Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,208 @@
----
-license: apache-2.0
----
+---
+base_model: Qwen/Qwen2.5-VL-3B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-VL-3B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.17.1

adapter_config.json

@@ -0,0 +1,147 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/yuxuanzhao/LLaMA-Factory/models/qwen2_5-vl-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.13.mlp.down_proj",
+    "layers.23.mlp.down_proj",
+    "33.mlp.gate_proj",
+    "layers.21.mlp.down_proj",
+    "layers.22.mlp.down_proj",
+    "layers.9.mlp.up_proj",
+    "layers.26.mlp.down_proj",
+    "layers.29.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.7.mlp.down_proj",
+    "layers.2.mlp.gate_proj",
+    "35.mlp.up_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.5.mlp.down_proj",
+    "layers.3.mlp.down_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.12.mlp.down_proj",
+    "layers.15.mlp.down_proj",
+    "layers.11.mlp.down_proj",
+    "layers.28.mlp.gate_proj",
+    "layers.27.mlp.up_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.18.mlp.down_proj",
+    "layers.24.mlp.gate_proj",
+    "32.mlp.gate_proj",
+    "layers.16.mlp.up_proj",
+    "layers.10.mlp.down_proj",
+    "layers.26.mlp.up_proj",
+    "layers.19.mlp.down_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.14.mlp.up_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.10.mlp.up_proj",
+    "layers.30.mlp.gate_proj",
+    "35.mlp.down_proj",
+    "layers.20.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "layers.21.mlp.up_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.12.mlp.up_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.13.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.16.mlp.gate_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.27.mlp.down_proj",
+    "34.mlp.gate_proj",
+    "layers.8.mlp.up_proj",
+    "32.mlp.up_proj",
+    "layers.18.mlp.up_proj",
+    "33.mlp.up_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.3.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "34.mlp.up_proj",
+    "layers.6.mlp.up_proj",
+    "layers.31.mlp.up_proj",
+    "layers.28.mlp.down_proj",
+    "layers.11.mlp.up_proj",
+    "layers.0.mlp.up_proj",
+    "layers.15.mlp.up_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.14.mlp.down_proj",
+    "layers.9.mlp.gate_proj",
+    "layers.22.mlp.up_proj",
+    "v_proj",
+    "layers.24.mlp.up_proj",
+    "layers.4.mlp.up_proj",
+    "layers.2.mlp.up_proj",
+    "33.mlp.down_proj",
+    "layers.30.mlp.down_proj",
+    "layers.29.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "34.mlp.down_proj",
+    "layers.28.mlp.up_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.17.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.0.mlp.down_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.0.mlp.gate_proj",
+    "q_proj",
+    "layers.1.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.5.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "35.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.16.mlp.down_proj",
+    "layers.30.mlp.up_proj",
+    "layers.7.mlp.up_proj",
+    "layers.9.mlp.down_proj",
+    "layers.25.mlp.down_proj",
+    "layers.13.mlp.gate_proj",
+    "k_proj",
+    "layers.23.mlp.gate_proj",
+    "layers.29.mlp.gate_proj",
+    "layers.24.mlp.down_proj",
+    "layers.4.mlp.down_proj",
+    "layers.1.mlp.down_proj",
+    "layers.20.mlp.down_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.31.mlp.down_proj",
+    "32.mlp.down_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.31.mlp.gate_proj",
+    "layers.27.mlp.gate_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff247cbb9fdf23a9eecb994c1c6ce4cd1d69080db92df885a69e305073db5cb8
+size 59941192

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
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% 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
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f871d769cbe42789dfe16018074563315d44ce5ce3a6afced77aa5f11af82fd
+size 120166091

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f91f87bd9a92e8739289f46162ef308559319763234c64c5b77db9ec569f87f
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d39b8b541e3fd455fdaac992f8e531a8b6ecbd342d84bd34ce103caf8c4829
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff092a382271ec0416bca1eaebe1589a5c027148f661f515a99be89a41550e9
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee31a8654359133d1c40cfb2da8b7350b44cc7eec9bf923c997643420f7061d
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63383dd5028e58f51e4e2027ea0e53aeee54da342c712efa83354d47656d14be
+size 1465

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 +1,209 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1063 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1473,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00679001867255135,
+      "grad_norm": 1.8175065517425537,
+      "learning_rate": 6.081081081081082e-06,
+      "loss": 0.1857,
+      "step": 10
+    },
+    {
+      "epoch": 0.0135800373451027,
+      "grad_norm": 0.9356499910354614,
+      "learning_rate": 1.2837837837837838e-05,
+      "loss": 0.1512,
+      "step": 20
+    },
+    {
+      "epoch": 0.02037005601765405,
+      "grad_norm": 0.19530220329761505,
+      "learning_rate": 1.9594594594594595e-05,
+      "loss": 0.1038,
+      "step": 30
+    },
+    {
+      "epoch": 0.0271600746902054,
+      "grad_norm": 0.1939963847398758,
+      "learning_rate": 2.635135135135135e-05,
+      "loss": 0.082,
+      "step": 40
+    },
+    {
+      "epoch": 0.03395009336275675,
+      "grad_norm": 0.25467729568481445,
+      "learning_rate": 3.310810810810811e-05,
+      "loss": 0.0825,
+      "step": 50
+    },
+    {
+      "epoch": 0.0407401120353081,
+      "grad_norm": 0.24394609034061432,
+      "learning_rate": 3.986486486486487e-05,
+      "loss": 0.0841,
+      "step": 60
+    },
+    {
+      "epoch": 0.04753013070785945,
+      "grad_norm": 0.18351706862449646,
+      "learning_rate": 4.662162162162162e-05,
+      "loss": 0.0795,
+      "step": 70
+    },
+    {
+      "epoch": 0.0543201493804108,
+      "grad_norm": 0.20120970904827118,
+      "learning_rate": 5.337837837837838e-05,
+      "loss": 0.072,
+      "step": 80
+    },
+    {
+      "epoch": 0.06111016805296215,
+      "grad_norm": 0.30063867568969727,
+      "learning_rate": 6.013513513513514e-05,
+      "loss": 0.0752,
+      "step": 90
+    },
+    {
+      "epoch": 0.0679001867255135,
+      "grad_norm": 0.35980555415153503,
+      "learning_rate": 6.68918918918919e-05,
+      "loss": 0.0673,
+      "step": 100
+    },
+    {
+      "epoch": 0.07469020539806484,
+      "grad_norm": 0.37400639057159424,
+      "learning_rate": 7.364864864864865e-05,
+      "loss": 0.069,
+      "step": 110
+    },
+    {
+      "epoch": 0.0814802240706162,
+      "grad_norm": 0.27199000120162964,
+      "learning_rate": 8.040540540540541e-05,
+      "loss": 0.0601,
+      "step": 120
+    },
+    {
+      "epoch": 0.08827024274316754,
+      "grad_norm": 0.3759700655937195,
+      "learning_rate": 8.716216216216216e-05,
+      "loss": 0.0655,
+      "step": 130
+    },
+    {
+      "epoch": 0.0950602614157189,
+      "grad_norm": 0.4591917395591736,
+      "learning_rate": 9.391891891891892e-05,
+      "loss": 0.0461,
+      "step": 140
+    },
+    {
+      "epoch": 0.10185028008827024,
+      "grad_norm": 0.2534618675708771,
+      "learning_rate": 9.999985945746134e-05,
+      "loss": 0.0515,
+      "step": 150
+    },
+    {
+      "epoch": 0.1086402987608216,
+      "grad_norm": 0.23862995207309723,
+      "learning_rate": 9.998299530880787e-05,
+      "loss": 0.054,
+      "step": 160
+    },
+    {
+      "epoch": 0.11543031743337294,
+      "grad_norm": 0.3287966847419739,
+      "learning_rate": 9.993803351513094e-05,
+      "loss": 0.041,
+      "step": 170
+    },
+    {
+      "epoch": 0.1222203361059243,
+      "grad_norm": 0.3776935636997223,
+      "learning_rate": 9.986499935143679e-05,
+      "loss": 0.0355,
+      "step": 180
+    },
+    {
+      "epoch": 0.12901035477847564,
+      "grad_norm": 0.503021776676178,
+      "learning_rate": 9.976393387344834e-05,
+      "loss": 0.0417,
+      "step": 190
+    },
+    {
+      "epoch": 0.135800373451027,
+      "grad_norm": 0.27203965187072754,
+      "learning_rate": 9.963489389452596e-05,
+      "loss": 0.0312,
+      "step": 200
+    },
+    {
+      "epoch": 0.14259039212357835,
+      "grad_norm": 0.37624090909957886,
+      "learning_rate": 9.947795195373016e-05,
+      "loss": 0.0379,
+      "step": 210
+    },
+    {
+      "epoch": 0.14938041079612968,
+      "grad_norm": 0.45090368390083313,
+      "learning_rate": 9.92931962750442e-05,
+      "loss": 0.0354,
+      "step": 220
+    },
+    {
+      "epoch": 0.15617042946868104,
+      "grad_norm": 0.26543551683425903,
+      "learning_rate": 9.908073071777954e-05,
+      "loss": 0.0274,
+      "step": 230
+    },
+    {
+      "epoch": 0.1629604481412324,
+      "grad_norm": 0.5471091270446777,
+      "learning_rate": 9.884067471819184e-05,
+      "loss": 0.0226,
+      "step": 240
+    },
+    {
+      "epoch": 0.16975046681378375,
+      "grad_norm": 0.5838286876678467,
+      "learning_rate": 9.857316322234067e-05,
+      "loss": 0.0288,
+      "step": 250
+    },
+    {
+      "epoch": 0.17654048548633508,
+      "grad_norm": 0.16055133938789368,
+      "learning_rate": 9.827834661023034e-05,
+      "loss": 0.0262,
+      "step": 260
+    },
+    {
+      "epoch": 0.18333050415888644,
+      "grad_norm": 0.33942335844039917,
+      "learning_rate": 9.795639061127468e-05,
+      "loss": 0.0233,
+      "step": 270
+    },
+    {
+      "epoch": 0.1901205228314378,
+      "grad_norm": 0.5522304177284241,
+      "learning_rate": 9.760747621113325e-05,
+      "loss": 0.0168,
+      "step": 280
+    },
+    {
+      "epoch": 0.19691054150398912,
+      "grad_norm": 0.6882764101028442,
+      "learning_rate": 9.723179954997125e-05,
+      "loss": 0.0184,
+      "step": 290
+    },
+    {
+      "epoch": 0.20370056017654048,
+      "grad_norm": 0.30410072207450867,
+      "learning_rate": 9.682957181220062e-05,
+      "loss": 0.0203,
+      "step": 300
+    },
+    {
+      "epoch": 0.21049057884909184,
+      "grad_norm": 0.30174189805984497,
+      "learning_rate": 9.640101910776381e-05,
+      "loss": 0.0191,
+      "step": 310
+    },
+    {
+      "epoch": 0.2172805975216432,
+      "grad_norm": 0.14357490837574005,
+      "learning_rate": 9.594638234502753e-05,
+      "loss": 0.0268,
+      "step": 320
+    },
+    {
+      "epoch": 0.22407061619419452,
+      "grad_norm": 0.19478002190589905,
+      "learning_rate": 9.546591709535751e-05,
+      "loss": 0.0218,
+      "step": 330
+    },
+    {
+      "epoch": 0.23086063486674588,
+      "grad_norm": 0.22178731858730316,
+      "learning_rate": 9.495989344945056e-05,
+      "loss": 0.0121,
+      "step": 340
+    },
+    {
+      "epoch": 0.23765065353929724,
+      "grad_norm": 0.5312681794166565,
+      "learning_rate": 9.442859586550468e-05,
+      "loss": 0.0096,
+      "step": 350
+    },
+    {
+      "epoch": 0.2444406722118486,
+      "grad_norm": 0.43574365973472595,
+      "learning_rate": 9.387232300931255e-05,
+      "loss": 0.0129,
+      "step": 360
+    },
+    {
+      "epoch": 0.2512306908843999,
+      "grad_norm": 0.029588760808110237,
+      "learning_rate": 9.32913875863684e-05,
+      "loss": 0.0193,
+      "step": 370
+    },
+    {
+      "epoch": 0.2580207095569513,
+      "grad_norm": 0.41019147634506226,
+      "learning_rate": 9.268611616608236e-05,
+      "loss": 0.0143,
+      "step": 380
+    },
+    {
+      "epoch": 0.26481072822950263,
+      "grad_norm": 0.13079501688480377,
+      "learning_rate": 9.205684899820147e-05,
+      "loss": 0.0197,
+      "step": 390
+    },
+    {
+      "epoch": 0.271600746902054,
+      "grad_norm": 0.04413610324263573,
+      "learning_rate": 9.140393982154026e-05,
+      "loss": 0.0163,
+      "step": 400
+    },
+    {
+      "epoch": 0.27839076557460535,
+      "grad_norm": 0.33774223923683167,
+      "learning_rate": 9.072775566512863e-05,
+      "loss": 0.0126,
+      "step": 410
+    },
+    {
+      "epoch": 0.2851807842471567,
+      "grad_norm": 0.11442425101995468,
+      "learning_rate": 9.002867664188858e-05,
+      "loss": 0.0049,
+      "step": 420
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 0.24148213863372803,
+      "learning_rate": 8.930709573495602e-05,
+      "loss": 0.0061,
+      "step": 430
+    },
+    {
+      "epoch": 0.29876082159225936,
+      "grad_norm": 0.49706923961639404,
+      "learning_rate": 8.856341857676758e-05,
+      "loss": 0.0069,
+      "step": 440
+    },
+    {
+      "epoch": 0.3055508402648107,
+      "grad_norm": 0.8686341047286987,
+      "learning_rate": 8.779806322103682e-05,
+      "loss": 0.0056,
+      "step": 450
+    },
+    {
+      "epoch": 0.3123408589373621,
+      "grad_norm": 0.3294643461704254,
+      "learning_rate": 8.701145990774775e-05,
+      "loss": 0.0074,
+      "step": 460
+    },
+    {
+      "epoch": 0.31913087760991343,
+      "grad_norm": 0.14896813035011292,
+      "learning_rate": 8.620405082129798e-05,
+      "loss": 0.0098,
+      "step": 470
+    },
+    {
+      "epoch": 0.3259208962824648,
+      "grad_norm": 0.009663172997534275,
+      "learning_rate": 8.537628984192736e-05,
+      "loss": 0.0058,
+      "step": 480
+    },
+    {
+      "epoch": 0.33271091495501615,
+      "grad_norm": 0.03118247166275978,
+      "learning_rate": 8.452864229057191e-05,
+      "loss": 0.0066,
+      "step": 490
+    },
+    {
+      "epoch": 0.3395009336275675,
+      "grad_norm": 0.2592410743236542,
+      "learning_rate": 8.366158466728644e-05,
+      "loss": 0.0038,
+      "step": 500
+    },
+    {
+      "epoch": 0.3462909523001188,
+      "grad_norm": 0.006336142774671316,
+      "learning_rate": 8.277560438338278e-05,
+      "loss": 0.0063,
+      "step": 510
+    },
+    {
+      "epoch": 0.35308097097267016,
+      "grad_norm": 0.9991777539253235,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 0.008,
+      "step": 520
+    },
+    {
+      "epoch": 0.3598709896452215,
+      "grad_norm": 0.03354354575276375,
+      "learning_rate": 8.094887838530174e-05,
+      "loss": 0.0023,
+      "step": 530
+    },
+    {
+      "epoch": 0.3666610083177729,
+      "grad_norm": 0.1517736166715622,
+      "learning_rate": 8.000915955433396e-05,
+      "loss": 0.0072,
+      "step": 540
+    },
+    {
+      "epoch": 0.37345102699032423,
+      "grad_norm": 0.3716999888420105,
+      "learning_rate": 7.905257125191094e-05,
+      "loss": 0.0072,
+      "step": 550
+    },
+    {
+      "epoch": 0.3802410456628756,
+      "grad_norm": 0.15485776960849762,
+      "learning_rate": 7.807965121848597e-05,
+      "loss": 0.0061,
+      "step": 560
+    },
+    {
+      "epoch": 0.38703106433542694,
+      "grad_norm": 0.015828760340809822,
+      "learning_rate": 7.70909463752983e-05,
+      "loss": 0.0031,
+      "step": 570
+    },
+    {
+      "epoch": 0.39382108300797825,
+      "grad_norm": 0.472591370344162,
+      "learning_rate": 7.608701251692457e-05,
+      "loss": 0.0061,
+      "step": 580
+    },
+    {
+      "epoch": 0.4006111016805296,
+      "grad_norm": 0.49039226770401,
+      "learning_rate": 7.506841399884217e-05,
+      "loss": 0.0032,
+      "step": 590
+    },
+    {
+      "epoch": 0.40740112035308096,
+      "grad_norm": 0.013108485378324986,
+      "learning_rate": 7.403572342018021e-05,
+      "loss": 0.0083,
+      "step": 600
+    },
+    {
+      "epoch": 0.4141911390256323,
+      "grad_norm": 0.014069960452616215,
+      "learning_rate": 7.29895213018362e-05,
+      "loss": 0.0076,
+      "step": 610
+    },
+    {
+      "epoch": 0.4209811576981837,
+      "grad_norm": 0.016907596960663795,
+      "learning_rate": 7.193039576013976e-05,
+      "loss": 0.0035,
+      "step": 620
+    },
+    {
+      "epoch": 0.42777117637073503,
+      "grad_norm": 0.02205067314207554,
+      "learning_rate": 7.085894217624645e-05,
+      "loss": 0.0035,
+      "step": 630
+    },
+    {
+      "epoch": 0.4345611950432864,
+      "grad_norm": 0.0153163131326437,
+      "learning_rate": 6.977576286144784e-05,
+      "loss": 0.0008,
+      "step": 640
+    },
+    {
+      "epoch": 0.44135121371583774,
+      "grad_norm": 0.0036254250444471836,
+      "learning_rate": 6.868146671858567e-05,
+      "loss": 0.0061,
+      "step": 650
+    },
+    {
+      "epoch": 0.44814123238838904,
+      "grad_norm": 0.026128802448511124,
+      "learning_rate": 6.757666889976085e-05,
+      "loss": 0.0004,
+      "step": 660
+    },
+    {
+      "epoch": 0.4549312510609404,
+      "grad_norm": 0.009841466322541237,
+      "learning_rate": 6.646199046052921e-05,
+      "loss": 0.0054,
+      "step": 670
+    },
+    {
+      "epoch": 0.46172126973349176,
+      "grad_norm": 0.1286161094903946,
+      "learning_rate": 6.533805801077899e-05,
+      "loss": 0.0083,
+      "step": 680
+    },
+    {
+      "epoch": 0.4685112884060431,
+      "grad_norm": 0.1420389711856842,
+      "learning_rate": 6.420550336248558e-05,
+      "loss": 0.0011,
+      "step": 690
+    },
+    {
+      "epoch": 0.47530130707859447,
+      "grad_norm": 0.019207162782549858,
+      "learning_rate": 6.306496317454227e-05,
+      "loss": 0.0014,
+      "step": 700
+    },
+    {
+      "epoch": 0.4820913257511458,
+      "grad_norm": 0.02628934569656849,
+      "learning_rate": 6.191707859486622e-05,
+      "loss": 0.0071,
+      "step": 710
+    },
+    {
+      "epoch": 0.4888813444236972,
+      "grad_norm": 0.07600024342536926,
+      "learning_rate": 6.076249489998097e-05,
+      "loss": 0.0007,
+      "step": 720
+    },
+    {
+      "epoch": 0.49567136309624854,
+      "grad_norm": 0.057020459324121475,
+      "learning_rate": 5.9601861132278e-05,
+      "loss": 0.0029,
+      "step": 730
+    },
+    {
+      "epoch": 0.5024613817687998,
+      "grad_norm": 0.18588444590568542,
+      "learning_rate": 5.8435829735161416e-05,
+      "loss": 0.0015,
+      "step": 740
+    },
+    {
+      "epoch": 0.5092514004413512,
+      "grad_norm": 0.08587218075990677,
+      "learning_rate": 5.7265056186280754e-05,
+      "loss": 0.0064,
+      "step": 750
+    },
+    {
+      "epoch": 0.5160414191139026,
+      "grad_norm": 0.027101216837763786,
+      "learning_rate": 5.6090198629058134e-05,
+      "loss": 0.0002,
+      "step": 760
+    },
+    {
+      "epoch": 0.5228314377864539,
+      "grad_norm": 0.008036206476390362,
+      "learning_rate": 5.491191750271677e-05,
+      "loss": 0.0096,
+      "step": 770
+    },
+    {
+      "epoch": 0.5296214564590053,
+      "grad_norm": 0.02794210985302925,
+      "learning_rate": 5.373087517101899e-05,
+      "loss": 0.0005,
+      "step": 780
+    },
+    {
+      "epoch": 0.5364114751315566,
+      "grad_norm": 0.015519050881266594,
+      "learning_rate": 5.254773554992242e-05,
+      "loss": 0.0012,
+      "step": 790
+    },
+    {
+      "epoch": 0.543201493804108,
+      "grad_norm": 0.5680004954338074,
+      "learning_rate": 5.136316373436343e-05,
+      "loss": 0.0011,
+      "step": 800
+    },
+    {
+      "epoch": 0.5499915124766593,
+      "grad_norm": 0.01568940281867981,
+      "learning_rate": 5.0177825624378114e-05,
+      "loss": 0.0006,
+      "step": 810
+    },
+    {
+      "epoch": 0.5567815311492107,
+      "grad_norm": 0.15695148706436157,
+      "learning_rate": 4.8992387550770373e-05,
+      "loss": 0.0064,
+      "step": 820
+    },
+    {
+      "epoch": 0.563571549821762,
+      "grad_norm": 0.24050813913345337,
+      "learning_rate": 4.780751590053813e-05,
+      "loss": 0.0054,
+      "step": 830
+    },
+    {
+      "epoch": 0.5703615684943134,
+      "grad_norm": 0.008626952767372131,
+      "learning_rate": 4.662387674226771e-05,
+      "loss": 0.0032,
+      "step": 840
+    },
+    {
+      "epoch": 0.5771515871668647,
+      "grad_norm": 0.007616691756993532,
+      "learning_rate": 4.544213545170741e-05,
+      "loss": 0.0039,
+      "step": 850
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 0.014656963758170605,
+      "learning_rate": 4.4262956337730385e-05,
+      "loss": 0.0012,
+      "step": 860
+    },
+    {
+      "epoch": 0.5907316245119674,
+      "grad_norm": 0.2970845401287079,
+      "learning_rate": 4.3087002268897434e-05,
+      "loss": 0.0011,
+      "step": 870
+    },
+    {
+      "epoch": 0.5975216431845187,
+      "grad_norm": 0.010836818255484104,
+      "learning_rate": 4.191493430082929e-05,
+      "loss": 0.0059,
+      "step": 880
+    },
+    {
+      "epoch": 0.6043116618570701,
+      "grad_norm": 0.016124485060572624,
+      "learning_rate": 4.074741130459813e-05,
+      "loss": 0.0051,
+      "step": 890
+    },
+    {
+      "epoch": 0.6111016805296214,
+      "grad_norm": 0.008550368249416351,
+      "learning_rate": 3.9585089596347094e-05,
+      "loss": 0.0006,
+      "step": 900
+    },
+    {
+      "epoch": 0.6178916992021728,
+      "grad_norm": 0.007996040396392345,
+      "learning_rate": 3.842862256834613e-05,
+      "loss": 0.0013,
+      "step": 910
+    },
+    {
+      "epoch": 0.6246817178747242,
+      "grad_norm": 0.01987188495695591,
+      "learning_rate": 3.727866032169127e-05,
+      "loss": 0.002,
+      "step": 920
+    },
+    {
+      "epoch": 0.6314717365472755,
+      "grad_norm": 0.006365388166159391,
+      "learning_rate": 3.6135849300854225e-05,
+      "loss": 0.0003,
+      "step": 930
+    },
+    {
+      "epoch": 0.6382617552198269,
+      "grad_norm": 0.029804030433297157,
+      "learning_rate": 3.500083193028741e-05,
+      "loss": 0.0052,
+      "step": 940
+    },
+    {
+      "epoch": 0.6450517738923782,
+      "grad_norm": 0.009540177881717682,
+      "learning_rate": 3.387424625328892e-05,
+      "loss": 0.0004,
+      "step": 950
+    },
+    {
+      "epoch": 0.6518417925649296,
+      "grad_norm": 0.007210243493318558,
+      "learning_rate": 3.275672557333015e-05,
+      "loss": 0.0038,
+      "step": 960
+    },
+    {
+      "epoch": 0.6586318112374809,
+      "grad_norm": 0.024687010794878006,
+      "learning_rate": 3.164889809804808e-05,
+      "loss": 0.0022,
+      "step": 970
+    },
+    {
+      "epoch": 0.6654218299100323,
+      "grad_norm": 0.005847941618412733,
+      "learning_rate": 3.055138658610202e-05,
+      "loss": 0.0035,
+      "step": 980
+    },
+    {
+      "epoch": 0.6722118485825836,
+      "grad_norm": 0.005948640406131744,
+      "learning_rate": 2.946480799709358e-05,
+      "loss": 0.0015,
+      "step": 990
+    },
+    {
+      "epoch": 0.679001867255135,
+      "grad_norm": 0.018232271075248718,
+      "learning_rate": 2.83897731447464e-05,
+      "loss": 0.0056,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6857918859276863,
+      "grad_norm": 0.4337656795978546,
+      "learning_rate": 2.7326886353540916e-05,
+      "loss": 0.0027,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6925819046002376,
+      "grad_norm": 0.4810737371444702,
+      "learning_rate": 2.627674511899678e-05,
+      "loss": 0.0042,
+      "step": 1020
+    },
+    {
+      "epoch": 0.699371923272789,
+      "grad_norm": 0.024683628231287003,
+      "learning_rate": 2.5239939771794563e-05,
+      "loss": 0.0006,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7061619419453403,
+      "grad_norm": 0.3206782639026642,
+      "learning_rate": 2.421705314592452e-05,
+      "loss": 0.0038,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7129519606178917,
+      "grad_norm": 0.194807767868042,
+      "learning_rate": 2.3208660251050158e-05,
+      "loss": 0.0012,
+      "step": 1050
+    },
+    {
+      "epoch": 0.719741979290443,
+      "grad_norm": 0.009538485668599606,
+      "learning_rate": 2.2215327949269886e-05,
+      "loss": 0.0004,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7265319979629944,
+      "grad_norm": 0.00484565319493413,
+      "learning_rate": 2.123761463645878e-05,
+      "loss": 0.0003,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7333220166355457,
+      "grad_norm": 0.0036626686342060566,
+      "learning_rate": 2.0276069928369746e-05,
+      "loss": 0.0002,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7401120353080971,
+      "grad_norm": 0.006346094887703657,
+      "learning_rate": 1.933123435167018e-05,
+      "loss": 0.0008,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7469020539806485,
+      "grad_norm": 0.0050748297944664955,
+      "learning_rate": 1.840363904008819e-05,
+      "loss": 0.0002,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7536920726531998,
+      "grad_norm": 0.0035511874593794346,
+      "learning_rate": 1.7493805435838874e-05,
+      "loss": 0.0002,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7604820913257512,
+      "grad_norm": 0.01719609834253788,
+      "learning_rate": 1.660224499649861e-05,
+      "loss": 0.0012,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7672721099983025,
+      "grad_norm": 0.5908659100532532,
+      "learning_rate": 1.5729458907492327e-05,
+      "loss": 0.0021,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7740621286708539,
+      "grad_norm": 0.0023723470512777567,
+      "learning_rate": 1.4875937800354988e-05,
+      "loss": 0.0002,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7808521473434052,
+      "grad_norm": 0.003473122837021947,
+      "learning_rate": 1.404216147692598e-05,
+      "loss": 0.0001,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7876421660159565,
+      "grad_norm": 0.0032885069958865643,
+      "learning_rate": 1.3228598639631418e-05,
+      "loss": 0.0046,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7944321846885078,
+      "grad_norm": 0.004905693233013153,
+      "learning_rate": 1.2435706628005767e-05,
+      "loss": 0.0016,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8012222033610592,
+      "grad_norm": 0.0058155064471066,
+      "learning_rate": 1.1663931161601188e-05,
+      "loss": 0.0027,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8080122220336106,
+      "grad_norm": 0.007166674826294184,
+      "learning_rate": 1.0913706089428932e-05,
+      "loss": 0.003,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8148022407061619,
+      "grad_norm": 0.002422675024718046,
+      "learning_rate": 1.0185453146073604e-05,
+      "loss": 0.0002,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8215922593787133,
+      "grad_norm": 0.5606914758682251,
+      "learning_rate": 9.479581714617668e-06,
+      "loss": 0.0043,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8283822780512646,
+      "grad_norm": 0.018740450963377953,
+      "learning_rate": 8.796488596509133e-06,
+      "loss": 0.0011,
+      "step": 1220
+    },
+    {
+      "epoch": 0.835172296723816,
+      "grad_norm": 0.0064006103202700615,
+      "learning_rate": 8.136557788501903e-06,
+      "loss": 0.0023,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8419623153963673,
+      "grad_norm": 0.01389048807322979,
+      "learning_rate": 7.500160266794371e-06,
+      "loss": 0.0003,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8487523340689187,
+      "grad_norm": 0.0191491711884737,
+      "learning_rate": 6.887653778487307e-06,
+      "loss": 0.0037,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8555423527414701,
+      "grad_norm": 0.010205433703958988,
+      "learning_rate": 6.2993826404783965e-06,
+      "loss": 0.0004,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8623323714140214,
+      "grad_norm": 0.005938360001891851,
+      "learning_rate": 5.735677545906626e-06,
+      "loss": 0.0002,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8691223900865728,
+      "grad_norm": 0.42641371488571167,
+      "learning_rate": 5.196855378254989e-06,
+      "loss": 0.0019,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 0.008787781931459904,
+      "learning_rate": 4.683219033216402e-06,
+      "loss": 0.0006,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8827024274316755,
+      "grad_norm": 0.001734372926875949,
+      "learning_rate": 4.1950572484226345e-06,
+      "loss": 0.0002,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8894924461042268,
+      "grad_norm": 0.13424113392829895,
+      "learning_rate": 3.7326444411321547e-06,
+      "loss": 0.0003,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8962824647767781,
+      "grad_norm": 0.0027601660694926977,
+      "learning_rate": 3.2962405539681217e-06,
+      "loss": 0.0002,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9030724834493294,
+      "grad_norm": 0.011034502647817135,
+      "learning_rate": 2.8860909087931543e-06,
+      "loss": 0.0002,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9098625021218808,
+      "grad_norm": 0.00510817626491189,
+      "learning_rate": 2.5024260688030987e-06,
+      "loss": 0.0002,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9166525207944322,
+      "grad_norm": 0.006623192224651575,
+      "learning_rate": 2.145461708917312e-06,
+      "loss": 0.0019,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9234425394669835,
+      "grad_norm": 0.008591300807893276,
+      "learning_rate": 1.8153984945382452e-06,
+      "loss": 0.0002,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.0064789485186338425,
+      "learning_rate": 1.512421968748623e-06,
+      "loss": 0.0006,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9370225768120862,
+      "grad_norm": 0.009375182911753654,
+      "learning_rate": 1.2367024480094691e-06,
+      "loss": 0.0026,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9438125954846376,
+      "grad_norm": 0.005188928451389074,
+      "learning_rate": 9.883949264176962e-07,
+      "loss": 0.0003,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9506026141571889,
+      "grad_norm": 0.006225943099707365,
+      "learning_rate": 7.676389885771518e-07,
+      "loss": 0.0015,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9573926328297403,
+      "grad_norm": 0.0153355086222291,
+      "learning_rate": 5.745587311318968e-07,
+      "loss": 0.0002,
+      "step": 1410
+    },
+    {
+      "epoch": 0.9641826515022917,
+      "grad_norm": 0.0042914156801998615,
+      "learning_rate": 4.0926269300603503e-07,
+      "loss": 0.0002,
+      "step": 1420
+    },
+    {
+      "epoch": 0.970972670174843,
+      "grad_norm": 0.011045188643038273,
+      "learning_rate": 2.71843794389226e-07,
+      "loss": 0.0002,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9777626888473944,
+      "grad_norm": 0.00516318716108799,
+      "learning_rate": 1.623792845020955e-07,
+      "loss": 0.0004,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9845527075199457,
+      "grad_norm": 0.008642218075692654,
+      "learning_rate": 8.093069817109445e-08,
+      "loss": 0.0002,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9913427261924971,
+      "grad_norm": 0.010795416310429573,
+      "learning_rate": 2.7543821237030475e-08,
+      "loss": 0.0002,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9981327448650483,
+      "grad_norm": 0.012065191753208637,
+      "learning_rate": 2.2486648168396075e-09,
+      "loss": 0.0002,
+      "step": 1470
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1473,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.075096721816289e+17,
+  "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 sha256:17719d1b14903d81189f39541b2d7229940ecfa9522af7547e1b56e13a59ac6c
+size 6225

video_preprocessor_config.json

@@ -0,0 +1,44 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}