Upload 14 files

.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 +1,202 @@
----
-license: apache-2.0
----
+---
+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 0.12.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "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": [
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_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:ef9be5b29b0e8bc173e8bfe434c3e4ac96e4ae96f4886863ffb6994b4407c98f
+size 59933632

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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afad067d396940a30fd1df1b6ef6597a344085b3cec71d221ac26dc4b8cea2b
+size 120158586

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd8154c634ebe949023adca2f683dca54b2554f2aa5d8c22dcdcf3164f0829e
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,469 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8034817542684968,
+  "eval_steps": 300,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013391362571141614,
+      "grad_norm": 2.4009346961975098,
+      "learning_rate": 2.2321428571428573e-06,
+      "loss": 1.3329,
+      "step": 10
+    },
+    {
+      "epoch": 0.026782725142283227,
+      "grad_norm": 2.416130781173706,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 1.2931,
+      "step": 20
+    },
+    {
+      "epoch": 0.040174087713424844,
+      "grad_norm": 2.9514546394348145,
+      "learning_rate": 6.696428571428572e-06,
+      "loss": 1.2808,
+      "step": 30
+    },
+    {
+      "epoch": 0.053565450284566454,
+      "grad_norm": 1.845926284790039,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 1.2348,
+      "step": 40
+    },
+    {
+      "epoch": 0.06695681285570806,
+      "grad_norm": 0.8614177107810974,
+      "learning_rate": 1.1160714285714287e-05,
+      "loss": 1.1273,
+      "step": 50
+    },
+    {
+      "epoch": 0.08034817542684969,
+      "grad_norm": 0.729676365852356,
+      "learning_rate": 1.3392857142857144e-05,
+      "loss": 0.9001,
+      "step": 60
+    },
+    {
+      "epoch": 0.0937395379979913,
+      "grad_norm": 0.6786935329437256,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.7691,
+      "step": 70
+    },
+    {
+      "epoch": 0.10713090056913291,
+      "grad_norm": 0.6628158092498779,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.6629,
+      "step": 80
+    },
+    {
+      "epoch": 0.12052226314027452,
+      "grad_norm": 0.39596471190452576,
+      "learning_rate": 2.0089285714285717e-05,
+      "loss": 0.6795,
+      "step": 90
+    },
+    {
+      "epoch": 0.13391362571141613,
+      "grad_norm": 0.45973294973373413,
+      "learning_rate": 2.2321428571428575e-05,
+      "loss": 0.6835,
+      "step": 100
+    },
+    {
+      "epoch": 0.14730498828255775,
+      "grad_norm": 0.43911251425743103,
+      "learning_rate": 2.455357142857143e-05,
+      "loss": 0.6344,
+      "step": 110
+    },
+    {
+      "epoch": 0.16069635085369938,
+      "grad_norm": 0.5540445446968079,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.5985,
+      "step": 120
+    },
+    {
+      "epoch": 0.17408771342484097,
+      "grad_norm": 0.5015535354614258,
+      "learning_rate": 2.9017857142857146e-05,
+      "loss": 0.5375,
+      "step": 130
+    },
+    {
+      "epoch": 0.1874790759959826,
+      "grad_norm": 0.6995676755905151,
+      "learning_rate": 3.125e-05,
+      "loss": 0.5493,
+      "step": 140
+    },
+    {
+      "epoch": 0.2008704385671242,
+      "grad_norm": 0.5413327813148499,
+      "learning_rate": 3.348214285714286e-05,
+      "loss": 0.5474,
+      "step": 150
+    },
+    {
+      "epoch": 0.21426180113826582,
+      "grad_norm": 0.5784323811531067,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.5712,
+      "step": 160
+    },
+    {
+      "epoch": 0.22765316370940744,
+      "grad_norm": 0.9611849188804626,
+      "learning_rate": 3.794642857142857e-05,
+      "loss": 0.5432,
+      "step": 170
+    },
+    {
+      "epoch": 0.24104452628054904,
+      "grad_norm": 0.5728833079338074,
+      "learning_rate": 4.017857142857143e-05,
+      "loss": 0.4972,
+      "step": 180
+    },
+    {
+      "epoch": 0.25443588885169066,
+      "grad_norm": 0.6023485660552979,
+      "learning_rate": 4.2410714285714285e-05,
+      "loss": 0.4769,
+      "step": 190
+    },
+    {
+      "epoch": 0.26782725142283226,
+      "grad_norm": 0.607907235622406,
+      "learning_rate": 4.464285714285715e-05,
+      "loss": 0.5039,
+      "step": 200
+    },
+    {
+      "epoch": 0.2812186139939739,
+      "grad_norm": 0.6248412728309631,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.4767,
+      "step": 210
+    },
+    {
+      "epoch": 0.2946099765651155,
+      "grad_norm": 0.6133660078048706,
+      "learning_rate": 4.910714285714286e-05,
+      "loss": 0.5234,
+      "step": 220
+    },
+    {
+      "epoch": 0.3080013391362571,
+      "grad_norm": 0.6181973218917847,
+      "learning_rate": 4.9998905060416096e-05,
+      "loss": 0.4192,
+      "step": 230
+    },
+    {
+      "epoch": 0.32139270170739875,
+      "grad_norm": 0.6632351875305176,
+      "learning_rate": 4.999221411028925e-05,
+      "loss": 0.4418,
+      "step": 240
+    },
+    {
+      "epoch": 0.33478406427854035,
+      "grad_norm": 0.8785191774368286,
+      "learning_rate": 4.997944213585113e-05,
+      "loss": 0.4684,
+      "step": 250
+    },
+    {
+      "epoch": 0.34817542684968195,
+      "grad_norm": 0.6774404644966125,
+      "learning_rate": 4.996059224473704e-05,
+      "loss": 0.4394,
+      "step": 260
+    },
+    {
+      "epoch": 0.36156678942082354,
+      "grad_norm": 0.792456328868866,
+      "learning_rate": 4.9935669023441236e-05,
+      "loss": 0.421,
+      "step": 270
+    },
+    {
+      "epoch": 0.3749581519919652,
+      "grad_norm": 0.9153772592544556,
+      "learning_rate": 4.99046785362009e-05,
+      "loss": 0.4788,
+      "step": 280
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.5768759250640869,
+      "learning_rate": 4.986762832352069e-05,
+      "loss": 0.4175,
+      "step": 290
+    },
+    {
+      "epoch": 0.4017408771342484,
+      "grad_norm": 0.736320972442627,
+      "learning_rate": 4.982452740033793e-05,
+      "loss": 0.4136,
+      "step": 300
+    },
+    {
+      "epoch": 0.4017408771342484,
+      "eval_loss": 0.4803064167499542,
+      "eval_runtime": 38.84,
+      "eval_samples_per_second": 17.096,
+      "eval_steps_per_second": 17.096,
+      "step": 300
+    },
+    {
+      "epoch": 0.41513223970539004,
+      "grad_norm": 0.9251226186752319,
+      "learning_rate": 4.977538625382916e-05,
+      "loss": 0.4248,
+      "step": 310
+    },
+    {
+      "epoch": 0.42852360227653163,
+      "grad_norm": 0.9105271100997925,
+      "learning_rate": 4.972021684085846e-05,
+      "loss": 0.4959,
+      "step": 320
+    },
+    {
+      "epoch": 0.44191496484767323,
+      "grad_norm": 0.525224506855011,
+      "learning_rate": 4.965903258506806e-05,
+      "loss": 0.4622,
+      "step": 330
+    },
+    {
+      "epoch": 0.4553063274188149,
+      "grad_norm": 0.7840506434440613,
+      "learning_rate": 4.9591848373612247e-05,
+      "loss": 0.32,
+      "step": 340
+    },
+    {
+      "epoch": 0.4686976899899565,
+      "grad_norm": 0.7537767887115479,
+      "learning_rate": 4.9518680553535004e-05,
+      "loss": 0.3984,
+      "step": 350
+    },
+    {
+      "epoch": 0.4820890525610981,
+      "grad_norm": 0.8291546702384949,
+      "learning_rate": 4.94395469277925e-05,
+      "loss": 0.4221,
+      "step": 360
+    },
+    {
+      "epoch": 0.4954804151322397,
+      "grad_norm": 0.7584542632102966,
+      "learning_rate": 4.935446675092137e-05,
+      "loss": 0.4015,
+      "step": 370
+    },
+    {
+      "epoch": 0.5088717777033813,
+      "grad_norm": 0.9720783233642578,
+      "learning_rate": 4.926346072435373e-05,
+      "loss": 0.4589,
+      "step": 380
+    },
+    {
+      "epoch": 0.5222631402745229,
+      "grad_norm": 1.1246592998504639,
+      "learning_rate": 4.916655099138019e-05,
+      "loss": 0.4344,
+      "step": 390
+    },
+    {
+      "epoch": 0.5356545028456645,
+      "grad_norm": 0.6652913093566895,
+      "learning_rate": 4.906376113176202e-05,
+      "loss": 0.4007,
+      "step": 400
+    },
+    {
+      "epoch": 0.5490458654168061,
+      "grad_norm": 0.8961889743804932,
+      "learning_rate": 4.895511615599379e-05,
+      "loss": 0.3503,
+      "step": 410
+    },
+    {
+      "epoch": 0.5624372279879478,
+      "grad_norm": 0.8319832682609558,
+      "learning_rate": 4.884064249921789e-05,
+      "loss": 0.3853,
+      "step": 420
+    },
+    {
+      "epoch": 0.5758285905590894,
+      "grad_norm": 0.5967663526535034,
+      "learning_rate": 4.872036801479246e-05,
+      "loss": 0.3836,
+      "step": 430
+    },
+    {
+      "epoch": 0.589219953130231,
+      "grad_norm": 0.7453261613845825,
+      "learning_rate": 4.859432196751414e-05,
+      "loss": 0.399,
+      "step": 440
+    },
+    {
+      "epoch": 0.6026113157013726,
+      "grad_norm": 0.8149186372756958,
+      "learning_rate": 4.8462535026497496e-05,
+      "loss": 0.3674,
+      "step": 450
+    },
+    {
+      "epoch": 0.6160026782725142,
+      "grad_norm": 0.6484460234642029,
+      "learning_rate": 4.8325039257712704e-05,
+      "loss": 0.3836,
+      "step": 460
+    },
+    {
+      "epoch": 0.6293940408436558,
+      "grad_norm": 0.689203679561615,
+      "learning_rate": 4.818186811618336e-05,
+      "loss": 0.3912,
+      "step": 470
+    },
+    {
+      "epoch": 0.6427854034147975,
+      "grad_norm": 0.7593767642974854,
+      "learning_rate": 4.8033056437846305e-05,
+      "loss": 0.3931,
+      "step": 480
+    },
+    {
+      "epoch": 0.6561767659859391,
+      "grad_norm": 1.0037031173706055,
+      "learning_rate": 4.787864043107546e-05,
+      "loss": 0.4235,
+      "step": 490
+    },
+    {
+      "epoch": 0.6695681285570807,
+      "grad_norm": 0.7254366874694824,
+      "learning_rate": 4.771865766787175e-05,
+      "loss": 0.397,
+      "step": 500
+    },
+    {
+      "epoch": 0.6829594911282223,
+      "grad_norm": 0.909480631351471,
+      "learning_rate": 4.755314707472114e-05,
+      "loss": 0.4276,
+      "step": 510
+    },
+    {
+      "epoch": 0.6963508536993639,
+      "grad_norm": 0.6278852820396423,
+      "learning_rate": 4.738214892312325e-05,
+      "loss": 0.3438,
+      "step": 520
+    },
+    {
+      "epoch": 0.7097422162705055,
+      "grad_norm": 0.7583978176116943,
+      "learning_rate": 4.7205704819792576e-05,
+      "loss": 0.4145,
+      "step": 530
+    },
+    {
+      "epoch": 0.7231335788416471,
+      "grad_norm": 1.1025863885879517,
+      "learning_rate": 4.702385769653488e-05,
+      "loss": 0.3728,
+      "step": 540
+    },
+    {
+      "epoch": 0.7365249414127888,
+      "grad_norm": 1.1275866031646729,
+      "learning_rate": 4.683665179980119e-05,
+      "loss": 0.3926,
+      "step": 550
+    },
+    {
+      "epoch": 0.7499163039839304,
+      "grad_norm": 0.9416183233261108,
+      "learning_rate": 4.664413267992187e-05,
+      "loss": 0.3751,
+      "step": 560
+    },
+    {
+      "epoch": 0.763307666555072,
+      "grad_norm": 1.1021020412445068,
+      "learning_rate": 4.644634718002346e-05,
+      "loss": 0.3818,
+      "step": 570
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 1.04265296459198,
+      "learning_rate": 4.624334342463099e-05,
+      "loss": 0.3823,
+      "step": 580
+    },
+    {
+      "epoch": 0.7900903916973552,
+      "grad_norm": 0.622381865978241,
+      "learning_rate": 4.603517080795844e-05,
+      "loss": 0.3784,
+      "step": 590
+    },
+    {
+      "epoch": 0.8034817542684968,
+      "grad_norm": 1.0999802350997925,
+      "learning_rate": 4.582187998189034e-05,
+      "loss": 0.3555,
+      "step": 600
+    },
+    {
+      "epoch": 0.8034817542684968,
+      "eval_loss": 0.4139007329940796,
+      "eval_runtime": 38.554,
+      "eval_samples_per_second": 17.223,
+      "eval_steps_per_second": 17.223,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2238,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.717600085324595e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6f1dfc6ee08bb086898240a2b9dd4b5953fc50a34910b487614197334f4f1c
+size 5496