Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+checkpoint-168/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -13,7 +13,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
@@ -24,16 +24,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "k_proj",
-    "down_proj",
-    "gate_proj",
+    "up_proj",
     "v_proj",
-    "up_proj"
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bccc7610bc3a6f98b5aae771ac7d3885ec093f46cef34880a9031c62883484
+oid sha256:a2c0809d5b852ea96f8c3c06f5b76924725311629e340f1ce3ef1581a6a2a6c9
 size 239536272

checkpoint-168/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-168/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-168/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567834b6ff04d3668b5de2d5f85afd7df36526153d0b77d89b22781ea03e6a88
+size 239536272

checkpoint-168/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
+}

checkpoint-168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d669a68b7b73b7e7af163e762a736dcc746b5a8e45336d24f6bdbe374571fd
+size 479362682

checkpoint-168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd537426bbd82b662fafa86b7065c28ed7aa4a6031082eed641c102efca2d46
+size 14244

checkpoint-168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ff20a43f6fe71a587a0c5d696980ee52d134230b9b7a2052d8673c3e62418a
+size 1064

checkpoint-168/special_tokens_map.json

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

checkpoint-168/tokenizer.json

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

checkpoint-168/tokenizer_config.json

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

checkpoint-168/trainer_state.json

@@ -0,0 +1,392 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.96,
+  "eval_steps": 10,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 3.625234603881836,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 2.8449,
+      "step": 5
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 3.762423276901245,
+      "learning_rate": 5.882352941176471e-05,
+      "loss": 2.6354,
+      "step": 10
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 2.638275384902954,
+      "eval_runtime": 47.4661,
+      "eval_samples_per_second": 2.528,
+      "eval_steps_per_second": 2.528,
+      "step": 10
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.1764352321624756,
+      "learning_rate": 8.823529411764706e-05,
+      "loss": 2.5755,
+      "step": 15
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.8172953128814697,
+      "learning_rate": 0.0001,
+      "loss": 2.5841,
+      "step": 20
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 2.5013585090637207,
+      "eval_runtime": 47.4359,
+      "eval_samples_per_second": 2.53,
+      "eval_steps_per_second": 2.53,
+      "step": 20
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 2.0410871505737305,
+      "learning_rate": 0.0001,
+      "loss": 2.5047,
+      "step": 25
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.6944037675857544,
+      "learning_rate": 0.0001,
+      "loss": 2.5006,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 2.4310765266418457,
+      "eval_runtime": 47.4218,
+      "eval_samples_per_second": 2.53,
+      "eval_steps_per_second": 2.53,
+      "step": 30
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.77070152759552,
+      "learning_rate": 0.0001,
+      "loss": 2.4332,
+      "step": 35
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 2.0665605068206787,
+      "learning_rate": 0.0001,
+      "loss": 2.361,
+      "step": 40
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 2.3814117908477783,
+      "eval_runtime": 47.4326,
+      "eval_samples_per_second": 2.53,
+      "eval_steps_per_second": 2.53,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.072492837905884,
+      "learning_rate": 0.0001,
+      "loss": 2.4844,
+      "step": 45
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.724406361579895,
+      "learning_rate": 0.0001,
+      "loss": 2.375,
+      "step": 50
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 2.331134080886841,
+      "eval_runtime": 47.6074,
+      "eval_samples_per_second": 2.521,
+      "eval_steps_per_second": 2.521,
+      "step": 50
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.9400808811187744,
+      "learning_rate": 0.0001,
+      "loss": 2.3608,
+      "step": 55
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 1.699751615524292,
+      "learning_rate": 0.0001,
+      "loss": 2.0964,
+      "step": 60
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "eval_loss": 2.3239781856536865,
+      "eval_runtime": 47.5467,
+      "eval_samples_per_second": 2.524,
+      "eval_steps_per_second": 2.524,
+      "step": 60
+    },
+    {
+      "epoch": 1.1422222222222222,
+      "grad_norm": 1.8274644613265991,
+      "learning_rate": 0.0001,
+      "loss": 1.9732,
+      "step": 65
+    },
+    {
+      "epoch": 1.231111111111111,
+      "grad_norm": 1.808166265487671,
+      "learning_rate": 0.0001,
+      "loss": 1.882,
+      "step": 70
+    },
+    {
+      "epoch": 1.231111111111111,
+      "eval_loss": 2.3200292587280273,
+      "eval_runtime": 47.4934,
+      "eval_samples_per_second": 2.527,
+      "eval_steps_per_second": 2.527,
+      "step": 70
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 3.130427598953247,
+      "learning_rate": 0.0001,
+      "loss": 1.8712,
+      "step": 75
+    },
+    {
+      "epoch": 1.4088888888888889,
+      "grad_norm": 2.2472410202026367,
+      "learning_rate": 0.0001,
+      "loss": 1.9349,
+      "step": 80
+    },
+    {
+      "epoch": 1.4088888888888889,
+      "eval_loss": 2.310476064682007,
+      "eval_runtime": 47.4743,
+      "eval_samples_per_second": 2.528,
+      "eval_steps_per_second": 2.528,
+      "step": 80
+    },
+    {
+      "epoch": 1.4977777777777779,
+      "grad_norm": 2.6739182472229004,
+      "learning_rate": 0.0001,
+      "loss": 2.0233,
+      "step": 85
+    },
+    {
+      "epoch": 1.5866666666666667,
+      "grad_norm": 1.9445191621780396,
+      "learning_rate": 0.0001,
+      "loss": 1.8915,
+      "step": 90
+    },
+    {
+      "epoch": 1.5866666666666667,
+      "eval_loss": 2.315756320953369,
+      "eval_runtime": 47.428,
+      "eval_samples_per_second": 2.53,
+      "eval_steps_per_second": 2.53,
+      "step": 90
+    },
+    {
+      "epoch": 1.6755555555555555,
+      "grad_norm": 2.230072259902954,
+      "learning_rate": 0.0001,
+      "loss": 1.9569,
+      "step": 95
+    },
+    {
+      "epoch": 1.7644444444444445,
+      "grad_norm": 2.215071678161621,
+      "learning_rate": 0.0001,
+      "loss": 1.9129,
+      "step": 100
+    },
+    {
+      "epoch": 1.7644444444444445,
+      "eval_loss": 2.293951988220215,
+      "eval_runtime": 47.6216,
+      "eval_samples_per_second": 2.52,
+      "eval_steps_per_second": 2.52,
+      "step": 100
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 2.5269975662231445,
+      "learning_rate": 0.0001,
+      "loss": 1.9823,
+      "step": 105
+    },
+    {
+      "epoch": 1.942222222222222,
+      "grad_norm": 2.0200388431549072,
+      "learning_rate": 0.0001,
+      "loss": 1.9038,
+      "step": 110
+    },
+    {
+      "epoch": 1.942222222222222,
+      "eval_loss": 2.2803099155426025,
+      "eval_runtime": 47.5459,
+      "eval_samples_per_second": 2.524,
+      "eval_steps_per_second": 2.524,
+      "step": 110
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 2.0417139530181885,
+      "learning_rate": 0.0001,
+      "loss": 1.9497,
+      "step": 115
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 3.4772863388061523,
+      "learning_rate": 0.0001,
+      "loss": 1.4558,
+      "step": 120
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "eval_loss": 2.546415090560913,
+      "eval_runtime": 47.4915,
+      "eval_samples_per_second": 2.527,
+      "eval_steps_per_second": 2.527,
+      "step": 120
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 2.348198413848877,
+      "learning_rate": 0.0001,
+      "loss": 1.4142,
+      "step": 125
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 2.7231850624084473,
+      "learning_rate": 0.0001,
+      "loss": 1.4393,
+      "step": 130
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "eval_loss": 2.4443583488464355,
+      "eval_runtime": 47.4261,
+      "eval_samples_per_second": 2.53,
+      "eval_steps_per_second": 2.53,
+      "step": 130
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 2.138868570327759,
+      "learning_rate": 0.0001,
+      "loss": 1.339,
+      "step": 135
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 2.7573513984680176,
+      "learning_rate": 0.0001,
+      "loss": 1.3999,
+      "step": 140
+    },
+    {
+      "epoch": 2.462222222222222,
+      "eval_loss": 2.4613397121429443,
+      "eval_runtime": 47.469,
+      "eval_samples_per_second": 2.528,
+      "eval_steps_per_second": 2.528,
+      "step": 140
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 2.5279624462127686,
+      "learning_rate": 0.0001,
+      "loss": 1.4729,
+      "step": 145
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 2.1908698081970215,
+      "learning_rate": 0.0001,
+      "loss": 1.3184,
+      "step": 150
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 2.461369752883911,
+      "eval_runtime": 47.4904,
+      "eval_samples_per_second": 2.527,
+      "eval_steps_per_second": 2.527,
+      "step": 150
+    },
+    {
+      "epoch": 2.728888888888889,
+      "grad_norm": 2.8457717895507812,
+      "learning_rate": 0.0001,
+      "loss": 1.4493,
+      "step": 155
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "grad_norm": 3.0878119468688965,
+      "learning_rate": 0.0001,
+      "loss": 1.4338,
+      "step": 160
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "eval_loss": 2.4270567893981934,
+      "eval_runtime": 47.5396,
+      "eval_samples_per_second": 2.524,
+      "eval_steps_per_second": 2.524,
+      "step": 160
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 2.3448030948638916,
+      "learning_rate": 0.0001,
+      "loss": 1.4075,
+      "step": 165
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 5.954718791663616e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ec3155257429ae0258c0a4c8331139da05236f834279a5e40e8c259fdbc1fc
+size 5496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329ead066dd17f4d28f788a172d99240b980c1ca974727deefe82ffb7a785c5f
+oid sha256:9eed6014de193813e3552880dd631ce163d9b40a535d999e4e7cc55644e96e8f
 size 5496