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

@@ -0,0 +1,202 @@
+---
+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 0.11.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "gate_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 sha256:9f215e14db03147c741af6e43ad3b669756f9aeafe4a800a6f322b8c80969e1d
+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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11abc68256c62b7826f0e5c17199705dd4d25946e72602226e0370f59403417e
+size 161810282

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e3955ad18010c39c711814732331b4e50b2a9232cb031dc53f75478f622e65
+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 +1,614 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.980568011958146,
+  "eval_steps": 500,
+  "global_step": 415,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.059790732436472344,
+      "grad_norm": 1.2978590726852417,
+      "learning_rate": 4.998209387040829e-05,
+      "loss": 1.1088,
+      "step": 5
+    },
+    {
+      "epoch": 0.11958146487294469,
+      "grad_norm": 0.4979011118412018,
+      "learning_rate": 4.9928401131991305e-05,
+      "loss": 0.8028,
+      "step": 10
+    },
+    {
+      "epoch": 0.17937219730941703,
+      "grad_norm": 0.48205411434173584,
+      "learning_rate": 4.9838998699079625e-05,
+      "loss": 0.6741,
+      "step": 15
+    },
+    {
+      "epoch": 0.23916292974588937,
+      "grad_norm": 0.48612523078918457,
+      "learning_rate": 4.971401463979721e-05,
+      "loss": 0.6049,
+      "step": 20
+    },
+    {
+      "epoch": 0.29895366218236175,
+      "grad_norm": 0.38566604256629944,
+      "learning_rate": 4.9553627992605066e-05,
+      "loss": 0.6004,
+      "step": 25
+    },
+    {
+      "epoch": 0.35874439461883406,
+      "grad_norm": 0.5367271900177002,
+      "learning_rate": 4.9358068509830334e-05,
+      "loss": 0.4998,
+      "step": 30
+    },
+    {
+      "epoch": 0.41853512705530643,
+      "grad_norm": 0.4608819782733917,
+      "learning_rate": 4.912761632854833e-05,
+      "loss": 0.5288,
+      "step": 35
+    },
+    {
+      "epoch": 0.47832585949177875,
+      "grad_norm": 0.4309336543083191,
+      "learning_rate": 4.886260156928888e-05,
+      "loss": 0.4841,
+      "step": 40
+    },
+    {
+      "epoch": 0.5381165919282511,
+      "grad_norm": 0.41779792308807373,
+      "learning_rate": 4.856340386314182e-05,
+      "loss": 0.521,
+      "step": 45
+    },
+    {
+      "epoch": 0.5979073243647235,
+      "grad_norm": 0.42198920249938965,
+      "learning_rate": 4.8230451807939135e-05,
+      "loss": 0.5161,
+      "step": 50
+    },
+    {
+      "epoch": 0.6576980568011959,
+      "grad_norm": 0.43890777230262756,
+      "learning_rate": 4.786422235429269e-05,
+      "loss": 0.4975,
+      "step": 55
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.40360623598098755,
+      "learning_rate": 4.746524012236706e-05,
+      "loss": 0.4515,
+      "step": 60
+    },
+    {
+      "epoch": 0.7772795216741405,
+      "grad_norm": 0.4691283106803894,
+      "learning_rate": 4.703407665036622e-05,
+      "loss": 0.4842,
+      "step": 65
+    },
+    {
+      "epoch": 0.8370702541106129,
+      "grad_norm": 0.5005263090133667,
+      "learning_rate": 4.657134957581057e-05,
+      "loss": 0.5417,
+      "step": 70
+    },
+    {
+      "epoch": 0.8968609865470852,
+      "grad_norm": 0.5099341869354248,
+      "learning_rate": 4.607772175077711e-05,
+      "loss": 0.4756,
+      "step": 75
+    },
+    {
+      "epoch": 0.9566517189835575,
+      "grad_norm": 0.5432000160217285,
+      "learning_rate": 4.555390029237026e-05,
+      "loss": 0.4343,
+      "step": 80
+    },
+    {
+      "epoch": 1.0209267563527653,
+      "grad_norm": 0.571912407875061,
+      "learning_rate": 4.500063556978337e-05,
+      "loss": 0.6003,
+      "step": 85
+    },
+    {
+      "epoch": 1.0807174887892377,
+      "grad_norm": 0.4976639151573181,
+      "learning_rate": 4.441872012940214e-05,
+      "loss": 0.425,
+      "step": 90
+    },
+    {
+      "epoch": 1.14050822122571,
+      "grad_norm": 0.4636209309101105,
+      "learning_rate": 4.380898755948953e-05,
+      "loss": 0.4477,
+      "step": 95
+    },
+    {
+      "epoch": 1.2002989536621824,
+      "grad_norm": 0.45289313793182373,
+      "learning_rate": 4.3172311296078595e-05,
+      "loss": 0.4374,
+      "step": 100
+    },
+    {
+      "epoch": 1.2600896860986546,
+      "grad_norm": 0.5313855409622192,
+      "learning_rate": 4.250960337178377e-05,
+      "loss": 0.4453,
+      "step": 105
+    },
+    {
+      "epoch": 1.319880418535127,
+      "grad_norm": 0.5582486987113953,
+      "learning_rate": 4.1821813109322974e-05,
+      "loss": 0.4482,
+      "step": 110
+    },
+    {
+      "epoch": 1.3796711509715993,
+      "grad_norm": 0.529606819152832,
+      "learning_rate": 4.1109925761621925e-05,
+      "loss": 0.4403,
+      "step": 115
+    },
+    {
+      "epoch": 1.4394618834080717,
+      "grad_norm": 0.5741641521453857,
+      "learning_rate": 4.037496110044884e-05,
+      "loss": 0.4462,
+      "step": 120
+    },
+    {
+      "epoch": 1.499252615844544,
+      "grad_norm": 0.47668057680130005,
+      "learning_rate": 3.961797195560118e-05,
+      "loss": 0.4522,
+      "step": 125
+    },
+    {
+      "epoch": 1.5590433482810164,
+      "grad_norm": 0.5119588971138,
+      "learning_rate": 3.8840042706737114e-05,
+      "loss": 0.4266,
+      "step": 130
+    },
+    {
+      "epoch": 1.6188340807174888,
+      "grad_norm": 0.7544881701469421,
+      "learning_rate": 3.804228773001212e-05,
+      "loss": 0.4448,
+      "step": 135
+    },
+    {
+      "epoch": 1.6786248131539612,
+      "grad_norm": 0.5197708606719971,
+      "learning_rate": 3.7225849801745835e-05,
+      "loss": 0.4406,
+      "step": 140
+    },
+    {
+      "epoch": 1.7384155455904335,
+      "grad_norm": 0.5973308682441711,
+      "learning_rate": 3.639189846140604e-05,
+      "loss": 0.4646,
+      "step": 145
+    },
+    {
+      "epoch": 1.798206278026906,
+      "grad_norm": 0.5432918071746826,
+      "learning_rate": 3.55416283362546e-05,
+      "loss": 0.391,
+      "step": 150
+    },
+    {
+      "epoch": 1.8579970104633783,
+      "grad_norm": 0.7063805460929871,
+      "learning_rate": 3.4676257430055434e-05,
+      "loss": 0.4536,
+      "step": 155
+    },
+    {
+      "epoch": 1.9177877428998507,
+      "grad_norm": 0.5936899185180664,
+      "learning_rate": 3.379702537829583e-05,
+      "loss": 0.4474,
+      "step": 160
+    },
+    {
+      "epoch": 1.977578475336323,
+      "grad_norm": 0.6480870842933655,
+      "learning_rate": 3.29051916724206e-05,
+      "loss": 0.393,
+      "step": 165
+    },
+    {
+      "epoch": 2.0418535127055306,
+      "grad_norm": 0.6020011305809021,
+      "learning_rate": 3.200203385562268e-05,
+      "loss": 0.4697,
+      "step": 170
+    },
+    {
+      "epoch": 2.101644245142003,
+      "grad_norm": 0.5606960654258728,
+      "learning_rate": 3.10888456927748e-05,
+      "loss": 0.4015,
+      "step": 175
+    },
+    {
+      "epoch": 2.1614349775784754,
+      "grad_norm": 0.5238797664642334,
+      "learning_rate": 3.0166935317123823e-05,
+      "loss": 0.3844,
+      "step": 180
+    },
+    {
+      "epoch": 2.2212257100149477,
+      "grad_norm": 0.5262567400932312,
+      "learning_rate": 2.923762335640242e-05,
+      "loss": 0.4319,
+      "step": 185
+    },
+    {
+      "epoch": 2.28101644245142,
+      "grad_norm": 0.6023457050323486,
+      "learning_rate": 2.8302241041042565e-05,
+      "loss": 0.3913,
+      "step": 190
+    },
+    {
+      "epoch": 2.3408071748878925,
+      "grad_norm": 0.6637177467346191,
+      "learning_rate": 2.7362128297200785e-05,
+      "loss": 0.4117,
+      "step": 195
+    },
+    {
+      "epoch": 2.400597907324365,
+      "grad_norm": 0.6618629693984985,
+      "learning_rate": 2.6418631827326857e-05,
+      "loss": 0.4395,
+      "step": 200
+    },
+    {
+      "epoch": 2.460388639760837,
+      "grad_norm": 0.6563321948051453,
+      "learning_rate": 2.5473103181025476e-05,
+      "loss": 0.4085,
+      "step": 205
+    },
+    {
+      "epoch": 2.520179372197309,
+      "grad_norm": 0.6196507215499878,
+      "learning_rate": 2.4526896818974533e-05,
+      "loss": 0.4174,
+      "step": 210
+    },
+    {
+      "epoch": 2.579970104633782,
+      "grad_norm": 0.6244773268699646,
+      "learning_rate": 2.3581368172673152e-05,
+      "loss": 0.409,
+      "step": 215
+    },
+    {
+      "epoch": 2.639760837070254,
+      "grad_norm": 0.6863143444061279,
+      "learning_rate": 2.263787170279922e-05,
+      "loss": 0.372,
+      "step": 220
+    },
+    {
+      "epoch": 2.6995515695067267,
+      "grad_norm": 0.6396352648735046,
+      "learning_rate": 2.1697758958957448e-05,
+      "loss": 0.3904,
+      "step": 225
+    },
+    {
+      "epoch": 2.7593423019431986,
+      "grad_norm": 0.6815731525421143,
+      "learning_rate": 2.0762376643597582e-05,
+      "loss": 0.4039,
+      "step": 230
+    },
+    {
+      "epoch": 2.819133034379671,
+      "grad_norm": 0.6671094298362732,
+      "learning_rate": 1.9833064682876176e-05,
+      "loss": 0.4058,
+      "step": 235
+    },
+    {
+      "epoch": 2.8789237668161434,
+      "grad_norm": 0.6419411301612854,
+      "learning_rate": 1.8911154307225203e-05,
+      "loss": 0.37,
+      "step": 240
+    },
+    {
+      "epoch": 2.9387144992526157,
+      "grad_norm": 0.741301417350769,
+      "learning_rate": 1.7997966144377325e-05,
+      "loss": 0.3926,
+      "step": 245
+    },
+    {
+      "epoch": 3.0029895366218238,
+      "grad_norm": 1.5108810663223267,
+      "learning_rate": 1.70948083275794e-05,
+      "loss": 0.4486,
+      "step": 250
+    },
+    {
+      "epoch": 3.062780269058296,
+      "grad_norm": 0.5916804075241089,
+      "learning_rate": 1.6202974621704175e-05,
+      "loss": 0.3531,
+      "step": 255
+    },
+    {
+      "epoch": 3.1225710014947685,
+      "grad_norm": 0.6299751996994019,
+      "learning_rate": 1.5323742569944572e-05,
+      "loss": 0.3961,
+      "step": 260
+    },
+    {
+      "epoch": 3.1823617339312404,
+      "grad_norm": 0.6683854460716248,
+      "learning_rate": 1.4458371663745401e-05,
+      "loss": 0.3722,
+      "step": 265
+    },
+    {
+      "epoch": 3.242152466367713,
+      "grad_norm": 0.6670008301734924,
+      "learning_rate": 1.3608101538593965e-05,
+      "loss": 0.3879,
+      "step": 270
+    },
+    {
+      "epoch": 3.301943198804185,
+      "grad_norm": 0.6568167209625244,
+      "learning_rate": 1.277415019825417e-05,
+      "loss": 0.409,
+      "step": 275
+    },
+    {
+      "epoch": 3.3617339312406576,
+      "grad_norm": 0.6944593191146851,
+      "learning_rate": 1.195771226998789e-05,
+      "loss": 0.3804,
+      "step": 280
+    },
+    {
+      "epoch": 3.42152466367713,
+      "grad_norm": 0.6333041191101074,
+      "learning_rate": 1.1159957293262888e-05,
+      "loss": 0.3679,
+      "step": 285
+    },
+    {
+      "epoch": 3.4813153961136023,
+      "grad_norm": 0.7222440838813782,
+      "learning_rate": 1.0382028044398822e-05,
+      "loss": 0.3877,
+      "step": 290
+    },
+    {
+      "epoch": 3.5411061285500747,
+      "grad_norm": 0.7552939653396606,
+      "learning_rate": 9.625038899551161e-06,
+      "loss": 0.4043,
+      "step": 295
+    },
+    {
+      "epoch": 3.600896860986547,
+      "grad_norm": 0.6875253319740295,
+      "learning_rate": 8.890074238378074e-06,
+      "loss": 0.3741,
+      "step": 300
+    },
+    {
+      "epoch": 3.6606875934230194,
+      "grad_norm": 0.7575701475143433,
+      "learning_rate": 8.178186890677029e-06,
+      "loss": 0.3729,
+      "step": 305
+    },
+    {
+      "epoch": 3.720478325859492,
+      "grad_norm": 0.7950400114059448,
+      "learning_rate": 7.490396628216237e-06,
+      "loss": 0.3847,
+      "step": 310
+    },
+    {
+      "epoch": 3.780269058295964,
+      "grad_norm": 0.7573489546775818,
+      "learning_rate": 6.827688703921406e-06,
+      "loss": 0.3447,
+      "step": 315
+    },
+    {
+      "epoch": 3.8400597907324365,
+      "grad_norm": 0.6731217503547668,
+      "learning_rate": 6.1910124405104686e-06,
+      "loss": 0.3898,
+      "step": 320
+    },
+    {
+      "epoch": 3.899850523168909,
+      "grad_norm": 0.7151201367378235,
+      "learning_rate": 5.581279870597867e-06,
+      "loss": 0.4087,
+      "step": 325
+    },
+    {
+      "epoch": 3.9596412556053813,
+      "grad_norm": 0.7048860788345337,
+      "learning_rate": 4.999364430216638e-06,
+      "loss": 0.351,
+      "step": 330
+    },
+    {
+      "epoch": 4.023916292974589,
+      "grad_norm": 0.6912049651145935,
+      "learning_rate": 4.44609970762975e-06,
+      "loss": 0.3908,
+      "step": 335
+    },
+    {
+      "epoch": 4.083707025411061,
+      "grad_norm": 0.657899796962738,
+      "learning_rate": 3.922278249222894e-06,
+      "loss": 0.3535,
+      "step": 340
+    },
+    {
+      "epoch": 4.143497757847534,
+      "grad_norm": 0.7527613043785095,
+      "learning_rate": 3.428650424189428e-06,
+      "loss": 0.3652,
+      "step": 345
+    },
+    {
+      "epoch": 4.203288490284006,
+      "grad_norm": 0.6919234991073608,
+      "learning_rate": 2.9659233496337786e-06,
+      "loss": 0.3521,
+      "step": 350
+    },
+    {
+      "epoch": 4.263079222720478,
+      "grad_norm": 0.7383163571357727,
+      "learning_rate": 2.53475987763295e-06,
+      "loss": 0.4015,
+      "step": 355
+    },
+    {
+      "epoch": 4.322869955156951,
+      "grad_norm": 0.7887938022613525,
+      "learning_rate": 2.135777645707318e-06,
+      "loss": 0.3534,
+      "step": 360
+    },
+    {
+      "epoch": 4.382660687593423,
+      "grad_norm": 0.670879602432251,
+      "learning_rate": 1.7695481920608715e-06,
+      "loss": 0.3773,
+      "step": 365
+    },
+    {
+      "epoch": 4.4424514200298955,
+      "grad_norm": 0.7601534128189087,
+      "learning_rate": 1.4365961368581842e-06,
+      "loss": 0.3672,
+      "step": 370
+    },
+    {
+      "epoch": 4.502242152466367,
+      "grad_norm": 0.7183623909950256,
+      "learning_rate": 1.137398430711123e-06,
+      "loss": 0.3576,
+      "step": 375
+    },
+    {
+      "epoch": 4.56203288490284,
+      "grad_norm": 0.6791078448295593,
+      "learning_rate": 8.723836714516681e-07,
+      "loss": 0.3762,
+      "step": 380
+    },
+    {
+      "epoch": 4.621823617339312,
+      "grad_norm": 0.6709511876106262,
+      "learning_rate": 6.419314901696671e-07,
+      "loss": 0.3529,
+      "step": 385
+    },
+    {
+      "epoch": 4.681614349775785,
+      "grad_norm": 0.6895151138305664,
+      "learning_rate": 4.463720073949351e-07,
+      "loss": 0.367,
+      "step": 390
+    },
+    {
+      "epoch": 4.741405082212257,
+      "grad_norm": 0.6979352831840515,
+      "learning_rate": 2.8598536020278677e-07,
+      "loss": 0.3853,
+      "step": 395
+    },
+    {
+      "epoch": 4.80119581464873,
+      "grad_norm": 0.6628928184509277,
+      "learning_rate": 1.6100130092037703e-07,
+      "loss": 0.3594,
+      "step": 400
+    },
+    {
+      "epoch": 4.860986547085202,
+      "grad_norm": 0.7289102673530579,
+      "learning_rate": 7.159886800869875e-08,
+      "loss": 0.3892,
+      "step": 405
+    },
+    {
+      "epoch": 4.920777279521674,
+      "grad_norm": 0.6815170645713806,
+      "learning_rate": 1.790612959171323e-08,
+      "loss": 0.3511,
+      "step": 410
+    },
+    {
+      "epoch": 4.980568011958146,
+      "grad_norm": 0.6885178685188293,
+      "learning_rate": 0.0,
+      "loss": 0.3585,
+      "step": 415
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 415,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0010831439303475e+17,
+  "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 sha256:75f220c63ddf4767614efac998531bf106f268e374a677d9f9224c253def95a3
+size 5432