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: unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit
+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 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|fc1|fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|fc1|fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_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 sha256:8952c53716b3e6c378709b8cd12b9ac961d097b87e9d8f6ed274c784ca374ee2
+size 203509368

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "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 %}"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9205a3f3b4e2e0bd2cff15357fa2a57160174581e64618310366349cffd07556
+size 82462068

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6fc5b16117008f259f41afb48f45f96dd31241d1a5f0c1619d6140c5ce7e89
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adaf1dfa61617159634e23ba894e13b4fc5a82405d7336c1449a41ac0ce672b8
+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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948c45c29a91dd2e6ae77d6f5a324a3d408bcca6ad443365b2e79986f1422771
+size 11420540

tokenizer_config.json

@@ -0,0 +1,148 @@
+{
+  "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
+    }
+  },
+  "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": {},
+  "max_length": null,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|vision_pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6812375816065853,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022707919386886176,
+      "grad_norm": 0.5527037382125854,
+      "learning_rate": 0.00019770114942528738,
+      "loss": 0.0749,
+      "step": 10
+    },
+    {
+      "epoch": 0.04541583877377235,
+      "grad_norm": 0.18355610966682434,
+      "learning_rate": 0.0001931034482758621,
+      "loss": 0.0973,
+      "step": 20
+    },
+    {
+      "epoch": 0.06812375816065853,
+      "grad_norm": 0.15812426805496216,
+      "learning_rate": 0.00018850574712643678,
+      "loss": 0.089,
+      "step": 30
+    },
+    {
+      "epoch": 0.0908316775475447,
+      "grad_norm": 0.19676333665847778,
+      "learning_rate": 0.0001839080459770115,
+      "loss": 0.0885,
+      "step": 40
+    },
+    {
+      "epoch": 0.11353959693443089,
+      "grad_norm": 0.23726195096969604,
+      "learning_rate": 0.0001793103448275862,
+      "loss": 0.0865,
+      "step": 50
+    },
+    {
+      "epoch": 0.11353959693443089,
+      "eval_loss": 0.09350696206092834,
+      "eval_runtime": 246.8339,
+      "eval_samples_per_second": 0.81,
+      "eval_steps_per_second": 0.81,
+      "step": 50
+    },
+    {
+      "epoch": 0.13624751632131707,
+      "grad_norm": 0.18502545356750488,
+      "learning_rate": 0.00017471264367816095,
+      "loss": 0.0823,
+      "step": 60
+    },
+    {
+      "epoch": 0.15895543570820322,
+      "grad_norm": 0.38577064871788025,
+      "learning_rate": 0.00017011494252873563,
+      "loss": 0.0813,
+      "step": 70
+    },
+    {
+      "epoch": 0.1816633550950894,
+      "grad_norm": 0.27274832129478455,
+      "learning_rate": 0.00016551724137931035,
+      "loss": 0.0887,
+      "step": 80
+    },
+    {
+      "epoch": 0.2043712744819756,
+      "grad_norm": 0.18888869881629944,
+      "learning_rate": 0.00016091954022988506,
+      "loss": 0.088,
+      "step": 90
+    },
+    {
+      "epoch": 0.22707919386886177,
+      "grad_norm": 0.19606022536754608,
+      "learning_rate": 0.0001563218390804598,
+      "loss": 0.0896,
+      "step": 100
+    },
+    {
+      "epoch": 0.22707919386886177,
+      "eval_loss": 0.09240507334470749,
+      "eval_runtime": 239.9776,
+      "eval_samples_per_second": 0.833,
+      "eval_steps_per_second": 0.833,
+      "step": 100
+    },
+    {
+      "epoch": 0.24978711325574796,
+      "grad_norm": 0.21395204961299896,
+      "learning_rate": 0.00015172413793103449,
+      "loss": 0.0782,
+      "step": 110
+    },
+    {
+      "epoch": 0.27249503264263414,
+      "grad_norm": 0.22302134335041046,
+      "learning_rate": 0.0001471264367816092,
+      "loss": 0.0794,
+      "step": 120
+    },
+    {
+      "epoch": 0.2952029520295203,
+      "grad_norm": 0.27699050307273865,
+      "learning_rate": 0.0001425287356321839,
+      "loss": 0.0802,
+      "step": 130
+    },
+    {
+      "epoch": 0.31791087141640645,
+      "grad_norm": 0.24119599163532257,
+      "learning_rate": 0.00013793103448275863,
+      "loss": 0.0829,
+      "step": 140
+    },
+    {
+      "epoch": 0.34061879080329266,
+      "grad_norm": 0.23131313920021057,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0796,
+      "step": 150
+    },
+    {
+      "epoch": 0.34061879080329266,
+      "eval_loss": 0.09314567595720291,
+      "eval_runtime": 243.4064,
+      "eval_samples_per_second": 0.822,
+      "eval_steps_per_second": 0.822,
+      "step": 150
+    },
+    {
+      "epoch": 0.3633267101901788,
+      "grad_norm": 0.311929851770401,
+      "learning_rate": 0.00012873563218390805,
+      "loss": 0.0783,
+      "step": 160
+    },
+    {
+      "epoch": 0.386034629577065,
+      "grad_norm": 0.2242027074098587,
+      "learning_rate": 0.00012413793103448277,
+      "loss": 0.0818,
+      "step": 170
+    },
+    {
+      "epoch": 0.4087425489639512,
+      "grad_norm": 0.2559347450733185,
+      "learning_rate": 0.00011954022988505748,
+      "loss": 0.0789,
+      "step": 180
+    },
+    {
+      "epoch": 0.43145046835083734,
+      "grad_norm": 0.23956073820590973,
+      "learning_rate": 0.00011494252873563218,
+      "loss": 0.0734,
+      "step": 190
+    },
+    {
+      "epoch": 0.45415838773772355,
+      "grad_norm": 0.290977418422699,
+      "learning_rate": 0.0001103448275862069,
+      "loss": 0.0753,
+      "step": 200
+    },
+    {
+      "epoch": 0.45415838773772355,
+      "eval_loss": 0.09412585943937302,
+      "eval_runtime": 243.3084,
+      "eval_samples_per_second": 0.822,
+      "eval_steps_per_second": 0.822,
+      "step": 200
+    },
+    {
+      "epoch": 0.4768663071246097,
+      "grad_norm": 0.37943148612976074,
+      "learning_rate": 0.00010574712643678162,
+      "loss": 0.0742,
+      "step": 210
+    },
+    {
+      "epoch": 0.4995742265114959,
+      "grad_norm": 0.25092101097106934,
+      "learning_rate": 0.00010114942528735633,
+      "loss": 0.0745,
+      "step": 220
+    },
+    {
+      "epoch": 0.5222821458983821,
+      "grad_norm": 0.27841272950172424,
+      "learning_rate": 9.655172413793105e-05,
+      "loss": 0.0732,
+      "step": 230
+    },
+    {
+      "epoch": 0.5449900652852683,
+      "grad_norm": 0.24122974276542664,
+      "learning_rate": 9.195402298850575e-05,
+      "loss": 0.0738,
+      "step": 240
+    },
+    {
+      "epoch": 0.5676979846721544,
+      "grad_norm": 0.33553385734558105,
+      "learning_rate": 8.735632183908047e-05,
+      "loss": 0.075,
+      "step": 250
+    },
+    {
+      "epoch": 0.5676979846721544,
+      "eval_loss": 0.08785887062549591,
+      "eval_runtime": 243.3288,
+      "eval_samples_per_second": 0.822,
+      "eval_steps_per_second": 0.822,
+      "step": 250
+    },
+    {
+      "epoch": 0.5904059040590406,
+      "grad_norm": 0.228590190410614,
+      "learning_rate": 8.275862068965517e-05,
+      "loss": 0.0743,
+      "step": 260
+    },
+    {
+      "epoch": 0.6131138234459268,
+      "grad_norm": 0.24921129643917084,
+      "learning_rate": 7.81609195402299e-05,
+      "loss": 0.075,
+      "step": 270
+    },
+    {
+      "epoch": 0.6358217428328129,
+      "grad_norm": 0.27115267515182495,
+      "learning_rate": 7.35632183908046e-05,
+      "loss": 0.0749,
+      "step": 280
+    },
+    {
+      "epoch": 0.6585296622196991,
+      "grad_norm": 0.1899242103099823,
+      "learning_rate": 6.896551724137931e-05,
+      "loss": 0.0705,
+      "step": 290
+    },
+    {
+      "epoch": 0.6812375816065853,
+      "grad_norm": 0.2068161964416504,
+      "learning_rate": 6.436781609195403e-05,
+      "loss": 0.0726,
+      "step": 300
+    },
+    {
+      "epoch": 0.6812375816065853,
+      "eval_loss": 0.08430539816617966,
+      "eval_runtime": 243.0981,
+      "eval_samples_per_second": 0.823,
+      "eval_steps_per_second": 0.823,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 7.261504929129062e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de0a8393eaffb97ac660136dcb9a631ae8d80949f4a6ece14cedff118ccd740
+size 5688