second model upload

.gitattributes

@@ -33,3 +33,6 @@ 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
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2-VL-7B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2vl_lora_16lr_7b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2vl_lora_16lr_7b
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) on the talk2car dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 5
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 10
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 25.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:k_proj|down_proj|v_proj|gate_proj|q_proj|up_proj|o_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 sha256:0966f4b2c6bda2ee9b2ce90fd34eebe05a397d8f376c839e336e39c3668148b2
+size 161533192

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 25.0,
+    "total_flos": 2.502555032784732e+17,
+    "train_loss": 0.12197050291108899,
+    "train_runtime": 13777.8614,
+    "train_samples_per_second": 0.907,
+    "train_steps_per_second": 0.091
+}

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 %}"
+}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-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 0.12.0

checkpoint-1000/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:k_proj|down_proj|v_proj|gate_proj|q_proj|up_proj|o_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc79efd5051870b5d616027eb4bf67a11d74ad439757f2ddb5b6169996876271
+size 161533192

checkpoint-1000/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
+}

checkpoint-1000/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 %}"
+}

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3571ff77b1ef5bec44089fef37f6ea566ee34d1e25a9e67f4b847b05662f2eba
+size 323291242

checkpoint-1000/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": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33051b9eb3114c963021f9df60752af83921fd52e5809bd85ce27e94f9d0d9ad
+size 14512

checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bccd7c24723c07f97d24e82405612113d129d077233ca61366b6299d4233c2d
+size 14512

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6fa2d0e3665a58927dbcc6644a1bcfe42a508e029d8b8762c092ea754b45a6
+size 1064

checkpoint-1000/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
+  }
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.459547519683838,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.2185,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5558891296386719,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.892,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5772704482078552,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.7887,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.40292349457740784,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.7111,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.35770532488822937,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6489,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.43718403577804565,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.5936,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.4591154158115387,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.6121,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6591519713401794,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.6059,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6931334733963013,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.6062,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6464695334434509,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.5929,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.7549647688865662,
+      "learning_rate": 1.76e-05,
+      "loss": 0.5138,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6728184819221497,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.4737,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7162397503852844,
+      "learning_rate": 1.9999025240093045e-05,
+      "loss": 0.4891,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.9795845150947571,
+      "learning_rate": 1.9991228300988586e-05,
+      "loss": 0.4663,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6311202049255371,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.5164,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.9567041993141174,
+      "learning_rate": 1.9952273999818312e-05,
+      "loss": 0.3981,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.8767746090888977,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.3761,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.8661500215530396,
+      "learning_rate": 1.988228381446553e-05,
+      "loss": 0.374,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.7793363332748413,
+      "learning_rate": 1.983571470813386e-05,
+      "loss": 0.3908,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8413230180740356,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.3527,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 1.5790411233901978,
+      "learning_rate": 1.9719610005785466e-05,
+      "loss": 0.2756,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.1819688081741333,
+      "learning_rate": 1.9650164944723116e-05,
+      "loss": 0.2622,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 1.2115598917007446,
+      "learning_rate": 1.9573194975320672e-05,
+      "loss": 0.2475,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.0625479221343994,
+      "learning_rate": 1.9488760116444966e-05,
+      "loss": 0.2682,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2376039028167725,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2514,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.6343020796775818,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.1448,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 1.1657440662384033,
+      "learning_rate": 1.9191353392552346e-05,
+      "loss": 0.1725,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.4713112115859985,
+      "learning_rate": 1.907777478532909e-05,
+      "loss": 0.1753,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 1.9010937213897705,
+      "learning_rate": 1.895711760239413e-05,
+      "loss": 0.1697,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.2462244033813477,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.157,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 1.5734026432037354,
+      "learning_rate": 1.869494929505219e-05,
+      "loss": 0.0987,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.6871922016143799,
+      "learning_rate": 1.855364260160507e-05,
+      "loss": 0.1122,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 0.8505676984786987,
+      "learning_rate": 1.8405666034956842e-05,
+      "loss": 0.0999,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 1.9714100360870361,
+      "learning_rate": 1.8251134982782952e-05,
+      "loss": 0.0925,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.3289463520050049,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.1034,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 1.7757859230041504,
+      "learning_rate": 1.792289643355191e-05,
+      "loss": 0.0538,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 1.5128904581069946,
+      "learning_rate": 1.7749444887041797e-05,
+      "loss": 0.0562,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 1.7095279693603516,
+      "learning_rate": 1.7569950556517566e-05,
+      "loss": 0.0656,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 1.7054250240325928,
+      "learning_rate": 1.7384553406258842e-05,
+      "loss": 0.0783,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.2087674140930176,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.0832,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 1.2171767950057983,
+      "learning_rate": 1.6996633405133656e-05,
+      "loss": 0.0389,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 1.2036916017532349,
+      "learning_rate": 1.6794413042615168e-05,
+      "loss": 0.0456,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 1.6378772258758545,
+      "learning_rate": 1.6586894601186804e-05,
+      "loss": 0.0539,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.062146544456482,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.0351,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7032294273376465,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.0331,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 1.2708150148391724,
+      "learning_rate": 1.5934188866037017e-05,
+      "loss": 0.0298,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 0.5238479375839233,
+      "learning_rate": 1.570713567684432e-05,
+      "loss": 0.0271,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.6896675229072571,
+      "learning_rate": 1.5475632234925505e-05,
+      "loss": 0.0148,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.8893882632255554,
+      "learning_rate": 1.5239859059700794e-05,
+      "loss": 0.0384,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.3057194948196411,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0216,
+      "step": 500
+    },
+    {
+      "epoch": 10.2,
+      "grad_norm": 0.4277481436729431,
+      "learning_rate": 1.4756242090702756e-05,
+      "loss": 0.0186,
+      "step": 510
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 2.500697374343872,
+      "learning_rate": 1.4508775406894308e-05,
+      "loss": 0.0289,
+      "step": 520
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 0.4189341366291046,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.0161,
+      "step": 530
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.6834658980369568,
+      "learning_rate": 1.4003490325568953e-05,
+      "loss": 0.016,
+      "step": 540
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.32209300994873047,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.0214,
+      "step": 550
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.6142628788948059,
+      "learning_rate": 1.3485720473218153e-05,
+      "loss": 0.0169,
+      "step": 560
+    },
+    {
+      "epoch": 11.4,
+      "grad_norm": 0.020493434742093086,
+      "learning_rate": 1.3222656952305113e-05,
+      "loss": 0.0072,
+      "step": 570
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.6618867516517639,
+      "learning_rate": 1.2957080500440469e-05,
+      "loss": 0.0134,
+      "step": 580
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 2.014190196990967,
+      "learning_rate": 1.2689198206152657e-05,
+      "loss": 0.0141,
+      "step": 590
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.3526052236557007,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.0152,
+      "step": 600
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 0.39659520983695984,
+      "learning_rate": 1.2147353271670634e-05,
+      "loss": 0.0082,
+      "step": 610
+    },
+    {
+      "epoch": 12.4,
+      "grad_norm": 1.6676621437072754,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.0086,
+      "step": 620
+    },
+    {
+      "epoch": 12.6,
+      "grad_norm": 0.48944175243377686,
+      "learning_rate": 1.159881187691835e-05,
+      "loss": 0.0073,
+      "step": 630
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.11040916293859482,
+      "learning_rate": 1.1322563902571227e-05,
+      "loss": 0.0111,
+      "step": 640
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.19332852959632874,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0084,
+      "step": 650
+    },
+    {
+      "epoch": 13.2,
+      "grad_norm": 0.5781747698783875,
+      "learning_rate": 1.0767190281268187e-05,
+      "loss": 0.0088,
+      "step": 660
+    },
+    {
+      "epoch": 13.4,
+      "grad_norm": 0.5372014045715332,
+      "learning_rate": 1.0488497697956134e-05,
+      "loss": 0.0129,
+      "step": 670
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 0.0674474835395813,
+      "learning_rate": 1.0209424198833571e-05,
+      "loss": 0.0047,
+      "step": 680
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.0646585077047348,
+      "learning_rate": 9.930187397020385e-06,
+      "loss": 0.0079,
+      "step": 690
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.16117724776268005,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0137,
+      "step": 700
+    },
+    {
+      "epoch": 14.2,
+      "grad_norm": 0.031529657542705536,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.0195,
+      "step": 710
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 0.7396082878112793,
+      "learning_rate": 9.093674198022201e-06,
+      "loss": 0.0038,
+      "step": 720
+    },
+    {
+      "epoch": 14.6,
+      "grad_norm": 0.131903737783432,
+      "learning_rate": 8.815960316934991e-06,
+      "loss": 0.009,
+      "step": 730
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 0.031985681504011154,
+      "learning_rate": 8.539169714375885e-06,
+      "loss": 0.0013,
+      "step": 740
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.12234848737716675,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0043,
+      "step": 750
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.10590848326683044,
+      "learning_rate": 7.989220788540356e-06,
+      "loss": 0.0016,
+      "step": 760
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 0.20384103059768677,
+      "learning_rate": 7.716491298893443e-06,
+      "loss": 0.0011,
+      "step": 770
+    },
+    {
+      "epoch": 15.6,
+      "grad_norm": 0.16497106850147247,
+      "learning_rate": 7.445542420642097e-06,
+      "loss": 0.002,
+      "step": 780
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 0.0461721308529377,
+      "learning_rate": 7.176585431571235e-06,
+      "loss": 0.0017,
+      "step": 790
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.023166760802268982,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0008,
+      "step": 800
+    },
+    {
+      "epoch": 16.2,
+      "grad_norm": 0.032082173973321915,
+      "learning_rate": 6.645484302497452e-06,
+      "loss": 0.0003,
+      "step": 810
+    },
+    {
+      "epoch": 16.4,
+      "grad_norm": 0.08265218138694763,
+      "learning_rate": 6.383754299179079e-06,
+      "loss": 0.0007,
+      "step": 820
+    },
+    {
+      "epoch": 16.6,
+      "grad_norm": 0.024636510759592056,
+      "learning_rate": 6.124844135478971e-06,
+      "loss": 0.005,
+      "step": 830
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.019458631053566933,
+      "learning_rate": 5.868955701754584e-06,
+      "loss": 0.0004,
+      "step": 840
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.01352341752499342,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0007,
+      "step": 850
+    },
+    {
+      "epoch": 17.2,
+      "grad_norm": 0.009102717973291874,
+      "learning_rate": 5.367039648801386e-06,
+      "loss": 0.0004,
+      "step": 860
+    },
+    {
+      "epoch": 17.4,
+      "grad_norm": 0.01286560669541359,
+      "learning_rate": 5.121403408612672e-06,
+      "loss": 0.0002,
+      "step": 870
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 0.36686578392982483,
+      "learning_rate": 4.879571351294287e-06,
+      "loss": 0.0007,
+      "step": 880
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.005845635663717985,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.0002,
+      "step": 890
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.06807386130094528,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0002,
+      "step": 900
+    },
+    {
+      "epoch": 18.2,
+      "grad_norm": 0.02204430289566517,
+      "learning_rate": 4.178770298427107e-06,
+      "loss": 0.0001,
+      "step": 910
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 0.008754129521548748,
+      "learning_rate": 3.954008851376252e-06,
+      "loss": 0.0001,
+      "step": 920
+    },
+    {
+      "epoch": 18.6,
+      "grad_norm": 0.00636293226853013,
+      "learning_rate": 3.7339618863553983e-06,
+      "loss": 0.0001,
+      "step": 930
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 0.004866347182542086,
+      "learning_rate": 3.5188009893686916e-06,
+      "loss": 0.0006,
+      "step": 940
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.004850468598306179,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0001,
+      "step": 950
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 0.0016120151849463582,
+      "learning_rate": 3.103804562643302e-06,
+      "loss": 0.0001,
+      "step": 960
+    },
+    {
+      "epoch": 19.4,
+      "grad_norm": 0.08115795254707336,
+      "learning_rate": 2.9042926346347932e-06,
+      "loss": 0.0002,
+      "step": 970
+    },
+    {
+      "epoch": 19.6,
+      "grad_norm": 0.0031273579224944115,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.0001,
+      "step": 980
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 0.005434623919427395,
+      "learning_rate": 2.522019095014683e-06,
+      "loss": 0.0001,
+      "step": 990
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.003434584243223071,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0003,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.001973013506949e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b461a8fd57f9dccc64796c48a45854cf5baf5b869fda0d17af67a1a0382daa8
+size 5560

checkpoint-1250/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-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 0.12.0

checkpoint-1250/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:k_proj|down_proj|v_proj|gate_proj|q_proj|up_proj|o_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0966f4b2c6bda2ee9b2ce90fd34eebe05a397d8f376c839e336e39c3668148b2
+size 161533192

checkpoint-1250/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
+}

checkpoint-1250/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 %}"
+}

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb342eb9be9a6d545bf949a4942b917be5f376c66fadd5451cdf280879fac6a7
+size 323291242

checkpoint-1250/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": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-1250/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a456c014f4062602da085bb6b03f6bda6f86ab8b2dcf1a268dd903ed52f3fb91
+size 14512

checkpoint-1250/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74ea19755c03db3ccc062fd1a38208daf2c7258b6dd1d567b2257f1306869548
+size 14512

checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862c685f46c4b9cec5c37f6baba43daa5a1cddab9e997a47d4f5e99ffae96c12
+size 1064

checkpoint-1250/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
+  }
+}

checkpoint-1250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

checkpoint-1250/tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1250/trainer_state.json

@@ -0,0 +1,908 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.459547519683838,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.2185,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5558891296386719,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.892,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5772704482078552,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.7887,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.40292349457740784,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.7111,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.35770532488822937,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6489,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.43718403577804565,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.5936,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.4591154158115387,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.6121,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6591519713401794,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.6059,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6931334733963013,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.6062,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6464695334434509,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.5929,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.7549647688865662,
+      "learning_rate": 1.76e-05,
+      "loss": 0.5138,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6728184819221497,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.4737,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7162397503852844,
+      "learning_rate": 1.9999025240093045e-05,
+      "loss": 0.4891,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.9795845150947571,
+      "learning_rate": 1.9991228300988586e-05,
+      "loss": 0.4663,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6311202049255371,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.5164,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.9567041993141174,
+      "learning_rate": 1.9952273999818312e-05,
+      "loss": 0.3981,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.8767746090888977,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.3761,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.8661500215530396,
+      "learning_rate": 1.988228381446553e-05,
+      "loss": 0.374,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.7793363332748413,
+      "learning_rate": 1.983571470813386e-05,
+      "loss": 0.3908,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8413230180740356,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.3527,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 1.5790411233901978,
+      "learning_rate": 1.9719610005785466e-05,
+      "loss": 0.2756,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.1819688081741333,
+      "learning_rate": 1.9650164944723116e-05,
+      "loss": 0.2622,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 1.2115598917007446,
+      "learning_rate": 1.9573194975320672e-05,
+      "loss": 0.2475,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.0625479221343994,
+      "learning_rate": 1.9488760116444966e-05,
+      "loss": 0.2682,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2376039028167725,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2514,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.6343020796775818,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.1448,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 1.1657440662384033,
+      "learning_rate": 1.9191353392552346e-05,
+      "loss": 0.1725,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.4713112115859985,
+      "learning_rate": 1.907777478532909e-05,
+      "loss": 0.1753,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 1.9010937213897705,
+      "learning_rate": 1.895711760239413e-05,
+      "loss": 0.1697,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.2462244033813477,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.157,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 1.5734026432037354,
+      "learning_rate": 1.869494929505219e-05,
+      "loss": 0.0987,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.6871922016143799,
+      "learning_rate": 1.855364260160507e-05,
+      "loss": 0.1122,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 0.8505676984786987,
+      "learning_rate": 1.8405666034956842e-05,
+      "loss": 0.0999,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 1.9714100360870361,
+      "learning_rate": 1.8251134982782952e-05,
+      "loss": 0.0925,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.3289463520050049,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.1034,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 1.7757859230041504,
+      "learning_rate": 1.792289643355191e-05,
+      "loss": 0.0538,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 1.5128904581069946,
+      "learning_rate": 1.7749444887041797e-05,
+      "loss": 0.0562,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 1.7095279693603516,
+      "learning_rate": 1.7569950556517566e-05,
+      "loss": 0.0656,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 1.7054250240325928,
+      "learning_rate": 1.7384553406258842e-05,
+      "loss": 0.0783,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.2087674140930176,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.0832,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 1.2171767950057983,
+      "learning_rate": 1.6996633405133656e-05,
+      "loss": 0.0389,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 1.2036916017532349,
+      "learning_rate": 1.6794413042615168e-05,
+      "loss": 0.0456,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 1.6378772258758545,
+      "learning_rate": 1.6586894601186804e-05,
+      "loss": 0.0539,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.062146544456482,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.0351,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7032294273376465,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.0331,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 1.2708150148391724,
+      "learning_rate": 1.5934188866037017e-05,
+      "loss": 0.0298,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 0.5238479375839233,
+      "learning_rate": 1.570713567684432e-05,
+      "loss": 0.0271,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.6896675229072571,
+      "learning_rate": 1.5475632234925505e-05,
+      "loss": 0.0148,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.8893882632255554,
+      "learning_rate": 1.5239859059700794e-05,
+      "loss": 0.0384,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.3057194948196411,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0216,
+      "step": 500
+    },
+    {
+      "epoch": 10.2,
+      "grad_norm": 0.4277481436729431,
+      "learning_rate": 1.4756242090702756e-05,
+      "loss": 0.0186,
+      "step": 510
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 2.500697374343872,
+      "learning_rate": 1.4508775406894308e-05,
+      "loss": 0.0289,
+      "step": 520
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 0.4189341366291046,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.0161,
+      "step": 530
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.6834658980369568,
+      "learning_rate": 1.4003490325568953e-05,
+      "loss": 0.016,
+      "step": 540
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.32209300994873047,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.0214,
+      "step": 550
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.6142628788948059,
+      "learning_rate": 1.3485720473218153e-05,
+      "loss": 0.0169,
+      "step": 560
+    },
+    {
+      "epoch": 11.4,
+      "grad_norm": 0.020493434742093086,
+      "learning_rate": 1.3222656952305113e-05,
+      "loss": 0.0072,
+      "step": 570
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.6618867516517639,
+      "learning_rate": 1.2957080500440469e-05,
+      "loss": 0.0134,
+      "step": 580
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 2.014190196990967,
+      "learning_rate": 1.2689198206152657e-05,
+      "loss": 0.0141,
+      "step": 590
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.3526052236557007,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.0152,
+      "step": 600
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 0.39659520983695984,
+      "learning_rate": 1.2147353271670634e-05,
+      "loss": 0.0082,
+      "step": 610
+    },
+    {
+      "epoch": 12.4,
+      "grad_norm": 1.6676621437072754,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.0086,
+      "step": 620
+    },
+    {
+      "epoch": 12.6,
+      "grad_norm": 0.48944175243377686,
+      "learning_rate": 1.159881187691835e-05,
+      "loss": 0.0073,
+      "step": 630
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.11040916293859482,
+      "learning_rate": 1.1322563902571227e-05,
+      "loss": 0.0111,
+      "step": 640
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.19332852959632874,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0084,
+      "step": 650
+    },
+    {
+      "epoch": 13.2,
+      "grad_norm": 0.5781747698783875,
+      "learning_rate": 1.0767190281268187e-05,
+      "loss": 0.0088,
+      "step": 660
+    },
+    {
+      "epoch": 13.4,
+      "grad_norm": 0.5372014045715332,
+      "learning_rate": 1.0488497697956134e-05,
+      "loss": 0.0129,
+      "step": 670
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 0.0674474835395813,
+      "learning_rate": 1.0209424198833571e-05,
+      "loss": 0.0047,
+      "step": 680
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.0646585077047348,
+      "learning_rate": 9.930187397020385e-06,
+      "loss": 0.0079,
+      "step": 690
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.16117724776268005,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0137,
+      "step": 700
+    },
+    {
+      "epoch": 14.2,
+      "grad_norm": 0.031529657542705536,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.0195,
+      "step": 710
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 0.7396082878112793,
+      "learning_rate": 9.093674198022201e-06,
+      "loss": 0.0038,
+      "step": 720
+    },
+    {
+      "epoch": 14.6,
+      "grad_norm": 0.131903737783432,
+      "learning_rate": 8.815960316934991e-06,
+      "loss": 0.009,
+      "step": 730
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 0.031985681504011154,
+      "learning_rate": 8.539169714375885e-06,
+      "loss": 0.0013,
+      "step": 740
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.12234848737716675,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0043,
+      "step": 750
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.10590848326683044,
+      "learning_rate": 7.989220788540356e-06,
+      "loss": 0.0016,
+      "step": 760
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 0.20384103059768677,
+      "learning_rate": 7.716491298893443e-06,
+      "loss": 0.0011,
+      "step": 770
+    },
+    {
+      "epoch": 15.6,
+      "grad_norm": 0.16497106850147247,
+      "learning_rate": 7.445542420642097e-06,
+      "loss": 0.002,
+      "step": 780
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 0.0461721308529377,
+      "learning_rate": 7.176585431571235e-06,
+      "loss": 0.0017,
+      "step": 790
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.023166760802268982,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0008,
+      "step": 800
+    },
+    {
+      "epoch": 16.2,
+      "grad_norm": 0.032082173973321915,
+      "learning_rate": 6.645484302497452e-06,
+      "loss": 0.0003,
+      "step": 810
+    },
+    {
+      "epoch": 16.4,
+      "grad_norm": 0.08265218138694763,
+      "learning_rate": 6.383754299179079e-06,
+      "loss": 0.0007,
+      "step": 820
+    },
+    {
+      "epoch": 16.6,
+      "grad_norm": 0.024636510759592056,
+      "learning_rate": 6.124844135478971e-06,
+      "loss": 0.005,
+      "step": 830
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.019458631053566933,
+      "learning_rate": 5.868955701754584e-06,
+      "loss": 0.0004,
+      "step": 840
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.01352341752499342,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0007,
+      "step": 850
+    },
+    {
+      "epoch": 17.2,
+      "grad_norm": 0.009102717973291874,
+      "learning_rate": 5.367039648801386e-06,
+      "loss": 0.0004,
+      "step": 860
+    },
+    {
+      "epoch": 17.4,
+      "grad_norm": 0.01286560669541359,
+      "learning_rate": 5.121403408612672e-06,
+      "loss": 0.0002,
+      "step": 870
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 0.36686578392982483,
+      "learning_rate": 4.879571351294287e-06,
+      "loss": 0.0007,
+      "step": 880
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.005845635663717985,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.0002,
+      "step": 890
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.06807386130094528,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0002,
+      "step": 900
+    },
+    {
+      "epoch": 18.2,
+      "grad_norm": 0.02204430289566517,
+      "learning_rate": 4.178770298427107e-06,
+      "loss": 0.0001,
+      "step": 910
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 0.008754129521548748,
+      "learning_rate": 3.954008851376252e-06,
+      "loss": 0.0001,
+      "step": 920
+    },
+    {
+      "epoch": 18.6,
+      "grad_norm": 0.00636293226853013,
+      "learning_rate": 3.7339618863553983e-06,
+      "loss": 0.0001,
+      "step": 930
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 0.004866347182542086,
+      "learning_rate": 3.5188009893686916e-06,
+      "loss": 0.0006,
+      "step": 940
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.004850468598306179,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0001,
+      "step": 950
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 0.0016120151849463582,
+      "learning_rate": 3.103804562643302e-06,
+      "loss": 0.0001,
+      "step": 960
+    },
+    {
+      "epoch": 19.4,
+      "grad_norm": 0.08115795254707336,
+      "learning_rate": 2.9042926346347932e-06,
+      "loss": 0.0002,
+      "step": 970
+    },
+    {
+      "epoch": 19.6,
+      "grad_norm": 0.0031273579224944115,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.0001,
+      "step": 980
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 0.005434623919427395,
+      "learning_rate": 2.522019095014683e-06,
+      "loss": 0.0001,
+      "step": 990
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.003434584243223071,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0003,
+      "step": 1000
+    },
+    {
+      "epoch": 20.2,
+      "grad_norm": 0.0036388696171343327,
+      "learning_rate": 2.163065426741603e-06,
+      "loss": 0.0003,
+      "step": 1010
+    },
+    {
+      "epoch": 20.4,
+      "grad_norm": 0.005258283577859402,
+      "learning_rate": 1.9926862905126663e-06,
+      "loss": 0.0001,
+      "step": 1020
+    },
+    {
+      "epoch": 20.6,
+      "grad_norm": 0.0052086408250033855,
+      "learning_rate": 1.8285510166487154e-06,
+      "loss": 0.0001,
+      "step": 1030
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 0.007011784706264734,
+      "learning_rate": 1.6707875928990059e-06,
+      "loss": 0.0001,
+      "step": 1040
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.008353537879884243,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0001,
+      "step": 1050
+    },
+    {
+      "epoch": 21.2,
+      "grad_norm": 0.005364676937460899,
+      "learning_rate": 1.3748633079274254e-06,
+      "loss": 0.0001,
+      "step": 1060
+    },
+    {
+      "epoch": 21.4,
+      "grad_norm": 0.07464922219514847,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.0003,
+      "step": 1070
+    },
+    {
+      "epoch": 21.6,
+      "grad_norm": 0.005178565625101328,
+      "learning_rate": 1.1058362670870248e-06,
+      "loss": 0.0001,
+      "step": 1080
+    },
+    {
+      "epoch": 21.8,
+      "grad_norm": 0.003679296700283885,
+      "learning_rate": 9.816747359488632e-07,
+      "loss": 0.0001,
+      "step": 1090
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.008506166748702526,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0001,
+      "step": 1100
+    },
+    {
+      "epoch": 22.2,
+      "grad_norm": 0.0045352838933467865,
+      "learning_rate": 7.545396638768698e-07,
+      "loss": 0.0001,
+      "step": 1110
+    },
+    {
+      "epoch": 22.4,
+      "grad_norm": 0.0041460818611085415,
+      "learning_rate": 6.517432360398556e-07,
+      "loss": 0.0002,
+      "step": 1120
+    },
+    {
+      "epoch": 22.6,
+      "grad_norm": 0.00789156835526228,
+      "learning_rate": 5.562362976251901e-07,
+      "loss": 0.0001,
+      "step": 1130
+    },
+    {
+      "epoch": 22.8,
+      "grad_norm": 0.004850171506404877,
+      "learning_rate": 4.6809332207053083e-07,
+      "loss": 0.0002,
+      "step": 1140
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.0024761913809925318,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0001,
+      "step": 1150
+    },
+    {
+      "epoch": 23.2,
+      "grad_norm": 0.004848626907914877,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.0002,
+      "step": 1160
+    },
+    {
+      "epoch": 23.4,
+      "grad_norm": 0.008169041946530342,
+      "learning_rate": 2.4850645694436736e-07,
+      "loss": 0.0001,
+      "step": 1170
+    },
+    {
+      "epoch": 23.6,
+      "grad_norm": 0.008230429142713547,
+      "learning_rate": 1.9044844650808468e-07,
+      "loss": 0.0001,
+      "step": 1180
+    },
+    {
+      "epoch": 23.8,
+      "grad_norm": 0.008880352601408958,
+      "learning_rate": 1.400396292949513e-07,
+      "loss": 0.0001,
+      "step": 1190
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.003499081125482917,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.0002,
+      "step": 1200
+    },
+    {
+      "epoch": 24.2,
+      "grad_norm": 0.002381326397880912,
+      "learning_rate": 6.232080839403631e-08,
+      "loss": 0.0001,
+      "step": 1210
+    },
+    {
+      "epoch": 24.4,
+      "grad_norm": 0.003195591736584902,
+      "learning_rate": 3.50714075049563e-08,
+      "loss": 0.0001,
+      "step": 1220
+    },
+    {
+      "epoch": 24.6,
+      "grad_norm": 0.003270337823778391,
+      "learning_rate": 1.5592358180189782e-08,
+      "loss": 0.0001,
+      "step": 1230
+    },
+    {
+      "epoch": 24.8,
+      "grad_norm": 0.00868391152471304,
+      "learning_rate": 3.898849596456477e-09,
+      "loss": 0.0001,
+      "step": 1240
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.0035359435714781284,
+      "learning_rate": 0.0,
+      "loss": 0.0002,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.502555032784732e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b461a8fd57f9dccc64796c48a45854cf5baf5b869fda0d17af67a1a0382daa8
+size 5560

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": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

runs/Jan18_05-17-00_eb238ab39206/events.out.tfevents.1737177929.eb238ab39206.145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8a041a08d99718a3dfd2cf06ecf49923ccd8fc95811bd71306305a2f8f5b51
+size 32945

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 sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 25.0,
+    "total_flos": 2.502555032784732e+17,
+    "train_loss": 0.12197050291108899,
+    "train_runtime": 13777.8614,
+    "train_samples_per_second": 0.907,
+    "train_steps_per_second": 0.091
+}

trainer_log.jsonl

@@ -0,0 +1,126 @@
+{"current_steps": 10, "total_steps": 1250, "loss": 1.2185, "lr": 1.6000000000000001e-06, "epoch": 0.2, "percentage": 0.8, "elapsed_time": "0:01:50", "remaining_time": "3:48:18"}
+{"current_steps": 20, "total_steps": 1250, "loss": 0.892, "lr": 3.2000000000000003e-06, "epoch": 0.4, "percentage": 1.6, "elapsed_time": "0:03:41", "remaining_time": "3:47:05"}
+{"current_steps": 30, "total_steps": 1250, "loss": 0.7887, "lr": 4.800000000000001e-06, "epoch": 0.6, "percentage": 2.4, "elapsed_time": "0:05:32", "remaining_time": "3:45:27"}
+{"current_steps": 40, "total_steps": 1250, "loss": 0.7111, "lr": 6.4000000000000006e-06, "epoch": 0.8, "percentage": 3.2, "elapsed_time": "0:07:23", "remaining_time": "3:43:28"}
+{"current_steps": 50, "total_steps": 1250, "loss": 0.6489, "lr": 8.000000000000001e-06, "epoch": 1.0, "percentage": 4.0, "elapsed_time": "0:09:14", "remaining_time": "3:41:43"}
+{"current_steps": 60, "total_steps": 1250, "loss": 0.5936, "lr": 9.600000000000001e-06, "epoch": 1.2, "percentage": 4.8, "elapsed_time": "0:11:05", "remaining_time": "3:39:55"}
+{"current_steps": 70, "total_steps": 1250, "loss": 0.6121, "lr": 1.1200000000000001e-05, "epoch": 1.4, "percentage": 5.6, "elapsed_time": "0:12:56", "remaining_time": "3:38:10"}
+{"current_steps": 80, "total_steps": 1250, "loss": 0.6059, "lr": 1.2800000000000001e-05, "epoch": 1.6, "percentage": 6.4, "elapsed_time": "0:14:46", "remaining_time": "3:36:08"}
+{"current_steps": 90, "total_steps": 1250, "loss": 0.6062, "lr": 1.4400000000000001e-05, "epoch": 1.8, "percentage": 7.2, "elapsed_time": "0:16:38", "remaining_time": "3:34:28"}
+{"current_steps": 100, "total_steps": 1250, "loss": 0.5929, "lr": 1.6000000000000003e-05, "epoch": 2.0, "percentage": 8.0, "elapsed_time": "0:18:30", "remaining_time": "3:32:47"}
+{"current_steps": 110, "total_steps": 1250, "loss": 0.5138, "lr": 1.76e-05, "epoch": 2.2, "percentage": 8.8, "elapsed_time": "0:20:20", "remaining_time": "3:30:51"}
+{"current_steps": 120, "total_steps": 1250, "loss": 0.4737, "lr": 1.9200000000000003e-05, "epoch": 2.4, "percentage": 9.6, "elapsed_time": "0:22:12", "remaining_time": "3:29:06"}
+{"current_steps": 130, "total_steps": 1250, "loss": 0.4891, "lr": 1.9999025240093045e-05, "epoch": 2.6, "percentage": 10.4, "elapsed_time": "0:24:03", "remaining_time": "3:27:18"}
+{"current_steps": 140, "total_steps": 1250, "loss": 0.4663, "lr": 1.9991228300988586e-05, "epoch": 2.8, "percentage": 11.2, "elapsed_time": "0:25:54", "remaining_time": "3:25:26"}
+{"current_steps": 150, "total_steps": 1250, "loss": 0.5164, "lr": 1.9975640502598243e-05, "epoch": 3.0, "percentage": 12.0, "elapsed_time": "0:27:45", "remaining_time": "3:23:37"}
+{"current_steps": 160, "total_steps": 1250, "loss": 0.3981, "lr": 1.9952273999818312e-05, "epoch": 3.2, "percentage": 12.8, "elapsed_time": "0:29:36", "remaining_time": "3:21:41"}
+{"current_steps": 170, "total_steps": 1250, "loss": 0.3761, "lr": 1.9921147013144782e-05, "epoch": 3.4, "percentage": 13.6, "elapsed_time": "0:31:27", "remaining_time": "3:19:51"}
+{"current_steps": 180, "total_steps": 1250, "loss": 0.374, "lr": 1.988228381446553e-05, "epoch": 3.6, "percentage": 14.4, "elapsed_time": "0:33:19", "remaining_time": "3:18:04"}
+{"current_steps": 190, "total_steps": 1250, "loss": 0.3908, "lr": 1.983571470813386e-05, "epoch": 3.8, "percentage": 15.2, "elapsed_time": "0:35:10", "remaining_time": "3:16:14"}
+{"current_steps": 200, "total_steps": 1250, "loss": 0.3527, "lr": 1.9781476007338058e-05, "epoch": 4.0, "percentage": 16.0, "elapsed_time": "0:37:02", "remaining_time": "3:14:25"}
+{"current_steps": 210, "total_steps": 1250, "loss": 0.2756, "lr": 1.9719610005785466e-05, "epoch": 4.2, "percentage": 16.8, "elapsed_time": "0:38:52", "remaining_time": "3:12:29"}
+{"current_steps": 220, "total_steps": 1250, "loss": 0.2622, "lr": 1.9650164944723116e-05, "epoch": 4.4, "percentage": 17.6, "elapsed_time": "0:40:42", "remaining_time": "3:10:36"}
+{"current_steps": 230, "total_steps": 1250, "loss": 0.2475, "lr": 1.9573194975320672e-05, "epoch": 4.6, "percentage": 18.4, "elapsed_time": "0:42:33", "remaining_time": "3:08:44"}
+{"current_steps": 240, "total_steps": 1250, "loss": 0.2682, "lr": 1.9488760116444966e-05, "epoch": 4.8, "percentage": 19.2, "elapsed_time": "0:44:24", "remaining_time": "3:06:51"}
+{"current_steps": 250, "total_steps": 1250, "loss": 0.2514, "lr": 1.9396926207859085e-05, "epoch": 5.0, "percentage": 20.0, "elapsed_time": "0:46:16", "remaining_time": "3:05:05"}
+{"current_steps": 260, "total_steps": 1250, "loss": 0.1448, "lr": 1.9297764858882516e-05, "epoch": 5.2, "percentage": 20.8, "elapsed_time": "0:48:08", "remaining_time": "3:03:16"}
+{"current_steps": 270, "total_steps": 1250, "loss": 0.1725, "lr": 1.9191353392552346e-05, "epoch": 5.4, "percentage": 21.6, "elapsed_time": "0:50:00", "remaining_time": "3:01:28"}
+{"current_steps": 280, "total_steps": 1250, "loss": 0.1753, "lr": 1.907777478532909e-05, "epoch": 5.6, "percentage": 22.4, "elapsed_time": "0:51:51", "remaining_time": "2:59:39"}
+{"current_steps": 290, "total_steps": 1250, "loss": 0.1697, "lr": 1.895711760239413e-05, "epoch": 5.8, "percentage": 23.2, "elapsed_time": "0:53:42", "remaining_time": "2:57:46"}
+{"current_steps": 300, "total_steps": 1250, "loss": 0.157, "lr": 1.8829475928589272e-05, "epoch": 6.0, "percentage": 24.0, "elapsed_time": "0:55:33", "remaining_time": "2:55:54"}
+{"current_steps": 310, "total_steps": 1250, "loss": 0.0987, "lr": 1.869494929505219e-05, "epoch": 6.2, "percentage": 24.8, "elapsed_time": "0:57:24", "remaining_time": "2:54:05"}
+{"current_steps": 320, "total_steps": 1250, "loss": 0.1122, "lr": 1.855364260160507e-05, "epoch": 6.4, "percentage": 25.6, "elapsed_time": "0:59:16", "remaining_time": "2:52:14"}
+{"current_steps": 330, "total_steps": 1250, "loss": 0.0999, "lr": 1.8405666034956842e-05, "epoch": 6.6, "percentage": 26.4, "elapsed_time": "1:01:06", "remaining_time": "2:50:22"}
+{"current_steps": 340, "total_steps": 1250, "loss": 0.0925, "lr": 1.8251134982782952e-05, "epoch": 6.8, "percentage": 27.2, "elapsed_time": "1:02:58", "remaining_time": "2:48:33"}
+{"current_steps": 350, "total_steps": 1250, "loss": 0.1034, "lr": 1.8090169943749477e-05, "epoch": 7.0, "percentage": 28.0, "elapsed_time": "1:04:50", "remaining_time": "2:46:43"}
+{"current_steps": 360, "total_steps": 1250, "loss": 0.0538, "lr": 1.792289643355191e-05, "epoch": 7.2, "percentage": 28.8, "elapsed_time": "1:06:42", "remaining_time": "2:44:54"}
+{"current_steps": 370, "total_steps": 1250, "loss": 0.0562, "lr": 1.7749444887041797e-05, "epoch": 7.4, "percentage": 29.6, "elapsed_time": "1:08:33", "remaining_time": "2:43:03"}
+{"current_steps": 380, "total_steps": 1250, "loss": 0.0656, "lr": 1.7569950556517566e-05, "epoch": 7.6, "percentage": 30.4, "elapsed_time": "1:10:24", "remaining_time": "2:41:12"}
+{"current_steps": 390, "total_steps": 1250, "loss": 0.0783, "lr": 1.7384553406258842e-05, "epoch": 7.8, "percentage": 31.2, "elapsed_time": "1:12:14", "remaining_time": "2:39:18"}
+{"current_steps": 400, "total_steps": 1250, "loss": 0.0832, "lr": 1.7193398003386514e-05, "epoch": 8.0, "percentage": 32.0, "elapsed_time": "1:14:05", "remaining_time": "2:37:26"}
+{"current_steps": 410, "total_steps": 1250, "loss": 0.0389, "lr": 1.6996633405133656e-05, "epoch": 8.2, "percentage": 32.8, "elapsed_time": "1:15:56", "remaining_time": "2:35:34"}
+{"current_steps": 420, "total_steps": 1250, "loss": 0.0456, "lr": 1.6794413042615168e-05, "epoch": 8.4, "percentage": 33.6, "elapsed_time": "1:17:46", "remaining_time": "2:33:42"}
+{"current_steps": 430, "total_steps": 1250, "loss": 0.0539, "lr": 1.6586894601186804e-05, "epoch": 8.6, "percentage": 34.4, "elapsed_time": "1:19:38", "remaining_time": "2:31:52"}
+{"current_steps": 440, "total_steps": 1250, "loss": 0.0351, "lr": 1.63742398974869e-05, "epoch": 8.8, "percentage": 35.2, "elapsed_time": "1:21:28", "remaining_time": "2:29:59"}
+{"current_steps": 450, "total_steps": 1250, "loss": 0.0331, "lr": 1.6156614753256583e-05, "epoch": 9.0, "percentage": 36.0, "elapsed_time": "1:23:18", "remaining_time": "2:28:05"}
+{"current_steps": 460, "total_steps": 1250, "loss": 0.0298, "lr": 1.5934188866037017e-05, "epoch": 9.2, "percentage": 36.8, "elapsed_time": "1:25:08", "remaining_time": "2:26:13"}
+{"current_steps": 470, "total_steps": 1250, "loss": 0.0271, "lr": 1.570713567684432e-05, "epoch": 9.4, "percentage": 37.6, "elapsed_time": "1:26:59", "remaining_time": "2:24:22"}
+{"current_steps": 480, "total_steps": 1250, "loss": 0.0148, "lr": 1.5475632234925505e-05, "epoch": 9.6, "percentage": 38.4, "elapsed_time": "1:28:50", "remaining_time": "2:22:31"}
+{"current_steps": 490, "total_steps": 1250, "loss": 0.0384, "lr": 1.5239859059700794e-05, "epoch": 9.8, "percentage": 39.2, "elapsed_time": "1:30:41", "remaining_time": "2:20:39"}
+{"current_steps": 500, "total_steps": 1250, "loss": 0.0216, "lr": 1.5000000000000002e-05, "epoch": 10.0, "percentage": 40.0, "elapsed_time": "1:32:31", "remaining_time": "2:18:47"}
+{"current_steps": 510, "total_steps": 1250, "loss": 0.0186, "lr": 1.4756242090702756e-05, "epoch": 10.2, "percentage": 40.8, "elapsed_time": "1:34:23", "remaining_time": "2:16:57"}
+{"current_steps": 520, "total_steps": 1250, "loss": 0.0289, "lr": 1.4508775406894308e-05, "epoch": 10.4, "percentage": 41.6, "elapsed_time": "1:36:14", "remaining_time": "2:15:06"}
+{"current_steps": 530, "total_steps": 1250, "loss": 0.0161, "lr": 1.4257792915650728e-05, "epoch": 10.6, "percentage": 42.4, "elapsed_time": "1:38:05", "remaining_time": "2:13:15"}
+{"current_steps": 540, "total_steps": 1250, "loss": 0.016, "lr": 1.4003490325568953e-05, "epoch": 10.8, "percentage": 43.2, "elapsed_time": "1:39:56", "remaining_time": "2:11:23"}
+{"current_steps": 550, "total_steps": 1250, "loss": 0.0214, "lr": 1.3746065934159123e-05, "epoch": 11.0, "percentage": 44.0, "elapsed_time": "1:41:46", "remaining_time": "2:09:31"}
+{"current_steps": 560, "total_steps": 1250, "loss": 0.0169, "lr": 1.3485720473218153e-05, "epoch": 11.2, "percentage": 44.8, "elapsed_time": "1:43:37", "remaining_time": "2:07:40"}
+{"current_steps": 570, "total_steps": 1250, "loss": 0.0072, "lr": 1.3222656952305113e-05, "epoch": 11.4, "percentage": 45.6, "elapsed_time": "1:45:27", "remaining_time": "2:05:48"}
+{"current_steps": 580, "total_steps": 1250, "loss": 0.0134, "lr": 1.2957080500440469e-05, "epoch": 11.6, "percentage": 46.4, "elapsed_time": "1:47:18", "remaining_time": "2:03:57"}
+{"current_steps": 590, "total_steps": 1250, "loss": 0.0141, "lr": 1.2689198206152657e-05, "epoch": 11.8, "percentage": 47.2, "elapsed_time": "1:49:08", "remaining_time": "2:02:05"}
+{"current_steps": 600, "total_steps": 1250, "loss": 0.0152, "lr": 1.2419218955996677e-05, "epoch": 12.0, "percentage": 48.0, "elapsed_time": "1:50:58", "remaining_time": "2:00:13"}
+{"current_steps": 610, "total_steps": 1250, "loss": 0.0082, "lr": 1.2147353271670634e-05, "epoch": 12.2, "percentage": 48.8, "elapsed_time": "1:52:49", "remaining_time": "1:58:22"}
+{"current_steps": 620, "total_steps": 1250, "loss": 0.0086, "lr": 1.187381314585725e-05, "epoch": 12.4, "percentage": 49.6, "elapsed_time": "1:54:39", "remaining_time": "1:56:30"}
+{"current_steps": 630, "total_steps": 1250, "loss": 0.0073, "lr": 1.159881187691835e-05, "epoch": 12.6, "percentage": 50.4, "elapsed_time": "1:56:29", "remaining_time": "1:54:39"}
+{"current_steps": 640, "total_steps": 1250, "loss": 0.0111, "lr": 1.1322563902571227e-05, "epoch": 12.8, "percentage": 51.2, "elapsed_time": "1:58:19", "remaining_time": "1:52:46"}
+{"current_steps": 650, "total_steps": 1250, "loss": 0.0084, "lr": 1.1045284632676535e-05, "epoch": 13.0, "percentage": 52.0, "elapsed_time": "2:00:09", "remaining_time": "1:50:54"}
+{"current_steps": 660, "total_steps": 1250, "loss": 0.0088, "lr": 1.0767190281268187e-05, "epoch": 13.2, "percentage": 52.8, "elapsed_time": "2:01:59", "remaining_time": "1:49:02"}
+{"current_steps": 670, "total_steps": 1250, "loss": 0.0129, "lr": 1.0488497697956134e-05, "epoch": 13.4, "percentage": 53.6, "elapsed_time": "2:03:49", "remaining_time": "1:47:11"}
+{"current_steps": 680, "total_steps": 1250, "loss": 0.0047, "lr": 1.0209424198833571e-05, "epoch": 13.6, "percentage": 54.4, "elapsed_time": "2:05:40", "remaining_time": "1:45:20"}
+{"current_steps": 690, "total_steps": 1250, "loss": 0.0079, "lr": 9.930187397020385e-06, "epoch": 13.8, "percentage": 55.2, "elapsed_time": "2:07:29", "remaining_time": "1:43:28"}
+{"current_steps": 700, "total_steps": 1250, "loss": 0.0137, "lr": 9.651005032974994e-06, "epoch": 14.0, "percentage": 56.0, "elapsed_time": "2:09:19", "remaining_time": "1:41:37"}
+{"current_steps": 710, "total_steps": 1250, "loss": 0.0195, "lr": 9.372094804706867e-06, "epoch": 14.2, "percentage": 56.8, "elapsed_time": "2:11:10", "remaining_time": "1:39:45"}
+{"current_steps": 720, "total_steps": 1250, "loss": 0.0038, "lr": 9.093674198022201e-06, "epoch": 14.4, "percentage": 57.6, "elapsed_time": "2:12:59", "remaining_time": "1:37:54"}
+{"current_steps": 730, "total_steps": 1250, "loss": 0.009, "lr": 8.815960316934991e-06, "epoch": 14.6, "percentage": 58.4, "elapsed_time": "2:14:49", "remaining_time": "1:36:02"}
+{"current_steps": 740, "total_steps": 1250, "loss": 0.0013, "lr": 8.539169714375885e-06, "epoch": 14.8, "percentage": 59.2, "elapsed_time": "2:16:38", "remaining_time": "1:34:10"}
+{"current_steps": 750, "total_steps": 1250, "loss": 0.0043, "lr": 8.263518223330698e-06, "epoch": 15.0, "percentage": 60.0, "elapsed_time": "2:18:28", "remaining_time": "1:32:18"}
+{"current_steps": 760, "total_steps": 1250, "loss": 0.0016, "lr": 7.989220788540356e-06, "epoch": 15.2, "percentage": 60.8, "elapsed_time": "2:20:18", "remaining_time": "1:30:27"}
+{"current_steps": 770, "total_steps": 1250, "loss": 0.0011, "lr": 7.716491298893443e-06, "epoch": 15.4, "percentage": 61.6, "elapsed_time": "2:22:07", "remaining_time": "1:28:35"}
+{"current_steps": 780, "total_steps": 1250, "loss": 0.002, "lr": 7.445542420642097e-06, "epoch": 15.6, "percentage": 62.4, "elapsed_time": "2:23:56", "remaining_time": "1:26:44"}
+{"current_steps": 790, "total_steps": 1250, "loss": 0.0017, "lr": 7.176585431571235e-06, "epoch": 15.8, "percentage": 63.2, "elapsed_time": "2:25:45", "remaining_time": "1:24:52"}
+{"current_steps": 800, "total_steps": 1250, "loss": 0.0008, "lr": 6.909830056250527e-06, "epoch": 16.0, "percentage": 64.0, "elapsed_time": "2:27:34", "remaining_time": "1:23:00"}
+{"current_steps": 810, "total_steps": 1250, "loss": 0.0003, "lr": 6.645484302497452e-06, "epoch": 16.2, "percentage": 64.8, "elapsed_time": "2:29:23", "remaining_time": "1:21:09"}
+{"current_steps": 820, "total_steps": 1250, "loss": 0.0007, "lr": 6.383754299179079e-06, "epoch": 16.4, "percentage": 65.6, "elapsed_time": "2:31:13", "remaining_time": "1:19:17"}
+{"current_steps": 830, "total_steps": 1250, "loss": 0.005, "lr": 6.124844135478971e-06, "epoch": 16.6, "percentage": 66.4, "elapsed_time": "2:33:03", "remaining_time": "1:17:26"}
+{"current_steps": 840, "total_steps": 1250, "loss": 0.0004, "lr": 5.868955701754584e-06, "epoch": 16.8, "percentage": 67.2, "elapsed_time": "2:34:51", "remaining_time": "1:15:35"}
+{"current_steps": 850, "total_steps": 1250, "loss": 0.0007, "lr": 5.616288532109225e-06, "epoch": 17.0, "percentage": 68.0, "elapsed_time": "2:36:40", "remaining_time": "1:13:43"}
+{"current_steps": 860, "total_steps": 1250, "loss": 0.0004, "lr": 5.367039648801386e-06, "epoch": 17.2, "percentage": 68.8, "elapsed_time": "2:38:29", "remaining_time": "1:11:52"}
+{"current_steps": 870, "total_steps": 1250, "loss": 0.0002, "lr": 5.121403408612672e-06, "epoch": 17.4, "percentage": 69.6, "elapsed_time": "2:40:18", "remaining_time": "1:10:01"}
+{"current_steps": 880, "total_steps": 1250, "loss": 0.0007, "lr": 4.879571351294287e-06, "epoch": 17.6, "percentage": 70.4, "elapsed_time": "2:42:08", "remaining_time": "1:08:10"}
+{"current_steps": 890, "total_steps": 1250, "loss": 0.0002, "lr": 4.641732050210032e-06, "epoch": 17.8, "percentage": 71.2, "elapsed_time": "2:43:57", "remaining_time": "1:06:19"}
+{"current_steps": 900, "total_steps": 1250, "loss": 0.0002, "lr": 4.408070965292534e-06, "epoch": 18.0, "percentage": 72.0, "elapsed_time": "2:45:46", "remaining_time": "1:04:28"}
+{"current_steps": 910, "total_steps": 1250, "loss": 0.0001, "lr": 4.178770298427107e-06, "epoch": 18.2, "percentage": 72.8, "elapsed_time": "2:47:35", "remaining_time": "1:02:37"}
+{"current_steps": 920, "total_steps": 1250, "loss": 0.0001, "lr": 3.954008851376252e-06, "epoch": 18.4, "percentage": 73.6, "elapsed_time": "2:49:24", "remaining_time": "1:00:45"}
+{"current_steps": 930, "total_steps": 1250, "loss": 0.0001, "lr": 3.7339618863553983e-06, "epoch": 18.6, "percentage": 74.4, "elapsed_time": "2:51:13", "remaining_time": "0:58:55"}
+{"current_steps": 940, "total_steps": 1250, "loss": 0.0006, "lr": 3.5188009893686916e-06, "epoch": 18.8, "percentage": 75.2, "elapsed_time": "2:53:02", "remaining_time": "0:57:04"}
+{"current_steps": 950, "total_steps": 1250, "loss": 0.0001, "lr": 3.308693936411421e-06, "epoch": 19.0, "percentage": 76.0, "elapsed_time": "2:54:52", "remaining_time": "0:55:13"}
+{"current_steps": 960, "total_steps": 1250, "loss": 0.0001, "lr": 3.103804562643302e-06, "epoch": 19.2, "percentage": 76.8, "elapsed_time": "2:56:40", "remaining_time": "0:53:22"}
+{"current_steps": 970, "total_steps": 1250, "loss": 0.0002, "lr": 2.9042926346347932e-06, "epoch": 19.4, "percentage": 77.6, "elapsed_time": "2:58:30", "remaining_time": "0:51:31"}
+{"current_steps": 980, "total_steps": 1250, "loss": 0.0001, "lr": 2.7103137257858867e-06, "epoch": 19.6, "percentage": 78.4, "elapsed_time": "3:00:19", "remaining_time": "0:49:40"}
+{"current_steps": 990, "total_steps": 1250, "loss": 0.0001, "lr": 2.522019095014683e-06, "epoch": 19.8, "percentage": 79.2, "elapsed_time": "3:02:09", "remaining_time": "0:47:50"}
+{"current_steps": 1000, "total_steps": 1250, "loss": 0.0003, "lr": 2.339555568810221e-06, "epoch": 20.0, "percentage": 80.0, "elapsed_time": "3:03:58", "remaining_time": "0:45:59"}
+{"current_steps": 1010, "total_steps": 1250, "loss": 0.0003, "lr": 2.163065426741603e-06, "epoch": 20.2, "percentage": 80.8, "elapsed_time": "3:05:49", "remaining_time": "0:44:09"}
+{"current_steps": 1020, "total_steps": 1250, "loss": 0.0001, "lr": 1.9926862905126663e-06, "epoch": 20.4, "percentage": 81.6, "elapsed_time": "3:07:37", "remaining_time": "0:42:18"}
+{"current_steps": 1030, "total_steps": 1250, "loss": 0.0001, "lr": 1.8285510166487154e-06, "epoch": 20.6, "percentage": 82.4, "elapsed_time": "3:09:26", "remaining_time": "0:40:27"}
+{"current_steps": 1040, "total_steps": 1250, "loss": 0.0001, "lr": 1.6707875928990059e-06, "epoch": 20.8, "percentage": 83.2, "elapsed_time": "3:11:16", "remaining_time": "0:38:37"}
+{"current_steps": 1050, "total_steps": 1250, "loss": 0.0001, "lr": 1.5195190384357405e-06, "epoch": 21.0, "percentage": 84.0, "elapsed_time": "3:13:05", "remaining_time": "0:36:46"}
+{"current_steps": 1060, "total_steps": 1250, "loss": 0.0001, "lr": 1.3748633079274254e-06, "epoch": 21.2, "percentage": 84.8, "elapsed_time": "3:14:55", "remaining_time": "0:34:56"}
+{"current_steps": 1070, "total_steps": 1250, "loss": 0.0003, "lr": 1.2369331995613664e-06, "epoch": 21.4, "percentage": 85.6, "elapsed_time": "3:16:44", "remaining_time": "0:33:05"}
+{"current_steps": 1080, "total_steps": 1250, "loss": 0.0001, "lr": 1.1058362670870248e-06, "epoch": 21.6, "percentage": 86.4, "elapsed_time": "3:18:33", "remaining_time": "0:31:15"}
+{"current_steps": 1090, "total_steps": 1250, "loss": 0.0001, "lr": 9.816747359488632e-07, "epoch": 21.8, "percentage": 87.2, "elapsed_time": "3:20:23", "remaining_time": "0:29:24"}
+{"current_steps": 1100, "total_steps": 1250, "loss": 0.0001, "lr": 8.645454235739903e-07, "epoch": 22.0, "percentage": 88.0, "elapsed_time": "3:22:12", "remaining_time": "0:27:34"}
+{"current_steps": 1110, "total_steps": 1250, "loss": 0.0001, "lr": 7.545396638768698e-07, "epoch": 22.2, "percentage": 88.8, "elapsed_time": "3:24:01", "remaining_time": "0:25:44"}
+{"current_steps": 1120, "total_steps": 1250, "loss": 0.0002, "lr": 6.517432360398556e-07, "epoch": 22.4, "percentage": 89.6, "elapsed_time": "3:25:51", "remaining_time": "0:23:53"}
+{"current_steps": 1130, "total_steps": 1250, "loss": 0.0001, "lr": 5.562362976251901e-07, "epoch": 22.6, "percentage": 90.4, "elapsed_time": "3:27:40", "remaining_time": "0:22:03"}
+{"current_steps": 1140, "total_steps": 1250, "loss": 0.0002, "lr": 4.6809332207053083e-07, "epoch": 22.8, "percentage": 91.2, "elapsed_time": "3:29:30", "remaining_time": "0:20:12"}
+{"current_steps": 1150, "total_steps": 1250, "loss": 0.0001, "lr": 3.8738304061681107e-07, "epoch": 23.0, "percentage": 92.0, "elapsed_time": "3:31:19", "remaining_time": "0:18:22"}
+{"current_steps": 1160, "total_steps": 1250, "loss": 0.0002, "lr": 3.1416838871368925e-07, "epoch": 23.2, "percentage": 92.8, "elapsed_time": "3:33:08", "remaining_time": "0:16:32"}
+{"current_steps": 1170, "total_steps": 1250, "loss": 0.0001, "lr": 2.4850645694436736e-07, "epoch": 23.4, "percentage": 93.6, "elapsed_time": "3:34:58", "remaining_time": "0:14:41"}
+{"current_steps": 1180, "total_steps": 1250, "loss": 0.0001, "lr": 1.9044844650808468e-07, "epoch": 23.6, "percentage": 94.4, "elapsed_time": "3:36:47", "remaining_time": "0:12:51"}
+{"current_steps": 1190, "total_steps": 1250, "loss": 0.0001, "lr": 1.400396292949513e-07, "epoch": 23.8, "percentage": 95.2, "elapsed_time": "3:38:36", "remaining_time": "0:11:01"}
+{"current_steps": 1200, "total_steps": 1250, "loss": 0.0002, "lr": 9.731931258429638e-08, "epoch": 24.0, "percentage": 96.0, "elapsed_time": "3:40:26", "remaining_time": "0:09:11"}
+{"current_steps": 1210, "total_steps": 1250, "loss": 0.0001, "lr": 6.232080839403631e-08, "epoch": 24.2, "percentage": 96.8, "elapsed_time": "3:42:14", "remaining_time": "0:07:20"}
+{"current_steps": 1220, "total_steps": 1250, "loss": 0.0001, "lr": 3.50714075049563e-08, "epoch": 24.4, "percentage": 97.6, "elapsed_time": "3:44:03", "remaining_time": "0:05:30"}
+{"current_steps": 1230, "total_steps": 1250, "loss": 0.0001, "lr": 1.5592358180189782e-08, "epoch": 24.6, "percentage": 98.4, "elapsed_time": "3:45:54", "remaining_time": "0:03:40"}
+{"current_steps": 1240, "total_steps": 1250, "loss": 0.0001, "lr": 3.898849596456477e-09, "epoch": 24.8, "percentage": 99.2, "elapsed_time": "3:47:43", "remaining_time": "0:01:50"}
+{"current_steps": 1250, "total_steps": 1250, "loss": 0.0002, "lr": 0.0, "epoch": 25.0, "percentage": 100.0, "elapsed_time": "3:49:31", "remaining_time": "0:00:00"}
+{"current_steps": 1250, "total_steps": 1250, "epoch": 25.0, "percentage": 100.0, "elapsed_time": "3:49:33", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,917 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 25.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.459547519683838,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.2185,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5558891296386719,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.892,
+      "step": 20
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5772704482078552,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.7887,
+      "step": 30
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.40292349457740784,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.7111,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.35770532488822937,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.6489,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.43718403577804565,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.5936,
+      "step": 60
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.4591154158115387,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.6121,
+      "step": 70
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6591519713401794,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.6059,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.6931334733963013,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.6062,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6464695334434509,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.5929,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.7549647688865662,
+      "learning_rate": 1.76e-05,
+      "loss": 0.5138,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6728184819221497,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.4737,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.7162397503852844,
+      "learning_rate": 1.9999025240093045e-05,
+      "loss": 0.4891,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.9795845150947571,
+      "learning_rate": 1.9991228300988586e-05,
+      "loss": 0.4663,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6311202049255371,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.5164,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.9567041993141174,
+      "learning_rate": 1.9952273999818312e-05,
+      "loss": 0.3981,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.8767746090888977,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.3761,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.8661500215530396,
+      "learning_rate": 1.988228381446553e-05,
+      "loss": 0.374,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.7793363332748413,
+      "learning_rate": 1.983571470813386e-05,
+      "loss": 0.3908,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8413230180740356,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.3527,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 1.5790411233901978,
+      "learning_rate": 1.9719610005785466e-05,
+      "loss": 0.2756,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 1.1819688081741333,
+      "learning_rate": 1.9650164944723116e-05,
+      "loss": 0.2622,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 1.2115598917007446,
+      "learning_rate": 1.9573194975320672e-05,
+      "loss": 0.2475,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.0625479221343994,
+      "learning_rate": 1.9488760116444966e-05,
+      "loss": 0.2682,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2376039028167725,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2514,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.6343020796775818,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.1448,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 1.1657440662384033,
+      "learning_rate": 1.9191353392552346e-05,
+      "loss": 0.1725,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 1.4713112115859985,
+      "learning_rate": 1.907777478532909e-05,
+      "loss": 0.1753,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 1.9010937213897705,
+      "learning_rate": 1.895711760239413e-05,
+      "loss": 0.1697,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.2462244033813477,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.157,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 1.5734026432037354,
+      "learning_rate": 1.869494929505219e-05,
+      "loss": 0.0987,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.6871922016143799,
+      "learning_rate": 1.855364260160507e-05,
+      "loss": 0.1122,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 0.8505676984786987,
+      "learning_rate": 1.8405666034956842e-05,
+      "loss": 0.0999,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 1.9714100360870361,
+      "learning_rate": 1.8251134982782952e-05,
+      "loss": 0.0925,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.3289463520050049,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.1034,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 1.7757859230041504,
+      "learning_rate": 1.792289643355191e-05,
+      "loss": 0.0538,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 1.5128904581069946,
+      "learning_rate": 1.7749444887041797e-05,
+      "loss": 0.0562,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 1.7095279693603516,
+      "learning_rate": 1.7569950556517566e-05,
+      "loss": 0.0656,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 1.7054250240325928,
+      "learning_rate": 1.7384553406258842e-05,
+      "loss": 0.0783,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.2087674140930176,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.0832,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 1.2171767950057983,
+      "learning_rate": 1.6996633405133656e-05,
+      "loss": 0.0389,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 1.2036916017532349,
+      "learning_rate": 1.6794413042615168e-05,
+      "loss": 0.0456,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 1.6378772258758545,
+      "learning_rate": 1.6586894601186804e-05,
+      "loss": 0.0539,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 1.062146544456482,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.0351,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7032294273376465,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.0331,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 1.2708150148391724,
+      "learning_rate": 1.5934188866037017e-05,
+      "loss": 0.0298,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 0.5238479375839233,
+      "learning_rate": 1.570713567684432e-05,
+      "loss": 0.0271,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 0.6896675229072571,
+      "learning_rate": 1.5475632234925505e-05,
+      "loss": 0.0148,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.8893882632255554,
+      "learning_rate": 1.5239859059700794e-05,
+      "loss": 0.0384,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.3057194948196411,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0216,
+      "step": 500
+    },
+    {
+      "epoch": 10.2,
+      "grad_norm": 0.4277481436729431,
+      "learning_rate": 1.4756242090702756e-05,
+      "loss": 0.0186,
+      "step": 510
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 2.500697374343872,
+      "learning_rate": 1.4508775406894308e-05,
+      "loss": 0.0289,
+      "step": 520
+    },
+    {
+      "epoch": 10.6,
+      "grad_norm": 0.4189341366291046,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.0161,
+      "step": 530
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.6834658980369568,
+      "learning_rate": 1.4003490325568953e-05,
+      "loss": 0.016,
+      "step": 540
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.32209300994873047,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.0214,
+      "step": 550
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 0.6142628788948059,
+      "learning_rate": 1.3485720473218153e-05,
+      "loss": 0.0169,
+      "step": 560
+    },
+    {
+      "epoch": 11.4,
+      "grad_norm": 0.020493434742093086,
+      "learning_rate": 1.3222656952305113e-05,
+      "loss": 0.0072,
+      "step": 570
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 0.6618867516517639,
+      "learning_rate": 1.2957080500440469e-05,
+      "loss": 0.0134,
+      "step": 580
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 2.014190196990967,
+      "learning_rate": 1.2689198206152657e-05,
+      "loss": 0.0141,
+      "step": 590
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.3526052236557007,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.0152,
+      "step": 600
+    },
+    {
+      "epoch": 12.2,
+      "grad_norm": 0.39659520983695984,
+      "learning_rate": 1.2147353271670634e-05,
+      "loss": 0.0082,
+      "step": 610
+    },
+    {
+      "epoch": 12.4,
+      "grad_norm": 1.6676621437072754,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.0086,
+      "step": 620
+    },
+    {
+      "epoch": 12.6,
+      "grad_norm": 0.48944175243377686,
+      "learning_rate": 1.159881187691835e-05,
+      "loss": 0.0073,
+      "step": 630
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.11040916293859482,
+      "learning_rate": 1.1322563902571227e-05,
+      "loss": 0.0111,
+      "step": 640
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.19332852959632874,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0084,
+      "step": 650
+    },
+    {
+      "epoch": 13.2,
+      "grad_norm": 0.5781747698783875,
+      "learning_rate": 1.0767190281268187e-05,
+      "loss": 0.0088,
+      "step": 660
+    },
+    {
+      "epoch": 13.4,
+      "grad_norm": 0.5372014045715332,
+      "learning_rate": 1.0488497697956134e-05,
+      "loss": 0.0129,
+      "step": 670
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 0.0674474835395813,
+      "learning_rate": 1.0209424198833571e-05,
+      "loss": 0.0047,
+      "step": 680
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.0646585077047348,
+      "learning_rate": 9.930187397020385e-06,
+      "loss": 0.0079,
+      "step": 690
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.16117724776268005,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0137,
+      "step": 700
+    },
+    {
+      "epoch": 14.2,
+      "grad_norm": 0.031529657542705536,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.0195,
+      "step": 710
+    },
+    {
+      "epoch": 14.4,
+      "grad_norm": 0.7396082878112793,
+      "learning_rate": 9.093674198022201e-06,
+      "loss": 0.0038,
+      "step": 720
+    },
+    {
+      "epoch": 14.6,
+      "grad_norm": 0.131903737783432,
+      "learning_rate": 8.815960316934991e-06,
+      "loss": 0.009,
+      "step": 730
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 0.031985681504011154,
+      "learning_rate": 8.539169714375885e-06,
+      "loss": 0.0013,
+      "step": 740
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.12234848737716675,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0043,
+      "step": 750
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.10590848326683044,
+      "learning_rate": 7.989220788540356e-06,
+      "loss": 0.0016,
+      "step": 760
+    },
+    {
+      "epoch": 15.4,
+      "grad_norm": 0.20384103059768677,
+      "learning_rate": 7.716491298893443e-06,
+      "loss": 0.0011,
+      "step": 770
+    },
+    {
+      "epoch": 15.6,
+      "grad_norm": 0.16497106850147247,
+      "learning_rate": 7.445542420642097e-06,
+      "loss": 0.002,
+      "step": 780
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 0.0461721308529377,
+      "learning_rate": 7.176585431571235e-06,
+      "loss": 0.0017,
+      "step": 790
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.023166760802268982,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0008,
+      "step": 800
+    },
+    {
+      "epoch": 16.2,
+      "grad_norm": 0.032082173973321915,
+      "learning_rate": 6.645484302497452e-06,
+      "loss": 0.0003,
+      "step": 810
+    },
+    {
+      "epoch": 16.4,
+      "grad_norm": 0.08265218138694763,
+      "learning_rate": 6.383754299179079e-06,
+      "loss": 0.0007,
+      "step": 820
+    },
+    {
+      "epoch": 16.6,
+      "grad_norm": 0.024636510759592056,
+      "learning_rate": 6.124844135478971e-06,
+      "loss": 0.005,
+      "step": 830
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.019458631053566933,
+      "learning_rate": 5.868955701754584e-06,
+      "loss": 0.0004,
+      "step": 840
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 0.01352341752499342,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0007,
+      "step": 850
+    },
+    {
+      "epoch": 17.2,
+      "grad_norm": 0.009102717973291874,
+      "learning_rate": 5.367039648801386e-06,
+      "loss": 0.0004,
+      "step": 860
+    },
+    {
+      "epoch": 17.4,
+      "grad_norm": 0.01286560669541359,
+      "learning_rate": 5.121403408612672e-06,
+      "loss": 0.0002,
+      "step": 870
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 0.36686578392982483,
+      "learning_rate": 4.879571351294287e-06,
+      "loss": 0.0007,
+      "step": 880
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.005845635663717985,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.0002,
+      "step": 890
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.06807386130094528,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0002,
+      "step": 900
+    },
+    {
+      "epoch": 18.2,
+      "grad_norm": 0.02204430289566517,
+      "learning_rate": 4.178770298427107e-06,
+      "loss": 0.0001,
+      "step": 910
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 0.008754129521548748,
+      "learning_rate": 3.954008851376252e-06,
+      "loss": 0.0001,
+      "step": 920
+    },
+    {
+      "epoch": 18.6,
+      "grad_norm": 0.00636293226853013,
+      "learning_rate": 3.7339618863553983e-06,
+      "loss": 0.0001,
+      "step": 930
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 0.004866347182542086,
+      "learning_rate": 3.5188009893686916e-06,
+      "loss": 0.0006,
+      "step": 940
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.004850468598306179,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0001,
+      "step": 950
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 0.0016120151849463582,
+      "learning_rate": 3.103804562643302e-06,
+      "loss": 0.0001,
+      "step": 960
+    },
+    {
+      "epoch": 19.4,
+      "grad_norm": 0.08115795254707336,
+      "learning_rate": 2.9042926346347932e-06,
+      "loss": 0.0002,
+      "step": 970
+    },
+    {
+      "epoch": 19.6,
+      "grad_norm": 0.0031273579224944115,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.0001,
+      "step": 980
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 0.005434623919427395,
+      "learning_rate": 2.522019095014683e-06,
+      "loss": 0.0001,
+      "step": 990
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.003434584243223071,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0003,
+      "step": 1000
+    },
+    {
+      "epoch": 20.2,
+      "grad_norm": 0.0036388696171343327,
+      "learning_rate": 2.163065426741603e-06,
+      "loss": 0.0003,
+      "step": 1010
+    },
+    {
+      "epoch": 20.4,
+      "grad_norm": 0.005258283577859402,
+      "learning_rate": 1.9926862905126663e-06,
+      "loss": 0.0001,
+      "step": 1020
+    },
+    {
+      "epoch": 20.6,
+      "grad_norm": 0.0052086408250033855,
+      "learning_rate": 1.8285510166487154e-06,
+      "loss": 0.0001,
+      "step": 1030
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 0.007011784706264734,
+      "learning_rate": 1.6707875928990059e-06,
+      "loss": 0.0001,
+      "step": 1040
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.008353537879884243,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0001,
+      "step": 1050
+    },
+    {
+      "epoch": 21.2,
+      "grad_norm": 0.005364676937460899,
+      "learning_rate": 1.3748633079274254e-06,
+      "loss": 0.0001,
+      "step": 1060
+    },
+    {
+      "epoch": 21.4,
+      "grad_norm": 0.07464922219514847,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.0003,
+      "step": 1070
+    },
+    {
+      "epoch": 21.6,
+      "grad_norm": 0.005178565625101328,
+      "learning_rate": 1.1058362670870248e-06,
+      "loss": 0.0001,
+      "step": 1080
+    },
+    {
+      "epoch": 21.8,
+      "grad_norm": 0.003679296700283885,
+      "learning_rate": 9.816747359488632e-07,
+      "loss": 0.0001,
+      "step": 1090
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.008506166748702526,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0001,
+      "step": 1100
+    },
+    {
+      "epoch": 22.2,
+      "grad_norm": 0.0045352838933467865,
+      "learning_rate": 7.545396638768698e-07,
+      "loss": 0.0001,
+      "step": 1110
+    },
+    {
+      "epoch": 22.4,
+      "grad_norm": 0.0041460818611085415,
+      "learning_rate": 6.517432360398556e-07,
+      "loss": 0.0002,
+      "step": 1120
+    },
+    {
+      "epoch": 22.6,
+      "grad_norm": 0.00789156835526228,
+      "learning_rate": 5.562362976251901e-07,
+      "loss": 0.0001,
+      "step": 1130
+    },
+    {
+      "epoch": 22.8,
+      "grad_norm": 0.004850171506404877,
+      "learning_rate": 4.6809332207053083e-07,
+      "loss": 0.0002,
+      "step": 1140
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.0024761913809925318,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0001,
+      "step": 1150
+    },
+    {
+      "epoch": 23.2,
+      "grad_norm": 0.004848626907914877,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.0002,
+      "step": 1160
+    },
+    {
+      "epoch": 23.4,
+      "grad_norm": 0.008169041946530342,
+      "learning_rate": 2.4850645694436736e-07,
+      "loss": 0.0001,
+      "step": 1170
+    },
+    {
+      "epoch": 23.6,
+      "grad_norm": 0.008230429142713547,
+      "learning_rate": 1.9044844650808468e-07,
+      "loss": 0.0001,
+      "step": 1180
+    },
+    {
+      "epoch": 23.8,
+      "grad_norm": 0.008880352601408958,
+      "learning_rate": 1.400396292949513e-07,
+      "loss": 0.0001,
+      "step": 1190
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.003499081125482917,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.0002,
+      "step": 1200
+    },
+    {
+      "epoch": 24.2,
+      "grad_norm": 0.002381326397880912,
+      "learning_rate": 6.232080839403631e-08,
+      "loss": 0.0001,
+      "step": 1210
+    },
+    {
+      "epoch": 24.4,
+      "grad_norm": 0.003195591736584902,
+      "learning_rate": 3.50714075049563e-08,
+      "loss": 0.0001,
+      "step": 1220
+    },
+    {
+      "epoch": 24.6,
+      "grad_norm": 0.003270337823778391,
+      "learning_rate": 1.5592358180189782e-08,
+      "loss": 0.0001,
+      "step": 1230
+    },
+    {
+      "epoch": 24.8,
+      "grad_norm": 0.00868391152471304,
+      "learning_rate": 3.898849596456477e-09,
+      "loss": 0.0001,
+      "step": 1240
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.0035359435714781284,
+      "learning_rate": 0.0,
+      "loss": 0.0002,
+      "step": 1250
+    },
+    {
+      "epoch": 25.0,
+      "step": 1250,
+      "total_flos": 2.502555032784732e+17,
+      "train_loss": 0.12197050291108899,
+      "train_runtime": 13777.8614,
+      "train_samples_per_second": 0.907,
+      "train_steps_per_second": 0.091
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.502555032784732e+17,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}