push first version model

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: IRL_iter0_best_of_16_spin_iter0_epoch_5_saving
+  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. -->
+
+# IRL_iter0_best_of_16_spin_iter0_epoch_5_saving
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the d, the a, the t, the a, the _, the g, the e, the n, the e, the r, the a, the t, the e, the d, the /, the s, the p, the i, the n, the _, the i, the t, the e, the r, the 0, the _, the b, the e, the s, the t, the _, the o, the f, the _, the 1, the 6, the /, the t, the o, the p, the 1, the _, the s, the e, the l, the e, the c, the t, the e, the d, the _, the I, the R, the L, the _, the r, the e, the w, the a, the r, the d, the _, the s, the e, the l, the e, the c, the t, the e and the d datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.0396
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0895        | 1.0   | 79   | 0.7223          |
+| 0.6454        | 2.0   | 158  | 0.3317          |
+| 0.2926        | 3.0   | 237  | 0.1293          |
+| 0.1048        | 4.0   | 316  | 0.0542          |
+| 0.0465        | 5.0   | 395  | 0.0396          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.039588429033756256,
+    "eval_runtime": 214.1263,
+    "eval_samples": 49792,
+    "eval_samples_per_second": 47.192,
+    "eval_steps_per_second": 0.738,
+    "total_flos": 165305238159360.0,
+    "train_loss": 0.43836132314386245,
+    "train_runtime": 6288.8643,
+    "train_samples": 49792,
+    "train_samples_per_second": 8.034,
+    "train_steps_per_second": 0.063
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.039588429033756256,
+    "eval_runtime": 214.1263,
+    "eval_samples": 49792,
+    "eval_samples_per_second": 47.192,
+    "eval_steps_per_second": 0.738
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8537b0cbce772547e5b7f8070cbf23b30637521bf08cafeb231b0c36cfa829c
+size 4943162336

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f891bb1b6838b429ffc2b9f8bdc7a2e010268eaa9737c26dd89d8c8fa00bc2
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b7097f0b7e0b93c2d3eb91d778a7bf91c645a0b0168a4bec9e5aa09f2da375
+size 4540516344

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 165305238159360.0,
+    "train_loss": 0.43836132314386245,
+    "train_runtime": 6288.8643,
+    "train_samples": 49792,
+    "train_samples_per_second": 8.034,
+    "train_steps_per_second": 0.063
+}

trainer_state.json

@@ -0,0 +1,642 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 395,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012658227848101266,
+      "grad_norm": 6.695639272540547,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.1195,
+      "step": 1
+    },
+    {
+      "epoch": 0.06329113924050633,
+      "grad_norm": 13.683866082279918,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0968,
+      "step": 5
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "grad_norm": 2.7914110872997275,
+      "learning_rate": 5e-06,
+      "loss": 1.0868,
+      "step": 10
+    },
+    {
+      "epoch": 0.189873417721519,
+      "grad_norm": 2.2869962494889995,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.0771,
+      "step": 15
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 2.315595057148159,
+      "learning_rate": 1e-05,
+      "loss": 1.0546,
+      "step": 20
+    },
+    {
+      "epoch": 0.31645569620253167,
+      "grad_norm": 1.9266353743480364,
+      "learning_rate": 1.25e-05,
+      "loss": 1.084,
+      "step": 25
+    },
+    {
+      "epoch": 0.379746835443038,
+      "grad_norm": 2.150532379708014,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.0654,
+      "step": 30
+    },
+    {
+      "epoch": 0.4430379746835443,
+      "grad_norm": 2.1018953026935905,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.0817,
+      "step": 35
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 2.3849545878679272,
+      "learning_rate": 2e-05,
+      "loss": 1.0971,
+      "step": 40
+    },
+    {
+      "epoch": 0.569620253164557,
+      "grad_norm": 2.345688862339495,
+      "learning_rate": 1.9990212265199738e-05,
+      "loss": 1.086,
+      "step": 45
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 2.5866807131537906,
+      "learning_rate": 1.996086822074945e-05,
+      "loss": 1.0656,
+      "step": 50
+    },
+    {
+      "epoch": 0.6962025316455697,
+      "grad_norm": 2.4392627537159655,
+      "learning_rate": 1.9912025308994146e-05,
+      "loss": 1.1059,
+      "step": 55
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 2.2706485443813276,
+      "learning_rate": 1.9843779142227258e-05,
+      "loss": 1.0973,
+      "step": 60
+    },
+    {
+      "epoch": 0.8227848101265823,
+      "grad_norm": 2.3020097653483496,
+      "learning_rate": 1.975626331552507e-05,
+      "loss": 1.1083,
+      "step": 65
+    },
+    {
+      "epoch": 0.8860759493670886,
+      "grad_norm": 2.0670888705685955,
+      "learning_rate": 1.96496491452281e-05,
+      "loss": 1.1039,
+      "step": 70
+    },
+    {
+      "epoch": 0.9493670886075949,
+      "grad_norm": 2.371742516361207,
+      "learning_rate": 1.9524145333581315e-05,
+      "loss": 1.0895,
+      "step": 75
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7223408222198486,
+      "eval_runtime": 213.2984,
+      "eval_samples_per_second": 47.375,
+      "eval_steps_per_second": 0.741,
+      "step": 79
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 8.106924593883994,
+      "learning_rate": 1.9379997560189677e-05,
+      "loss": 1.0198,
+      "step": 80
+    },
+    {
+      "epoch": 1.0759493670886076,
+      "grad_norm": 3.486817193319529,
+      "learning_rate": 1.9217488001088784e-05,
+      "loss": 0.6812,
+      "step": 85
+    },
+    {
+      "epoch": 1.139240506329114,
+      "grad_norm": 2.921219837737029,
+      "learning_rate": 1.903693477637204e-05,
+      "loss": 0.6683,
+      "step": 90
+    },
+    {
+      "epoch": 1.2025316455696202,
+      "grad_norm": 3.1078224489011683,
+      "learning_rate": 1.883869132745561e-05,
+      "loss": 0.653,
+      "step": 95
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 2.8280645620621874,
+      "learning_rate": 1.862314572520028e-05,
+      "loss": 0.6501,
+      "step": 100
+    },
+    {
+      "epoch": 1.3291139240506329,
+      "grad_norm": 2.920193489057834,
+      "learning_rate": 1.8390719910244487e-05,
+      "loss": 0.647,
+      "step": 105
+    },
+    {
+      "epoch": 1.3924050632911391,
+      "grad_norm": 2.647561794905359,
+      "learning_rate": 1.8141868867035745e-05,
+      "loss": 0.6531,
+      "step": 110
+    },
+    {
+      "epoch": 1.4556962025316456,
+      "grad_norm": 2.7660605803019447,
+      "learning_rate": 1.7877079733177185e-05,
+      "loss": 0.6232,
+      "step": 115
+    },
+    {
+      "epoch": 1.518987341772152,
+      "grad_norm": 2.497219995540892,
+      "learning_rate": 1.759687084583285e-05,
+      "loss": 0.6401,
+      "step": 120
+    },
+    {
+      "epoch": 1.5822784810126582,
+      "grad_norm": 2.447623483254921,
+      "learning_rate": 1.7301790727058344e-05,
+      "loss": 0.6592,
+      "step": 125
+    },
+    {
+      "epoch": 1.6455696202531644,
+      "grad_norm": 2.4783693483832563,
+      "learning_rate": 1.6992417010043144e-05,
+      "loss": 0.6441,
+      "step": 130
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 2.348228472338975,
+      "learning_rate": 1.666935530836651e-05,
+      "loss": 0.6439,
+      "step": 135
+    },
+    {
+      "epoch": 1.7721518987341773,
+      "grad_norm": 2.316917620320839,
+      "learning_rate": 1.6333238030480473e-05,
+      "loss": 0.6572,
+      "step": 140
+    },
+    {
+      "epoch": 1.8354430379746836,
+      "grad_norm": 2.614503810192861,
+      "learning_rate": 1.5984723141740578e-05,
+      "loss": 0.6764,
+      "step": 145
+    },
+    {
+      "epoch": 1.8987341772151898,
+      "grad_norm": 2.452736422029602,
+      "learning_rate": 1.562449287640781e-05,
+      "loss": 0.6555,
+      "step": 150
+    },
+    {
+      "epoch": 1.9620253164556962,
+      "grad_norm": 2.737510300725156,
+      "learning_rate": 1.5253252402142989e-05,
+      "loss": 0.6454,
+      "step": 155
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.33173683285713196,
+      "eval_runtime": 213.2106,
+      "eval_samples_per_second": 47.394,
+      "eval_steps_per_second": 0.741,
+      "step": 158
+    },
+    {
+      "epoch": 2.0253164556962027,
+      "grad_norm": 3.9057198522311167,
+      "learning_rate": 1.4871728439607967e-05,
+      "loss": 0.5134,
+      "step": 160
+    },
+    {
+      "epoch": 2.088607594936709,
+      "grad_norm": 3.4868328352161817,
+      "learning_rate": 1.4480667839875786e-05,
+      "loss": 0.3096,
+      "step": 165
+    },
+    {
+      "epoch": 2.151898734177215,
+      "grad_norm": 2.9717493172755014,
+      "learning_rate": 1.408083612243465e-05,
+      "loss": 0.2909,
+      "step": 170
+    },
+    {
+      "epoch": 2.2151898734177213,
+      "grad_norm": 2.642444961402327,
+      "learning_rate": 1.367301597664757e-05,
+      "loss": 0.2837,
+      "step": 175
+    },
+    {
+      "epoch": 2.278481012658228,
+      "grad_norm": 2.3997899647768346,
+      "learning_rate": 1.3258005729601178e-05,
+      "loss": 0.2818,
+      "step": 180
+    },
+    {
+      "epoch": 2.3417721518987342,
+      "grad_norm": 2.7423823494323774,
+      "learning_rate": 1.2836617783342968e-05,
+      "loss": 0.2907,
+      "step": 185
+    },
+    {
+      "epoch": 2.4050632911392404,
+      "grad_norm": 2.3807259553082276,
+      "learning_rate": 1.2409677024566145e-05,
+      "loss": 0.2872,
+      "step": 190
+    },
+    {
+      "epoch": 2.4683544303797467,
+      "grad_norm": 2.336572941961749,
+      "learning_rate": 1.1978019209855174e-05,
+      "loss": 0.2866,
+      "step": 195
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "grad_norm": 2.2601309613900757,
+      "learning_rate": 1.1542489329653024e-05,
+      "loss": 0.2945,
+      "step": 200
+    },
+    {
+      "epoch": 2.5949367088607596,
+      "grad_norm": 2.3050926972713968,
+      "learning_rate": 1.11039399541527e-05,
+      "loss": 0.2937,
+      "step": 205
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 2.221130883158219,
+      "learning_rate": 1.066322956435104e-05,
+      "loss": 0.2961,
+      "step": 210
+    },
+    {
+      "epoch": 2.721518987341772,
+      "grad_norm": 2.270387701106379,
+      "learning_rate": 1.022122087153187e-05,
+      "loss": 0.2965,
+      "step": 215
+    },
+    {
+      "epoch": 2.7848101265822782,
+      "grad_norm": 2.279056997659604,
+      "learning_rate": 9.778779128468133e-06,
+      "loss": 0.2964,
+      "step": 220
+    },
+    {
+      "epoch": 2.848101265822785,
+      "grad_norm": 2.1417041666216696,
+      "learning_rate": 9.336770435648963e-06,
+      "loss": 0.2931,
+      "step": 225
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 2.439196726609028,
+      "learning_rate": 8.896060045847305e-06,
+      "loss": 0.2977,
+      "step": 230
+    },
+    {
+      "epoch": 2.9746835443037973,
+      "grad_norm": 2.2397521488796417,
+      "learning_rate": 8.457510670346976e-06,
+      "loss": 0.2926,
+      "step": 235
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.12934371829032898,
+      "eval_runtime": 213.237,
+      "eval_samples_per_second": 47.389,
+      "eval_steps_per_second": 0.741,
+      "step": 237
+    },
+    {
+      "epoch": 3.037974683544304,
+      "grad_norm": 2.2704813832171142,
+      "learning_rate": 8.021980790144828e-06,
+      "loss": 0.199,
+      "step": 240
+    },
+    {
+      "epoch": 3.1012658227848102,
+      "grad_norm": 2.132226843273487,
+      "learning_rate": 7.590322975433857e-06,
+      "loss": 0.1128,
+      "step": 245
+    },
+    {
+      "epoch": 3.1645569620253164,
+      "grad_norm": 2.0782142465832236,
+      "learning_rate": 7.163382216657033e-06,
+      "loss": 0.1129,
+      "step": 250
+    },
+    {
+      "epoch": 3.2278481012658227,
+      "grad_norm": 1.761669140987703,
+      "learning_rate": 6.741994270398826e-06,
+      "loss": 0.1099,
+      "step": 255
+    },
+    {
+      "epoch": 3.291139240506329,
+      "grad_norm": 1.717634933034142,
+      "learning_rate": 6.326984023352435e-06,
+      "loss": 0.1086,
+      "step": 260
+    },
+    {
+      "epoch": 3.3544303797468356,
+      "grad_norm": 1.6608157157785954,
+      "learning_rate": 5.919163877565351e-06,
+      "loss": 0.1068,
+      "step": 265
+    },
+    {
+      "epoch": 3.4177215189873418,
+      "grad_norm": 1.6064024695135044,
+      "learning_rate": 5.519332160124215e-06,
+      "loss": 0.1101,
+      "step": 270
+    },
+    {
+      "epoch": 3.481012658227848,
+      "grad_norm": 1.6349645931027217,
+      "learning_rate": 5.128271560392037e-06,
+      "loss": 0.1074,
+      "step": 275
+    },
+    {
+      "epoch": 3.5443037974683547,
+      "grad_norm": 1.7679069294086043,
+      "learning_rate": 4.746747597857014e-06,
+      "loss": 0.1118,
+      "step": 280
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 1.5530405205049536,
+      "learning_rate": 4.375507123592194e-06,
+      "loss": 0.1077,
+      "step": 285
+    },
+    {
+      "epoch": 3.670886075949367,
+      "grad_norm": 1.5871889705183277,
+      "learning_rate": 4.015276858259427e-06,
+      "loss": 0.1082,
+      "step": 290
+    },
+    {
+      "epoch": 3.7341772151898733,
+      "grad_norm": 1.5985959451025067,
+      "learning_rate": 3.6667619695195287e-06,
+      "loss": 0.1063,
+      "step": 295
+    },
+    {
+      "epoch": 3.7974683544303796,
+      "grad_norm": 1.567040797684349,
+      "learning_rate": 3.330644691633492e-06,
+      "loss": 0.1067,
+      "step": 300
+    },
+    {
+      "epoch": 3.8607594936708862,
+      "grad_norm": 1.6098560275600409,
+      "learning_rate": 3.00758298995686e-06,
+      "loss": 0.1045,
+      "step": 305
+    },
+    {
+      "epoch": 3.9240506329113924,
+      "grad_norm": 1.495424841878041,
+      "learning_rate": 2.698209272941659e-06,
+      "loss": 0.1076,
+      "step": 310
+    },
+    {
+      "epoch": 3.9873417721518987,
+      "grad_norm": 1.4612235257248143,
+      "learning_rate": 2.403129154167153e-06,
+      "loss": 0.1048,
+      "step": 315
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.054249346256256104,
+      "eval_runtime": 213.4038,
+      "eval_samples_per_second": 47.352,
+      "eval_steps_per_second": 0.74,
+      "step": 316
+    },
+    {
+      "epoch": 4.050632911392405,
+      "grad_norm": 0.8970304833218358,
+      "learning_rate": 2.1229202668228197e-06,
+      "loss": 0.0643,
+      "step": 320
+    },
+    {
+      "epoch": 4.113924050632911,
+      "grad_norm": 1.3031778574429476,
+      "learning_rate": 1.8581311329642592e-06,
+      "loss": 0.0496,
+      "step": 325
+    },
+    {
+      "epoch": 4.177215189873418,
+      "grad_norm": 1.0494986965992847,
+      "learning_rate": 1.609280089755515e-06,
+      "loss": 0.0498,
+      "step": 330
+    },
+    {
+      "epoch": 4.2405063291139244,
+      "grad_norm": 0.8871889072165642,
+      "learning_rate": 1.3768542747997215e-06,
+      "loss": 0.048,
+      "step": 335
+    },
+    {
+      "epoch": 4.30379746835443,
+      "grad_norm": 0.8947823783464494,
+      "learning_rate": 1.161308672544389e-06,
+      "loss": 0.0491,
+      "step": 340
+    },
+    {
+      "epoch": 4.367088607594937,
+      "grad_norm": 0.8681171283598373,
+      "learning_rate": 9.630652236279626e-07,
+      "loss": 0.0467,
+      "step": 345
+    },
+    {
+      "epoch": 4.430379746835443,
+      "grad_norm": 0.8483515397273593,
+      "learning_rate": 7.825119989112173e-07,
+      "loss": 0.0474,
+      "step": 350
+    },
+    {
+      "epoch": 4.493670886075949,
+      "grad_norm": 0.883073997111795,
+      "learning_rate": 6.200024398103255e-07,
+      "loss": 0.0461,
+      "step": 355
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.8423665781515933,
+      "learning_rate": 4.7585466641868696e-07,
+      "loss": 0.0474,
+      "step": 360
+    },
+    {
+      "epoch": 4.620253164556962,
+      "grad_norm": 1.0038851569615406,
+      "learning_rate": 3.5035085477190143e-07,
+      "loss": 0.0476,
+      "step": 365
+    },
+    {
+      "epoch": 4.6835443037974684,
+      "grad_norm": 0.9089402076181121,
+      "learning_rate": 2.4373668447493225e-07,
+      "loss": 0.0467,
+      "step": 370
+    },
+    {
+      "epoch": 4.746835443037975,
+      "grad_norm": 0.8530919153878059,
+      "learning_rate": 1.562208577727442e-07,
+      "loss": 0.0469,
+      "step": 375
+    },
+    {
+      "epoch": 4.810126582278481,
+      "grad_norm": 0.8298393668849166,
+      "learning_rate": 8.797469100585432e-08,
+      "loss": 0.0481,
+      "step": 380
+    },
+    {
+      "epoch": 4.8734177215189876,
+      "grad_norm": 0.986632852960438,
+      "learning_rate": 3.913177925055189e-08,
+      "loss": 0.0471,
+      "step": 385
+    },
+    {
+      "epoch": 4.936708860759493,
+      "grad_norm": 0.9075462948662969,
+      "learning_rate": 9.78773480026396e-09,
+      "loss": 0.0474,
+      "step": 390
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7480159011876264,
+      "learning_rate": 0.0,
+      "loss": 0.0465,
+      "step": 395
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.039588429033756256,
+      "eval_runtime": 213.3054,
+      "eval_samples_per_second": 47.373,
+      "eval_steps_per_second": 0.741,
+      "step": 395
+    },
+    {
+      "epoch": 5.0,
+      "step": 395,
+      "total_flos": 165305238159360.0,
+      "train_loss": 0.43836132314386245,
+      "train_runtime": 6288.8643,
+      "train_samples_per_second": 8.034,
+      "train_steps_per_second": 0.063
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 395,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 165305238159360.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ffc04f64ae9bc197484fd7b6a1c0cb35fb961b932b98746fd5162e9a75d6ab
+size 6968