Upload folder using huggingface_hub

.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: mit
----
+---
+base_model: Qwen/Qwen2.5-7B-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 0.13.3.dev0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "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": 32,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_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 sha256:78b8a04cb5dafb97963b561e4acc6fc3560c972431061f7dd611e7012908fac4
+size 2503003904

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:d7a9cff383f91905b29cfb59c7d2d4494537d514f0d62f1be8bc5af88268c4be
+size 5006244836

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:712be9f571382d532b6ff725a512d1f8a8623dc6abf13e342076de43748d2168
+size 15408

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9414bfcad3e169778677d596b072b4d2ff3197cab4f5a35854346b01f77475ce
+size 15408

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155ca390850f13d6898525b5209cde3cb0d7e5317f1262323788ee89936ce567
+size 15408

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c553ab1cf765c3539b7a39e4a9f05a9f072e120a92f86fa592438b187532e3
+size 15408

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f32656ab17a1b7ff962506aa2d7ce8cfb4edeae919e6b5a2cab274e48f1bcf9
+size 15408

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590b45062af4f692268d7347b5419d6f48c728adc86d41fea1417e2fc275caad
+size 15408

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17d65356bb98532788aaecb209c13649135b8f86f410118fa8605676af0eecb
+size 1064

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": "<|im_start|>",
+  "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:eccfe8446b814d6120eec3f96528c1faf44f51410f2524c11cac30fda10c9ee9
+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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<|im_start|>",
+  "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
+}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.5309734513274336,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11799410029498525,
+      "grad_norm": 2.4879140853881836,
+      "learning_rate": 0.0003,
+      "loss": 1.8567,
+      "step": 10
+    },
+    {
+      "epoch": 0.2359882005899705,
+      "grad_norm": 0.8311281204223633,
+      "learning_rate": 0.0002963855421686747,
+      "loss": 1.3245,
+      "step": 20
+    },
+    {
+      "epoch": 0.35398230088495575,
+      "grad_norm": 0.6665307879447937,
+      "learning_rate": 0.0002927710843373494,
+      "loss": 1.1834,
+      "step": 30
+    },
+    {
+      "epoch": 0.471976401179941,
+      "grad_norm": 0.5632417798042297,
+      "learning_rate": 0.0002891566265060241,
+      "loss": 1.0915,
+      "step": 40
+    },
+    {
+      "epoch": 0.5899705014749262,
+      "grad_norm": 0.4381982684135437,
+      "learning_rate": 0.00028554216867469873,
+      "loss": 1.0438,
+      "step": 50
+    },
+    {
+      "epoch": 0.5899705014749262,
+      "eval_loss": 1.0292344093322754,
+      "eval_runtime": 20.4608,
+      "eval_samples_per_second": 8.015,
+      "eval_steps_per_second": 0.684,
+      "step": 50
+    },
+    {
+      "epoch": 0.7079646017699115,
+      "grad_norm": 0.43256932497024536,
+      "learning_rate": 0.0002819277108433735,
+      "loss": 1.0156,
+      "step": 60
+    },
+    {
+      "epoch": 0.8259587020648967,
+      "grad_norm": 0.3582414388656616,
+      "learning_rate": 0.0002783132530120482,
+      "loss": 0.9793,
+      "step": 70
+    },
+    {
+      "epoch": 0.943952802359882,
+      "grad_norm": 0.3671708405017853,
+      "learning_rate": 0.00027469879518072284,
+      "loss": 0.9644,
+      "step": 80
+    },
+    {
+      "epoch": 1.0589970501474926,
+      "grad_norm": 0.34048739075660706,
+      "learning_rate": 0.0002710843373493976,
+      "loss": 0.9173,
+      "step": 90
+    },
+    {
+      "epoch": 1.176991150442478,
+      "grad_norm": 0.29820743203163147,
+      "learning_rate": 0.00026746987951807225,
+      "loss": 0.8913,
+      "step": 100
+    },
+    {
+      "epoch": 1.176991150442478,
+      "eval_loss": 0.9288875460624695,
+      "eval_runtime": 20.3929,
+      "eval_samples_per_second": 8.042,
+      "eval_steps_per_second": 0.687,
+      "step": 100
+    },
+    {
+      "epoch": 1.294985250737463,
+      "grad_norm": 0.31813672184944153,
+      "learning_rate": 0.00026385542168674695,
+      "loss": 0.8801,
+      "step": 110
+    },
+    {
+      "epoch": 1.4129793510324484,
+      "grad_norm": 0.2814970016479492,
+      "learning_rate": 0.00026024096385542165,
+      "loss": 0.875,
+      "step": 120
+    },
+    {
+      "epoch": 1.5309734513274336,
+      "grad_norm": 0.2815490663051605,
+      "learning_rate": 0.00025662650602409636,
+      "loss": 0.8642,
+      "step": 130
+    },
+    {
+      "epoch": 1.648967551622419,
+      "grad_norm": 0.2590789198875427,
+      "learning_rate": 0.00025301204819277106,
+      "loss": 0.8501,
+      "step": 140
+    },
+    {
+      "epoch": 1.7669616519174043,
+      "grad_norm": 0.25773778557777405,
+      "learning_rate": 0.00024939759036144576,
+      "loss": 0.8487,
+      "step": 150
+    },
+    {
+      "epoch": 1.7669616519174043,
+      "eval_loss": 0.8774459362030029,
+      "eval_runtime": 20.4395,
+      "eval_samples_per_second": 8.024,
+      "eval_steps_per_second": 0.685,
+      "step": 150
+    },
+    {
+      "epoch": 1.8849557522123894,
+      "grad_norm": 0.2629424035549164,
+      "learning_rate": 0.00024578313253012046,
+      "loss": 0.8427,
+      "step": 160
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2865707278251648,
+      "learning_rate": 0.00024216867469879517,
+      "loss": 0.8258,
+      "step": 170
+    },
+    {
+      "epoch": 2.117994100294985,
+      "grad_norm": 0.27073633670806885,
+      "learning_rate": 0.00023855421686746987,
+      "loss": 0.7835,
+      "step": 180
+    },
+    {
+      "epoch": 2.2359882005899703,
+      "grad_norm": 0.2692751884460449,
+      "learning_rate": 0.00023493975903614455,
+      "loss": 0.7804,
+      "step": 190
+    },
+    {
+      "epoch": 2.353982300884956,
+      "grad_norm": 0.2548248767852783,
+      "learning_rate": 0.00023132530120481928,
+      "loss": 0.7756,
+      "step": 200
+    },
+    {
+      "epoch": 2.353982300884956,
+      "eval_loss": 0.8462932109832764,
+      "eval_runtime": 20.4134,
+      "eval_samples_per_second": 8.034,
+      "eval_steps_per_second": 0.686,
+      "step": 200
+    },
+    {
+      "epoch": 2.471976401179941,
+      "grad_norm": 0.21938325464725494,
+      "learning_rate": 0.00022771084337349395,
+      "loss": 0.7695,
+      "step": 210
+    },
+    {
+      "epoch": 2.589970501474926,
+      "grad_norm": 0.23754891753196716,
+      "learning_rate": 0.00022409638554216866,
+      "loss": 0.7771,
+      "step": 220
+    },
+    {
+      "epoch": 2.7079646017699117,
+      "grad_norm": 0.2382248044013977,
+      "learning_rate": 0.00022048192771084336,
+      "loss": 0.7672,
+      "step": 230
+    },
+    {
+      "epoch": 2.825958702064897,
+      "grad_norm": 0.2536454200744629,
+      "learning_rate": 0.00021686746987951806,
+      "loss": 0.7645,
+      "step": 240
+    },
+    {
+      "epoch": 2.943952802359882,
+      "grad_norm": 0.21255475282669067,
+      "learning_rate": 0.00021325301204819274,
+      "loss": 0.7667,
+      "step": 250
+    },
+    {
+      "epoch": 2.943952802359882,
+      "eval_loss": 0.8220995664596558,
+      "eval_runtime": 20.3922,
+      "eval_samples_per_second": 8.042,
+      "eval_steps_per_second": 0.687,
+      "step": 250
+    },
+    {
+      "epoch": 3.0589970501474926,
+      "grad_norm": 0.2579372227191925,
+      "learning_rate": 0.00020963855421686747,
+      "loss": 0.7418,
+      "step": 260
+    },
+    {
+      "epoch": 3.1769911504424777,
+      "grad_norm": 0.2223750501871109,
+      "learning_rate": 0.00020602409638554214,
+      "loss": 0.7198,
+      "step": 270
+    },
+    {
+      "epoch": 3.2949852507374633,
+      "grad_norm": 0.26154494285583496,
+      "learning_rate": 0.00020240963855421685,
+      "loss": 0.7188,
+      "step": 280
+    },
+    {
+      "epoch": 3.4129793510324484,
+      "grad_norm": 0.2428540140390396,
+      "learning_rate": 0.00019879518072289155,
+      "loss": 0.7158,
+      "step": 290
+    },
+    {
+      "epoch": 3.5309734513274336,
+      "grad_norm": 0.2056645303964615,
+      "learning_rate": 0.00019518072289156625,
+      "loss": 0.7103,
+      "step": 300
+    },
+    {
+      "epoch": 3.5309734513274336,
+      "eval_loss": 0.8080394864082336,
+      "eval_runtime": 20.4084,
+      "eval_samples_per_second": 8.036,
+      "eval_steps_per_second": 0.686,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.433776809382511e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bdaef3aa2eb3ea9f60001d9e326e6ff485513720e843a3664a26ea06e785824
+size 5560