
+      "loss": 0.5312,
+      "step": 283
+    },
+    {
+      "epoch": 1.2347826086956522,
+      "grad_norm": 3.707995507157655,
+      "learning_rate": 3.197538348747927e-06,
+      "loss": 0.5066,
+      "step": 284
+    },
+    {
+      "epoch": 1.2391304347826086,
+      "grad_norm": 2.7635931646672565,
+      "learning_rate": 3.1657289059347184e-06,
+      "loss": 0.3998,
+      "step": 285
+    },
+    {
+      "epoch": 1.2434782608695651,
+      "grad_norm": 5.451849629778433,
+      "learning_rate": 3.1340050182240438e-06,
+      "loss": 0.4784,
+      "step": 286
+    },
+    {
+      "epoch": 1.2478260869565219,
+      "grad_norm": 4.782698874791613,
+      "learning_rate": 3.1023681652992925e-06,
+      "loss": 0.6345,
+      "step": 287
+    },
+    {
+      "epoch": 1.2521739130434781,
+      "grad_norm": 3.672795410107192,
+      "learning_rate": 3.070819822784323e-06,
+      "loss": 0.4243,
+      "step": 288
+    },
+    {
+      "epoch": 1.2565217391304349,
+      "grad_norm": 3.861532750319747,
+      "learning_rate": 3.03936146217465e-06,
+      "loss": 0.4092,
+      "step": 289
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 6.800888319310977,
+      "learning_rate": 3.007994550768793e-06,
+      "loss": 0.4044,
+      "step": 290
+    },
+    {
+      "epoch": 1.2652173913043478,
+      "grad_norm": 2.8381684901106143,
+      "learning_rate": 2.976720551599852e-06,
+      "loss": 0.4325,
+      "step": 291
+    },
+    {
+      "epoch": 1.2695652173913043,
+      "grad_norm": 4.2780921182664144,
+      "learning_rate": 2.9455409233672594e-06,
+      "loss": 0.8048,
+      "step": 292
+    },
+    {
+      "epoch": 1.2739130434782608,
+      "grad_norm": 4.836689064373329,
+      "learning_rate": 2.914457120368748e-06,
+      "loss": 0.7234,
+      "step": 293
+    },
+    {
+      "epoch": 1.2782608695652173,
+      "grad_norm": 4.0103776843864125,
+      "learning_rate": 2.883470592432512e-06,
+      "loss": 0.4799,
+      "step": 294
+    },
+    {
+      "epoch": 1.2826086956521738,
+      "grad_norm": 2.861102985436097,
+      "learning_rate": 2.8525827848495912e-06,
+      "loss": 0.4406,
+      "step": 295
+    },
+    {
+      "epoch": 1.2869565217391306,
+      "grad_norm": 4.175986317455729,
+      "learning_rate": 2.8217951383064546e-06,
+      "loss": 0.5246,
+      "step": 296
+    },
+    {
+      "epoch": 1.2913043478260868,
+      "grad_norm": 3.470122787658186,
+      "learning_rate": 2.7911090888178033e-06,
+      "loss": 0.5552,
+      "step": 297
+    },
+    {
+      "epoch": 1.2956521739130435,
+      "grad_norm": 3.435883911757588,
+      "learning_rate": 2.760526067659591e-06,
+      "loss": 0.6207,
+      "step": 298
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 3.882897336083524,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.5759,
+      "step": 299
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 2.842616852615547,
+      "learning_rate": 2.6996748113442397e-06,
+      "loss": 0.3266,
+      "step": 300
+    },
+    {
+      "epoch": 1.308695652173913,
+      "grad_norm": 4.601459226364831,
+      "learning_rate": 2.669409414445574e-06,
+      "loss": 0.5043,
+      "step": 301
+    },
+    {
+      "epoch": 1.3130434782608695,
+      "grad_norm": 3.643401762012329,
+      "learning_rate": 2.6392527222619078e-06,
+      "loss": 0.4729,
+      "step": 302
+    },
+    {
+      "epoch": 1.317391304347826,
+      "grad_norm": 4.175796804404032,
+      "learning_rate": 2.6092061413786158e-06,
+      "loss": 0.5379,
+      "step": 303
+    },
+    {
+      "epoch": 1.3217391304347825,
+      "grad_norm": 4.787195403434198,
+      "learning_rate": 2.5792710732452e-06,
+      "loss": 0.6848,
+      "step": 304
+    },
+    {
+      "epoch": 1.3260869565217392,
+      "grad_norm": 3.5409175757216054,
+      "learning_rate": 2.5494489141099155e-06,
+      "loss": 0.3645,
+      "step": 305
+    },
+    {
+      "epoch": 1.3304347826086955,
+      "grad_norm": 3.861897686189232,
+      "learning_rate": 2.5197410549546598e-06,
+      "loss": 0.3829,
+      "step": 306
+    },
+    {
+      "epoch": 1.3347826086956522,
+      "grad_norm": 5.3825995531189905,
+      "learning_rate": 2.4901488814300855e-06,
+      "loss": 0.5438,
+      "step": 307
+    },
+    {
+      "epoch": 1.3391304347826087,
+      "grad_norm": 3.3702469438449247,
+      "learning_rate": 2.4606737737909696e-06,
+      "loss": 0.3286,
+      "step": 308
+    },
+    {
+      "epoch": 1.3434782608695652,
+      "grad_norm": 4.690400044449517,
+      "learning_rate": 2.431317106831836e-06,
+      "loss": 0.7414,
+      "step": 309
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 2.9599127269025005,
+      "learning_rate": 2.4020802498228333e-06,
+      "loss": 0.5214,
+      "step": 310
+    },
+    {
+      "epoch": 1.3521739130434782,
+      "grad_norm": 4.746471132028925,
+      "learning_rate": 2.3729645664458637e-06,
+      "loss": 0.7109,
+      "step": 311
+    },
+    {
+      "epoch": 1.3565217391304347,
+      "grad_norm": 5.25212834865194,
+      "learning_rate": 2.3439714147309845e-06,
+      "loss": 0.4919,
+      "step": 312
+    },
+    {
+      "epoch": 1.3608695652173912,
+      "grad_norm": 3.125614769821592,
+      "learning_rate": 2.315102146993061e-06,
+      "loss": 0.3315,
+      "step": 313
+    },
+    {
+      "epoch": 1.365217391304348,
+      "grad_norm": 4.108407402987031,
+      "learning_rate": 2.286358109768693e-06,
+      "loss": 0.4416,
+      "step": 314
+    },
+    {
+      "epoch": 1.3695652173913042,
+      "grad_norm": 3.4235864126497555,
+      "learning_rate": 2.2577406437534055e-06,
+      "loss": 0.4012,
+      "step": 315
+    },
+    {
+      "epoch": 1.373913043478261,
+      "grad_norm": 2.9536303450719505,
+      "learning_rate": 2.229251083739127e-06,
+      "loss": 0.4213,
+      "step": 316
+    },
+    {
+      "epoch": 1.3782608695652174,
+      "grad_norm": 4.275562425786293,
+      "learning_rate": 2.2008907585519094e-06,
+      "loss": 0.6007,
+      "step": 317
+    },
+    {
+      "epoch": 1.382608695652174,
+      "grad_norm": 4.439744549643693,
+      "learning_rate": 2.172660990989971e-06,
+      "loss": 0.5128,
+      "step": 318
+    },
+    {
+      "epoch": 1.3869565217391304,
+      "grad_norm": 4.387149839982964,
+      "learning_rate": 2.144563097761984e-06,
+      "loss": 0.6044,
+      "step": 319
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 3.8269926419825393,
+      "learning_rate": 2.1165983894256647e-06,
+      "loss": 0.5243,
+      "step": 320
+    },
+    {
+      "epoch": 1.3956521739130434,
+      "grad_norm": 4.263234062205227,
+      "learning_rate": 2.0887681703266453e-06,
+      "loss": 0.6501,
+      "step": 321
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.288715945278797,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.4023,
+      "step": 322
+    },
+    {
+      "epoch": 1.4043478260869566,
+      "grad_norm": 4.840903830572076,
+      "learning_rate": 2.0335163857978747e-06,
+      "loss": 0.584,
+      "step": 323
+    },
+    {
+      "epoch": 1.4086956521739131,
+      "grad_norm": 3.816755859554486,
+      "learning_rate": 2.0060973974528873e-06,
+      "loss": 0.4691,
+      "step": 324
+    },
+    {
+      "epoch": 1.4130434782608696,
+      "grad_norm": 4.094050804066009,
+      "learning_rate": 1.978818052394528e-06,
+      "loss": 0.3754,
+      "step": 325
+    },
+    {
+      "epoch": 1.4173913043478261,
+      "grad_norm": 4.305208159329463,
+      "learning_rate": 1.9516796230013275e-06,
+      "loss": 0.3779,
+      "step": 326
+    },
+    {
+      "epoch": 1.4217391304347826,
+      "grad_norm": 6.126499754720256,
+      "learning_rate": 1.9246833750791526e-06,
+      "loss": 0.5946,
+      "step": 327
+    },
+    {
+      "epoch": 1.4260869565217391,
+      "grad_norm": 4.986094326020495,
+      "learning_rate": 1.8978305678021598e-06,
+      "loss": 0.5896,
+      "step": 328
+    },
+    {
+      "epoch": 1.4304347826086956,
+      "grad_norm": 5.166024500275062,
+      "learning_rate": 1.8711224536540678e-06,
+      "loss": 0.4248,
+      "step": 329
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 3.8712679668213323,
+      "learning_rate": 1.8445602783697375e-06,
+      "loss": 0.5666,
+      "step": 330
+    },
+    {
+      "epoch": 1.4391304347826086,
+      "grad_norm": 4.205692307851411,
+      "learning_rate": 1.8181452808770638e-06,
+      "loss": 0.4982,
+      "step": 331
+    },
+    {
+      "epoch": 1.4434782608695653,
+      "grad_norm": 3.8983034740726428,
+      "learning_rate": 1.7918786932391945e-06,
+      "loss": 0.5396,
+      "step": 332
+    },
+    {
+      "epoch": 1.4478260869565218,
+      "grad_norm": 3.4651082117419802,
+      "learning_rate": 1.765761740597065e-06,
+      "loss": 0.679,
+      "step": 333
+    },
+    {
+      "epoch": 1.4521739130434783,
+      "grad_norm": 3.8564393361166216,
+      "learning_rate": 1.739795641112248e-06,
+      "loss": 0.6588,
+      "step": 334
+    },
+    {
+      "epoch": 1.4565217391304348,
+      "grad_norm": 4.272975876505804,
+      "learning_rate": 1.7139816059101372e-06,
+      "loss": 0.8358,
+      "step": 335
+    },
+    {
+      "epoch": 1.4608695652173913,
+      "grad_norm": 4.076839893426693,
+      "learning_rate": 1.688320839023463e-06,
+      "loss": 0.5513,
+      "step": 336
+    },
+    {
+      "epoch": 1.4652173913043478,
+      "grad_norm": 2.774567334417496,
+      "learning_rate": 1.662814537336122e-06,
+      "loss": 0.5271,
+      "step": 337
+    },
+    {
+      "epoch": 1.4695652173913043,
+      "grad_norm": 3.667368206450109,
+      "learning_rate": 1.6374638905273643e-06,
+      "loss": 0.5086,
+      "step": 338
+    },
+    {
+      "epoch": 1.4739130434782608,
+      "grad_norm": 2.6774469570055284,
+      "learning_rate": 1.6122700810162967e-06,
+      "loss": 0.4622,
+      "step": 339
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 4.058760037761275,
+      "learning_rate": 1.5872342839067305e-06,
+      "loss": 0.3739,
+      "step": 340
+    },
+    {
+      "epoch": 1.482608695652174,
+      "grad_norm": 4.232366716311447,
+      "learning_rate": 1.5623576669323743e-06,
+      "loss": 0.631,
+      "step": 341
+    },
+    {
+      "epoch": 1.4869565217391305,
+      "grad_norm": 3.8466635247767553,
+      "learning_rate": 1.5376413904023723e-06,
+      "loss": 0.5104,
+      "step": 342
+    },
+    {
+      "epoch": 1.491304347826087,
+      "grad_norm": 4.135942120347136,
+      "learning_rate": 1.5130866071471717e-06,
+      "loss": 0.5094,
+      "step": 343
+    },
+    {
+      "epoch": 1.4956521739130435,
+      "grad_norm": 4.304273024625908,
+      "learning_rate": 1.4886944624647647e-06,
+      "loss": 0.3944,
+      "step": 344
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 4.785895968414715,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.6328,
+      "step": 345
+    },
+    {
+      "epoch": 1.5043478260869565,
+      "grad_norm": 4.304489013184394,
+      "learning_rate": 1.4404026320278318e-06,
+      "loss": 0.4224,
+      "step": 346
+    },
+    {
+      "epoch": 1.508695652173913,
+      "grad_norm": 5.048498818452494,
+      "learning_rate": 1.4165051987279832e-06,
+      "loss": 0.6405,
+      "step": 347
+    },
+    {
+      "epoch": 1.5130434782608697,
+      "grad_norm": 3.61479089476453,
+      "learning_rate": 1.3927749088052218e-06,
+      "loss": 0.56,
+      "step": 348
+    },
+    {
+      "epoch": 1.517391304347826,
+      "grad_norm": 4.236357069281796,
+      "learning_rate": 1.3692128691010592e-06,
+      "loss": 0.4332,
+      "step": 349
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 4.341493660417522,
+      "learning_rate": 1.3458201786093795e-06,
+      "loss": 0.5717,
+      "step": 350
+    },
+    {
+      "epoch": 1.526086956521739,
+      "grad_norm": 4.9176115607656845,
+      "learning_rate": 1.3225979284251955e-06,
+      "loss": 0.3907,
+      "step": 351
+    },
+    {
+      "epoch": 1.5304347826086957,
+      "grad_norm": 3.801480760249645,
+      "learning_rate": 1.2995472016937405e-06,
+      "loss": 0.5003,
+      "step": 352
+    },
+    {
+      "epoch": 1.5347826086956522,
+      "grad_norm": 3.4307384301286956,
+      "learning_rate": 1.2766690735599569e-06,
+      "loss": 0.5317,
+      "step": 353
+    },
+    {
+      "epoch": 1.5391304347826087,
+      "grad_norm": 4.016082443019338,
+      "learning_rate": 1.2539646111183452e-06,
+      "loss": 0.43,
+      "step": 354
+    },
+    {
+      "epoch": 1.5434782608695652,
+      "grad_norm": 3.594983855812303,
+      "learning_rate": 1.2314348733631958e-06,
+      "loss": 0.5412,
+      "step": 355
+    },
+    {
+      "epoch": 1.5478260869565217,
+      "grad_norm": 2.6282395580601547,
+      "learning_rate": 1.209080911139187e-06,
+      "loss": 0.3157,
+      "step": 356
+    },
+    {
+      "epoch": 1.5521739130434784,
+      "grad_norm": 4.17706565626502,
+      "learning_rate": 1.1869037670923817e-06,
+      "loss": 0.4854,
+      "step": 357
+    },
+    {
+      "epoch": 1.5565217391304347,
+      "grad_norm": 3.527144570708999,
+      "learning_rate": 1.1649044756215872e-06,
+      "loss": 0.6346,
+      "step": 358
+    },
+    {
+      "epoch": 1.5608695652173914,
+      "grad_norm": 3.0628314553388827,
+      "learning_rate": 1.1430840628301093e-06,
+      "loss": 0.5448,
+      "step": 359
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 2.848515880653068,
+      "learning_rate": 1.1214435464779006e-06,
+      "loss": 0.568,
+      "step": 360
+    },
+    {
+      "epoch": 1.5695652173913044,
+      "grad_norm": 6.516959915724072,
+      "learning_rate": 1.099983935934077e-06,
+      "loss": 0.7196,
+      "step": 361
+    },
+    {
+      "epoch": 1.5739130434782609,
+      "grad_norm": 5.057293110141789,
+      "learning_rate": 1.0787062321298441e-06,
+      "loss": 0.6018,
+      "step": 362
+    },
+    {
+      "epoch": 1.5782608695652174,
+      "grad_norm": 4.77065142413127,
+      "learning_rate": 1.0576114275118132e-06,
+      "loss": 0.493,
+      "step": 363
+    },
+    {
+      "epoch": 1.5826086956521739,
+      "grad_norm": 2.4354456562647635,
+      "learning_rate": 1.0367005059957097e-06,
+      "loss": 0.4647,
+      "step": 364
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 4.274318416743583,
+      "learning_rate": 1.0159744429204776e-06,
+      "loss": 0.4877,
+      "step": 365
+    },
+    {
+      "epoch": 1.591304347826087,
+      "grad_norm": 6.539038228109423,
+      "learning_rate": 9.954342050027922e-07,
+      "loss": 0.7812,
+      "step": 366
+    },
+    {
+      "epoch": 1.5956521739130434,
+      "grad_norm": 4.146697517540566,
+      "learning_rate": 9.75080750291965e-07,
+      "loss": 0.6274,
+      "step": 367
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.372204077398317,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.4421,
+      "step": 368
+    },
+    {
+      "epoch": 1.6043478260869564,
+      "grad_norm": 2.955199194745197,
+      "learning_rate": 9.349379790836243e-07,
+      "loss": 0.5028,
+      "step": 369
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 3.6177018572948736,
+      "learning_rate": 9.151505349477901e-07,
+      "loss": 0.5141,
+      "step": 370
+    },
+    {
+      "epoch": 1.6130434782608696,
+      "grad_norm": 3.6516021998980017,
+      "learning_rate": 8.955536186548425e-07,
+      "loss": 0.6085,
+      "step": 371
+    },
+    {
+      "epoch": 1.617391304347826,
+      "grad_norm": 3.500880225513966,
+      "learning_rate": 8.761481442551573e-07,
+      "loss": 0.5389,
+      "step": 372
+    },
+    {
+      "epoch": 1.6217391304347826,
+      "grad_norm": 4.680508116117162,
+      "learning_rate": 8.569350168697705e-07,
+      "loss": 0.6038,
+      "step": 373
+    },
+    {
+      "epoch": 1.626086956521739,
+      "grad_norm": 4.03657843570234,
+      "learning_rate": 8.379151326481588e-07,
+      "loss": 0.4799,
+      "step": 374
+    },
+    {
+      "epoch": 1.6304347826086958,
+      "grad_norm": 3.651603518512998,
+      "learning_rate": 8.19089378726447e-07,
+      "loss": 0.6335,
+      "step": 375
+    },
+    {
+      "epoch": 1.634782608695652,
+      "grad_norm": 3.181550181803468,
+      "learning_rate": 8.004586331860176e-07,
+      "loss": 0.3404,
+      "step": 376
+    },
+    {
+      "epoch": 1.6391304347826088,
+      "grad_norm": 4.474431730080835,
+      "learning_rate": 7.820237650125711e-07,
+      "loss": 0.4203,
+      "step": 377
+    },
+    {
+      "epoch": 1.643478260869565,
+      "grad_norm": 4.57860916947871,
+      "learning_rate": 7.637856340555822e-07,
+      "loss": 0.7531,
+      "step": 378
+    },
+    {
+      "epoch": 1.6478260869565218,
+      "grad_norm": 3.5893337731483412,
+      "learning_rate": 7.457450909881969e-07,
+      "loss": 0.6053,
+      "step": 379
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 3.281855093440728,
+      "learning_rate": 7.279029772675572e-07,
+      "loss": 0.46,
+      "step": 380
+    },
+    {
+      "epoch": 1.6565217391304348,
+      "grad_norm": 3.5331855572127333,
+      "learning_rate": 7.102601250955526e-07,
+      "loss": 0.3617,
+      "step": 381
+    },
+    {
+      "epoch": 1.6608695652173913,
+      "grad_norm": 3.32305374567492,
+      "learning_rate": 6.928173573800007e-07,
+      "loss": 0.739,
+      "step": 382
+    },
+    {
+      "epoch": 1.6652173913043478,
+      "grad_norm": 2.998766048205789,
+      "learning_rate": 6.755754876962711e-07,
+      "loss": 0.463,
+      "step": 383
+    },
+    {
+      "epoch": 1.6695652173913045,
+      "grad_norm": 3.144044172604275,
+      "learning_rate": 6.585353202493322e-07,
+      "loss": 0.5875,
+      "step": 384
+    },
+    {
+      "epoch": 1.6739130434782608,
+      "grad_norm": 3.096077345682249,
+      "learning_rate": 6.416976498362432e-07,
+      "loss": 0.5305,
+      "step": 385
+    },
+    {
+      "epoch": 1.6782608695652175,
+      "grad_norm": 2.738317055507431,
+      "learning_rate": 6.250632618090868e-07,
+      "loss": 0.4703,
+      "step": 386
+    },
+    {
+      "epoch": 1.6826086956521737,
+      "grad_norm": 3.5071473316541826,
+      "learning_rate": 6.086329320383311e-07,
+      "loss": 0.4213,
+      "step": 387
+    },
+    {
+      "epoch": 1.6869565217391305,
+      "grad_norm": 3.8877032575124137,
+      "learning_rate": 5.924074268766422e-07,
+      "loss": 0.4856,
+      "step": 388
+    },
+    {
+      "epoch": 1.691304347826087,
+      "grad_norm": 4.828638835996497,
+      "learning_rate": 5.763875031231464e-07,
+      "loss": 0.5905,
+      "step": 389
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 5.896054080665568,
+      "learning_rate": 5.60573907988124e-07,
+      "loss": 0.4024,
+      "step": 390
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 3.896327908000081,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.5591,
+      "step": 391
+    },
+    {
+      "epoch": 1.7043478260869565,
+      "grad_norm": 3.3185586531295677,
+      "learning_rate": 5.295686442617442e-07,
+      "loss": 0.4434,
+      "step": 392
+    },
+    {
+      "epoch": 1.7086956521739132,
+      "grad_norm": 3.263140832538685,
+      "learning_rate": 5.143784218353104e-07,
+      "loss": 0.7183,
+      "step": 393
+    },
+    {
+      "epoch": 1.7130434782608694,
+      "grad_norm": 3.00513867387302,
+      "learning_rate": 4.993974202897456e-07,
+      "loss": 0.5925,
+      "step": 394
+    },
+    {
+      "epoch": 1.7173913043478262,
+      "grad_norm": 4.514101571491169,
+      "learning_rate": 4.846263383773364e-07,
+      "loss": 0.4831,
+      "step": 395
+    },
+    {
+      "epoch": 1.7217391304347827,
+      "grad_norm": 4.069820180851384,
+      "learning_rate": 4.7006586505918273e-07,
+      "loss": 0.4127,
+      "step": 396
+    },
+    {
+      "epoch": 1.7260869565217392,
+      "grad_norm": 3.4177761306996666,
+      "learning_rate": 4.557166794730572e-07,
+      "loss": 0.5253,
+      "step": 397
+    },
+    {
+      "epoch": 1.7304347826086957,
+      "grad_norm": 3.1509456616908365,
+      "learning_rate": 4.4157945090173294e-07,
+      "loss": 0.5074,
+      "step": 398
+    },
+    {
+      "epoch": 1.7347826086956522,
+      "grad_norm": 3.696243545583048,
+      "learning_rate": 4.276548387417656e-07,
+      "loss": 0.5885,
+      "step": 399
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 3.7886982318851805,
+      "learning_rate": 4.139434924727359e-07,
+      "loss": 0.2754,
+      "step": 400
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "eval_loss": 0.8716984987258911,
+      "eval_runtime": 1.212,
+      "eval_samples_per_second": 15.677,
+      "eval_steps_per_second": 4.125,
+      "step": 400
+    },
+    {
+      "epoch": 1.7434782608695651,
+      "grad_norm": 4.101705505067162,
+      "learning_rate": 4.004460516269554e-07,
+      "loss": 0.3822,
+      "step": 401
+    },
+    {
+      "epoch": 1.7478260869565219,
+      "grad_norm": 4.276148559341361,
+      "learning_rate": 3.8716314575964197e-07,
+      "loss": 0.56,
+      "step": 402
+    },
+    {
+      "epoch": 1.7521739130434781,
+      "grad_norm": 3.4463007331708395,
+      "learning_rate": 3.740953944195497e-07,
+      "loss": 0.4291,
+      "step": 403
+    },
+    {
+      "epoch": 1.7565217391304349,
+      "grad_norm": 4.323773987111401,
+      "learning_rate": 3.612434071200771e-07,
+      "loss": 0.5948,
+      "step": 404
+    },
+    {
+      "epoch": 1.7608695652173914,
+      "grad_norm": 3.8045725056072612,
+      "learning_rate": 3.486077833108342e-07,
+      "loss": 0.5438,
+      "step": 405
+    },
+    {
+      "epoch": 1.7652173913043478,
+      "grad_norm": 3.751096313013388,
+      "learning_rate": 3.361891123496824e-07,
+      "loss": 0.4442,
+      "step": 406
+    },
+    {
+      "epoch": 1.7695652173913043,
+      "grad_norm": 5.6873886034585865,
+      "learning_rate": 3.2398797347524656e-07,
+      "loss": 0.5722,
+      "step": 407
+    },
+    {
+      "epoch": 1.7739130434782608,
+      "grad_norm": 3.4440987994083754,
+      "learning_rate": 3.1200493577989875e-07,
+      "loss": 0.5971,
+      "step": 408
+    },
+    {
+      "epoch": 1.7782608695652173,
+      "grad_norm": 4.500827009009169,
+      "learning_rate": 3.002405581832135e-07,
+      "loss": 0.8116,
+      "step": 409
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 4.466563287701003,
+      "learning_rate": 2.88695389405898e-07,
+      "loss": 0.6865,
+      "step": 410
+    },
+    {
+      "epoch": 1.7869565217391306,
+      "grad_norm": 3.603233112278287,
+      "learning_rate": 2.7736996794419767e-07,
+      "loss": 0.5216,
+      "step": 411
+    },
+    {
+      "epoch": 1.7913043478260868,
+      "grad_norm": 3.875200007299088,
+      "learning_rate": 2.662648220447811e-07,
+      "loss": 0.6106,
+      "step": 412
+    },
+    {
+      "epoch": 1.7956521739130435,
+      "grad_norm": 3.534753252029232,
+      "learning_rate": 2.5538046968010097e-07,
+      "loss": 0.636,
+      "step": 413
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.461839191222703,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.6309,
+      "step": 414
+    },
+    {
+      "epoch": 1.8043478260869565,
+      "grad_norm": 4.482635011621374,
+      "learning_rate": 2.3427616592919587e-07,
+      "loss": 0.2978,
+      "step": 415
+    },
+    {
+      "epoch": 1.808695652173913,
+      "grad_norm": 5.623046102327689,
+      "learning_rate": 2.240571989017598e-07,
+      "loss": 0.3982,
+      "step": 416
+    },
+    {
+      "epoch": 1.8130434782608695,
+      "grad_norm": 4.340291840632997,
+      "learning_rate": 2.1406099408072256e-07,
+      "loss": 0.4452,
+      "step": 417
+    },
+    {
+      "epoch": 1.8173913043478263,
+      "grad_norm": 4.373122353194206,
+      "learning_rate": 2.0428801771468388e-07,
+      "loss": 0.5546,
+      "step": 418
+    },
+    {
+      "epoch": 1.8217391304347825,
+      "grad_norm": 4.978141436723412,
+      "learning_rate": 1.947387256402966e-07,
+      "loss": 0.6283,
+      "step": 419
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 4.9421439442580155,
+      "learning_rate": 1.8541356326100436e-07,
+      "loss": 0.5615,
+      "step": 420
+    },
+    {
+      "epoch": 1.8304347826086955,
+      "grad_norm": 4.662787149917992,
+      "learning_rate": 1.7631296552626687e-07,
+      "loss": 0.6423,
+      "step": 421
+    },
+    {
+      "epoch": 1.8347826086956522,
+      "grad_norm": 4.8067902104365645,
+      "learning_rate": 1.6743735691127639e-07,
+      "loss": 0.413,
+      "step": 422
+    },
+    {
+      "epoch": 1.8391304347826087,
+      "grad_norm": 4.40926589583089,
+      "learning_rate": 1.5878715139715395e-07,
+      "loss": 0.5572,
+      "step": 423
+    },
+    {
+      "epoch": 1.8434782608695652,
+      "grad_norm": 2.8704530992170514,
+      "learning_rate": 1.5036275245164377e-07,
+      "loss": 0.4556,
+      "step": 424
+    },
+    {
+      "epoch": 1.8478260869565217,
+      "grad_norm": 4.55581396084849,
+      "learning_rate": 1.4216455301029274e-07,
+      "loss": 0.3541,
+      "step": 425
+    },
+    {
+      "epoch": 1.8521739130434782,
+      "grad_norm": 14.46427054288811,
+      "learning_rate": 1.341929354581234e-07,
+      "loss": 0.4864,
+      "step": 426
+    },
+    {
+      "epoch": 1.856521739130435,
+      "grad_norm": 3.2179410576367027,
+      "learning_rate": 1.2644827161179763e-07,
+      "loss": 0.4733,
+      "step": 427
+    },
+    {
+      "epoch": 1.8608695652173912,
+      "grad_norm": 3.8030605461121274,
+      "learning_rate": 1.1893092270227724e-07,
+      "loss": 0.4404,
+      "step": 428
+    },
+    {
+      "epoch": 1.865217391304348,
+      "grad_norm": 3.8617739599125946,
+      "learning_rate": 1.1164123935797189e-07,
+      "loss": 0.5796,
+      "step": 429
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 3.7521959371096867,
+      "learning_rate": 1.0457956158838545e-07,
+      "loss": 0.5444,
+      "step": 430
+    },
+    {
+      "epoch": 1.873913043478261,
+      "grad_norm": 4.360768628277166,
+      "learning_rate": 9.774621876825985e-08,
+      "loss": 0.7298,
+      "step": 431
+    },
+    {
+      "epoch": 1.8782608695652174,
+      "grad_norm": 3.910205294075997,
+      "learning_rate": 9.114152962220734e-08,
+      "loss": 0.542,
+      "step": 432
+    },
+    {
+      "epoch": 1.882608695652174,
+      "grad_norm": 4.005132857310367,
+      "learning_rate": 8.476580220984854e-08,
+      "loss": 0.6349,
+      "step": 433
+    },
+    {
+      "epoch": 1.8869565217391304,
+      "grad_norm": 4.596239343877202,
+      "learning_rate": 7.861933391144272e-08,
+      "loss": 0.4515,
+      "step": 434
+    },
+    {
+      "epoch": 1.891304347826087,
+      "grad_norm": 3.9563035871216643,
+      "learning_rate": 7.270241141401568e-08,
+      "loss": 0.6042,
+      "step": 435
+    },
+    {
+      "epoch": 1.8956521739130436,
+      "grad_norm": 2.99941894532922,
+      "learning_rate": 6.701531069799039e-08,
+      "loss": 0.3209,
+      "step": 436
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 4.126028774169588,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.6095,
+      "step": 437
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "grad_norm": 4.219172610306852,
+      "learning_rate": 5.633162492207633e-08,
+      "loss": 0.5979,
+      "step": 438
+    },
+    {
+      "epoch": 1.908695652173913,
+      "grad_norm": 4.866427440568141,
+      "learning_rate": 5.133553817665948e-08,
+      "loss": 0.662,
+      "step": 439
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 4.6700212829119385,
+      "learning_rate": 4.657026981834623e-08,
+      "loss": 0.5815,
+      "step": 440
+    },
+    {
+      "epoch": 1.9173913043478261,
+      "grad_norm": 3.0191187442564003,
+      "learning_rate": 4.203604211145851e-08,
+      "loss": 0.3505,
+      "step": 441
+    },
+    {
+      "epoch": 1.9217391304347826,
+      "grad_norm": 3.3555580221359538,
+      "learning_rate": 3.773306654399234e-08,
+      "loss": 0.4539,
+      "step": 442
+    },
+    {
+      "epoch": 1.9260869565217391,
+      "grad_norm": 3.932100191195551,
+      "learning_rate": 3.366154381775011e-08,
+      "loss": 0.5395,
+      "step": 443
+    },
+    {
+      "epoch": 1.9304347826086956,
+      "grad_norm": 4.543654718724428,
+      "learning_rate": 2.9821663838981994e-08,
+      "loss": 0.5999,
+      "step": 444
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "grad_norm": 3.2027549612689263,
+      "learning_rate": 2.6213605709525803e-08,
+      "loss": 0.3673,
+      "step": 445
+    },
+    {
+      "epoch": 1.9391304347826086,
+      "grad_norm": 3.1103705554436694,
+      "learning_rate": 2.283753771845587e-08,
+      "loss": 0.3699,
+      "step": 446
+    },
+    {
+      "epoch": 1.9434782608695653,
+      "grad_norm": 3.596434865326805,
+      "learning_rate": 1.969361733423103e-08,
+      "loss": 0.6307,
+      "step": 447
+    },
+    {
+      "epoch": 1.9478260869565216,
+      "grad_norm": 4.349343114323385,
+      "learning_rate": 1.6781991197352133e-08,
+      "loss": 0.5428,
+      "step": 448
+    },
+    {
+      "epoch": 1.9521739130434783,
+      "grad_norm": 4.855414536760434,
+      "learning_rate": 1.4102795113520307e-08,
+      "loss": 0.4092,
+      "step": 449
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 3.0119883785611585,
+      "learning_rate": 1.1656154047303691e-08,
+      "loss": 0.4938,
+      "step": 450
+    },
+    {
+      "epoch": 1.9608695652173913,
+      "grad_norm": 4.642330127831433,
+      "learning_rate": 9.442182116309872e-09,
+      "loss": 0.7239,
+      "step": 451
+    },
+    {
+      "epoch": 1.9652173913043478,
+      "grad_norm": 3.663654111517379,
+      "learning_rate": 7.460982585860144e-09,
+      "loss": 0.3265,
+      "step": 452
+    },
+    {
+      "epoch": 1.9695652173913043,
+      "grad_norm": 2.870263572172439,
+      "learning_rate": 5.712647864176135e-09,
+      "loss": 0.5066,
+      "step": 453
+    },
+    {
+      "epoch": 1.973913043478261,
+      "grad_norm": 3.8955974016594053,
+      "learning_rate": 4.197259498067707e-09,
+      "loss": 0.5468,
+      "step": 454
+    },
+    {
+      "epoch": 1.9782608695652173,
+      "grad_norm": 3.973489744191462,
+      "learning_rate": 2.9148881691298812e-09,
+      "loss": 0.4732,
+      "step": 455
+    },
+    {
+      "epoch": 1.982608695652174,
+      "grad_norm": 4.726977182661161,
+      "learning_rate": 1.865593690446588e-09,
+      "loss": 0.5222,
+      "step": 456
+    },
+    {
+      "epoch": 1.9869565217391303,
+      "grad_norm": 3.1878654907075217,
+      "learning_rate": 1.0494250038006747e-09,
+      "loss": 0.4729,
+      "step": 457
+    },
+    {
+      "epoch": 1.991304347826087,
+      "grad_norm": 5.2096767935404324,
+      "learning_rate": 4.664201773896259e-10,
+      "loss": 0.5507,
+      "step": 458
+    },
+    {
+      "epoch": 1.9956521739130435,
+      "grad_norm": 4.661539977777431,
+      "learning_rate": 1.1660640405308787e-10,
+      "loss": 0.7135,
+      "step": 459
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.192820799122638,
+      "learning_rate": 0.0,
+      "loss": 0.4461,
+      "step": 460
+    },
+    {
+      "epoch": 2.0,
+      "step": 460,
+      "total_flos": 2556217393152.0,
+      "train_loss": 0.679824001374452,
+      "train_runtime": 538.1176,
+      "train_samples_per_second": 6.839,
+      "train_steps_per_second": 0.855
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2556217393152.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5af1e7b46d13a20081021d82d4f001ef7f58a25f99500a6998ea7a08b38b98
+size 7160