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

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-14B-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 0.13.2

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b503ef6faf74264717ff8590e188464c00250a7dbe4132d4c77bcd4f904969a
+size 137714904

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 sha256:9235d49cd02b9ed0cf3a86f123bd049f368a6cf8930e17baa84441e03b5ce613
+size 275650130

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52cb8ede25112a44eacff6554058030d46511b9d1f259bb694ef8f2af245168c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0216c1328f25d2f143e055ea0a88b490f91df772e897e9a417c133bfda33c8
+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 +1,207 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,521 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9986219568213137,
+  "eval_steps": 100,
+  "global_step": 3264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009186954524575103,
+      "eval_loss": 0.45365288853645325,
+      "eval_runtime": 91.7013,
+      "eval_samples_per_second": 1.254,
+      "eval_steps_per_second": 1.254,
+      "step": 1
+    },
+    {
+      "epoch": 0.09186954524575103,
+      "grad_norm": 0.28536465764045715,
+      "learning_rate": 3.6809815950920246e-05,
+      "loss": 0.2258,
+      "step": 100
+    },
+    {
+      "epoch": 0.09186954524575103,
+      "eval_loss": 0.15162889659404755,
+      "eval_runtime": 93.0623,
+      "eval_samples_per_second": 1.236,
+      "eval_steps_per_second": 1.236,
+      "step": 100
+    },
+    {
+      "epoch": 0.18373909049150206,
+      "grad_norm": 0.2759454846382141,
+      "learning_rate": 5.997892633518568e-05,
+      "loss": 0.0446,
+      "step": 200
+    },
+    {
+      "epoch": 0.18373909049150206,
+      "eval_loss": 0.11803138256072998,
+      "eval_runtime": 93.1015,
+      "eval_samples_per_second": 1.235,
+      "eval_steps_per_second": 1.235,
+      "step": 200
+    },
+    {
+      "epoch": 0.2756086357372531,
+      "grad_norm": 0.08795227855443954,
+      "learning_rate": 5.9711509629421385e-05,
+      "loss": 0.0306,
+      "step": 300
+    },
+    {
+      "epoch": 0.2756086357372531,
+      "eval_loss": 0.11304458230733871,
+      "eval_runtime": 92.9919,
+      "eval_samples_per_second": 1.237,
+      "eval_steps_per_second": 1.237,
+      "step": 300
+    },
+    {
+      "epoch": 0.3674781809830041,
+      "grad_norm": 0.4415115416049957,
+      "learning_rate": 5.913940906241118e-05,
+      "loss": 0.0323,
+      "step": 400
+    },
+    {
+      "epoch": 0.3674781809830041,
+      "eval_loss": 0.10952312499284744,
+      "eval_runtime": 93.0072,
+      "eval_samples_per_second": 1.236,
+      "eval_steps_per_second": 1.236,
+      "step": 400
+    },
+    {
+      "epoch": 0.4593477262287552,
+      "grad_norm": 0.4124976396560669,
+      "learning_rate": 5.8268491377782436e-05,
+      "loss": 0.0292,
+      "step": 500
+    },
+    {
+      "epoch": 0.4593477262287552,
+      "eval_loss": 0.11130835860967636,
+      "eval_runtime": 93.0093,
+      "eval_samples_per_second": 1.236,
+      "eval_steps_per_second": 1.236,
+      "step": 500
+    },
+    {
+      "epoch": 0.5512172714745062,
+      "grad_norm": 0.1237436980009079,
+      "learning_rate": 5.7107687611564266e-05,
+      "loss": 0.0307,
+      "step": 600
+    },
+    {
+      "epoch": 0.5512172714745062,
+      "eval_loss": 0.10875777900218964,
+      "eval_runtime": 93.0208,
+      "eval_samples_per_second": 1.236,
+      "eval_steps_per_second": 1.236,
+      "step": 600
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "grad_norm": 0.11754359304904938,
+      "learning_rate": 5.5668901506718624e-05,
+      "loss": 0.0188,
+      "step": 700
+    },
+    {
+      "epoch": 0.6430868167202572,
+      "eval_loss": 0.10625847429037094,
+      "eval_runtime": 93.0782,
+      "eval_samples_per_second": 1.236,
+      "eval_steps_per_second": 1.236,
+      "step": 700
+    },
+    {
+      "epoch": 0.7349563619660082,
+      "grad_norm": 0.08325380831956863,
+      "learning_rate": 5.396688744332915e-05,
+      "loss": 0.0222,
+      "step": 800
+    },
+    {
+      "epoch": 0.7349563619660082,
+      "eval_loss": 0.10221564024686813,
+      "eval_runtime": 92.9651,
+      "eval_samples_per_second": 1.237,
+      "eval_steps_per_second": 1.237,
+      "step": 800
+    },
+    {
+      "epoch": 0.8268259072117593,
+      "grad_norm": 0.06664737313985825,
+      "learning_rate": 5.201909913624226e-05,
+      "loss": 0.0232,
+      "step": 900
+    },
+    {
+      "epoch": 0.8268259072117593,
+      "eval_loss": 0.10889119654893875,
+      "eval_runtime": 93.0863,
+      "eval_samples_per_second": 1.235,
+      "eval_steps_per_second": 1.235,
+      "step": 900
+    },
+    {
+      "epoch": 0.9186954524575104,
+      "grad_norm": 0.1651008129119873,
+      "learning_rate": 4.984551065172704e-05,
+      "loss": 0.0232,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9186954524575104,
+      "eval_loss": 0.10011124610900879,
+      "eval_runtime": 92.6471,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0105649977032614,
+      "grad_norm": 0.06963470578193665,
+      "learning_rate": 4.746841157858199e-05,
+      "loss": 0.0186,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0105649977032614,
+      "eval_loss": 0.10491956770420074,
+      "eval_runtime": 92.7173,
+      "eval_samples_per_second": 1.24,
+      "eval_steps_per_second": 1.24,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1024345429490123,
+      "grad_norm": 0.1768687665462494,
+      "learning_rate": 4.491217845415585e-05,
+      "loss": 0.0165,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1024345429490123,
+      "eval_loss": 0.10712870955467224,
+      "eval_runtime": 92.6774,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1943040881947635,
+      "grad_norm": 0.03774058446288109,
+      "learning_rate": 4.220302478924997e-05,
+      "loss": 0.0144,
+      "step": 1300
+    },
+    {
+      "epoch": 1.1943040881947635,
+      "eval_loss": 0.10197390615940094,
+      "eval_runtime": 92.6938,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "grad_norm": 0.190536767244339,
+      "learning_rate": 3.936873225533197e-05,
+      "loss": 0.0165,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2861736334405145,
+      "eval_loss": 0.10447957366704941,
+      "eval_runtime": 92.6748,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3780431786862655,
+      "grad_norm": 0.12491453438997269,
+      "learning_rate": 3.6438365790666724e-05,
+      "loss": 0.0157,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3780431786862655,
+      "eval_loss": 0.10409318655729294,
+      "eval_runtime": 92.6809,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4699127239320164,
+      "grad_norm": 0.24747562408447266,
+      "learning_rate": 3.344197554687745e-05,
+      "loss": 0.0156,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4699127239320164,
+      "eval_loss": 0.11097286641597748,
+      "eval_runtime": 92.7408,
+      "eval_samples_per_second": 1.24,
+      "eval_steps_per_second": 1.24,
+      "step": 1600
+    },
+    {
+      "epoch": 1.5617822691777676,
+      "grad_norm": 0.10677100718021393,
+      "learning_rate": 3.0410288732398347e-05,
+      "loss": 0.0142,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5617822691777676,
+      "eval_loss": 0.10534139722585678,
+      "eval_runtime": 92.5904,
+      "eval_samples_per_second": 1.242,
+      "eval_steps_per_second": 1.242,
+      "step": 1700
+    },
+    {
+      "epoch": 1.6536518144235186,
+      "grad_norm": 0.025434676557779312,
+      "learning_rate": 2.7374394512884237e-05,
+      "loss": 0.0153,
+      "step": 1800
+    },
+    {
+      "epoch": 1.6536518144235186,
+      "eval_loss": 0.10420160740613937,
+      "eval_runtime": 92.6901,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1800
+    },
+    {
+      "epoch": 1.7455213596692696,
+      "grad_norm": 0.07759197056293488,
+      "learning_rate": 2.4365425199842408e-05,
+      "loss": 0.0149,
+      "step": 1900
+    },
+    {
+      "epoch": 1.7455213596692696,
+      "eval_loss": 0.10568808764219284,
+      "eval_runtime": 92.7012,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 1900
+    },
+    {
+      "epoch": 1.8373909049150208,
+      "grad_norm": 0.049779146909713745,
+      "learning_rate": 2.1414236996814956e-05,
+      "loss": 0.0136,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8373909049150208,
+      "eval_loss": 0.10744442045688629,
+      "eval_runtime": 92.6071,
+      "eval_samples_per_second": 1.242,
+      "eval_steps_per_second": 1.242,
+      "step": 2000
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 0.16362594068050385,
+      "learning_rate": 1.8551093576976936e-05,
+      "loss": 0.0128,
+      "step": 2100
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "eval_loss": 0.1033589243888855,
+      "eval_runtime": 92.6218,
+      "eval_samples_per_second": 1.242,
+      "eval_steps_per_second": 1.242,
+      "step": 2100
+    },
+    {
+      "epoch": 2.0211299954065227,
+      "grad_norm": 0.08395898342132568,
+      "learning_rate": 1.5805355736980443e-05,
+      "loss": 0.0131,
+      "step": 2200
+    },
+    {
+      "epoch": 2.0211299954065227,
+      "eval_loss": 0.10516863316297531,
+      "eval_runtime": 92.6782,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 2200
+    },
+    {
+      "epoch": 2.112999540652274,
+      "grad_norm": 0.17860834300518036,
+      "learning_rate": 1.320518030956451e-05,
+      "loss": 0.0079,
+      "step": 2300
+    },
+    {
+      "epoch": 2.112999540652274,
+      "eval_loss": 0.10896279662847519,
+      "eval_runtime": 92.5937,
+      "eval_samples_per_second": 1.242,
+      "eval_steps_per_second": 1.242,
+      "step": 2300
+    },
+    {
+      "epoch": 2.2048690858980247,
+      "grad_norm": 0.09517592191696167,
+      "learning_rate": 1.077723142250394e-05,
+      "loss": 0.0093,
+      "step": 2400
+    },
+    {
+      "epoch": 2.2048690858980247,
+      "eval_loss": 0.11196599900722504,
+      "eval_runtime": 92.7043,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 2400
+    },
+    {
+      "epoch": 2.296738631143776,
+      "grad_norm": 0.3143569231033325,
+      "learning_rate": 8.546407064862392e-06,
+      "loss": 0.0091,
+      "step": 2500
+    },
+    {
+      "epoch": 2.296738631143776,
+      "eval_loss": 0.1142640933394432,
+      "eval_runtime": 92.6858,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 2500
+    },
+    {
+      "epoch": 2.388608176389527,
+      "grad_norm": 0.06993573904037476,
+      "learning_rate": 6.535583764541832e-06,
+      "loss": 0.0104,
+      "step": 2600
+    },
+    {
+      "epoch": 2.388608176389527,
+      "eval_loss": 0.11303328722715378,
+      "eval_runtime": 92.6449,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 2600
+    },
+    {
+      "epoch": 2.480477721635278,
+      "grad_norm": 0.057985495775938034,
+      "learning_rate": 4.765381995394528e-06,
+      "loss": 0.0064,
+      "step": 2700
+    },
+    {
+      "epoch": 2.480477721635278,
+      "eval_loss": 0.11439105868339539,
+      "eval_runtime": 92.6853,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 2700
+    },
+    {
+      "epoch": 2.572347266881029,
+      "grad_norm": 0.2965603768825531,
+      "learning_rate": 3.253954719586846e-06,
+      "loss": 0.0098,
+      "step": 2800
+    },
+    {
+      "epoch": 2.572347266881029,
+      "eval_loss": 0.11455501616001129,
+      "eval_runtime": 92.6971,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 2800
+    },
+    {
+      "epoch": 2.6642168121267797,
+      "grad_norm": 0.1485712081193924,
+      "learning_rate": 2.016801233658385e-06,
+      "loss": 0.0093,
+      "step": 2900
+    },
+    {
+      "epoch": 2.6642168121267797,
+      "eval_loss": 0.1141701489686966,
+      "eval_runtime": 92.8761,
+      "eval_samples_per_second": 1.238,
+      "eval_steps_per_second": 1.238,
+      "step": 2900
+    },
+    {
+      "epoch": 2.756086357372531,
+      "grad_norm": 0.1018487960100174,
+      "learning_rate": 1.0666082272370813e-06,
+      "loss": 0.0079,
+      "step": 3000
+    },
+    {
+      "epoch": 2.756086357372531,
+      "eval_loss": 0.11440093070268631,
+      "eval_runtime": 92.6137,
+      "eval_samples_per_second": 1.242,
+      "eval_steps_per_second": 1.242,
+      "step": 3000
+    },
+    {
+      "epoch": 2.847955902618282,
+      "grad_norm": 0.15277303755283356,
+      "learning_rate": 4.1311968431219205e-07,
+      "loss": 0.0085,
+      "step": 3100
+    },
+    {
+      "epoch": 2.847955902618282,
+      "eval_loss": 0.11437059193849564,
+      "eval_runtime": 92.6248,
+      "eval_samples_per_second": 1.242,
+      "eval_steps_per_second": 1.242,
+      "step": 3100
+    },
+    {
+      "epoch": 2.939825447864033,
+      "grad_norm": 0.8881728053092957,
+      "learning_rate": 6.303696119383862e-08,
+      "loss": 0.0092,
+      "step": 3200
+    },
+    {
+      "epoch": 2.939825447864033,
+      "eval_loss": 0.11437766253948212,
+      "eval_runtime": 92.635,
+      "eval_samples_per_second": 1.241,
+      "eval_steps_per_second": 1.241,
+      "step": 3200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3264,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.2502005536215532e+18,
+  "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 sha256:3ed2415f531a4741a5240bcd7f8c0d6ad57d26df92ddac52da39e093c62e936b
+size 6200