Init commit

.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

@@ -1,3 +1,60 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2.5-7B-q4-abstrct-normalized-text
+  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. -->
+
+# qwen2.5-7B-q4-abstrct-normalized-text
+
+This model is a fine-tuned version of [unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit) on the abstrct 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: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_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 sha256:3d3d88897f14aca48b1c6ac7495f67953d60bd069211680d0f6a0d0cf8249abe
+size 80792096

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 +1,8 @@
+{
+    "epoch": 4.982857142857143,
+    "total_flos": 8.918620683072307e+16,
+    "train_loss": 0.008782218914305749,
+    "train_runtime": 2136.729,
+    "train_samples_per_second": 0.819,
+    "train_steps_per_second": 0.101
+}

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": "<|vision_pad|>",
+    "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 +1,209 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.982857142857143,
+    "total_flos": 8.918620683072307e+16,
+    "train_loss": 0.008782218914305749,
+    "train_runtime": 2136.729,
+    "train_samples_per_second": 0.819,
+    "train_steps_per_second": 0.101
+}

trainer_log.jsonl

@@ -0,0 +1,26 @@
+{"current_steps": 10, "total_steps": 215, "loss": 0.0615, "lr": 2.272727272727273e-05, "epoch": 0.22857142857142856, "percentage": 4.65, "elapsed_time": "0:01:33", "remaining_time": "0:31:53"}
+{"current_steps": 20, "total_steps": 215, "loss": 0.0209, "lr": 4.545454545454546e-05, "epoch": 0.45714285714285713, "percentage": 9.3, "elapsed_time": "0:03:12", "remaining_time": "0:31:18"}
+{"current_steps": 10, "total_steps": 215, "loss": 0.0615, "lr": 2.272727272727273e-05, "epoch": 0.22857142857142856, "percentage": 4.65, "elapsed_time": "0:01:33", "remaining_time": "0:32:00"}
+{"current_steps": 20, "total_steps": 215, "loss": 0.0209, "lr": 4.545454545454546e-05, "epoch": 0.45714285714285713, "percentage": 9.3, "elapsed_time": "0:03:13", "remaining_time": "0:31:27"}
+{"current_steps": 10, "total_steps": 215, "loss": 0.0615, "lr": 2.272727272727273e-05, "epoch": 0.22857142857142856, "percentage": 4.65, "elapsed_time": "0:01:33", "remaining_time": "0:31:55"}
+{"current_steps": 20, "total_steps": 215, "loss": 0.0209, "lr": 4.545454545454546e-05, "epoch": 0.45714285714285713, "percentage": 9.3, "elapsed_time": "0:03:13", "remaining_time": "0:31:23"}
+{"current_steps": 30, "total_steps": 215, "loss": 0.0134, "lr": 4.9788329024834144e-05, "epoch": 0.6857142857142857, "percentage": 13.95, "elapsed_time": "0:04:52", "remaining_time": "0:30:02"}
+{"current_steps": 40, "total_steps": 215, "loss": 0.0108, "lr": 4.893455513052003e-05, "epoch": 0.9142857142857143, "percentage": 18.6, "elapsed_time": "0:06:36", "remaining_time": "0:28:55"}
+{"current_steps": 50, "total_steps": 215, "loss": 0.0089, "lr": 4.7448003278586086e-05, "epoch": 1.16, "percentage": 23.26, "elapsed_time": "0:08:21", "remaining_time": "0:27:36"}
+{"current_steps": 60, "total_steps": 215, "loss": 0.0084, "lr": 4.536797469020116e-05, "epoch": 1.3885714285714286, "percentage": 27.91, "elapsed_time": "0:09:59", "remaining_time": "0:25:47"}
+{"current_steps": 70, "total_steps": 215, "loss": 0.008, "lr": 4.274946082999753e-05, "epoch": 1.617142857142857, "percentage": 32.56, "elapsed_time": "0:11:35", "remaining_time": "0:24:00"}
+{"current_steps": 80, "total_steps": 215, "loss": 0.0082, "lr": 3.9661689550484805e-05, "epoch": 1.8457142857142856, "percentage": 37.21, "elapsed_time": "0:13:11", "remaining_time": "0:22:15"}
+{"current_steps": 90, "total_steps": 215, "loss": 0.0077, "lr": 3.6186294857107936e-05, "epoch": 2.0914285714285716, "percentage": 41.86, "elapsed_time": "0:14:58", "remaining_time": "0:20:47"}
+{"current_steps": 100, "total_steps": 215, "loss": 0.0046, "lr": 3.241515868140921e-05, "epoch": 2.32, "percentage": 46.51, "elapsed_time": "0:16:39", "remaining_time": "0:19:09"}
+{"current_steps": 110, "total_steps": 215, "loss": 0.0058, "lr": 2.844798172115185e-05, "epoch": 2.5485714285714285, "percentage": 51.16, "elapsed_time": "0:18:18", "remaining_time": "0:17:28"}
+{"current_steps": 120, "total_steps": 215, "loss": 0.0049, "lr": 2.438964756914712e-05, "epoch": 2.777142857142857, "percentage": 55.81, "elapsed_time": "0:19:53", "remaining_time": "0:15:45"}
+{"current_steps": 130, "total_steps": 215, "loss": 0.0057, "lr": 2.034744981752741e-05, "epoch": 3.0228571428571427, "percentage": 60.47, "elapsed_time": "0:21:35", "remaining_time": "0:14:07"}
+{"current_steps": 140, "total_steps": 215, "loss": 0.0031, "lr": 1.642825544684101e-05, "epoch": 3.2514285714285713, "percentage": 65.12, "elapsed_time": "0:23:09", "remaining_time": "0:12:24"}
+{"current_steps": 150, "total_steps": 215, "loss": 0.0028, "lr": 1.2735679493836009e-05, "epoch": 3.48, "percentage": 69.77, "elapsed_time": "0:24:49", "remaining_time": "0:10:45"}
+{"current_steps": 160, "total_steps": 215, "loss": 0.0033, "lr": 9.367345693616624e-06, "epoch": 3.7085714285714286, "percentage": 74.42, "elapsed_time": "0:26:28", "remaining_time": "0:09:06"}
+{"current_steps": 170, "total_steps": 215, "loss": 0.0028, "lr": 6.412305518878342e-06, "epoch": 3.9371428571428573, "percentage": 79.07, "elapsed_time": "0:28:07", "remaining_time": "0:07:26"}
+{"current_steps": 180, "total_steps": 215, "loss": 0.0025, "lr": 3.948683851251878e-06, "epoch": 4.182857142857143, "percentage": 83.72, "elapsed_time": "0:29:54", "remaining_time": "0:05:48"}
+{"current_steps": 190, "total_steps": 215, "loss": 0.0018, "lr": 2.041613528121822e-06, "epoch": 4.411428571428571, "percentage": 88.37, "elapsed_time": "0:31:37", "remaining_time": "0:04:09"}
+{"current_steps": 200, "total_steps": 215, "loss": 0.0014, "lr": 7.415133710424793e-07, "epoch": 4.64, "percentage": 93.02, "elapsed_time": "0:33:09", "remaining_time": "0:02:29"}
+{"current_steps": 210, "total_steps": 215, "loss": 0.0016, "lr": 8.275522096146405e-08, "epoch": 4.868571428571428, "percentage": 97.67, "elapsed_time": "0:34:46", "remaining_time": "0:00:49"}
+{"current_steps": 215, "total_steps": 215, "epoch": 4.982857142857143, "percentage": 100.0, "elapsed_time": "0:35:35", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.982857142857143,
+  "eval_steps": 500,
+  "global_step": 215,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.06870704144239426,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 0.0615,
+      "step": 10
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.07055369019508362,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.0209,
+      "step": 20
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.036877382546663284,
+      "learning_rate": 4.9788329024834144e-05,
+      "loss": 0.0134,
+      "step": 30
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.041551634669303894,
+      "learning_rate": 4.893455513052003e-05,
+      "loss": 0.0108,
+      "step": 40
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.030595853924751282,
+      "learning_rate": 4.7448003278586086e-05,
+      "loss": 0.0089,
+      "step": 50
+    },
+    {
+      "epoch": 1.3885714285714286,
+      "grad_norm": 0.029393771663308144,
+      "learning_rate": 4.536797469020116e-05,
+      "loss": 0.0084,
+      "step": 60
+    },
+    {
+      "epoch": 1.617142857142857,
+      "grad_norm": 0.07787137478590012,
+      "learning_rate": 4.274946082999753e-05,
+      "loss": 0.008,
+      "step": 70
+    },
+    {
+      "epoch": 1.8457142857142856,
+      "grad_norm": 0.041888438165187836,
+      "learning_rate": 3.9661689550484805e-05,
+      "loss": 0.0082,
+      "step": 80
+    },
+    {
+      "epoch": 2.0914285714285716,
+      "grad_norm": 0.03249946981668472,
+      "learning_rate": 3.6186294857107936e-05,
+      "loss": 0.0077,
+      "step": 90
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.0420403890311718,
+      "learning_rate": 3.241515868140921e-05,
+      "loss": 0.0046,
+      "step": 100
+    },
+    {
+      "epoch": 2.5485714285714285,
+      "grad_norm": 0.0769946500658989,
+      "learning_rate": 2.844798172115185e-05,
+      "loss": 0.0058,
+      "step": 110
+    },
+    {
+      "epoch": 2.777142857142857,
+      "grad_norm": 0.02508358843624592,
+      "learning_rate": 2.438964756914712e-05,
+      "loss": 0.0049,
+      "step": 120
+    },
+    {
+      "epoch": 3.0228571428571427,
+      "grad_norm": 0.06438242644071579,
+      "learning_rate": 2.034744981752741e-05,
+      "loss": 0.0057,
+      "step": 130
+    },
+    {
+      "epoch": 3.2514285714285713,
+      "grad_norm": 0.02097385935485363,
+      "learning_rate": 1.642825544684101e-05,
+      "loss": 0.0031,
+      "step": 140
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.02690581977367401,
+      "learning_rate": 1.2735679493836009e-05,
+      "loss": 0.0028,
+      "step": 150
+    },
+    {
+      "epoch": 3.7085714285714286,
+      "grad_norm": 0.021756254136562347,
+      "learning_rate": 9.367345693616624e-06,
+      "loss": 0.0033,
+      "step": 160
+    },
+    {
+      "epoch": 3.9371428571428573,
+      "grad_norm": 0.0332612618803978,
+      "learning_rate": 6.412305518878342e-06,
+      "loss": 0.0028,
+      "step": 170
+    },
+    {
+      "epoch": 4.182857142857143,
+      "grad_norm": 0.03361232951283455,
+      "learning_rate": 3.948683851251878e-06,
+      "loss": 0.0025,
+      "step": 180
+    },
+    {
+      "epoch": 4.411428571428571,
+      "grad_norm": 0.025048233568668365,
+      "learning_rate": 2.041613528121822e-06,
+      "loss": 0.0018,
+      "step": 190
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.04568938910961151,
+      "learning_rate": 7.415133710424793e-07,
+      "loss": 0.0014,
+      "step": 200
+    },
+    {
+      "epoch": 4.868571428571428,
+      "grad_norm": 0.04061714932322502,
+      "learning_rate": 8.275522096146405e-08,
+      "loss": 0.0016,
+      "step": 210
+    },
+    {
+      "epoch": 4.982857142857143,
+      "step": 215,
+      "total_flos": 8.918620683072307e+16,
+      "train_loss": 0.008782218914305749,
+      "train_runtime": 2136.729,
+      "train_samples_per_second": 0.819,
+      "train_steps_per_second": 0.101
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 215,
+  "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": 8.918620683072307e+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 sha256:938f00fb987e1b6a219cb5fa2f901a0dba83fae45c2bae8e5755271b77243ad4
+size 5752