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-VL-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 0.14.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "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": [
+    "q_proj",
+    "v_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 sha256:21bb1393842eec510fcb4c5a631d05e26e9b1fb8551bad12addc2041de394f51
+size 10107280

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 sha256:7c2cada59e5902aaad29759c008dd11358663ba69fee43842a768bd145972128
+size 20280890

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f370fe44b56d5084b2b90722b93e0223688ffb3af3a5109a883a0e5e72e7b915
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa967f990168a530e88ae8b8795df76b2e71d52f0690de47483c7f1210a8359c
+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": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "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 +1,745 @@
+{
+  "best_metric": 1.3700028657913208,
+  "best_model_checkpoint": "/app/finetuned_weights/checkpoint-800",
+  "epoch": 0.4591434105746467,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005739292632183084,
+      "grad_norm": 0.43322139978408813,
+      "learning_rate": 0.0002,
+      "loss": 2.051,
+      "mean_token_accuracy": 0.6683308390900493,
+      "step": 10
+    },
+    {
+      "epoch": 0.011478585264366167,
+      "grad_norm": 0.40237197279930115,
+      "learning_rate": 0.0002,
+      "loss": 1.7549,
+      "mean_token_accuracy": 0.6822433151304722,
+      "step": 20
+    },
+    {
+      "epoch": 0.01721787789654925,
+      "grad_norm": 0.43123266100883484,
+      "learning_rate": 0.0002,
+      "loss": 1.5103,
+      "mean_token_accuracy": 0.7066726513206959,
+      "step": 30
+    },
+    {
+      "epoch": 0.022957170528732335,
+      "grad_norm": 0.16466361284255981,
+      "learning_rate": 0.0002,
+      "loss": 1.4444,
+      "mean_token_accuracy": 0.7159745823591948,
+      "step": 40
+    },
+    {
+      "epoch": 0.02869646316091542,
+      "grad_norm": 0.3186506927013397,
+      "learning_rate": 0.0002,
+      "loss": 1.4808,
+      "mean_token_accuracy": 0.7143966030329466,
+      "step": 50
+    },
+    {
+      "epoch": 0.0344357557930985,
+      "grad_norm": 0.49696969985961914,
+      "learning_rate": 0.0002,
+      "loss": 1.5015,
+      "mean_token_accuracy": 0.7038091894239187,
+      "step": 60
+    },
+    {
+      "epoch": 0.040175048425281586,
+      "grad_norm": 0.2998158037662506,
+      "learning_rate": 0.0002,
+      "loss": 1.345,
+      "mean_token_accuracy": 0.7281523209065199,
+      "step": 70
+    },
+    {
+      "epoch": 0.04591434105746467,
+      "grad_norm": 0.2879635989665985,
+      "learning_rate": 0.0002,
+      "loss": 1.4034,
+      "mean_token_accuracy": 0.7154877178370953,
+      "step": 80
+    },
+    {
+      "epoch": 0.05165363368964775,
+      "grad_norm": 0.16925716400146484,
+      "learning_rate": 0.0002,
+      "loss": 1.6293,
+      "mean_token_accuracy": 0.6787833951413631,
+      "step": 90
+    },
+    {
+      "epoch": 0.05739292632183084,
+      "grad_norm": 0.2507581412792206,
+      "learning_rate": 0.0002,
+      "loss": 1.3949,
+      "mean_token_accuracy": 0.7227997560054064,
+      "step": 100
+    },
+    {
+      "epoch": 0.05739292632183084,
+      "eval_loss": 1.4279941320419312,
+      "eval_mean_token_accuracy": 0.7138351793184543,
+      "eval_runtime": 4534.8411,
+      "eval_samples_per_second": 0.768,
+      "eval_steps_per_second": 0.384,
+      "step": 100
+    },
+    {
+      "epoch": 0.06313221895401391,
+      "grad_norm": 0.24556811153888702,
+      "learning_rate": 0.0002,
+      "loss": 1.3832,
+      "mean_token_accuracy": 0.7172763034701347,
+      "step": 110
+    },
+    {
+      "epoch": 0.068871511586197,
+      "grad_norm": 0.24670149385929108,
+      "learning_rate": 0.0002,
+      "loss": 1.4245,
+      "mean_token_accuracy": 0.7150326510891318,
+      "step": 120
+    },
+    {
+      "epoch": 0.07461080421838008,
+      "grad_norm": 0.27052056789398193,
+      "learning_rate": 0.0002,
+      "loss": 1.2266,
+      "mean_token_accuracy": 0.7490846037864685,
+      "step": 130
+    },
+    {
+      "epoch": 0.08035009685056317,
+      "grad_norm": 0.2287702113389969,
+      "learning_rate": 0.0002,
+      "loss": 1.4237,
+      "mean_token_accuracy": 0.7114990293979645,
+      "step": 140
+    },
+    {
+      "epoch": 0.08608938948274625,
+      "grad_norm": 0.2251950353384018,
+      "learning_rate": 0.0002,
+      "loss": 1.4939,
+      "mean_token_accuracy": 0.7060536827892065,
+      "step": 150
+    },
+    {
+      "epoch": 0.09182868211492934,
+      "grad_norm": 0.2458341121673584,
+      "learning_rate": 0.0002,
+      "loss": 1.4142,
+      "mean_token_accuracy": 0.7157001797109842,
+      "step": 160
+    },
+    {
+      "epoch": 0.09756797474711242,
+      "grad_norm": 0.1824209988117218,
+      "learning_rate": 0.0002,
+      "loss": 1.2918,
+      "mean_token_accuracy": 0.7333439949899911,
+      "step": 170
+    },
+    {
+      "epoch": 0.1033072673792955,
+      "grad_norm": 0.23465971648693085,
+      "learning_rate": 0.0002,
+      "loss": 1.3675,
+      "mean_token_accuracy": 0.7236015398055315,
+      "step": 180
+    },
+    {
+      "epoch": 0.10904656001147858,
+      "grad_norm": 0.2167435586452484,
+      "learning_rate": 0.0002,
+      "loss": 1.4979,
+      "mean_token_accuracy": 0.7010378727689386,
+      "step": 190
+    },
+    {
+      "epoch": 0.11478585264366167,
+      "grad_norm": 0.24258023500442505,
+      "learning_rate": 0.0002,
+      "loss": 1.3437,
+      "mean_token_accuracy": 0.7294836457818746,
+      "step": 200
+    },
+    {
+      "epoch": 0.11478585264366167,
+      "eval_loss": 1.402819037437439,
+      "eval_mean_token_accuracy": 0.716681150906536,
+      "eval_runtime": 4414.3312,
+      "eval_samples_per_second": 0.789,
+      "eval_steps_per_second": 0.395,
+      "step": 200
+    },
+    {
+      "epoch": 0.12052514527584475,
+      "grad_norm": 0.24051423370838165,
+      "learning_rate": 0.0002,
+      "loss": 1.3826,
+      "mean_token_accuracy": 0.7158944692462683,
+      "step": 210
+    },
+    {
+      "epoch": 0.12626443790802783,
+      "grad_norm": 0.25226420164108276,
+      "learning_rate": 0.0002,
+      "loss": 1.2985,
+      "mean_token_accuracy": 0.733695725724101,
+      "step": 220
+    },
+    {
+      "epoch": 0.13200373054021092,
+      "grad_norm": 0.2106948047876358,
+      "learning_rate": 0.0002,
+      "loss": 1.3394,
+      "mean_token_accuracy": 0.7303649850189686,
+      "step": 230
+    },
+    {
+      "epoch": 0.137743023172394,
+      "grad_norm": 0.21339824795722961,
+      "learning_rate": 0.0002,
+      "loss": 1.3752,
+      "mean_token_accuracy": 0.7253331538289786,
+      "step": 240
+    },
+    {
+      "epoch": 0.1434823158045771,
+      "grad_norm": 0.2484087496995926,
+      "learning_rate": 0.0002,
+      "loss": 1.4659,
+      "mean_token_accuracy": 0.7037245020270347,
+      "step": 250
+    },
+    {
+      "epoch": 0.14922160843676016,
+      "grad_norm": 0.24411025643348694,
+      "learning_rate": 0.0002,
+      "loss": 1.3957,
+      "mean_token_accuracy": 0.7138343520462513,
+      "step": 260
+    },
+    {
+      "epoch": 0.15496090106894325,
+      "grad_norm": 0.2551439702510834,
+      "learning_rate": 0.0002,
+      "loss": 1.3914,
+      "mean_token_accuracy": 0.713682159781456,
+      "step": 270
+    },
+    {
+      "epoch": 0.16070019370112634,
+      "grad_norm": 0.258771151304245,
+      "learning_rate": 0.0002,
+      "loss": 1.4153,
+      "mean_token_accuracy": 0.7100905137136578,
+      "step": 280
+    },
+    {
+      "epoch": 0.16643948633330943,
+      "grad_norm": 0.20730619132518768,
+      "learning_rate": 0.0002,
+      "loss": 1.3201,
+      "mean_token_accuracy": 0.733038941025734,
+      "step": 290
+    },
+    {
+      "epoch": 0.1721787789654925,
+      "grad_norm": 0.17945091426372528,
+      "learning_rate": 0.0002,
+      "loss": 1.5173,
+      "mean_token_accuracy": 0.6967695135623216,
+      "step": 300
+    },
+    {
+      "epoch": 0.1721787789654925,
+      "eval_loss": 1.3912384510040283,
+      "eval_mean_token_accuracy": 0.7176746699191754,
+      "eval_runtime": 4400.1017,
+      "eval_samples_per_second": 0.792,
+      "eval_steps_per_second": 0.396,
+      "step": 300
+    },
+    {
+      "epoch": 0.1779180715976756,
+      "grad_norm": 0.25128230452537537,
+      "learning_rate": 0.0002,
+      "loss": 1.4181,
+      "mean_token_accuracy": 0.715370923653245,
+      "step": 310
+    },
+    {
+      "epoch": 0.18365736422985868,
+      "grad_norm": 0.22883553802967072,
+      "learning_rate": 0.0002,
+      "loss": 1.4089,
+      "mean_token_accuracy": 0.718804694339633,
+      "step": 320
+    },
+    {
+      "epoch": 0.18939665686204174,
+      "grad_norm": 0.2196984440088272,
+      "learning_rate": 0.0002,
+      "loss": 1.2547,
+      "mean_token_accuracy": 0.7411983285099268,
+      "step": 330
+    },
+    {
+      "epoch": 0.19513594949422483,
+      "grad_norm": 0.374326229095459,
+      "learning_rate": 0.0002,
+      "loss": 1.552,
+      "mean_token_accuracy": 0.6875970430672169,
+      "step": 340
+    },
+    {
+      "epoch": 0.20087524212640792,
+      "grad_norm": 0.6579405665397644,
+      "learning_rate": 0.0002,
+      "loss": 1.3655,
+      "mean_token_accuracy": 0.7201284021139145,
+      "step": 350
+    },
+    {
+      "epoch": 0.206614534758591,
+      "grad_norm": 0.2102547287940979,
+      "learning_rate": 0.0002,
+      "loss": 1.3867,
+      "mean_token_accuracy": 0.7191131260246039,
+      "step": 360
+    },
+    {
+      "epoch": 0.21235382739077407,
+      "grad_norm": 0.26832231879234314,
+      "learning_rate": 0.0002,
+      "loss": 1.4089,
+      "mean_token_accuracy": 0.7181429363787174,
+      "step": 370
+    },
+    {
+      "epoch": 0.21809312002295717,
+      "grad_norm": 0.25602883100509644,
+      "learning_rate": 0.0002,
+      "loss": 1.3422,
+      "mean_token_accuracy": 0.7277179971337319,
+      "step": 380
+    },
+    {
+      "epoch": 0.22383241265514026,
+      "grad_norm": 0.2577485144138336,
+      "learning_rate": 0.0002,
+      "loss": 1.4422,
+      "mean_token_accuracy": 0.7109258253127336,
+      "step": 390
+    },
+    {
+      "epoch": 0.22957170528732335,
+      "grad_norm": 0.2750665247440338,
+      "learning_rate": 0.0002,
+      "loss": 1.2633,
+      "mean_token_accuracy": 0.7383943419903517,
+      "step": 400
+    },
+    {
+      "epoch": 0.22957170528732335,
+      "eval_loss": 1.38496732711792,
+      "eval_mean_token_accuracy": 0.7186302011869997,
+      "eval_runtime": 4400.5889,
+      "eval_samples_per_second": 0.792,
+      "eval_steps_per_second": 0.396,
+      "step": 400
+    },
+    {
+      "epoch": 0.2353109979195064,
+      "grad_norm": 0.23557531833648682,
+      "learning_rate": 0.0002,
+      "loss": 1.3842,
+      "mean_token_accuracy": 0.7180797912180423,
+      "step": 410
+    },
+    {
+      "epoch": 0.2410502905516895,
+      "grad_norm": 0.2660968601703644,
+      "learning_rate": 0.0002,
+      "loss": 1.401,
+      "mean_token_accuracy": 0.7145325090736151,
+      "step": 420
+    },
+    {
+      "epoch": 0.2467895831838726,
+      "grad_norm": 0.2272387444972992,
+      "learning_rate": 0.0002,
+      "loss": 1.4956,
+      "mean_token_accuracy": 0.6978571161627769,
+      "step": 430
+    },
+    {
+      "epoch": 0.25252887581605565,
+      "grad_norm": 0.2202438861131668,
+      "learning_rate": 0.0002,
+      "loss": 1.3757,
+      "mean_token_accuracy": 0.7206571504473687,
+      "step": 440
+    },
+    {
+      "epoch": 0.25826816844823874,
+      "grad_norm": 0.24659469723701477,
+      "learning_rate": 0.0002,
+      "loss": 1.388,
+      "mean_token_accuracy": 0.7190396279096604,
+      "step": 450
+    },
+    {
+      "epoch": 0.26400746108042183,
+      "grad_norm": 0.20384320616722107,
+      "learning_rate": 0.0002,
+      "loss": 1.2807,
+      "mean_token_accuracy": 0.7384566117078066,
+      "step": 460
+    },
+    {
+      "epoch": 0.2697467537126049,
+      "grad_norm": 0.2716342806816101,
+      "learning_rate": 0.0002,
+      "loss": 1.3157,
+      "mean_token_accuracy": 0.7307378999888897,
+      "step": 470
+    },
+    {
+      "epoch": 0.275486046344788,
+      "grad_norm": 0.2534655034542084,
+      "learning_rate": 0.0002,
+      "loss": 1.3959,
+      "mean_token_accuracy": 0.7178040158003569,
+      "step": 480
+    },
+    {
+      "epoch": 0.2812253389769711,
+      "grad_norm": 0.21825498342514038,
+      "learning_rate": 0.0002,
+      "loss": 1.387,
+      "mean_token_accuracy": 0.7204662635922432,
+      "step": 490
+    },
+    {
+      "epoch": 0.2869646316091542,
+      "grad_norm": 0.2534162402153015,
+      "learning_rate": 0.0002,
+      "loss": 1.2776,
+      "mean_token_accuracy": 0.7423365503549576,
+      "step": 500
+    },
+    {
+      "epoch": 0.2869646316091542,
+      "eval_loss": 1.3787877559661865,
+      "eval_mean_token_accuracy": 0.7194652643548437,
+      "eval_runtime": 7761.4408,
+      "eval_samples_per_second": 0.449,
+      "eval_steps_per_second": 0.225,
+      "step": 500
+    },
+    {
+      "epoch": 0.29270392424133723,
+      "grad_norm": 0.23998941481113434,
+      "learning_rate": 0.0002,
+      "loss": 1.2277,
+      "mean_token_accuracy": 0.7432656295597553,
+      "step": 510
+    },
+    {
+      "epoch": 0.2984432168735203,
+      "grad_norm": 0.23271049559116364,
+      "learning_rate": 0.0002,
+      "loss": 1.2776,
+      "mean_token_accuracy": 0.7337239418178797,
+      "step": 520
+    },
+    {
+      "epoch": 0.3041825095057034,
+      "grad_norm": 0.2755042016506195,
+      "learning_rate": 0.0002,
+      "loss": 1.4288,
+      "mean_token_accuracy": 0.7133219081908464,
+      "step": 530
+    },
+    {
+      "epoch": 0.3099218021378865,
+      "grad_norm": 0.21231453120708466,
+      "learning_rate": 0.0002,
+      "loss": 1.4229,
+      "mean_token_accuracy": 0.7119937628507614,
+      "step": 540
+    },
+    {
+      "epoch": 0.3156610947700696,
+      "grad_norm": 0.2159433215856552,
+      "learning_rate": 0.0002,
+      "loss": 1.3043,
+      "mean_token_accuracy": 0.7337923284620047,
+      "step": 550
+    },
+    {
+      "epoch": 0.3214003874022527,
+      "grad_norm": 0.238509863615036,
+      "learning_rate": 0.0002,
+      "loss": 1.3429,
+      "mean_token_accuracy": 0.7277234088629484,
+      "step": 560
+    },
+    {
+      "epoch": 0.3271396800344358,
+      "grad_norm": 0.27093520760536194,
+      "learning_rate": 0.0002,
+      "loss": 1.3089,
+      "mean_token_accuracy": 0.7319676581770181,
+      "step": 570
+    },
+    {
+      "epoch": 0.33287897266661887,
+      "grad_norm": 0.21662364900112152,
+      "learning_rate": 0.0002,
+      "loss": 1.3448,
+      "mean_token_accuracy": 0.72448665574193,
+      "step": 580
+    },
+    {
+      "epoch": 0.3386182652988019,
+      "grad_norm": 0.25919026136398315,
+      "learning_rate": 0.0002,
+      "loss": 1.3413,
+      "mean_token_accuracy": 0.7278214626014232,
+      "step": 590
+    },
+    {
+      "epoch": 0.344357557930985,
+      "grad_norm": 0.2097223550081253,
+      "learning_rate": 0.0002,
+      "loss": 1.3812,
+      "mean_token_accuracy": 0.7174393549561501,
+      "step": 600
+    },
+    {
+      "epoch": 0.344357557930985,
+      "eval_loss": 1.3745734691619873,
+      "eval_mean_token_accuracy": 0.7201109681998733,
+      "eval_runtime": 6592.6776,
+      "eval_samples_per_second": 0.529,
+      "eval_steps_per_second": 0.264,
+      "step": 600
+    },
+    {
+      "epoch": 0.3500968505631681,
+      "grad_norm": 0.27309486269950867,
+      "learning_rate": 0.0002,
+      "loss": 1.3764,
+      "mean_token_accuracy": 0.7236971091479063,
+      "step": 610
+    },
+    {
+      "epoch": 0.3558361431953512,
+      "grad_norm": 0.2800423204898834,
+      "learning_rate": 0.0002,
+      "loss": 1.4141,
+      "mean_token_accuracy": 0.7132530447095633,
+      "step": 620
+    },
+    {
+      "epoch": 0.36157543582753426,
+      "grad_norm": 0.32200849056243896,
+      "learning_rate": 0.0002,
+      "loss": 1.5291,
+      "mean_token_accuracy": 0.6955816943198443,
+      "step": 630
+    },
+    {
+      "epoch": 0.36731472845971735,
+      "grad_norm": 0.1762777417898178,
+      "learning_rate": 0.0002,
+      "loss": 1.2729,
+      "mean_token_accuracy": 0.7379875779151917,
+      "step": 640
+    },
+    {
+      "epoch": 0.37305402109190045,
+      "grad_norm": 0.27259498834609985,
+      "learning_rate": 0.0002,
+      "loss": 1.3315,
+      "mean_token_accuracy": 0.7254374325275421,
+      "step": 650
+    },
+    {
+      "epoch": 0.3787933137240835,
+      "grad_norm": 0.3148305118083954,
+      "learning_rate": 0.0002,
+      "loss": 1.4009,
+      "mean_token_accuracy": 0.7169190965592861,
+      "step": 660
+    },
+    {
+      "epoch": 0.38453260635626657,
+      "grad_norm": 0.2222924679517746,
+      "learning_rate": 0.0002,
+      "loss": 1.4422,
+      "mean_token_accuracy": 0.7057445451617241,
+      "step": 670
+    },
+    {
+      "epoch": 0.39027189898844966,
+      "grad_norm": 0.30782487988471985,
+      "learning_rate": 0.0002,
+      "loss": 1.3916,
+      "mean_token_accuracy": 0.7196735937148333,
+      "step": 680
+    },
+    {
+      "epoch": 0.39601119162063275,
+      "grad_norm": 0.24766255915164948,
+      "learning_rate": 0.0002,
+      "loss": 1.3191,
+      "mean_token_accuracy": 0.7313117351382971,
+      "step": 690
+    },
+    {
+      "epoch": 0.40175048425281584,
+      "grad_norm": 0.26929622888565063,
+      "learning_rate": 0.0002,
+      "loss": 1.3379,
+      "mean_token_accuracy": 0.7244091514497996,
+      "step": 700
+    },
+    {
+      "epoch": 0.40175048425281584,
+      "eval_loss": 1.370943307876587,
+      "eval_mean_token_accuracy": 0.720665924306649,
+      "eval_runtime": 4504.2557,
+      "eval_samples_per_second": 0.774,
+      "eval_steps_per_second": 0.387,
+      "step": 700
+    },
+    {
+      "epoch": 0.40748977688499893,
+      "grad_norm": 0.22724460065364838,
+      "learning_rate": 0.0002,
+      "loss": 1.3541,
+      "mean_token_accuracy": 0.7258114762604236,
+      "step": 710
+    },
+    {
+      "epoch": 0.413229069517182,
+      "grad_norm": 0.22957713901996613,
+      "learning_rate": 0.0002,
+      "loss": 1.3855,
+      "mean_token_accuracy": 0.7198538523167372,
+      "step": 720
+    },
+    {
+      "epoch": 0.4189683621493651,
+      "grad_norm": 0.23907890915870667,
+      "learning_rate": 0.0002,
+      "loss": 1.427,
+      "mean_token_accuracy": 0.7128315325826406,
+      "step": 730
+    },
+    {
+      "epoch": 0.42470765478154815,
+      "grad_norm": 0.2534020245075226,
+      "learning_rate": 0.0002,
+      "loss": 1.3615,
+      "mean_token_accuracy": 0.7198588822036982,
+      "step": 740
+    },
+    {
+      "epoch": 0.43044694741373124,
+      "grad_norm": 0.24605919420719147,
+      "learning_rate": 0.0002,
+      "loss": 1.3972,
+      "mean_token_accuracy": 0.7115087192505598,
+      "step": 750
+    },
+    {
+      "epoch": 0.43618624004591433,
+      "grad_norm": 0.2243734747171402,
+      "learning_rate": 0.0002,
+      "loss": 1.2523,
+      "mean_token_accuracy": 0.7429927971214056,
+      "step": 760
+    },
+    {
+      "epoch": 0.4419255326780974,
+      "grad_norm": 0.230802983045578,
+      "learning_rate": 0.0002,
+      "loss": 1.4611,
+      "mean_token_accuracy": 0.7064661320298911,
+      "step": 770
+    },
+    {
+      "epoch": 0.4476648253102805,
+      "grad_norm": 0.23596514761447906,
+      "learning_rate": 0.0002,
+      "loss": 1.3961,
+      "mean_token_accuracy": 0.7153716452419758,
+      "step": 780
+    },
+    {
+      "epoch": 0.4534041179424636,
+      "grad_norm": 0.29981374740600586,
+      "learning_rate": 0.0002,
+      "loss": 1.3467,
+      "mean_token_accuracy": 0.722964895889163,
+      "step": 790
+    },
+    {
+      "epoch": 0.4591434105746467,
+      "grad_norm": 0.25450626015663147,
+      "learning_rate": 0.0002,
+      "loss": 1.3928,
+      "mean_token_accuracy": 0.7192676767706871,
+      "step": 800
+    },
+    {
+      "epoch": 0.4591434105746467,
+      "eval_loss": 1.3700028657913208,
+      "eval_mean_token_accuracy": 0.720344717953647,
+      "eval_runtime": 5677.4803,
+      "eval_samples_per_second": 0.614,
+      "eval_steps_per_second": 0.307,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3484,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 3.3950907424144466e+18,
+  "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 sha256:8cc680829e5e25608d9770d527e351eb6315a34b36fbd9a50c1bb73dc9f064a5
+size 5624