Upload 11 files

README.md

@@ -1,3 +1,59 @@
 ---
-license: apache-2.0
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: alpindale/Mistral-7B-v0.2-hf
+model-index:
+- name: train_2024-04-06-15-56-06
+  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. -->
+
+# train_2024-04-06-15-56-06
+
+This model is a fine-tuned version of [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) on the dsm dataset.
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.37.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c158a5fc7c17bc4233b68cd98bde5b105f0cc8ef4b94dd7329f3ddb688df27bc
+size 13648432

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.91,
+    "train_loss": 0.15196624583211438,
+    "train_runtime": 473.0573,
+    "train_samples_per_second": 9.872,
+    "train_steps_per_second": 0.613
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.91,
+    "train_loss": 0.15196624583211438,
+    "train_runtime": 473.0573,
+    "train_samples_per_second": 9.872,
+    "train_steps_per_second": 0.613
+}

trainer_log.jsonl

@@ -0,0 +1,59 @@
+{"current_steps": 5, "total_steps": 290, "loss": 0.4005, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.996333534627809e-05, "epoch": 0.17, "percentage": 1.72, "elapsed_time": "0:00:07", "remaining_time": "0:07:32"}
+{"current_steps": 10, "total_steps": 290, "loss": 0.3409, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.985344892885899e-05, "epoch": 0.34, "percentage": 3.45, "elapsed_time": "0:00:15", "remaining_time": "0:07:12"}
+{"current_steps": 15, "total_steps": 290, "loss": 0.3372, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.967066306353816e-05, "epoch": 0.51, "percentage": 5.17, "elapsed_time": "0:00:22", "remaining_time": "0:07:00"}
+{"current_steps": 20, "total_steps": 290, "loss": 0.334, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.941551389275217e-05, "epoch": 0.68, "percentage": 6.9, "elapsed_time": "0:00:31", "remaining_time": "0:07:01"}
+{"current_steps": 25, "total_steps": 290, "loss": 0.348, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.908874981298057e-05, "epoch": 0.85, "percentage": 8.62, "elapsed_time": "0:00:39", "remaining_time": "0:06:58"}
+{"current_steps": 30, "total_steps": 290, "loss": 0.3413, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.869132927957007e-05, "epoch": 1.03, "percentage": 10.34, "elapsed_time": "0:00:47", "remaining_time": "0:06:49"}
+{"current_steps": 35, "total_steps": 290, "loss": 0.2458, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.822441799541979e-05, "epoch": 1.2, "percentage": 12.07, "elapsed_time": "0:00:55", "remaining_time": "0:06:44"}
+{"current_steps": 40, "total_steps": 290, "loss": 0.2715, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.768938549177393e-05, "epoch": 1.37, "percentage": 13.79, "elapsed_time": "0:01:04", "remaining_time": "0:06:42"}
+{"current_steps": 45, "total_steps": 290, "loss": 0.2079, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.708780111115057e-05, "epoch": 1.54, "percentage": 15.52, "elapsed_time": "0:01:12", "remaining_time": "0:06:36"}
+{"current_steps": 50, "total_steps": 290, "loss": 0.2698, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.642142940418973e-05, "epoch": 1.71, "percentage": 17.24, "elapsed_time": "0:01:21", "remaining_time": "0:06:29"}
+{"current_steps": 55, "total_steps": 290, "loss": 0.2543, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.5692224953922266e-05, "epoch": 1.88, "percentage": 18.97, "elapsed_time": "0:01:29", "remaining_time": "0:06:21"}
+{"current_steps": 60, "total_steps": 290, "loss": 0.2492, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4902326642641095e-05, "epoch": 2.05, "percentage": 20.69, "elapsed_time": "0:01:38", "remaining_time": "0:06:16"}
+{"current_steps": 65, "total_steps": 290, "loss": 0.2308, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4054051378190915e-05, "epoch": 2.22, "percentage": 22.41, "elapsed_time": "0:01:46", "remaining_time": "0:06:07"}
+{"current_steps": 70, "total_steps": 290, "loss": 0.2018, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.3149887298078276e-05, "epoch": 2.39, "percentage": 24.14, "elapsed_time": "0:01:54", "remaining_time": "0:05:59"}
+{"current_steps": 75, "total_steps": 290, "loss": 0.1668, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.2192486471335585e-05, "epoch": 2.56, "percentage": 25.86, "elapsed_time": "0:02:02", "remaining_time": "0:05:51"}
+{"current_steps": 80, "total_steps": 290, "loss": 0.2045, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.118465711954569e-05, "epoch": 2.74, "percentage": 27.59, "elapsed_time": "0:02:10", "remaining_time": "0:05:41"}
+{"current_steps": 85, "total_steps": 290, "loss": 0.1961, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.012935537984414e-05, "epoch": 2.91, "percentage": 29.31, "elapsed_time": "0:02:19", "remaining_time": "0:05:36"}
+{"current_steps": 90, "total_steps": 290, "loss": 0.1978, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.902967663405956e-05, "epoch": 3.08, "percentage": 31.03, "elapsed_time": "0:02:27", "remaining_time": "0:05:27"}
+{"current_steps": 95, "total_steps": 290, "loss": 0.1409, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.7888846429425546e-05, "epoch": 3.25, "percentage": 32.76, "elapsed_time": "0:02:35", "remaining_time": "0:05:19"}
+{"current_steps": 100, "total_steps": 290, "loss": 0.1534, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.671021101749476e-05, "epoch": 3.42, "percentage": 34.48, "elapsed_time": "0:02:42", "remaining_time": "0:05:09"}
+{"current_steps": 105, "total_steps": 290, "loss": 0.1634, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.5497227539006614e-05, "epoch": 3.59, "percentage": 36.21, "elapsed_time": "0:02:51", "remaining_time": "0:05:02"}
+{"current_steps": 110, "total_steps": 290, "loss": 0.1796, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.425345388349786e-05, "epoch": 3.76, "percentage": 37.93, "elapsed_time": "0:02:59", "remaining_time": "0:04:53"}
+{"current_steps": 115, "total_steps": 290, "loss": 0.1492, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.29825382533995e-05, "epoch": 3.93, "percentage": 39.66, "elapsed_time": "0:03:07", "remaining_time": "0:04:45"}
+{"current_steps": 120, "total_steps": 290, "loss": 0.1366, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.168820846323053e-05, "epoch": 4.1, "percentage": 41.38, "elapsed_time": "0:03:15", "remaining_time": "0:04:36"}
+{"current_steps": 125, "total_steps": 290, "loss": 0.1133, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.0374261005275607e-05, "epoch": 4.27, "percentage": 43.1, "elapsed_time": "0:03:24", "remaining_time": "0:04:29"}
+{"current_steps": 130, "total_steps": 290, "loss": 0.1561, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9044549913819124e-05, "epoch": 4.44, "percentage": 44.83, "elapsed_time": "0:03:32", "remaining_time": "0:04:21"}
+{"current_steps": 135, "total_steps": 290, "loss": 0.1161, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.7702975460598547e-05, "epoch": 4.62, "percentage": 46.55, "elapsed_time": "0:03:39", "remaining_time": "0:04:12"}
+{"current_steps": 140, "total_steps": 290, "loss": 0.137, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.635347271463544e-05, "epoch": 4.79, "percentage": 48.28, "elapsed_time": "0:03:48", "remaining_time": "0:04:04"}
+{"current_steps": 145, "total_steps": 290, "loss": 0.1271, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.5e-05, "epoch": 4.96, "percentage": 50.0, "elapsed_time": "0:03:56", "remaining_time": "0:03:56"}
+{"current_steps": 150, "total_steps": 290, "loss": 0.1031, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3646527285364565e-05, "epoch": 5.13, "percentage": 51.72, "elapsed_time": "0:04:04", "remaining_time": "0:03:48"}
+{"current_steps": 155, "total_steps": 290, "loss": 0.0881, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.2297024539401463e-05, "epoch": 5.3, "percentage": 53.45, "elapsed_time": "0:04:12", "remaining_time": "0:03:39"}
+{"current_steps": 160, "total_steps": 290, "loss": 0.094, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0955450086180882e-05, "epoch": 5.47, "percentage": 55.17, "elapsed_time": "0:04:20", "remaining_time": "0:03:31"}
+{"current_steps": 165, "total_steps": 290, "loss": 0.1292, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.96257389947244e-05, "epoch": 5.64, "percentage": 56.9, "elapsed_time": "0:04:29", "remaining_time": "0:03:23"}
+{"current_steps": 170, "total_steps": 290, "loss": 0.1146, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.8311791536769483e-05, "epoch": 5.81, "percentage": 58.62, "elapsed_time": "0:04:37", "remaining_time": "0:03:15"}
+{"current_steps": 175, "total_steps": 290, "loss": 0.0954, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7017461746600506e-05, "epoch": 5.98, "percentage": 60.34, "elapsed_time": "0:04:45", "remaining_time": "0:03:07"}
+{"current_steps": 180, "total_steps": 290, "loss": 0.1114, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.574654611650214e-05, "epoch": 6.15, "percentage": 62.07, "elapsed_time": "0:04:53", "remaining_time": "0:02:59"}
+{"current_steps": 185, "total_steps": 290, "loss": 0.0744, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4502772460993385e-05, "epoch": 6.32, "percentage": 63.79, "elapsed_time": "0:05:02", "remaining_time": "0:02:51"}
+{"current_steps": 190, "total_steps": 290, "loss": 0.0752, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.328978898250525e-05, "epoch": 6.5, "percentage": 65.52, "elapsed_time": "0:05:09", "remaining_time": "0:02:42"}
+{"current_steps": 195, "total_steps": 290, "loss": 0.0957, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2111153570574454e-05, "epoch": 6.67, "percentage": 67.24, "elapsed_time": "0:05:17", "remaining_time": "0:02:34"}
+{"current_steps": 200, "total_steps": 290, "loss": 0.0871, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.0970323365940444e-05, "epoch": 6.84, "percentage": 68.97, "elapsed_time": "0:05:26", "remaining_time": "0:02:26"}
+{"current_steps": 205, "total_steps": 290, "loss": 0.087, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.870644620155877e-06, "epoch": 7.01, "percentage": 70.69, "elapsed_time": "0:05:34", "remaining_time": "0:02:18"}
+{"current_steps": 210, "total_steps": 290, "loss": 0.0768, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.815342880454311e-06, "epoch": 7.18, "percentage": 72.41, "elapsed_time": "0:05:42", "remaining_time": "0:02:10"}
+{"current_steps": 215, "total_steps": 290, "loss": 0.0738, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.807513528664414e-06, "epoch": 7.35, "percentage": 74.14, "elapsed_time": "0:05:50", "remaining_time": "0:02:02"}
+{"current_steps": 220, "total_steps": 290, "loss": 0.0953, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 6.8501127019217346e-06, "epoch": 7.52, "percentage": 75.86, "elapsed_time": "0:05:58", "remaining_time": "0:01:54"}
+{"current_steps": 225, "total_steps": 290, "loss": 0.0948, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.945948621809091e-06, "epoch": 7.69, "percentage": 77.59, "elapsed_time": "0:06:07", "remaining_time": "0:01:46"}
+{"current_steps": 230, "total_steps": 290, "loss": 0.075, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.097673357358907e-06, "epoch": 7.86, "percentage": 79.31, "elapsed_time": "0:06:16", "remaining_time": "0:01:38"}
+{"current_steps": 235, "total_steps": 290, "loss": 0.0638, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.307775046077739e-06, "epoch": 8.03, "percentage": 81.03, "elapsed_time": "0:06:24", "remaining_time": "0:01:29"}
+{"current_steps": 240, "total_steps": 290, "loss": 0.0898, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.578570595810274e-06, "epoch": 8.21, "percentage": 82.76, "elapsed_time": "0:06:32", "remaining_time": "0:01:21"}
+{"current_steps": 245, "total_steps": 290, "loss": 0.0799, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.9121988888494297e-06, "epoch": 8.38, "percentage": 84.48, "elapsed_time": "0:06:41", "remaining_time": "0:01:13"}
+{"current_steps": 250, "total_steps": 290, "loss": 0.0688, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.310614508226078e-06, "epoch": 8.55, "percentage": 86.21, "elapsed_time": "0:06:49", "remaining_time": "0:01:05"}
+{"current_steps": 255, "total_steps": 290, "loss": 0.0676, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7755820045802145e-06, "epoch": 8.72, "percentage": 87.93, "elapsed_time": "0:06:57", "remaining_time": "0:00:57"}
+{"current_steps": 260, "total_steps": 290, "loss": 0.0726, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.3086707204299414e-06, "epoch": 8.89, "percentage": 89.66, "elapsed_time": "0:07:05", "remaining_time": "0:00:49"}
+{"current_steps": 265, "total_steps": 290, "loss": 0.072, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.112501870194273e-07, "epoch": 9.06, "percentage": 91.38, "elapsed_time": "0:07:13", "remaining_time": "0:00:40"}
+{"current_steps": 270, "total_steps": 290, "loss": 0.0584, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.844861072478336e-07, "epoch": 9.23, "percentage": 93.1, "elapsed_time": "0:07:20", "remaining_time": "0:00:32"}
+{"current_steps": 275, "total_steps": 290, "loss": 0.0617, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.293369364618465e-07, "epoch": 9.4, "percentage": 94.83, "elapsed_time": "0:07:28", "remaining_time": "0:00:24"}
+{"current_steps": 280, "total_steps": 290, "loss": 0.0779, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4655107114101007e-07, "epoch": 9.57, "percentage": 96.55, "elapsed_time": "0:07:36", "remaining_time": "0:00:16"}
+{"current_steps": 285, "total_steps": 290, "loss": 0.0803, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.666465372190453e-08, "epoch": 9.74, "percentage": 98.28, "elapsed_time": "0:07:44", "remaining_time": "0:00:08"}
+{"current_steps": 290, "total_steps": 290, "loss": 0.0796, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 0.0, "epoch": 9.91, "percentage": 100.0, "elapsed_time": "0:07:53", "remaining_time": "0:00:00"}
+{"current_steps": 290, "total_steps": 290, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 9.91, "percentage": 100.0, "elapsed_time": "0:07:53", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,378 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.914529914529915,
+  "eval_steps": 500,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.996333534627809e-05,
+      "loss": 0.4005,
+      "step": 5
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.985344892885899e-05,
+      "loss": 0.3409,
+      "step": 10
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.967066306353816e-05,
+      "loss": 0.3372,
+      "step": 15
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.941551389275217e-05,
+      "loss": 0.334,
+      "step": 20
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.908874981298057e-05,
+      "loss": 0.348,
+      "step": 25
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 4.869132927957007e-05,
+      "loss": 0.3413,
+      "step": 30
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.822441799541979e-05,
+      "loss": 0.2458,
+      "step": 35
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.768938549177393e-05,
+      "loss": 0.2715,
+      "step": 40
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.708780111115057e-05,
+      "loss": 0.2079,
+      "step": 45
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.642142940418973e-05,
+      "loss": 0.2698,
+      "step": 50
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.5692224953922266e-05,
+      "loss": 0.2543,
+      "step": 55
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.4902326642641095e-05,
+      "loss": 0.2492,
+      "step": 60
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 4.4054051378190915e-05,
+      "loss": 0.2308,
+      "step": 65
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 4.3149887298078276e-05,
+      "loss": 0.2018,
+      "step": 70
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.2192486471335585e-05,
+      "loss": 0.1668,
+      "step": 75
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.118465711954569e-05,
+      "loss": 0.2045,
+      "step": 80
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.012935537984414e-05,
+      "loss": 0.1961,
+      "step": 85
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.902967663405956e-05,
+      "loss": 0.1978,
+      "step": 90
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.7888846429425546e-05,
+      "loss": 0.1409,
+      "step": 95
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 3.671021101749476e-05,
+      "loss": 0.1534,
+      "step": 100
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 3.5497227539006614e-05,
+      "loss": 0.1634,
+      "step": 105
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 3.425345388349786e-05,
+      "loss": 0.1796,
+      "step": 110
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 3.29825382533995e-05,
+      "loss": 0.1492,
+      "step": 115
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 3.168820846323053e-05,
+      "loss": 0.1366,
+      "step": 120
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 3.0374261005275607e-05,
+      "loss": 0.1133,
+      "step": 125
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 2.9044549913819124e-05,
+      "loss": 0.1561,
+      "step": 130
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 2.7702975460598547e-05,
+      "loss": 0.1161,
+      "step": 135
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.635347271463544e-05,
+      "loss": 0.137,
+      "step": 140
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1271,
+      "step": 145
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 2.3646527285364565e-05,
+      "loss": 0.1031,
+      "step": 150
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 2.2297024539401463e-05,
+      "loss": 0.0881,
+      "step": 155
+    },
+    {
+      "epoch": 5.47,
+      "learning_rate": 2.0955450086180882e-05,
+      "loss": 0.094,
+      "step": 160
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 1.96257389947244e-05,
+      "loss": 0.1292,
+      "step": 165
+    },
+    {
+      "epoch": 5.81,
+      "learning_rate": 1.8311791536769483e-05,
+      "loss": 0.1146,
+      "step": 170
+    },
+    {
+      "epoch": 5.98,
+      "learning_rate": 1.7017461746600506e-05,
+      "loss": 0.0954,
+      "step": 175
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.574654611650214e-05,
+      "loss": 0.1114,
+      "step": 180
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 1.4502772460993385e-05,
+      "loss": 0.0744,
+      "step": 185
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 1.328978898250525e-05,
+      "loss": 0.0752,
+      "step": 190
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 1.2111153570574454e-05,
+      "loss": 0.0957,
+      "step": 195
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 1.0970323365940444e-05,
+      "loss": 0.0871,
+      "step": 200
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 9.870644620155877e-06,
+      "loss": 0.087,
+      "step": 205
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 8.815342880454311e-06,
+      "loss": 0.0768,
+      "step": 210
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 7.807513528664414e-06,
+      "loss": 0.0738,
+      "step": 215
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 6.8501127019217346e-06,
+      "loss": 0.0953,
+      "step": 220
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 5.945948621809091e-06,
+      "loss": 0.0948,
+      "step": 225
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 5.097673357358907e-06,
+      "loss": 0.075,
+      "step": 230
+    },
+    {
+      "epoch": 8.03,
+      "learning_rate": 4.307775046077739e-06,
+      "loss": 0.0638,
+      "step": 235
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 3.578570595810274e-06,
+      "loss": 0.0898,
+      "step": 240
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 2.9121988888494297e-06,
+      "loss": 0.0799,
+      "step": 245
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.310614508226078e-06,
+      "loss": 0.0688,
+      "step": 250
+    },
+    {
+      "epoch": 8.72,
+      "learning_rate": 1.7755820045802145e-06,
+      "loss": 0.0676,
+      "step": 255
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 1.3086707204299414e-06,
+      "loss": 0.0726,
+      "step": 260
+    },
+    {
+      "epoch": 9.06,
+      "learning_rate": 9.112501870194273e-07,
+      "loss": 0.072,
+      "step": 265
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 5.844861072478336e-07,
+      "loss": 0.0584,
+      "step": 270
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 3.293369364618465e-07,
+      "loss": 0.0617,
+      "step": 275
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 1.4655107114101007e-07,
+      "loss": 0.0779,
+      "step": 280
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 3.666465372190453e-08,
+      "loss": 0.0803,
+      "step": 285
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 0.0,
+      "loss": 0.0796,
+      "step": 290
+    },
+    {
+      "epoch": 9.91,
+      "step": 290,
+      "total_flos": 2.384077839944909e+16,
+      "train_loss": 0.15196624583211438,
+      "train_runtime": 473.0573,
+      "train_samples_per_second": 9.872,
+      "train_steps_per_second": 0.613
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 2.384077839944909e+16,
+  "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:cbc8919e4888a1db6caf59a21fb5e936b61c9762c9e78cae010fbd2769997c08
+size 4920