Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,40 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3536/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2024-10-08-13-11-54
+  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. -->
+
+# train_2024-10-08-13-11-54
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the my_chartQA 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:gate_proj|o_proj|k_proj|up_proj|down_proj|q_proj|v_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd5bd5146534a2c5a7d2c61c14635cb2fa7f1e0411eafa0a530325f83a5aa9b
+size 36981072

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 +1,9 @@
+{
+    "epoch": 1.9991519434628975,
+    "num_input_tokens_seen": 16589520,
+    "total_flos": 1.9756568407597056e+17,
+    "train_loss": 0.6868792008187167,
+    "train_runtime": 16975.4651,
+    "train_samples_per_second": 3.334,
+    "train_steps_per_second": 0.208
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-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-100/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:gate_proj|o_proj|k_proj|up_proj|down_proj|q_proj|v_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac2e728957f043c95e95615ffb829382845bb36269e39e8e21ee5d8999c3a5e
+size 36981072

checkpoint-100/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-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8b0e1e4ffb5b7a836c5801aad9a981aa89dd92b33ad2a3b039f46521b218fc
+size 74188650

checkpoint-100/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-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ecbfc6406ff4e880fcd78d140dab0dc9dffc51304a988cf3de3a415cd59f18
+size 1064

checkpoint-100/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-100/tokenizer.json

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05653710247349823,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0028268551236749115,
+      "grad_norm": 3.236659288406372,
+      "learning_rate": 4.999975332533892e-05,
+      "loss": 1.1521,
+      "num_input_tokens_seen": 23072,
+      "step": 5
+    },
+    {
+      "epoch": 0.005653710247349823,
+      "grad_norm": 2.117961883544922,
+      "learning_rate": 4.999901330622352e-05,
+      "loss": 1.1355,
+      "num_input_tokens_seen": 46144,
+      "step": 10
+    },
+    {
+      "epoch": 0.008480565371024734,
+      "grad_norm": 1.072292447090149,
+      "learning_rate": 4.999777995725733e-05,
+      "loss": 1.0243,
+      "num_input_tokens_seen": 69232,
+      "step": 15
+    },
+    {
+      "epoch": 0.011307420494699646,
+      "grad_norm": 2.135847330093384,
+      "learning_rate": 4.999605330277923e-05,
+      "loss": 0.8573,
+      "num_input_tokens_seen": 93072,
+      "step": 20
+    },
+    {
+      "epoch": 0.014134275618374558,
+      "grad_norm": 1.1360677480697632,
+      "learning_rate": 4.9993833376862976e-05,
+      "loss": 0.8121,
+      "num_input_tokens_seen": 116624,
+      "step": 25
+    },
+    {
+      "epoch": 0.01696113074204947,
+      "grad_norm": 1.7201180458068848,
+      "learning_rate": 4.9991120223316514e-05,
+      "loss": 0.7727,
+      "num_input_tokens_seen": 140448,
+      "step": 30
+    },
+    {
+      "epoch": 0.019787985865724382,
+      "grad_norm": 2.26900577545166,
+      "learning_rate": 4.998791389568115e-05,
+      "loss": 1.0105,
+      "num_input_tokens_seen": 164656,
+      "step": 35
+    },
+    {
+      "epoch": 0.022614840989399292,
+      "grad_norm": 1.620118260383606,
+      "learning_rate": 4.998421445723046e-05,
+      "loss": 0.7647,
+      "num_input_tokens_seen": 188288,
+      "step": 40
+    },
+    {
+      "epoch": 0.025441696113074206,
+      "grad_norm": 1.4073580503463745,
+      "learning_rate": 4.998002198096906e-05,
+      "loss": 1.0147,
+      "num_input_tokens_seen": 211616,
+      "step": 45
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "grad_norm": 1.7421135902404785,
+      "learning_rate": 4.997533654963118e-05,
+      "loss": 0.7942,
+      "num_input_tokens_seen": 235200,
+      "step": 50
+    },
+    {
+      "epoch": 0.03109540636042403,
+      "grad_norm": 2.93461537361145,
+      "learning_rate": 4.997015825567898e-05,
+      "loss": 0.9321,
+      "num_input_tokens_seen": 258800,
+      "step": 55
+    },
+    {
+      "epoch": 0.03392226148409894,
+      "grad_norm": 1.723960518836975,
+      "learning_rate": 4.996448720130077e-05,
+      "loss": 0.8301,
+      "num_input_tokens_seen": 282176,
+      "step": 60
+    },
+    {
+      "epoch": 0.03674911660777385,
+      "grad_norm": 1.5170176029205322,
+      "learning_rate": 4.9958323498408994e-05,
+      "loss": 0.9043,
+      "num_input_tokens_seen": 305632,
+      "step": 65
+    },
+    {
+      "epoch": 0.039575971731448764,
+      "grad_norm": 1.414136290550232,
+      "learning_rate": 4.995166726863799e-05,
+      "loss": 0.8304,
+      "num_input_tokens_seen": 328608,
+      "step": 70
+    },
+    {
+      "epoch": 0.04240282685512368,
+      "grad_norm": 1.5558068752288818,
+      "learning_rate": 4.994451864334162e-05,
+      "loss": 0.8947,
+      "num_input_tokens_seen": 352032,
+      "step": 75
+    },
+    {
+      "epoch": 0.045229681978798585,
+      "grad_norm": 1.669939398765564,
+      "learning_rate": 4.9936877763590664e-05,
+      "loss": 0.9019,
+      "num_input_tokens_seen": 375904,
+      "step": 80
+    },
+    {
+      "epoch": 0.0480565371024735,
+      "grad_norm": 2.2579429149627686,
+      "learning_rate": 4.992874478017003e-05,
+      "loss": 0.9061,
+      "num_input_tokens_seen": 399472,
+      "step": 85
+    },
+    {
+      "epoch": 0.05088339222614841,
+      "grad_norm": 1.8936649560928345,
+      "learning_rate": 4.99201198535758e-05,
+      "loss": 0.8414,
+      "num_input_tokens_seen": 422592,
+      "step": 90
+    },
+    {
+      "epoch": 0.05371024734982332,
+      "grad_norm": 2.1161952018737793,
+      "learning_rate": 4.991100315401203e-05,
+      "loss": 1.0194,
+      "num_input_tokens_seen": 445744,
+      "step": 95
+    },
+    {
+      "epoch": 0.05653710247349823,
+      "grad_norm": 2.3125863075256348,
+      "learning_rate": 4.990139486138743e-05,
+      "loss": 0.7639,
+      "num_input_tokens_seen": 469184,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3536,
+  "num_input_tokens_seen": 469184,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5587543094525952.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cbc94a713da9a44fc659b7c77cb3a54484d5d6762cafa7efa3cea0c036c9ff
+size 5432

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-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-2B-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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:gate_proj|o_proj|k_proj|up_proj|down_proj|q_proj|v_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 sha256:1f9b04b10ef8a062ef333b09af3e40f37cd44ce49afd8fbcd7064de04312cae4
+size 36981072

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/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b7811058bc84b591923a39146d0019523a27dbab869cbecdcb65daa29e39fe
+size 74188650

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.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e04fd97f511b92a6e1024345b1ae35d04a1ae2b5f0010df21361208dcd861de
+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 +1,143 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5653710247349824,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0028268551236749115,
+      "grad_norm": 3.236659288406372,
+      "learning_rate": 4.999975332533892e-05,
+      "loss": 1.1521,
+      "num_input_tokens_seen": 23072,
+      "step": 5
+    },
+    {
+      "epoch": 0.005653710247349823,
+      "grad_norm": 2.117961883544922,
+      "learning_rate": 4.999901330622352e-05,
+      "loss": 1.1355,
+      "num_input_tokens_seen": 46144,
+      "step": 10
+    },
+    {
+      "epoch": 0.008480565371024734,
+      "grad_norm": 1.072292447090149,
+      "learning_rate": 4.999777995725733e-05,
+      "loss": 1.0243,
+      "num_input_tokens_seen": 69232,
+      "step": 15
+    },
+    {
+      "epoch": 0.011307420494699646,
+      "grad_norm": 2.135847330093384,
+      "learning_rate": 4.999605330277923e-05,
+      "loss": 0.8573,
+      "num_input_tokens_seen": 93072,
+      "step": 20
+    },
+    {
+      "epoch": 0.014134275618374558,
+      "grad_norm": 1.1360677480697632,
+      "learning_rate": 4.9993833376862976e-05,
+      "loss": 0.8121,
+      "num_input_tokens_seen": 116624,
+      "step": 25
+    },
+    {
+      "epoch": 0.01696113074204947,
+      "grad_norm": 1.7201180458068848,
+      "learning_rate": 4.9991120223316514e-05,
+      "loss": 0.7727,
+      "num_input_tokens_seen": 140448,
+      "step": 30
+    },
+    {
+      "epoch": 0.019787985865724382,
+      "grad_norm": 2.26900577545166,
+      "learning_rate": 4.998791389568115e-05,
+      "loss": 1.0105,
+      "num_input_tokens_seen": 164656,
+      "step": 35
+    },
+    {
+      "epoch": 0.022614840989399292,
+      "grad_norm": 1.620118260383606,
+      "learning_rate": 4.998421445723046e-05,
+      "loss": 0.7647,
+      "num_input_tokens_seen": 188288,
+      "step": 40
+    },
+    {
+      "epoch": 0.025441696113074206,
+      "grad_norm": 1.4073580503463745,
+      "learning_rate": 4.998002198096906e-05,
+      "loss": 1.0147,
+      "num_input_tokens_seen": 211616,
+      "step": 45
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "grad_norm": 1.7421135902404785,
+      "learning_rate": 4.997533654963118e-05,
+      "loss": 0.7942,
+      "num_input_tokens_seen": 235200,
+      "step": 50
+    },
+    {
+      "epoch": 0.03109540636042403,
+      "grad_norm": 2.93461537361145,
+      "learning_rate": 4.997015825567898e-05,
+      "loss": 0.9321,
+      "num_input_tokens_seen": 258800,
+      "step": 55
+    },
+    {
+      "epoch": 0.03392226148409894,
+      "grad_norm": 1.723960518836975,
+      "learning_rate": 4.996448720130077e-05,
+      "loss": 0.8301,
+      "num_input_tokens_seen": 282176,
+      "step": 60
+    },
+    {
+      "epoch": 0.03674911660777385,
+      "grad_norm": 1.5170176029205322,
+      "learning_rate": 4.9958323498408994e-05,
+      "loss": 0.9043,
+      "num_input_tokens_seen": 305632,
+      "step": 65
+    },
+    {
+      "epoch": 0.039575971731448764,
+      "grad_norm": 1.414136290550232,
+      "learning_rate": 4.995166726863799e-05,
+      "loss": 0.8304,
+      "num_input_tokens_seen": 328608,
+      "step": 70
+    },
+    {
+      "epoch": 0.04240282685512368,
+      "grad_norm": 1.5558068752288818,
+      "learning_rate": 4.994451864334162e-05,
+      "loss": 0.8947,
+      "num_input_tokens_seen": 352032,
+      "step": 75
+    },
+    {
+      "epoch": 0.045229681978798585,
+      "grad_norm": 1.669939398765564,
+      "learning_rate": 4.9936877763590664e-05,
+      "loss": 0.9019,
+      "num_input_tokens_seen": 375904,
+      "step": 80
+    },
+    {
+      "epoch": 0.0480565371024735,
+      "grad_norm": 2.2579429149627686,
+      "learning_rate": 4.992874478017003e-05,
+      "loss": 0.9061,
+      "num_input_tokens_seen": 399472,
+      "step": 85
+    },
+    {
+      "epoch": 0.05088339222614841,
+      "grad_norm": 1.8936649560928345,
+      "learning_rate": 4.99201198535758e-05,
+      "loss": 0.8414,
+      "num_input_tokens_seen": 422592,
+      "step": 90
+    },
+    {
+      "epoch": 0.05371024734982332,
+      "grad_norm": 2.1161952018737793,
+      "learning_rate": 4.991100315401203e-05,
+      "loss": 1.0194,
+      "num_input_tokens_seen": 445744,
+      "step": 95
+    },
+    {
+      "epoch": 0.05653710247349823,
+      "grad_norm": 2.3125863075256348,
+      "learning_rate": 4.990139486138743e-05,
+      "loss": 0.7639,
+      "num_input_tokens_seen": 469184,
+      "step": 100
+    },
+    {
+      "epoch": 0.059363957597173146,
+      "grad_norm": 2.460916757583618,
+      "learning_rate": 4.989129516531178e-05,
+      "loss": 0.8552,
+      "num_input_tokens_seen": 492800,
+      "step": 105
+    },
+    {
+      "epoch": 0.06219081272084806,
+      "grad_norm": 1.7828129529953003,
+      "learning_rate": 4.9880704265092225e-05,
+      "loss": 0.7322,
+      "num_input_tokens_seen": 516912,
+      "step": 110
+    },
+    {
+      "epoch": 0.06501766784452297,
+      "grad_norm": 2.2058181762695312,
+      "learning_rate": 4.9869622369729286e-05,
+      "loss": 0.8776,
+      "num_input_tokens_seen": 540800,
+      "step": 115
+    },
+    {
+      "epoch": 0.06784452296819787,
+      "grad_norm": 2.826209545135498,
+      "learning_rate": 4.985804969791279e-05,
+      "loss": 0.7862,
+      "num_input_tokens_seen": 564672,
+      "step": 120
+    },
+    {
+      "epoch": 0.0706713780918728,
+      "grad_norm": 2.14705491065979,
+      "learning_rate": 4.9845986478017526e-05,
+      "loss": 0.9268,
+      "num_input_tokens_seen": 588384,
+      "step": 125
+    },
+    {
+      "epoch": 0.0734982332155477,
+      "grad_norm": 1.8558905124664307,
+      "learning_rate": 4.9833432948098754e-05,
+      "loss": 0.8998,
+      "num_input_tokens_seen": 611888,
+      "step": 130
+    },
+    {
+      "epoch": 0.07632508833922262,
+      "grad_norm": 1.619469404220581,
+      "learning_rate": 4.9820389355887484e-05,
+      "loss": 0.9142,
+      "num_input_tokens_seen": 635392,
+      "step": 135
+    },
+    {
+      "epoch": 0.07915194346289753,
+      "grad_norm": 2.032025098800659,
+      "learning_rate": 4.9806855958785625e-05,
+      "loss": 0.9182,
+      "num_input_tokens_seen": 658880,
+      "step": 140
+    },
+    {
+      "epoch": 0.08197879858657244,
+      "grad_norm": 2.5096957683563232,
+      "learning_rate": 4.979283302386086e-05,
+      "loss": 0.9964,
+      "num_input_tokens_seen": 681792,
+      "step": 145
+    },
+    {
+      "epoch": 0.08480565371024736,
+      "grad_norm": 2.0987000465393066,
+      "learning_rate": 4.9778320827841416e-05,
+      "loss": 0.9709,
+      "num_input_tokens_seen": 704944,
+      "step": 150
+    },
+    {
+      "epoch": 0.08763250883392226,
+      "grad_norm": 1.7368932962417603,
+      "learning_rate": 4.976331965711056e-05,
+      "loss": 0.8381,
+      "num_input_tokens_seen": 728288,
+      "step": 155
+    },
+    {
+      "epoch": 0.09045936395759717,
+      "grad_norm": 1.3404303789138794,
+      "learning_rate": 4.9747829807701e-05,
+      "loss": 0.746,
+      "num_input_tokens_seen": 752208,
+      "step": 160
+    },
+    {
+      "epoch": 0.09328621908127209,
+      "grad_norm": 2.785475969314575,
+      "learning_rate": 4.973185158528899e-05,
+      "loss": 0.933,
+      "num_input_tokens_seen": 775472,
+      "step": 165
+    },
+    {
+      "epoch": 0.096113074204947,
+      "grad_norm": 1.7333956956863403,
+      "learning_rate": 4.971538530518836e-05,
+      "loss": 0.9036,
+      "num_input_tokens_seen": 798912,
+      "step": 170
+    },
+    {
+      "epoch": 0.0989399293286219,
+      "grad_norm": 2.1001110076904297,
+      "learning_rate": 4.9698431292344216e-05,
+      "loss": 0.7976,
+      "num_input_tokens_seen": 822480,
+      "step": 175
+    },
+    {
+      "epoch": 0.10176678445229682,
+      "grad_norm": 1.8633843660354614,
+      "learning_rate": 4.96809898813266e-05,
+      "loss": 0.7499,
+      "num_input_tokens_seen": 845456,
+      "step": 180
+    },
+    {
+      "epoch": 0.10459363957597173,
+      "grad_norm": 1.7571918964385986,
+      "learning_rate": 4.966306141632384e-05,
+      "loss": 0.7536,
+      "num_input_tokens_seen": 868592,
+      "step": 185
+    },
+    {
+      "epoch": 0.10742049469964664,
+      "grad_norm": 2.424466371536255,
+      "learning_rate": 4.964464625113578e-05,
+      "loss": 0.7603,
+      "num_input_tokens_seen": 892288,
+      "step": 190
+    },
+    {
+      "epoch": 0.11024734982332156,
+      "grad_norm": 3.250654935836792,
+      "learning_rate": 4.9625744749166776e-05,
+      "loss": 0.7796,
+      "num_input_tokens_seen": 916016,
+      "step": 195
+    },
+    {
+      "epoch": 0.11307420494699646,
+      "grad_norm": 2.098060369491577,
+      "learning_rate": 4.9606357283418575e-05,
+      "loss": 0.7504,
+      "num_input_tokens_seen": 939696,
+      "step": 200
+    },
+    {
+      "epoch": 0.11590106007067137,
+      "grad_norm": 1.9629781246185303,
+      "learning_rate": 4.958648423648289e-05,
+      "loss": 0.9839,
+      "num_input_tokens_seen": 962656,
+      "step": 205
+    },
+    {
+      "epoch": 0.11872791519434629,
+      "grad_norm": 3.670927047729492,
+      "learning_rate": 4.95661260005339e-05,
+      "loss": 0.9137,
+      "num_input_tokens_seen": 985808,
+      "step": 210
+    },
+    {
+      "epoch": 0.1215547703180212,
+      "grad_norm": 1.5907021760940552,
+      "learning_rate": 4.9545282977320464e-05,
+      "loss": 0.8635,
+      "num_input_tokens_seen": 1008992,
+      "step": 215
+    },
+    {
+      "epoch": 0.12438162544169612,
+      "grad_norm": 1.8623510599136353,
+      "learning_rate": 4.952395557815826e-05,
+      "loss": 0.8384,
+      "num_input_tokens_seen": 1032576,
+      "step": 220
+    },
+    {
+      "epoch": 0.127208480565371,
+      "grad_norm": 2.1950509548187256,
+      "learning_rate": 4.9502144223921584e-05,
+      "loss": 0.9326,
+      "num_input_tokens_seen": 1056224,
+      "step": 225
+    },
+    {
+      "epoch": 0.13003533568904593,
+      "grad_norm": 1.7406038045883179,
+      "learning_rate": 4.9479849345035125e-05,
+      "loss": 0.7225,
+      "num_input_tokens_seen": 1079616,
+      "step": 230
+    },
+    {
+      "epoch": 0.13286219081272085,
+      "grad_norm": 1.8558340072631836,
+      "learning_rate": 4.9457071381465406e-05,
+      "loss": 0.8379,
+      "num_input_tokens_seen": 1102720,
+      "step": 235
+    },
+    {
+      "epoch": 0.13568904593639575,
+      "grad_norm": 1.887434959411621,
+      "learning_rate": 4.943381078271214e-05,
+      "loss": 0.8197,
+      "num_input_tokens_seen": 1126144,
+      "step": 240
+    },
+    {
+      "epoch": 0.13851590106007067,
+      "grad_norm": 2.088313579559326,
+      "learning_rate": 4.941006800779937e-05,
+      "loss": 0.7736,
+      "num_input_tokens_seen": 1149632,
+      "step": 245
+    },
+    {
+      "epoch": 0.1413427561837456,
+      "grad_norm": 2.0320558547973633,
+      "learning_rate": 4.938584352526636e-05,
+      "loss": 1.009,
+      "num_input_tokens_seen": 1173040,
+      "step": 250
+    },
+    {
+      "epoch": 0.14416961130742048,
+      "grad_norm": 2.0947532653808594,
+      "learning_rate": 4.93611378131584e-05,
+      "loss": 0.9782,
+      "num_input_tokens_seen": 1196768,
+      "step": 255
+    },
+    {
+      "epoch": 0.1469964664310954,
+      "grad_norm": 1.8757507801055908,
+      "learning_rate": 4.933595135901732e-05,
+      "loss": 0.8654,
+      "num_input_tokens_seen": 1220048,
+      "step": 260
+    },
+    {
+      "epoch": 0.14982332155477032,
+      "grad_norm": 2.3573222160339355,
+      "learning_rate": 4.9310284659871955e-05,
+      "loss": 0.795,
+      "num_input_tokens_seen": 1243600,
+      "step": 265
+    },
+    {
+      "epoch": 0.15265017667844524,
+      "grad_norm": 1.9607449769973755,
+      "learning_rate": 4.928413822222822e-05,
+      "loss": 0.8133,
+      "num_input_tokens_seen": 1266864,
+      "step": 270
+    },
+    {
+      "epoch": 0.15547703180212014,
+      "grad_norm": 1.5924804210662842,
+      "learning_rate": 4.9257512562059236e-05,
+      "loss": 0.7734,
+      "num_input_tokens_seen": 1289856,
+      "step": 275
+    },
+    {
+      "epoch": 0.15830388692579506,
+      "grad_norm": 1.3379789590835571,
+      "learning_rate": 4.9230408204795034e-05,
+      "loss": 0.8799,
+      "num_input_tokens_seen": 1313632,
+      "step": 280
+    },
+    {
+      "epoch": 0.16113074204946998,
+      "grad_norm": 2.136787176132202,
+      "learning_rate": 4.920282568531228e-05,
+      "loss": 0.6354,
+      "num_input_tokens_seen": 1337504,
+      "step": 285
+    },
+    {
+      "epoch": 0.16395759717314487,
+      "grad_norm": 2.280400037765503,
+      "learning_rate": 4.9174765547923665e-05,
+      "loss": 0.64,
+      "num_input_tokens_seen": 1360944,
+      "step": 290
+    },
+    {
+      "epoch": 0.1667844522968198,
+      "grad_norm": 1.2323652505874634,
+      "learning_rate": 4.9146228346367165e-05,
+      "loss": 0.7516,
+      "num_input_tokens_seen": 1385008,
+      "step": 295
+    },
+    {
+      "epoch": 0.1696113074204947,
+      "grad_norm": 2.9730310440063477,
+      "learning_rate": 4.911721464379516e-05,
+      "loss": 0.8796,
+      "num_input_tokens_seen": 1408112,
+      "step": 300
+    },
+    {
+      "epoch": 0.1724381625441696,
+      "grad_norm": 2.245002269744873,
+      "learning_rate": 4.9087725012763265e-05,
+      "loss": 0.8443,
+      "num_input_tokens_seen": 1431104,
+      "step": 305
+    },
+    {
+      "epoch": 0.17526501766784452,
+      "grad_norm": 2.2738306522369385,
+      "learning_rate": 4.905776003521905e-05,
+      "loss": 0.7832,
+      "num_input_tokens_seen": 1454544,
+      "step": 310
+    },
+    {
+      "epoch": 0.17809187279151945,
+      "grad_norm": 1.9596010446548462,
+      "learning_rate": 4.9027320302490575e-05,
+      "loss": 0.678,
+      "num_input_tokens_seen": 1477904,
+      "step": 315
+    },
+    {
+      "epoch": 0.18091872791519434,
+      "grad_norm": 2.4512102603912354,
+      "learning_rate": 4.89964064152747e-05,
+      "loss": 0.9236,
+      "num_input_tokens_seen": 1501632,
+      "step": 320
+    },
+    {
+      "epoch": 0.18374558303886926,
+      "grad_norm": 1.3344308137893677,
+      "learning_rate": 4.896501898362524e-05,
+      "loss": 0.7098,
+      "num_input_tokens_seen": 1525040,
+      "step": 325
+    },
+    {
+      "epoch": 0.18657243816254418,
+      "grad_norm": 2.6979386806488037,
+      "learning_rate": 4.893315862694092e-05,
+      "loss": 0.9233,
+      "num_input_tokens_seen": 1548448,
+      "step": 330
+    },
+    {
+      "epoch": 0.18939929328621907,
+      "grad_norm": 2.9867770671844482,
+      "learning_rate": 4.8900825973953156e-05,
+      "loss": 0.826,
+      "num_input_tokens_seen": 1571328,
+      "step": 335
+    },
+    {
+      "epoch": 0.192226148409894,
+      "grad_norm": 1.992570161819458,
+      "learning_rate": 4.886802166271364e-05,
+      "loss": 0.9075,
+      "num_input_tokens_seen": 1594576,
+      "step": 340
+    },
+    {
+      "epoch": 0.1950530035335689,
+      "grad_norm": 2.016847848892212,
+      "learning_rate": 4.8834746340581764e-05,
+      "loss": 0.885,
+      "num_input_tokens_seen": 1617824,
+      "step": 345
+    },
+    {
+      "epoch": 0.1978798586572438,
+      "grad_norm": 2.3614108562469482,
+      "learning_rate": 4.880100066421184e-05,
+      "loss": 0.7843,
+      "num_input_tokens_seen": 1641456,
+      "step": 350
+    },
+    {
+      "epoch": 0.20070671378091873,
+      "grad_norm": 2.5570292472839355,
+      "learning_rate": 4.8766785299540104e-05,
+      "loss": 0.8996,
+      "num_input_tokens_seen": 1665280,
+      "step": 355
+    },
+    {
+      "epoch": 0.20353356890459365,
+      "grad_norm": 2.0213332176208496,
+      "learning_rate": 4.873210092177167e-05,
+      "loss": 0.7071,
+      "num_input_tokens_seen": 1688912,
+      "step": 360
+    },
+    {
+      "epoch": 0.20636042402826854,
+      "grad_norm": 1.7091903686523438,
+      "learning_rate": 4.869694821536709e-05,
+      "loss": 0.8665,
+      "num_input_tokens_seen": 1712000,
+      "step": 365
+    },
+    {
+      "epoch": 0.20918727915194346,
+      "grad_norm": 2.611337661743164,
+      "learning_rate": 4.866132787402892e-05,
+      "loss": 0.896,
+      "num_input_tokens_seen": 1735552,
+      "step": 370
+    },
+    {
+      "epoch": 0.21201413427561838,
+      "grad_norm": 2.5628631114959717,
+      "learning_rate": 4.8625240600688e-05,
+      "loss": 0.8333,
+      "num_input_tokens_seen": 1759152,
+      "step": 375
+    },
+    {
+      "epoch": 0.21484098939929328,
+      "grad_norm": 1.7002663612365723,
+      "learning_rate": 4.858868710748963e-05,
+      "loss": 0.891,
+      "num_input_tokens_seen": 1782560,
+      "step": 380
+    },
+    {
+      "epoch": 0.2176678445229682,
+      "grad_norm": 2.2017710208892822,
+      "learning_rate": 4.855166811577943e-05,
+      "loss": 0.7332,
+      "num_input_tokens_seen": 1805760,
+      "step": 385
+    },
+    {
+      "epoch": 0.22049469964664312,
+      "grad_norm": 1.9160822629928589,
+      "learning_rate": 4.8514184356089195e-05,
+      "loss": 0.6767,
+      "num_input_tokens_seen": 1828944,
+      "step": 390
+    },
+    {
+      "epoch": 0.223321554770318,
+      "grad_norm": 1.42445707321167,
+      "learning_rate": 4.847623656812241e-05,
+      "loss": 0.7443,
+      "num_input_tokens_seen": 1853024,
+      "step": 395
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "grad_norm": 1.6845754384994507,
+      "learning_rate": 4.8437825500739696e-05,
+      "loss": 0.8442,
+      "num_input_tokens_seen": 1876352,
+      "step": 400
+    },
+    {
+      "epoch": 0.22897526501766785,
+      "grad_norm": 2.3869645595550537,
+      "learning_rate": 4.8398951911944024e-05,
+      "loss": 0.6776,
+      "num_input_tokens_seen": 1899392,
+      "step": 405
+    },
+    {
+      "epoch": 0.23180212014134274,
+      "grad_norm": 1.6154192686080933,
+      "learning_rate": 4.835961656886573e-05,
+      "loss": 0.703,
+      "num_input_tokens_seen": 1922720,
+      "step": 410
+    },
+    {
+      "epoch": 0.23462897526501766,
+      "grad_norm": 1.8866560459136963,
+      "learning_rate": 4.831982024774742e-05,
+      "loss": 0.8077,
+      "num_input_tokens_seen": 1945984,
+      "step": 415
+    },
+    {
+      "epoch": 0.23745583038869258,
+      "grad_norm": 1.444536805152893,
+      "learning_rate": 4.82795637339286e-05,
+      "loss": 0.7253,
+      "num_input_tokens_seen": 1969728,
+      "step": 420
+    },
+    {
+      "epoch": 0.24028268551236748,
+      "grad_norm": 1.3602782487869263,
+      "learning_rate": 4.823884782183023e-05,
+      "loss": 0.9074,
+      "num_input_tokens_seen": 1993440,
+      "step": 425
+    },
+    {
+      "epoch": 0.2431095406360424,
+      "grad_norm": 1.8072354793548584,
+      "learning_rate": 4.819767331493903e-05,
+      "loss": 0.7784,
+      "num_input_tokens_seen": 2016864,
+      "step": 430
+    },
+    {
+      "epoch": 0.24593639575971732,
+      "grad_norm": 1.8679770231246948,
+      "learning_rate": 4.815604102579158e-05,
+      "loss": 0.7329,
+      "num_input_tokens_seen": 2040224,
+      "step": 435
+    },
+    {
+      "epoch": 0.24876325088339224,
+      "grad_norm": 2.396023988723755,
+      "learning_rate": 4.811395177595836e-05,
+      "loss": 1.041,
+      "num_input_tokens_seen": 2063728,
+      "step": 440
+    },
+    {
+      "epoch": 0.25159010600706716,
+      "grad_norm": 2.3674533367156982,
+      "learning_rate": 4.8071406396027474e-05,
+      "loss": 0.898,
+      "num_input_tokens_seen": 2087728,
+      "step": 445
+    },
+    {
+      "epoch": 0.254416961130742,
+      "grad_norm": 1.884262204170227,
+      "learning_rate": 4.802840572558831e-05,
+      "loss": 0.674,
+      "num_input_tokens_seen": 2111360,
+      "step": 450
+    },
+    {
+      "epoch": 0.25724381625441695,
+      "grad_norm": 1.729224443435669,
+      "learning_rate": 4.7984950613214915e-05,
+      "loss": 0.736,
+      "num_input_tokens_seen": 2135296,
+      "step": 455
+    },
+    {
+      "epoch": 0.26007067137809187,
+      "grad_norm": 2.1859536170959473,
+      "learning_rate": 4.7941041916449316e-05,
+      "loss": 0.8091,
+      "num_input_tokens_seen": 2158400,
+      "step": 460
+    },
+    {
+      "epoch": 0.2628975265017668,
+      "grad_norm": 1.97829270362854,
+      "learning_rate": 4.789668050178453e-05,
+      "loss": 0.7761,
+      "num_input_tokens_seen": 2181776,
+      "step": 465
+    },
+    {
+      "epoch": 0.2657243816254417,
+      "grad_norm": 2.6589503288269043,
+      "learning_rate": 4.785186724464752e-05,
+      "loss": 0.7418,
+      "num_input_tokens_seen": 2205328,
+      "step": 470
+    },
+    {
+      "epoch": 0.26855123674911663,
+      "grad_norm": 2.8116209506988525,
+      "learning_rate": 4.780660302938188e-05,
+      "loss": 0.8057,
+      "num_input_tokens_seen": 2228704,
+      "step": 475
+    },
+    {
+      "epoch": 0.2713780918727915,
+      "grad_norm": 2.4145610332489014,
+      "learning_rate": 4.7760888749230416e-05,
+      "loss": 0.8408,
+      "num_input_tokens_seen": 2252320,
+      "step": 480
+    },
+    {
+      "epoch": 0.2742049469964664,
+      "grad_norm": 2.821458578109741,
+      "learning_rate": 4.7714725306317486e-05,
+      "loss": 0.8051,
+      "num_input_tokens_seen": 2275424,
+      "step": 485
+    },
+    {
+      "epoch": 0.27703180212014133,
+      "grad_norm": 1.8652580976486206,
+      "learning_rate": 4.766811361163123e-05,
+      "loss": 0.599,
+      "num_input_tokens_seen": 2298528,
+      "step": 490
+    },
+    {
+      "epoch": 0.27985865724381626,
+      "grad_norm": 3.773435115814209,
+      "learning_rate": 4.762105458500555e-05,
+      "loss": 0.7394,
+      "num_input_tokens_seen": 2322336,
+      "step": 495
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 3.6460142135620117,
+      "learning_rate": 4.7573549155102014e-05,
+      "loss": 0.8013,
+      "num_input_tokens_seen": 2345360,
+      "step": 500
+    },
+    {
+      "epoch": 0.2855123674911661,
+      "grad_norm": 2.0722692012786865,
+      "learning_rate": 4.752559825939149e-05,
+      "loss": 0.632,
+      "num_input_tokens_seen": 2368960,
+      "step": 505
+    },
+    {
+      "epoch": 0.28833922261484096,
+      "grad_norm": 2.3719353675842285,
+      "learning_rate": 4.7477202844135646e-05,
+      "loss": 0.8097,
+      "num_input_tokens_seen": 2391728,
+      "step": 510
+    },
+    {
+      "epoch": 0.2911660777385159,
+      "grad_norm": 1.8794598579406738,
+      "learning_rate": 4.742836386436831e-05,
+      "loss": 0.647,
+      "num_input_tokens_seen": 2414720,
+      "step": 515
+    },
+    {
+      "epoch": 0.2939929328621908,
+      "grad_norm": 2.5139925479888916,
+      "learning_rate": 4.7379082283876566e-05,
+      "loss": 0.6771,
+      "num_input_tokens_seen": 2438016,
+      "step": 520
+    },
+    {
+      "epoch": 0.2968197879858657,
+      "grad_norm": 2.5874509811401367,
+      "learning_rate": 4.7329359075181786e-05,
+      "loss": 0.7763,
+      "num_input_tokens_seen": 2460992,
+      "step": 525
+    },
+    {
+      "epoch": 0.29964664310954064,
+      "grad_norm": 1.524685025215149,
+      "learning_rate": 4.727919521952043e-05,
+      "loss": 0.7088,
+      "num_input_tokens_seen": 2484944,
+      "step": 530
+    },
+    {
+      "epoch": 0.30247349823321557,
+      "grad_norm": 2.759699821472168,
+      "learning_rate": 4.7228591706824674e-05,
+      "loss": 0.927,
+      "num_input_tokens_seen": 2507936,
+      "step": 535
+    },
+    {
+      "epoch": 0.3053003533568905,
+      "grad_norm": 1.58765709400177,
+      "learning_rate": 4.717754953570286e-05,
+      "loss": 0.8371,
+      "num_input_tokens_seen": 2532032,
+      "step": 540
+    },
+    {
+      "epoch": 0.30812720848056535,
+      "grad_norm": 1.9688793420791626,
+      "learning_rate": 4.71260697134198e-05,
+      "loss": 0.8103,
+      "num_input_tokens_seen": 2555056,
+      "step": 545
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 1.984244465827942,
+      "learning_rate": 4.707415325587692e-05,
+      "loss": 0.7173,
+      "num_input_tokens_seen": 2578288,
+      "step": 550
+    },
+    {
+      "epoch": 0.3137809187279152,
+      "grad_norm": 2.331401824951172,
+      "learning_rate": 4.7021801187592184e-05,
+      "loss": 0.8489,
+      "num_input_tokens_seen": 2601712,
+      "step": 555
+    },
+    {
+      "epoch": 0.3166077738515901,
+      "grad_norm": 2.049757480621338,
+      "learning_rate": 4.696901454167988e-05,
+      "loss": 0.7262,
+      "num_input_tokens_seen": 2625056,
+      "step": 560
+    },
+    {
+      "epoch": 0.31943462897526503,
+      "grad_norm": 1.7714154720306396,
+      "learning_rate": 4.691579435983027e-05,
+      "loss": 0.6455,
+      "num_input_tokens_seen": 2648688,
+      "step": 565
+    },
+    {
+      "epoch": 0.32226148409893995,
+      "grad_norm": 1.9945061206817627,
+      "learning_rate": 4.6862141692288944e-05,
+      "loss": 0.8747,
+      "num_input_tokens_seen": 2672352,
+      "step": 570
+    },
+    {
+      "epoch": 0.3250883392226148,
+      "grad_norm": 2.4137539863586426,
+      "learning_rate": 4.680805759783622e-05,
+      "loss": 0.9107,
+      "num_input_tokens_seen": 2695744,
+      "step": 575
+    },
+    {
+      "epoch": 0.32791519434628974,
+      "grad_norm": 2.3516249656677246,
+      "learning_rate": 4.675354314376614e-05,
+      "loss": 0.7114,
+      "num_input_tokens_seen": 2719168,
+      "step": 580
+    },
+    {
+      "epoch": 0.33074204946996466,
+      "grad_norm": 4.508022785186768,
+      "learning_rate": 4.6698599405865463e-05,
+      "loss": 0.8522,
+      "num_input_tokens_seen": 2742640,
+      "step": 585
+    },
+    {
+      "epoch": 0.3335689045936396,
+      "grad_norm": 2.1811635494232178,
+      "learning_rate": 4.6643227468392416e-05,
+      "loss": 0.7518,
+      "num_input_tokens_seen": 2765584,
+      "step": 590
+    },
+    {
+      "epoch": 0.3363957597173145,
+      "grad_norm": 2.110956907272339,
+      "learning_rate": 4.6587428424055326e-05,
+      "loss": 1.0063,
+      "num_input_tokens_seen": 2788656,
+      "step": 595
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 1.8346225023269653,
+      "learning_rate": 4.6531203373991014e-05,
+      "loss": 0.6981,
+      "num_input_tokens_seen": 2811760,
+      "step": 600
+    },
+    {
+      "epoch": 0.3420494699646643,
+      "grad_norm": 1.713894009590149,
+      "learning_rate": 4.647455342774308e-05,
+      "loss": 0.6034,
+      "num_input_tokens_seen": 2835024,
+      "step": 605
+    },
+    {
+      "epoch": 0.3448763250883392,
+      "grad_norm": 1.5277444124221802,
+      "learning_rate": 4.6417479703240055e-05,
+      "loss": 0.6798,
+      "num_input_tokens_seen": 2858432,
+      "step": 610
+    },
+    {
+      "epoch": 0.34770318021201413,
+      "grad_norm": 2.02787184715271,
+      "learning_rate": 4.635998332677325e-05,
+      "loss": 0.7001,
+      "num_input_tokens_seen": 2881968,
+      "step": 615
+    },
+    {
+      "epoch": 0.35053003533568905,
+      "grad_norm": 2.788226366043091,
+      "learning_rate": 4.6302065432974616e-05,
+      "loss": 0.9002,
+      "num_input_tokens_seen": 2905184,
+      "step": 620
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "grad_norm": 2.641052484512329,
+      "learning_rate": 4.624372716479428e-05,
+      "loss": 0.7627,
+      "num_input_tokens_seen": 2928336,
+      "step": 625
+    },
+    {
+      "epoch": 0.3561837455830389,
+      "grad_norm": 2.559187889099121,
+      "learning_rate": 4.618496967347805e-05,
+      "loss": 0.848,
+      "num_input_tokens_seen": 2951952,
+      "step": 630
+    },
+    {
+      "epoch": 0.35901060070671376,
+      "grad_norm": 2.07712459564209,
+      "learning_rate": 4.6125794118544675e-05,
+      "loss": 0.807,
+      "num_input_tokens_seen": 2975840,
+      "step": 635
+    },
+    {
+      "epoch": 0.3618374558303887,
+      "grad_norm": 2.694662094116211,
+      "learning_rate": 4.606620166776294e-05,
+      "loss": 0.6978,
+      "num_input_tokens_seen": 2999088,
+      "step": 640
+    },
+    {
+      "epoch": 0.3646643109540636,
+      "grad_norm": 2.0563204288482666,
+      "learning_rate": 4.6006193497128666e-05,
+      "loss": 0.6892,
+      "num_input_tokens_seen": 3022224,
+      "step": 645
+    },
+    {
+      "epoch": 0.3674911660777385,
+      "grad_norm": 1.8163408041000366,
+      "learning_rate": 4.594577079084146e-05,
+      "loss": 0.6717,
+      "num_input_tokens_seen": 3045104,
+      "step": 650
+    },
+    {
+      "epoch": 0.37031802120141344,
+      "grad_norm": 2.1439476013183594,
+      "learning_rate": 4.588493474128136e-05,
+      "loss": 0.6975,
+      "num_input_tokens_seen": 3068256,
+      "step": 655
+    },
+    {
+      "epoch": 0.37314487632508836,
+      "grad_norm": 2.6993794441223145,
+      "learning_rate": 4.582368654898533e-05,
+      "loss": 0.692,
+      "num_input_tokens_seen": 3092096,
+      "step": 660
+    },
+    {
+      "epoch": 0.3759717314487632,
+      "grad_norm": 3.1468234062194824,
+      "learning_rate": 4.5762027422623546e-05,
+      "loss": 0.762,
+      "num_input_tokens_seen": 3115440,
+      "step": 665
+    },
+    {
+      "epoch": 0.37879858657243815,
+      "grad_norm": 2.1956112384796143,
+      "learning_rate": 4.569995857897551e-05,
+      "loss": 0.759,
+      "num_input_tokens_seen": 3138960,
+      "step": 670
+    },
+    {
+      "epoch": 0.38162544169611307,
+      "grad_norm": 3.2120509147644043,
+      "learning_rate": 4.563748124290611e-05,
+      "loss": 0.8743,
+      "num_input_tokens_seen": 3163088,
+      "step": 675
+    },
+    {
+      "epoch": 0.384452296819788,
+      "grad_norm": 2.3125061988830566,
+      "learning_rate": 4.557459664734141e-05,
+      "loss": 0.7595,
+      "num_input_tokens_seen": 3186336,
+      "step": 680
+    },
+    {
+      "epoch": 0.3872791519434629,
+      "grad_norm": 2.3744454383850098,
+      "learning_rate": 4.551130603324431e-05,
+      "loss": 0.7657,
+      "num_input_tokens_seen": 3209744,
+      "step": 685
+    },
+    {
+      "epoch": 0.3901060070671378,
+      "grad_norm": 2.250967025756836,
+      "learning_rate": 4.5447610649590064e-05,
+      "loss": 0.7593,
+      "num_input_tokens_seen": 3233632,
+      "step": 690
+    },
+    {
+      "epoch": 0.39293286219081275,
+      "grad_norm": 2.090684175491333,
+      "learning_rate": 4.538351175334167e-05,
+      "loss": 0.6963,
+      "num_input_tokens_seen": 3256960,
+      "step": 695
+    },
+    {
+      "epoch": 0.3957597173144876,
+      "grad_norm": 1.8485418558120728,
+      "learning_rate": 4.531901060942497e-05,
+      "loss": 0.835,
+      "num_input_tokens_seen": 3280432,
+      "step": 700
+    },
+    {
+      "epoch": 0.39858657243816253,
+      "grad_norm": 2.028855800628662,
+      "learning_rate": 4.5254108490703824e-05,
+      "loss": 0.9134,
+      "num_input_tokens_seen": 3304064,
+      "step": 705
+    },
+    {
+      "epoch": 0.40141342756183745,
+      "grad_norm": 2.0917155742645264,
+      "learning_rate": 4.5188806677954864e-05,
+      "loss": 0.8666,
+      "num_input_tokens_seen": 3327632,
+      "step": 710
+    },
+    {
+      "epoch": 0.4042402826855124,
+      "grad_norm": 1.842624306678772,
+      "learning_rate": 4.51231064598423e-05,
+      "loss": 0.6044,
+      "num_input_tokens_seen": 3351104,
+      "step": 715
+    },
+    {
+      "epoch": 0.4070671378091873,
+      "grad_norm": 2.7080881595611572,
+      "learning_rate": 4.505700913289246e-05,
+      "loss": 0.9124,
+      "num_input_tokens_seen": 3375360,
+      "step": 720
+    },
+    {
+      "epoch": 0.4098939929328622,
+      "grad_norm": 2.348064661026001,
+      "learning_rate": 4.499051600146819e-05,
+      "loss": 0.6307,
+      "num_input_tokens_seen": 3398736,
+      "step": 725
+    },
+    {
+      "epoch": 0.4127208480565371,
+      "grad_norm": 2.623867988586426,
+      "learning_rate": 4.4923628377743146e-05,
+      "loss": 0.7896,
+      "num_input_tokens_seen": 3422432,
+      "step": 730
+    },
+    {
+      "epoch": 0.415547703180212,
+      "grad_norm": 2.413691520690918,
+      "learning_rate": 4.485634758167589e-05,
+      "loss": 0.8459,
+      "num_input_tokens_seen": 3446272,
+      "step": 735
+    },
+    {
+      "epoch": 0.4183745583038869,
+      "grad_norm": 2.2855966091156006,
+      "learning_rate": 4.478867494098381e-05,
+      "loss": 0.6007,
+      "num_input_tokens_seen": 3470064,
+      "step": 740
+    },
+    {
+      "epoch": 0.42120141342756184,
+      "grad_norm": 2.137235164642334,
+      "learning_rate": 4.4720611791116986e-05,
+      "loss": 0.5928,
+      "num_input_tokens_seen": 3493824,
+      "step": 745
+    },
+    {
+      "epoch": 0.42402826855123676,
+      "grad_norm": 2.7548105716705322,
+      "learning_rate": 4.4652159475231745e-05,
+      "loss": 0.8043,
+      "num_input_tokens_seen": 3517296,
+      "step": 750
+    },
+    {
+      "epoch": 0.4268551236749117,
+      "grad_norm": 1.7610399723052979,
+      "learning_rate": 4.458331934416427e-05,
+      "loss": 0.7569,
+      "num_input_tokens_seen": 3540640,
+      "step": 755
+    },
+    {
+      "epoch": 0.42968197879858655,
+      "grad_norm": 1.7641017436981201,
+      "learning_rate": 4.451409275640379e-05,
+      "loss": 0.7176,
+      "num_input_tokens_seen": 3564240,
+      "step": 760
+    },
+    {
+      "epoch": 0.43250883392226147,
+      "grad_norm": 2.505873441696167,
+      "learning_rate": 4.444448107806596e-05,
+      "loss": 0.8584,
+      "num_input_tokens_seen": 3587552,
+      "step": 765
+    },
+    {
+      "epoch": 0.4353356890459364,
+      "grad_norm": 1.663974404335022,
+      "learning_rate": 4.4374485682865716e-05,
+      "loss": 0.8907,
+      "num_input_tokens_seen": 3610848,
+      "step": 770
+    },
+    {
+      "epoch": 0.4381625441696113,
+      "grad_norm": 1.5447556972503662,
+      "learning_rate": 4.4304107952090316e-05,
+      "loss": 0.6835,
+      "num_input_tokens_seen": 3634784,
+      "step": 775
+    },
+    {
+      "epoch": 0.44098939929328623,
+      "grad_norm": 2.8021128177642822,
+      "learning_rate": 4.423334927457198e-05,
+      "loss": 0.7266,
+      "num_input_tokens_seen": 3657808,
+      "step": 780
+    },
+    {
+      "epoch": 0.44381625441696115,
+      "grad_norm": 2.9464962482452393,
+      "learning_rate": 4.416221104666052e-05,
+      "loss": 0.8822,
+      "num_input_tokens_seen": 3681216,
+      "step": 785
+    },
+    {
+      "epoch": 0.446643109540636,
+      "grad_norm": 3.3185925483703613,
+      "learning_rate": 4.409069467219582e-05,
+      "loss": 0.7421,
+      "num_input_tokens_seen": 3704144,
+      "step": 790
+    },
+    {
+      "epoch": 0.44946996466431094,
+      "grad_norm": 1.573012351989746,
+      "learning_rate": 4.4018801562480064e-05,
+      "loss": 0.6448,
+      "num_input_tokens_seen": 3727648,
+      "step": 795
+    },
+    {
+      "epoch": 0.45229681978798586,
+      "grad_norm": 3.2603092193603516,
+      "learning_rate": 4.3946533136249926e-05,
+      "loss": 0.7036,
+      "num_input_tokens_seen": 3751296,
+      "step": 800
+    },
+    {
+      "epoch": 0.4551236749116608,
+      "grad_norm": 2.652745246887207,
+      "learning_rate": 4.387389081964857e-05,
+      "loss": 0.9158,
+      "num_input_tokens_seen": 3774560,
+      "step": 805
+    },
+    {
+      "epoch": 0.4579505300353357,
+      "grad_norm": 3.102360486984253,
+      "learning_rate": 4.3800876046197506e-05,
+      "loss": 0.8552,
+      "num_input_tokens_seen": 3797264,
+      "step": 810
+    },
+    {
+      "epoch": 0.4607773851590106,
+      "grad_norm": 2.058687210083008,
+      "learning_rate": 4.372749025676829e-05,
+      "loss": 0.7733,
+      "num_input_tokens_seen": 3821120,
+      "step": 815
+    },
+    {
+      "epoch": 0.4636042402826855,
+      "grad_norm": 2.0987045764923096,
+      "learning_rate": 4.365373489955411e-05,
+      "loss": 0.7368,
+      "num_input_tokens_seen": 3844816,
+      "step": 820
+    },
+    {
+      "epoch": 0.4664310954063604,
+      "grad_norm": 1.813137173652649,
+      "learning_rate": 4.357961143004117e-05,
+      "loss": 0.8172,
+      "num_input_tokens_seen": 3868128,
+      "step": 825
+    },
+    {
+      "epoch": 0.46925795053003533,
+      "grad_norm": 2.0965216159820557,
+      "learning_rate": 4.3505121310980024e-05,
+      "loss": 0.721,
+      "num_input_tokens_seen": 3891184,
+      "step": 830
+    },
+    {
+      "epoch": 0.47208480565371025,
+      "grad_norm": 1.9453920125961304,
+      "learning_rate": 4.3430266012356656e-05,
+      "loss": 0.9005,
+      "num_input_tokens_seen": 3914592,
+      "step": 835
+    },
+    {
+      "epoch": 0.47491166077738517,
+      "grad_norm": 1.8437124490737915,
+      "learning_rate": 4.33550470113635e-05,
+      "loss": 0.8215,
+      "num_input_tokens_seen": 3938352,
+      "step": 840
+    },
+    {
+      "epoch": 0.4777385159010601,
+      "grad_norm": 2.2815515995025635,
+      "learning_rate": 4.3279465792370275e-05,
+      "loss": 0.7864,
+      "num_input_tokens_seen": 3961952,
+      "step": 845
+    },
+    {
+      "epoch": 0.48056537102473496,
+      "grad_norm": 1.6929998397827148,
+      "learning_rate": 4.320352384689471e-05,
+      "loss": 0.7437,
+      "num_input_tokens_seen": 3985456,
+      "step": 850
+    },
+    {
+      "epoch": 0.4833922261484099,
+      "grad_norm": 1.790462613105774,
+      "learning_rate": 4.312722267357311e-05,
+      "loss": 0.5711,
+      "num_input_tokens_seen": 4008784,
+      "step": 855
+    },
+    {
+      "epoch": 0.4862190812720848,
+      "grad_norm": 3.130824327468872,
+      "learning_rate": 4.305056377813075e-05,
+      "loss": 0.6519,
+      "num_input_tokens_seen": 4032752,
+      "step": 860
+    },
+    {
+      "epoch": 0.4890459363957597,
+      "grad_norm": 2.7931573390960693,
+      "learning_rate": 4.297354867335219e-05,
+      "loss": 0.6296,
+      "num_input_tokens_seen": 4056240,
+      "step": 865
+    },
+    {
+      "epoch": 0.49187279151943464,
+      "grad_norm": 2.679901361465454,
+      "learning_rate": 4.289617887905143e-05,
+      "loss": 0.8868,
+      "num_input_tokens_seen": 4079296,
+      "step": 870
+    },
+    {
+      "epoch": 0.49469964664310956,
+      "grad_norm": 1.973581075668335,
+      "learning_rate": 4.2818455922041876e-05,
+      "loss": 0.696,
+      "num_input_tokens_seen": 4103120,
+      "step": 875
+    },
+    {
+      "epoch": 0.4975265017667845,
+      "grad_norm": 2.4409375190734863,
+      "learning_rate": 4.274038133610628e-05,
+      "loss": 0.798,
+      "num_input_tokens_seen": 4127008,
+      "step": 880
+    },
+    {
+      "epoch": 0.5003533568904593,
+      "grad_norm": 3.359973907470703,
+      "learning_rate": 4.266195666196639e-05,
+      "loss": 0.7207,
+      "num_input_tokens_seen": 4151024,
+      "step": 885
+    },
+    {
+      "epoch": 0.5031802120141343,
+      "grad_norm": 1.7413347959518433,
+      "learning_rate": 4.2583183447252596e-05,
+      "loss": 0.774,
+      "num_input_tokens_seen": 4174896,
+      "step": 890
+    },
+    {
+      "epoch": 0.5060070671378092,
+      "grad_norm": 1.6167852878570557,
+      "learning_rate": 4.250406324647339e-05,
+      "loss": 0.805,
+      "num_input_tokens_seen": 4198528,
+      "step": 895
+    },
+    {
+      "epoch": 0.508833922261484,
+      "grad_norm": 2.1960134506225586,
+      "learning_rate": 4.242459762098466e-05,
+      "loss": 0.714,
+      "num_input_tokens_seen": 4222160,
+      "step": 900
+    },
+    {
+      "epoch": 0.511660777385159,
+      "grad_norm": 1.9099704027175903,
+      "learning_rate": 4.234478813895891e-05,
+      "loss": 0.7326,
+      "num_input_tokens_seen": 4245424,
+      "step": 905
+    },
+    {
+      "epoch": 0.5144876325088339,
+      "grad_norm": 3.273469924926758,
+      "learning_rate": 4.226463637535429e-05,
+      "loss": 0.8094,
+      "num_input_tokens_seen": 4269232,
+      "step": 910
+    },
+    {
+      "epoch": 0.5173144876325089,
+      "grad_norm": 1.889750361442566,
+      "learning_rate": 4.218414391188353e-05,
+      "loss": 0.697,
+      "num_input_tokens_seen": 4292688,
+      "step": 915
+    },
+    {
+      "epoch": 0.5201413427561837,
+      "grad_norm": 2.302185535430908,
+      "learning_rate": 4.2103312336982734e-05,
+      "loss": 0.8087,
+      "num_input_tokens_seen": 4316192,
+      "step": 920
+    },
+    {
+      "epoch": 0.5229681978798587,
+      "grad_norm": 3.6521856784820557,
+      "learning_rate": 4.2022143245779996e-05,
+      "loss": 0.7683,
+      "num_input_tokens_seen": 4340016,
+      "step": 925
+    },
+    {
+      "epoch": 0.5257950530035336,
+      "grad_norm": 1.4392321109771729,
+      "learning_rate": 4.194063824006397e-05,
+      "loss": 0.7393,
+      "num_input_tokens_seen": 4364048,
+      "step": 930
+    },
+    {
+      "epoch": 0.5286219081272084,
+      "grad_norm": 1.6422187089920044,
+      "learning_rate": 4.185879892825222e-05,
+      "loss": 0.8686,
+      "num_input_tokens_seen": 4387456,
+      "step": 935
+    },
+    {
+      "epoch": 0.5314487632508834,
+      "grad_norm": 2.241570472717285,
+      "learning_rate": 4.177662692535952e-05,
+      "loss": 0.7628,
+      "num_input_tokens_seen": 4410768,
+      "step": 940
+    },
+    {
+      "epoch": 0.5342756183745583,
+      "grad_norm": 2.3923139572143555,
+      "learning_rate": 4.1694123852965926e-05,
+      "loss": 0.6928,
+      "num_input_tokens_seen": 4434064,
+      "step": 945
+    },
+    {
+      "epoch": 0.5371024734982333,
+      "grad_norm": 2.7285265922546387,
+      "learning_rate": 4.161129133918485e-05,
+      "loss": 0.7368,
+      "num_input_tokens_seen": 4457760,
+      "step": 950
+    },
+    {
+      "epoch": 0.5399293286219081,
+      "grad_norm": 2.306457757949829,
+      "learning_rate": 4.152813101863087e-05,
+      "loss": 0.7434,
+      "num_input_tokens_seen": 4480688,
+      "step": 955
+    },
+    {
+      "epoch": 0.542756183745583,
+      "grad_norm": 1.9828684329986572,
+      "learning_rate": 4.144464453238748e-05,
+      "loss": 0.7868,
+      "num_input_tokens_seen": 4504496,
+      "step": 960
+    },
+    {
+      "epoch": 0.545583038869258,
+      "grad_norm": 2.1162819862365723,
+      "learning_rate": 4.136083352797476e-05,
+      "loss": 0.8646,
+      "num_input_tokens_seen": 4527600,
+      "step": 965
+    },
+    {
+      "epoch": 0.5484098939929328,
+      "grad_norm": 1.9256089925765991,
+      "learning_rate": 4.1276699659316787e-05,
+      "loss": 0.7628,
+      "num_input_tokens_seen": 4551600,
+      "step": 970
+    },
+    {
+      "epoch": 0.5512367491166078,
+      "grad_norm": 2.933058738708496,
+      "learning_rate": 4.119224458670905e-05,
+      "loss": 0.7804,
+      "num_input_tokens_seen": 4575408,
+      "step": 975
+    },
+    {
+      "epoch": 0.5540636042402827,
+      "grad_norm": 2.9193356037139893,
+      "learning_rate": 4.110746997678565e-05,
+      "loss": 0.7821,
+      "num_input_tokens_seen": 4598912,
+      "step": 980
+    },
+    {
+      "epoch": 0.5568904593639576,
+      "grad_norm": 2.562621831893921,
+      "learning_rate": 4.102237750248645e-05,
+      "loss": 0.6505,
+      "num_input_tokens_seen": 4622416,
+      "step": 985
+    },
+    {
+      "epoch": 0.5597173144876325,
+      "grad_norm": 1.7989310026168823,
+      "learning_rate": 4.093696884302404e-05,
+      "loss": 0.7531,
+      "num_input_tokens_seen": 4646032,
+      "step": 990
+    },
+    {
+      "epoch": 0.5625441696113074,
+      "grad_norm": 2.9085874557495117,
+      "learning_rate": 4.085124568385057e-05,
+      "loss": 0.7638,
+      "num_input_tokens_seen": 4669584,
+      "step": 995
+    },
+    {
+      "epoch": 0.5653710247349824,
+      "grad_norm": 2.0637929439544678,
+      "learning_rate": 4.076520971662455e-05,
+      "loss": 0.5917,
+      "num_input_tokens_seen": 4693296,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3536,
+  "num_input_tokens_seen": 4693296,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.589277054495949e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cbc94a713da9a44fc659b7c77cb3a54484d5d6762cafa7efa3cea0c036c9ff
+size 5432

checkpoint-1100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-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-1100/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:gate_proj|o_proj|k_proj|up_proj|down_proj|q_proj|v_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075e73d9f06d162d467ac8cd476edbcf520e1c239d299add03684b2ed5e91459
+size 36981072

checkpoint-1100/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-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810fa08d1246439cd8918816a671596a3fbd6030be4e6930d5cc79a44bcb4d62
+size 74188650

checkpoint-1100/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-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d70878378da620d2cdac8346d4671c588982ceb384c39f8fdcdf79dd7d4c3f
+size 1064

checkpoint-1100/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-1100/tokenizer.json

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

checkpoint-1100/tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1100/trainer_state.json

@@ -0,0 +1,1793 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6219081272084805,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0028268551236749115,
+      "grad_norm": 3.236659288406372,
+      "learning_rate": 4.999975332533892e-05,
+      "loss": 1.1521,
+      "num_input_tokens_seen": 23072,
+      "step": 5
+    },
+    {
+      "epoch": 0.005653710247349823,
+      "grad_norm": 2.117961883544922,
+      "learning_rate": 4.999901330622352e-05,
+      "loss": 1.1355,
+      "num_input_tokens_seen": 46144,
+      "step": 10
+    },
+    {
+      "epoch": 0.008480565371024734,
+      "grad_norm": 1.072292447090149,
+      "learning_rate": 4.999777995725733e-05,
+      "loss": 1.0243,
+      "num_input_tokens_seen": 69232,
+      "step": 15
+    },
+    {
+      "epoch": 0.011307420494699646,
+      "grad_norm": 2.135847330093384,
+      "learning_rate": 4.999605330277923e-05,
+      "loss": 0.8573,
+      "num_input_tokens_seen": 93072,
+      "step": 20
+    },
+    {
+      "epoch": 0.014134275618374558,
+      "grad_norm": 1.1360677480697632,
+      "learning_rate": 4.9993833376862976e-05,
+      "loss": 0.8121,
+      "num_input_tokens_seen": 116624,
+      "step": 25
+    },
+    {
+      "epoch": 0.01696113074204947,
+      "grad_norm": 1.7201180458068848,
+      "learning_rate": 4.9991120223316514e-05,
+      "loss": 0.7727,
+      "num_input_tokens_seen": 140448,
+      "step": 30
+    },
+    {
+      "epoch": 0.019787985865724382,
+      "grad_norm": 2.26900577545166,
+      "learning_rate": 4.998791389568115e-05,
+      "loss": 1.0105,
+      "num_input_tokens_seen": 164656,
+      "step": 35
+    },
+    {
+      "epoch": 0.022614840989399292,
+      "grad_norm": 1.620118260383606,
+      "learning_rate": 4.998421445723046e-05,
+      "loss": 0.7647,
+      "num_input_tokens_seen": 188288,
+      "step": 40
+    },
+    {
+      "epoch": 0.025441696113074206,
+      "grad_norm": 1.4073580503463745,
+      "learning_rate": 4.998002198096906e-05,
+      "loss": 1.0147,
+      "num_input_tokens_seen": 211616,
+      "step": 45
+    },
+    {
+      "epoch": 0.028268551236749116,
+      "grad_norm": 1.7421135902404785,
+      "learning_rate": 4.997533654963118e-05,
+      "loss": 0.7942,
+      "num_input_tokens_seen": 235200,
+      "step": 50
+    },
+    {
+      "epoch": 0.03109540636042403,
+      "grad_norm": 2.93461537361145,
+      "learning_rate": 4.997015825567898e-05,
+      "loss": 0.9321,
+      "num_input_tokens_seen": 258800,
+      "step": 55
+    },
+    {
+      "epoch": 0.03392226148409894,
+      "grad_norm": 1.723960518836975,
+      "learning_rate": 4.996448720130077e-05,
+      "loss": 0.8301,
+      "num_input_tokens_seen": 282176,
+      "step": 60
+    },
+    {
+      "epoch": 0.03674911660777385,
+      "grad_norm": 1.5170176029205322,
+      "learning_rate": 4.9958323498408994e-05,
+      "loss": 0.9043,
+      "num_input_tokens_seen": 305632,
+      "step": 65
+    },
+    {
+      "epoch": 0.039575971731448764,
+      "grad_norm": 1.414136290550232,
+      "learning_rate": 4.995166726863799e-05,
+      "loss": 0.8304,
+      "num_input_tokens_seen": 328608,
+      "step": 70
+    },
+    {
+      "epoch": 0.04240282685512368,
+      "grad_norm": 1.5558068752288818,
+      "learning_rate": 4.994451864334162e-05,
+      "loss": 0.8947,
+      "num_input_tokens_seen": 352032,
+      "step": 75
+    },
+    {
+      "epoch": 0.045229681978798585,
+      "grad_norm": 1.669939398765564,
+      "learning_rate": 4.9936877763590664e-05,
+      "loss": 0.9019,
+      "num_input_tokens_seen": 375904,
+      "step": 80
+    },
+    {
+      "epoch": 0.0480565371024735,
+      "grad_norm": 2.2579429149627686,
+      "learning_rate": 4.992874478017003e-05,
+      "loss": 0.9061,
+      "num_input_tokens_seen": 399472,
+      "step": 85
+    },
+    {
+      "epoch": 0.05088339222614841,
+      "grad_norm": 1.8936649560928345,
+      "learning_rate": 4.99201198535758e-05,
+      "loss": 0.8414,
+      "num_input_tokens_seen": 422592,
+      "step": 90
+    },
+    {
+      "epoch": 0.05371024734982332,
+      "grad_norm": 2.1161952018737793,
+      "learning_rate": 4.991100315401203e-05,
+      "loss": 1.0194,
+      "num_input_tokens_seen": 445744,
+      "step": 95
+    },
+    {
+      "epoch": 0.05653710247349823,
+      "grad_norm": 2.3125863075256348,
+      "learning_rate": 4.990139486138743e-05,
+      "loss": 0.7639,
+      "num_input_tokens_seen": 469184,
+      "step": 100
+    },
+    {
+      "epoch": 0.059363957597173146,
+      "grad_norm": 2.460916757583618,
+      "learning_rate": 4.989129516531178e-05,
+      "loss": 0.8552,
+      "num_input_tokens_seen": 492800,
+      "step": 105
+    },
+    {
+      "epoch": 0.06219081272084806,
+      "grad_norm": 1.7828129529953003,
+      "learning_rate": 4.9880704265092225e-05,
+      "loss": 0.7322,
+      "num_input_tokens_seen": 516912,
+      "step": 110
+    },
+    {
+      "epoch": 0.06501766784452297,
+      "grad_norm": 2.2058181762695312,
+      "learning_rate": 4.9869622369729286e-05,
+      "loss": 0.8776,
+      "num_input_tokens_seen": 540800,
+      "step": 115
+    },
+    {
+      "epoch": 0.06784452296819787,
+      "grad_norm": 2.826209545135498,
+      "learning_rate": 4.985804969791279e-05,
+      "loss": 0.7862,
+      "num_input_tokens_seen": 564672,
+      "step": 120
+    },
+    {
+      "epoch": 0.0706713780918728,
+      "grad_norm": 2.14705491065979,
+      "learning_rate": 4.9845986478017526e-05,
+      "loss": 0.9268,
+      "num_input_tokens_seen": 588384,
+      "step": 125
+    },
+    {
+      "epoch": 0.0734982332155477,
+      "grad_norm": 1.8558905124664307,
+      "learning_rate": 4.9833432948098754e-05,
+      "loss": 0.8998,
+      "num_input_tokens_seen": 611888,
+      "step": 130
+    },
+    {
+      "epoch": 0.07632508833922262,
+      "grad_norm": 1.619469404220581,
+      "learning_rate": 4.9820389355887484e-05,
+      "loss": 0.9142,
+      "num_input_tokens_seen": 635392,
+      "step": 135
+    },
+    {
+      "epoch": 0.07915194346289753,
+      "grad_norm": 2.032025098800659,
+      "learning_rate": 4.9806855958785625e-05,
+      "loss": 0.9182,
+      "num_input_tokens_seen": 658880,
+      "step": 140
+    },
+    {
+      "epoch": 0.08197879858657244,
+      "grad_norm": 2.5096957683563232,
+      "learning_rate": 4.979283302386086e-05,
+      "loss": 0.9964,
+      "num_input_tokens_seen": 681792,
+      "step": 145
+    },
+    {
+      "epoch": 0.08480565371024736,
+      "grad_norm": 2.0987000465393066,
+      "learning_rate": 4.9778320827841416e-05,
+      "loss": 0.9709,
+      "num_input_tokens_seen": 704944,
+      "step": 150
+    },
+    {
+      "epoch": 0.08763250883392226,
+      "grad_norm": 1.7368932962417603,
+      "learning_rate": 4.976331965711056e-05,
+      "loss": 0.8381,
+      "num_input_tokens_seen": 728288,
+      "step": 155
+    },
+    {
+      "epoch": 0.09045936395759717,
+      "grad_norm": 1.3404303789138794,
+      "learning_rate": 4.9747829807701e-05,
+      "loss": 0.746,
+      "num_input_tokens_seen": 752208,
+      "step": 160
+    },
+    {
+      "epoch": 0.09328621908127209,
+      "grad_norm": 2.785475969314575,
+      "learning_rate": 4.973185158528899e-05,
+      "loss": 0.933,
+      "num_input_tokens_seen": 775472,
+      "step": 165
+    },
+    {
+      "epoch": 0.096113074204947,
+      "grad_norm": 1.7333956956863403,
+      "learning_rate": 4.971538530518836e-05,
+      "loss": 0.9036,
+      "num_input_tokens_seen": 798912,
+      "step": 170
+    },
+    {
+      "epoch": 0.0989399293286219,
+      "grad_norm": 2.1001110076904297,
+      "learning_rate": 4.9698431292344216e-05,
+      "loss": 0.7976,
+      "num_input_tokens_seen": 822480,
+      "step": 175
+    },
+    {
+      "epoch": 0.10176678445229682,
+      "grad_norm": 1.8633843660354614,
+      "learning_rate": 4.96809898813266e-05,
+      "loss": 0.7499,
+      "num_input_tokens_seen": 845456,
+      "step": 180
+    },
+    {
+      "epoch": 0.10459363957597173,
+      "grad_norm": 1.7571918964385986,
+      "learning_rate": 4.966306141632384e-05,
+      "loss": 0.7536,
+      "num_input_tokens_seen": 868592,
+      "step": 185
+    },
+    {
+      "epoch": 0.10742049469964664,
+      "grad_norm": 2.424466371536255,
+      "learning_rate": 4.964464625113578e-05,
+      "loss": 0.7603,
+      "num_input_tokens_seen": 892288,
+      "step": 190
+    },
+    {
+      "epoch": 0.11024734982332156,
+      "grad_norm": 3.250654935836792,
+      "learning_rate": 4.9625744749166776e-05,
+      "loss": 0.7796,
+      "num_input_tokens_seen": 916016,
+      "step": 195
+    },
+    {
+      "epoch": 0.11307420494699646,
+      "grad_norm": 2.098060369491577,
+      "learning_rate": 4.9606357283418575e-05,
+      "loss": 0.7504,
+      "num_input_tokens_seen": 939696,
+      "step": 200
+    },
+    {
+      "epoch": 0.11590106007067137,
+      "grad_norm": 1.9629781246185303,
+      "learning_rate": 4.958648423648289e-05,
+      "loss": 0.9839,
+      "num_input_tokens_seen": 962656,
+      "step": 205
+    },
+    {
+      "epoch": 0.11872791519434629,
+      "grad_norm": 3.670927047729492,
+      "learning_rate": 4.95661260005339e-05,
+      "loss": 0.9137,
+      "num_input_tokens_seen": 985808,
+      "step": 210
+    },
+    {
+      "epoch": 0.1215547703180212,
+      "grad_norm": 1.5907021760940552,
+      "learning_rate": 4.9545282977320464e-05,
+      "loss": 0.8635,
+      "num_input_tokens_seen": 1008992,
+      "step": 215
+    },
+    {
+      "epoch": 0.12438162544169612,
+      "grad_norm": 1.8623510599136353,
+      "learning_rate": 4.952395557815826e-05,
+      "loss": 0.8384,
+      "num_input_tokens_seen": 1032576,
+      "step": 220
+    },
+    {
+      "epoch": 0.127208480565371,
+      "grad_norm": 2.1950509548187256,
+      "learning_rate": 4.9502144223921584e-05,
+      "loss": 0.9326,
+      "num_input_tokens_seen": 1056224,
+      "step": 225
+    },
+    {
+      "epoch": 0.13003533568904593,
+      "grad_norm": 1.7406038045883179,
+      "learning_rate": 4.9479849345035125e-05,
+      "loss": 0.7225,
+      "num_input_tokens_seen": 1079616,
+      "step": 230
+    },
+    {
+      "epoch": 0.13286219081272085,
+      "grad_norm": 1.8558340072631836,
+      "learning_rate": 4.9457071381465406e-05,
+      "loss": 0.8379,
+      "num_input_tokens_seen": 1102720,
+      "step": 235
+    },
+    {
+      "epoch": 0.13568904593639575,
+      "grad_norm": 1.887434959411621,
+      "learning_rate": 4.943381078271214e-05,
+      "loss": 0.8197,
+      "num_input_tokens_seen": 1126144,
+      "step": 240
+    },
+    {
+      "epoch": 0.13851590106007067,
+      "grad_norm": 2.088313579559326,
+      "learning_rate": 4.941006800779937e-05,
+      "loss": 0.7736,
+      "num_input_tokens_seen": 1149632,
+      "step": 245
+    },
+    {
+      "epoch": 0.1413427561837456,
+      "grad_norm": 2.0320558547973633,
+      "learning_rate": 4.938584352526636e-05,
+      "loss": 1.009,
+      "num_input_tokens_seen": 1173040,
+      "step": 250
+    },
+    {
+      "epoch": 0.14416961130742048,
+      "grad_norm": 2.0947532653808594,
+      "learning_rate": 4.93611378131584e-05,
+      "loss": 0.9782,
+      "num_input_tokens_seen": 1196768,
+      "step": 255
+    },
+    {
+      "epoch": 0.1469964664310954,
+      "grad_norm": 1.8757507801055908,
+      "learning_rate": 4.933595135901732e-05,
+      "loss": 0.8654,
+      "num_input_tokens_seen": 1220048,
+      "step": 260
+    },
+    {
+      "epoch": 0.14982332155477032,
+      "grad_norm": 2.3573222160339355,
+      "learning_rate": 4.9310284659871955e-05,
+      "loss": 0.795,
+      "num_input_tokens_seen": 1243600,
+      "step": 265
+    },
+    {
+      "epoch": 0.15265017667844524,
+      "grad_norm": 1.9607449769973755,
+      "learning_rate": 4.928413822222822e-05,
+      "loss": 0.8133,
+      "num_input_tokens_seen": 1266864,
+      "step": 270
+    },
+    {
+      "epoch": 0.15547703180212014,
+      "grad_norm": 1.5924804210662842,
+      "learning_rate": 4.9257512562059236e-05,
+      "loss": 0.7734,
+      "num_input_tokens_seen": 1289856,
+      "step": 275
+    },
+    {
+      "epoch": 0.15830388692579506,
+      "grad_norm": 1.3379789590835571,
+      "learning_rate": 4.9230408204795034e-05,
+      "loss": 0.8799,
+      "num_input_tokens_seen": 1313632,
+      "step": 280
+    },
+    {
+      "epoch": 0.16113074204946998,
+      "grad_norm": 2.136787176132202,
+      "learning_rate": 4.920282568531228e-05,
+      "loss": 0.6354,
+      "num_input_tokens_seen": 1337504,
+      "step": 285
+    },
+    {
+      "epoch": 0.16395759717314487,
+      "grad_norm": 2.280400037765503,
+      "learning_rate": 4.9174765547923665e-05,
+      "loss": 0.64,
+      "num_input_tokens_seen": 1360944,
+      "step": 290
+    },
+    {
+      "epoch": 0.1667844522968198,
+      "grad_norm": 1.2323652505874634,
+      "learning_rate": 4.9146228346367165e-05,
+      "loss": 0.7516,
+      "num_input_tokens_seen": 1385008,
+      "step": 295
+    },
+    {
+      "epoch": 0.1696113074204947,
+      "grad_norm": 2.9730310440063477,
+      "learning_rate": 4.911721464379516e-05,
+      "loss": 0.8796,
+      "num_input_tokens_seen": 1408112,
+      "step": 300
+    },
+    {
+      "epoch": 0.1724381625441696,
+      "grad_norm": 2.245002269744873,
+      "learning_rate": 4.9087725012763265e-05,
+      "loss": 0.8443,
+      "num_input_tokens_seen": 1431104,
+      "step": 305
+    },
+    {
+      "epoch": 0.17526501766784452,
+      "grad_norm": 2.2738306522369385,
+      "learning_rate": 4.905776003521905e-05,
+      "loss": 0.7832,
+      "num_input_tokens_seen": 1454544,
+      "step": 310
+    },
+    {
+      "epoch": 0.17809187279151945,
+      "grad_norm": 1.9596010446548462,
+      "learning_rate": 4.9027320302490575e-05,
+      "loss": 0.678,
+      "num_input_tokens_seen": 1477904,
+      "step": 315
+    },
+    {
+      "epoch": 0.18091872791519434,
+      "grad_norm": 2.4512102603912354,
+      "learning_rate": 4.89964064152747e-05,
+      "loss": 0.9236,
+      "num_input_tokens_seen": 1501632,
+      "step": 320
+    },
+    {
+      "epoch": 0.18374558303886926,
+      "grad_norm": 1.3344308137893677,
+      "learning_rate": 4.896501898362524e-05,
+      "loss": 0.7098,
+      "num_input_tokens_seen": 1525040,
+      "step": 325
+    },
+    {
+      "epoch": 0.18657243816254418,
+      "grad_norm": 2.6979386806488037,
+      "learning_rate": 4.893315862694092e-05,
+      "loss": 0.9233,
+      "num_input_tokens_seen": 1548448,
+      "step": 330
+    },
+    {
+      "epoch": 0.18939929328621907,
+      "grad_norm": 2.9867770671844482,
+      "learning_rate": 4.8900825973953156e-05,
+      "loss": 0.826,
+      "num_input_tokens_seen": 1571328,
+      "step": 335
+    },
+    {
+      "epoch": 0.192226148409894,
+      "grad_norm": 1.992570161819458,
+      "learning_rate": 4.886802166271364e-05,
+      "loss": 0.9075,
+      "num_input_tokens_seen": 1594576,
+      "step": 340
+    },
+    {
+      "epoch": 0.1950530035335689,
+      "grad_norm": 2.016847848892212,
+      "learning_rate": 4.8834746340581764e-05,
+      "loss": 0.885,
+      "num_input_tokens_seen": 1617824,
+      "step": 345
+    },
+    {
+      "epoch": 0.1978798586572438,
+      "grad_norm": 2.3614108562469482,
+      "learning_rate": 4.880100066421184e-05,
+      "loss": 0.7843,
+      "num_input_tokens_seen": 1641456,
+      "step": 350
+    },
+    {
+      "epoch": 0.20070671378091873,
+      "grad_norm": 2.5570292472839355,
+      "learning_rate": 4.8766785299540104e-05,
+      "loss": 0.8996,
+      "num_input_tokens_seen": 1665280,
+      "step": 355
+    },
+    {
+      "epoch": 0.20353356890459365,
+      "grad_norm": 2.0213332176208496,
+      "learning_rate": 4.873210092177167e-05,
+      "loss": 0.7071,
+      "num_input_tokens_seen": 1688912,
+      "step": 360
+    },
+    {
+      "epoch": 0.20636042402826854,
+      "grad_norm": 1.7091903686523438,
+      "learning_rate": 4.869694821536709e-05,
+      "loss": 0.8665,
+      "num_input_tokens_seen": 1712000,
+      "step": 365
+    },
+    {
+      "epoch": 0.20918727915194346,
+      "grad_norm": 2.611337661743164,
+      "learning_rate": 4.866132787402892e-05,
+      "loss": 0.896,
+      "num_input_tokens_seen": 1735552,
+      "step": 370
+    },
+    {
+      "epoch": 0.21201413427561838,
+      "grad_norm": 2.5628631114959717,
+      "learning_rate": 4.8625240600688e-05,
+      "loss": 0.8333,
+      "num_input_tokens_seen": 1759152,
+      "step": 375
+    },
+    {
+      "epoch": 0.21484098939929328,
+      "grad_norm": 1.7002663612365723,
+      "learning_rate": 4.858868710748963e-05,
+      "loss": 0.891,
+      "num_input_tokens_seen": 1782560,
+      "step": 380
+    },
+    {
+      "epoch": 0.2176678445229682,
+      "grad_norm": 2.2017710208892822,
+      "learning_rate": 4.855166811577943e-05,
+      "loss": 0.7332,
+      "num_input_tokens_seen": 1805760,
+      "step": 385
+    },
+    {
+      "epoch": 0.22049469964664312,
+      "grad_norm": 1.9160822629928589,
+      "learning_rate": 4.8514184356089195e-05,
+      "loss": 0.6767,
+      "num_input_tokens_seen": 1828944,
+      "step": 390
+    },
+    {
+      "epoch": 0.223321554770318,
+      "grad_norm": 1.42445707321167,
+      "learning_rate": 4.847623656812241e-05,
+      "loss": 0.7443,
+      "num_input_tokens_seen": 1853024,
+      "step": 395
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "grad_norm": 1.6845754384994507,
+      "learning_rate": 4.8437825500739696e-05,
+      "loss": 0.8442,
+      "num_input_tokens_seen": 1876352,
+      "step": 400
+    },
+    {
+      "epoch": 0.22897526501766785,
+      "grad_norm": 2.3869645595550537,
+      "learning_rate": 4.8398951911944024e-05,
+      "loss": 0.6776,
+      "num_input_tokens_seen": 1899392,
+      "step": 405
+    },
+    {
+      "epoch": 0.23180212014134274,
+      "grad_norm": 1.6154192686080933,
+      "learning_rate": 4.835961656886573e-05,
+      "loss": 0.703,
+      "num_input_tokens_seen": 1922720,
+      "step": 410
+    },
+    {
+      "epoch": 0.23462897526501766,
+      "grad_norm": 1.8866560459136963,
+      "learning_rate": 4.831982024774742e-05,
+      "loss": 0.8077,
+      "num_input_tokens_seen": 1945984,
+      "step": 415
+    },
+    {
+      "epoch": 0.23745583038869258,
+      "grad_norm": 1.444536805152893,
+      "learning_rate": 4.82795637339286e-05,
+      "loss": 0.7253,
+      "num_input_tokens_seen": 1969728,
+      "step": 420
+    },
+    {
+      "epoch": 0.24028268551236748,
+      "grad_norm": 1.3602782487869263,
+      "learning_rate": 4.823884782183023e-05,
+      "loss": 0.9074,
+      "num_input_tokens_seen": 1993440,
+      "step": 425
+    },
+    {
+      "epoch": 0.2431095406360424,
+      "grad_norm": 1.8072354793548584,
+      "learning_rate": 4.819767331493903e-05,
+      "loss": 0.7784,
+      "num_input_tokens_seen": 2016864,
+      "step": 430
+    },
+    {
+      "epoch": 0.24593639575971732,
+      "grad_norm": 1.8679770231246948,
+      "learning_rate": 4.815604102579158e-05,
+      "loss": 0.7329,
+      "num_input_tokens_seen": 2040224,
+      "step": 435
+    },
+    {
+      "epoch": 0.24876325088339224,
+      "grad_norm": 2.396023988723755,
+      "learning_rate": 4.811395177595836e-05,
+      "loss": 1.041,
+      "num_input_tokens_seen": 2063728,
+      "step": 440
+    },
+    {
+      "epoch": 0.25159010600706716,
+      "grad_norm": 2.3674533367156982,
+      "learning_rate": 4.8071406396027474e-05,
+      "loss": 0.898,
+      "num_input_tokens_seen": 2087728,
+      "step": 445
+    },
+    {
+      "epoch": 0.254416961130742,
+      "grad_norm": 1.884262204170227,
+      "learning_rate": 4.802840572558831e-05,
+      "loss": 0.674,
+      "num_input_tokens_seen": 2111360,
+      "step": 450
+    },
+    {
+      "epoch": 0.25724381625441695,
+      "grad_norm": 1.729224443435669,
+      "learning_rate": 4.7984950613214915e-05,
+      "loss": 0.736,
+      "num_input_tokens_seen": 2135296,
+      "step": 455
+    },
+    {
+      "epoch": 0.26007067137809187,
+      "grad_norm": 2.1859536170959473,
+      "learning_rate": 4.7941041916449316e-05,
+      "loss": 0.8091,
+      "num_input_tokens_seen": 2158400,
+      "step": 460
+    },
+    {
+      "epoch": 0.2628975265017668,
+      "grad_norm": 1.97829270362854,
+      "learning_rate": 4.789668050178453e-05,
+      "loss": 0.7761,
+      "num_input_tokens_seen": 2181776,
+      "step": 465
+    },
+    {
+      "epoch": 0.2657243816254417,
+      "grad_norm": 2.6589503288269043,
+      "learning_rate": 4.785186724464752e-05,
+      "loss": 0.7418,
+      "num_input_tokens_seen": 2205328,
+      "step": 470
+    },
+    {
+      "epoch": 0.26855123674911663,
+      "grad_norm": 2.8116209506988525,
+      "learning_rate": 4.780660302938188e-05,
+      "loss": 0.8057,
+      "num_input_tokens_seen": 2228704,
+      "step": 475
+    },
+    {
+      "epoch": 0.2713780918727915,
+      "grad_norm": 2.4145610332489014,
+      "learning_rate": 4.7760888749230416e-05,
+      "loss": 0.8408,
+      "num_input_tokens_seen": 2252320,
+      "step": 480
+    },
+    {
+      "epoch": 0.2742049469964664,
+      "grad_norm": 2.821458578109741,
+      "learning_rate": 4.7714725306317486e-05,
+      "loss": 0.8051,
+      "num_input_tokens_seen": 2275424,
+      "step": 485
+    },
+    {
+      "epoch": 0.27703180212014133,
+      "grad_norm": 1.8652580976486206,
+      "learning_rate": 4.766811361163123e-05,
+      "loss": 0.599,
+      "num_input_tokens_seen": 2298528,
+      "step": 490
+    },
+    {
+      "epoch": 0.27985865724381626,
+      "grad_norm": 3.773435115814209,
+      "learning_rate": 4.762105458500555e-05,
+      "loss": 0.7394,
+      "num_input_tokens_seen": 2322336,
+      "step": 495
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 3.6460142135620117,
+      "learning_rate": 4.7573549155102014e-05,
+      "loss": 0.8013,
+      "num_input_tokens_seen": 2345360,
+      "step": 500
+    },
+    {
+      "epoch": 0.2855123674911661,
+      "grad_norm": 2.0722692012786865,
+      "learning_rate": 4.752559825939149e-05,
+      "loss": 0.632,
+      "num_input_tokens_seen": 2368960,
+      "step": 505
+    },
+    {
+      "epoch": 0.28833922261484096,
+      "grad_norm": 2.3719353675842285,
+      "learning_rate": 4.7477202844135646e-05,
+      "loss": 0.8097,
+      "num_input_tokens_seen": 2391728,
+      "step": 510
+    },
+    {
+      "epoch": 0.2911660777385159,
+      "grad_norm": 1.8794598579406738,
+      "learning_rate": 4.742836386436831e-05,
+      "loss": 0.647,
+      "num_input_tokens_seen": 2414720,
+      "step": 515
+    },
+    {
+      "epoch": 0.2939929328621908,
+      "grad_norm": 2.5139925479888916,
+      "learning_rate": 4.7379082283876566e-05,
+      "loss": 0.6771,
+      "num_input_tokens_seen": 2438016,
+      "step": 520
+    },
+    {
+      "epoch": 0.2968197879858657,
+      "grad_norm": 2.5874509811401367,
+      "learning_rate": 4.7329359075181786e-05,
+      "loss": 0.7763,
+      "num_input_tokens_seen": 2460992,
+      "step": 525
+    },
+    {
+      "epoch": 0.29964664310954064,
+      "grad_norm": 1.524685025215149,
+      "learning_rate": 4.727919521952043e-05,
+      "loss": 0.7088,
+      "num_input_tokens_seen": 2484944,
+      "step": 530
+    },
+    {
+      "epoch": 0.30247349823321557,
+      "grad_norm": 2.759699821472168,
+      "learning_rate": 4.7228591706824674e-05,
+      "loss": 0.927,
+      "num_input_tokens_seen": 2507936,
+      "step": 535
+    },
+    {
+      "epoch": 0.3053003533568905,
+      "grad_norm": 1.58765709400177,
+      "learning_rate": 4.717754953570286e-05,
+      "loss": 0.8371,
+      "num_input_tokens_seen": 2532032,
+      "step": 540
+    },
+    {
+      "epoch": 0.30812720848056535,
+      "grad_norm": 1.9688793420791626,
+      "learning_rate": 4.71260697134198e-05,
+      "loss": 0.8103,
+      "num_input_tokens_seen": 2555056,
+      "step": 545
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 1.984244465827942,
+      "learning_rate": 4.707415325587692e-05,
+      "loss": 0.7173,
+      "num_input_tokens_seen": 2578288,
+      "step": 550
+    },
+    {
+      "epoch": 0.3137809187279152,
+      "grad_norm": 2.331401824951172,
+      "learning_rate": 4.7021801187592184e-05,
+      "loss": 0.8489,
+      "num_input_tokens_seen": 2601712,
+      "step": 555
+    },
+    {
+      "epoch": 0.3166077738515901,
+      "grad_norm": 2.049757480621338,
+      "learning_rate": 4.696901454167988e-05,
+      "loss": 0.7262,
+      "num_input_tokens_seen": 2625056,
+      "step": 560
+    },
+    {
+      "epoch": 0.31943462897526503,
+      "grad_norm": 1.7714154720306396,
+      "learning_rate": 4.691579435983027e-05,
+      "loss": 0.6455,
+      "num_input_tokens_seen": 2648688,
+      "step": 565
+    },
+    {
+      "epoch": 0.32226148409893995,
+      "grad_norm": 1.9945061206817627,
+      "learning_rate": 4.6862141692288944e-05,
+      "loss": 0.8747,
+      "num_input_tokens_seen": 2672352,
+      "step": 570
+    },
+    {
+      "epoch": 0.3250883392226148,
+      "grad_norm": 2.4137539863586426,
+      "learning_rate": 4.680805759783622e-05,
+      "loss": 0.9107,
+      "num_input_tokens_seen": 2695744,
+      "step": 575
+    },
+    {
+      "epoch": 0.32791519434628974,
+      "grad_norm": 2.3516249656677246,
+      "learning_rate": 4.675354314376614e-05,
+      "loss": 0.7114,
+      "num_input_tokens_seen": 2719168,
+      "step": 580
+    },
+    {
+      "epoch": 0.33074204946996466,
+      "grad_norm": 4.508022785186768,
+      "learning_rate": 4.6698599405865463e-05,
+      "loss": 0.8522,
+      "num_input_tokens_seen": 2742640,
+      "step": 585
+    },
+    {
+      "epoch": 0.3335689045936396,
+      "grad_norm": 2.1811635494232178,
+      "learning_rate": 4.6643227468392416e-05,
+      "loss": 0.7518,
+      "num_input_tokens_seen": 2765584,
+      "step": 590
+    },
+    {
+      "epoch": 0.3363957597173145,
+      "grad_norm": 2.110956907272339,
+      "learning_rate": 4.6587428424055326e-05,
+      "loss": 1.0063,
+      "num_input_tokens_seen": 2788656,
+      "step": 595
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 1.8346225023269653,
+      "learning_rate": 4.6531203373991014e-05,
+      "loss": 0.6981,
+      "num_input_tokens_seen": 2811760,
+      "step": 600
+    },
+    {
+      "epoch": 0.3420494699646643,
+      "grad_norm": 1.713894009590149,
+      "learning_rate": 4.647455342774308e-05,
+      "loss": 0.6034,
+      "num_input_tokens_seen": 2835024,
+      "step": 605
+    },
+    {
+      "epoch": 0.3448763250883392,
+      "grad_norm": 1.5277444124221802,
+      "learning_rate": 4.6417479703240055e-05,
+      "loss": 0.6798,
+      "num_input_tokens_seen": 2858432,
+      "step": 610
+    },
+    {
+      "epoch": 0.34770318021201413,
+      "grad_norm": 2.02787184715271,
+      "learning_rate": 4.635998332677325e-05,
+      "loss": 0.7001,
+      "num_input_tokens_seen": 2881968,
+      "step": 615
+    },
+    {
+      "epoch": 0.35053003533568905,
+      "grad_norm": 2.788226366043091,
+      "learning_rate": 4.6302065432974616e-05,
+      "loss": 0.9002,
+      "num_input_tokens_seen": 2905184,
+      "step": 620
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "grad_norm": 2.641052484512329,
+      "learning_rate": 4.624372716479428e-05,
+      "loss": 0.7627,
+      "num_input_tokens_seen": 2928336,
+      "step": 625
+    },
+    {
+      "epoch": 0.3561837455830389,
+      "grad_norm": 2.559187889099121,
+      "learning_rate": 4.618496967347805e-05,
+      "loss": 0.848,
+      "num_input_tokens_seen": 2951952,
+      "step": 630
+    },
+    {
+      "epoch": 0.35901060070671376,
+      "grad_norm": 2.07712459564209,
+      "learning_rate": 4.6125794118544675e-05,
+      "loss": 0.807,
+      "num_input_tokens_seen": 2975840,
+      "step": 635
+    },
+    {
+      "epoch": 0.3618374558303887,
+      "grad_norm": 2.694662094116211,
+      "learning_rate": 4.606620166776294e-05,
+      "loss": 0.6978,
+      "num_input_tokens_seen": 2999088,
+      "step": 640
+    },
+    {
+      "epoch": 0.3646643109540636,
+      "grad_norm": 2.0563204288482666,
+      "learning_rate": 4.6006193497128666e-05,
+      "loss": 0.6892,
+      "num_input_tokens_seen": 3022224,
+      "step": 645
+    },
+    {
+      "epoch": 0.3674911660777385,
+      "grad_norm": 1.8163408041000366,
+      "learning_rate": 4.594577079084146e-05,
+      "loss": 0.6717,
+      "num_input_tokens_seen": 3045104,
+      "step": 650
+    },
+    {
+      "epoch": 0.37031802120141344,
+      "grad_norm": 2.1439476013183594,
+      "learning_rate": 4.588493474128136e-05,
+      "loss": 0.6975,
+      "num_input_tokens_seen": 3068256,
+      "step": 655
+    },
+    {
+      "epoch": 0.37314487632508836,
+      "grad_norm": 2.6993794441223145,
+      "learning_rate": 4.582368654898533e-05,
+      "loss": 0.692,
+      "num_input_tokens_seen": 3092096,
+      "step": 660
+    },
+    {
+      "epoch": 0.3759717314487632,
+      "grad_norm": 3.1468234062194824,
+      "learning_rate": 4.5762027422623546e-05,
+      "loss": 0.762,
+      "num_input_tokens_seen": 3115440,
+      "step": 665
+    },
+    {
+      "epoch": 0.37879858657243815,
+      "grad_norm": 2.1956112384796143,
+      "learning_rate": 4.569995857897551e-05,
+      "loss": 0.759,
+      "num_input_tokens_seen": 3138960,
+      "step": 670
+    },
+    {
+      "epoch": 0.38162544169611307,
+      "grad_norm": 3.2120509147644043,
+      "learning_rate": 4.563748124290611e-05,
+      "loss": 0.8743,
+      "num_input_tokens_seen": 3163088,
+      "step": 675
+    },
+    {
+      "epoch": 0.384452296819788,
+      "grad_norm": 2.3125061988830566,
+      "learning_rate": 4.557459664734141e-05,
+      "loss": 0.7595,
+      "num_input_tokens_seen": 3186336,
+      "step": 680
+    },
+    {
+      "epoch": 0.3872791519434629,
+      "grad_norm": 2.3744454383850098,
+      "learning_rate": 4.551130603324431e-05,
+      "loss": 0.7657,
+      "num_input_tokens_seen": 3209744,
+      "step": 685
+    },
+    {
+      "epoch": 0.3901060070671378,
+      "grad_norm": 2.250967025756836,
+      "learning_rate": 4.5447610649590064e-05,
+      "loss": 0.7593,
+      "num_input_tokens_seen": 3233632,
+      "step": 690
+    },
+    {
+      "epoch": 0.39293286219081275,
+      "grad_norm": 2.090684175491333,
+      "learning_rate": 4.538351175334167e-05,
+      "loss": 0.6963,
+      "num_input_tokens_seen": 3256960,
+      "step": 695
+    },
+    {
+      "epoch": 0.3957597173144876,
+      "grad_norm": 1.8485418558120728,
+      "learning_rate": 4.531901060942497e-05,
+      "loss": 0.835,
+      "num_input_tokens_seen": 3280432,
+      "step": 700
+    },
+    {
+      "epoch": 0.39858657243816253,
+      "grad_norm": 2.028855800628662,
+      "learning_rate": 4.5254108490703824e-05,
+      "loss": 0.9134,
+      "num_input_tokens_seen": 3304064,
+      "step": 705
+    },
+    {
+      "epoch": 0.40141342756183745,
+      "grad_norm": 2.0917155742645264,
+      "learning_rate": 4.5188806677954864e-05,
+      "loss": 0.8666,
+      "num_input_tokens_seen": 3327632,
+      "step": 710
+    },
+    {
+      "epoch": 0.4042402826855124,
+      "grad_norm": 1.842624306678772,
+      "learning_rate": 4.51231064598423e-05,
+      "loss": 0.6044,
+      "num_input_tokens_seen": 3351104,
+      "step": 715
+    },
+    {
+      "epoch": 0.4070671378091873,
+      "grad_norm": 2.7080881595611572,
+      "learning_rate": 4.505700913289246e-05,
+      "loss": 0.9124,
+      "num_input_tokens_seen": 3375360,
+      "step": 720
+    },
+    {
+      "epoch": 0.4098939929328622,
+      "grad_norm": 2.348064661026001,
+      "learning_rate": 4.499051600146819e-05,
+      "loss": 0.6307,
+      "num_input_tokens_seen": 3398736,
+      "step": 725
+    },
+    {
+      "epoch": 0.4127208480565371,
+      "grad_norm": 2.623867988586426,
+      "learning_rate": 4.4923628377743146e-05,
+      "loss": 0.7896,
+      "num_input_tokens_seen": 3422432,
+      "step": 730
+    },
+    {
+      "epoch": 0.415547703180212,
+      "grad_norm": 2.413691520690918,
+      "learning_rate": 4.485634758167589e-05,
+      "loss": 0.8459,
+      "num_input_tokens_seen": 3446272,
+      "step": 735
+    },
+    {
+      "epoch": 0.4183745583038869,
+      "grad_norm": 2.2855966091156006,
+      "learning_rate": 4.478867494098381e-05,
+      "loss": 0.6007,
+      "num_input_tokens_seen": 3470064,
+      "step": 740
+    },
+    {
+      "epoch": 0.42120141342756184,
+      "grad_norm": 2.137235164642334,
+      "learning_rate": 4.4720611791116986e-05,
+      "loss": 0.5928,
+      "num_input_tokens_seen": 3493824,
+      "step": 745
+    },
+    {
+      "epoch": 0.42402826855123676,
+      "grad_norm": 2.7548105716705322,
+      "learning_rate": 4.4652159475231745e-05,
+      "loss": 0.8043,
+      "num_input_tokens_seen": 3517296,
+      "step": 750
+    },
+    {
+      "epoch": 0.4268551236749117,
+      "grad_norm": 1.7610399723052979,
+      "learning_rate": 4.458331934416427e-05,
+      "loss": 0.7569,
+      "num_input_tokens_seen": 3540640,
+      "step": 755
+    },
+    {
+      "epoch": 0.42968197879858655,
+      "grad_norm": 1.7641017436981201,
+      "learning_rate": 4.451409275640379e-05,
+      "loss": 0.7176,
+      "num_input_tokens_seen": 3564240,
+      "step": 760
+    },
+    {
+      "epoch": 0.43250883392226147,
+      "grad_norm": 2.505873441696167,
+      "learning_rate": 4.444448107806596e-05,
+      "loss": 0.8584,
+      "num_input_tokens_seen": 3587552,
+      "step": 765
+    },
+    {
+      "epoch": 0.4353356890459364,
+      "grad_norm": 1.663974404335022,
+      "learning_rate": 4.4374485682865716e-05,
+      "loss": 0.8907,
+      "num_input_tokens_seen": 3610848,
+      "step": 770
+    },
+    {
+      "epoch": 0.4381625441696113,
+      "grad_norm": 1.5447556972503662,
+      "learning_rate": 4.4304107952090316e-05,
+      "loss": 0.6835,
+      "num_input_tokens_seen": 3634784,
+      "step": 775
+    },
+    {
+      "epoch": 0.44098939929328623,
+      "grad_norm": 2.8021128177642822,
+      "learning_rate": 4.423334927457198e-05,
+      "loss": 0.7266,
+      "num_input_tokens_seen": 3657808,
+      "step": 780
+    },
+    {
+      "epoch": 0.44381625441696115,
+      "grad_norm": 2.9464962482452393,
+      "learning_rate": 4.416221104666052e-05,
+      "loss": 0.8822,
+      "num_input_tokens_seen": 3681216,
+      "step": 785
+    },
+    {
+      "epoch": 0.446643109540636,
+      "grad_norm": 3.3185925483703613,
+      "learning_rate": 4.409069467219582e-05,
+      "loss": 0.7421,
+      "num_input_tokens_seen": 3704144,
+      "step": 790
+    },
+    {
+      "epoch": 0.44946996466431094,
+      "grad_norm": 1.573012351989746,
+      "learning_rate": 4.4018801562480064e-05,
+      "loss": 0.6448,
+      "num_input_tokens_seen": 3727648,
+      "step": 795
+    },
+    {
+      "epoch": 0.45229681978798586,
+      "grad_norm": 3.2603092193603516,
+      "learning_rate": 4.3946533136249926e-05,
+      "loss": 0.7036,
+      "num_input_tokens_seen": 3751296,
+      "step": 800
+    },
+    {
+      "epoch": 0.4551236749116608,
+      "grad_norm": 2.652745246887207,
+      "learning_rate": 4.387389081964857e-05,
+      "loss": 0.9158,
+      "num_input_tokens_seen": 3774560,
+      "step": 805
+    },
+    {
+      "epoch": 0.4579505300353357,
+      "grad_norm": 3.102360486984253,
+      "learning_rate": 4.3800876046197506e-05,
+      "loss": 0.8552,
+      "num_input_tokens_seen": 3797264,
+      "step": 810
+    },
+    {
+      "epoch": 0.4607773851590106,
+      "grad_norm": 2.058687210083008,
+      "learning_rate": 4.372749025676829e-05,
+      "loss": 0.7733,
+      "num_input_tokens_seen": 3821120,
+      "step": 815
+    },
+    {
+      "epoch": 0.4636042402826855,
+      "grad_norm": 2.0987045764923096,
+      "learning_rate": 4.365373489955411e-05,
+      "loss": 0.7368,
+      "num_input_tokens_seen": 3844816,
+      "step": 820
+    },
+    {
+      "epoch": 0.4664310954063604,
+      "grad_norm": 1.813137173652649,
+      "learning_rate": 4.357961143004117e-05,
+      "loss": 0.8172,
+      "num_input_tokens_seen": 3868128,
+      "step": 825
+    },
+    {
+      "epoch": 0.46925795053003533,
+      "grad_norm": 2.0965216159820557,
+      "learning_rate": 4.3505121310980024e-05,
+      "loss": 0.721,
+      "num_input_tokens_seen": 3891184,
+      "step": 830
+    },
+    {
+      "epoch": 0.47208480565371025,
+      "grad_norm": 1.9453920125961304,
+      "learning_rate": 4.3430266012356656e-05,
+      "loss": 0.9005,
+      "num_input_tokens_seen": 3914592,
+      "step": 835
+    },
+    {
+      "epoch": 0.47491166077738517,
+      "grad_norm": 1.8437124490737915,
+      "learning_rate": 4.33550470113635e-05,
+      "loss": 0.8215,
+      "num_input_tokens_seen": 3938352,
+      "step": 840
+    },
+    {
+      "epoch": 0.4777385159010601,
+      "grad_norm": 2.2815515995025635,
+      "learning_rate": 4.3279465792370275e-05,
+      "loss": 0.7864,
+      "num_input_tokens_seen": 3961952,
+      "step": 845
+    },
+    {
+      "epoch": 0.48056537102473496,
+      "grad_norm": 1.6929998397827148,
+      "learning_rate": 4.320352384689471e-05,
+      "loss": 0.7437,
+      "num_input_tokens_seen": 3985456,
+      "step": 850
+    },
+    {
+      "epoch": 0.4833922261484099,
+      "grad_norm": 1.790462613105774,
+      "learning_rate": 4.312722267357311e-05,
+      "loss": 0.5711,
+      "num_input_tokens_seen": 4008784,
+      "step": 855
+    },
+    {
+      "epoch": 0.4862190812720848,
+      "grad_norm": 3.130824327468872,
+      "learning_rate": 4.305056377813075e-05,
+      "loss": 0.6519,
+      "num_input_tokens_seen": 4032752,
+      "step": 860
+    },
+    {
+      "epoch": 0.4890459363957597,
+      "grad_norm": 2.7931573390960693,
+      "learning_rate": 4.297354867335219e-05,
+      "loss": 0.6296,
+      "num_input_tokens_seen": 4056240,
+      "step": 865
+    },
+    {
+      "epoch": 0.49187279151943464,
+      "grad_norm": 2.679901361465454,
+      "learning_rate": 4.289617887905143e-05,
+      "loss": 0.8868,
+      "num_input_tokens_seen": 4079296,
+      "step": 870
+    },
+    {
+      "epoch": 0.49469964664310956,
+      "grad_norm": 1.973581075668335,
+      "learning_rate": 4.2818455922041876e-05,
+      "loss": 0.696,
+      "num_input_tokens_seen": 4103120,
+      "step": 875
+    },
+    {
+      "epoch": 0.4975265017667845,
+      "grad_norm": 2.4409375190734863,
+      "learning_rate": 4.274038133610628e-05,
+      "loss": 0.798,
+      "num_input_tokens_seen": 4127008,
+      "step": 880
+    },
+    {
+      "epoch": 0.5003533568904593,
+      "grad_norm": 3.359973907470703,
+      "learning_rate": 4.266195666196639e-05,
+      "loss": 0.7207,
+      "num_input_tokens_seen": 4151024,
+      "step": 885
+    },
+    {
+      "epoch": 0.5031802120141343,
+      "grad_norm": 1.7413347959518433,
+      "learning_rate": 4.2583183447252596e-05,
+      "loss": 0.774,
+      "num_input_tokens_seen": 4174896,
+      "step": 890
+    },
+    {
+      "epoch": 0.5060070671378092,
+      "grad_norm": 1.6167852878570557,
+      "learning_rate": 4.250406324647339e-05,
+      "loss": 0.805,
+      "num_input_tokens_seen": 4198528,
+      "step": 895
+    },
+    {
+      "epoch": 0.508833922261484,
+      "grad_norm": 2.1960134506225586,
+      "learning_rate": 4.242459762098466e-05,
+      "loss": 0.714,
+      "num_input_tokens_seen": 4222160,
+      "step": 900
+    },
+    {
+      "epoch": 0.511660777385159,
+      "grad_norm": 1.9099704027175903,
+      "learning_rate": 4.234478813895891e-05,
+      "loss": 0.7326,
+      "num_input_tokens_seen": 4245424,
+      "step": 905
+    },
+    {
+      "epoch": 0.5144876325088339,
+      "grad_norm": 3.273469924926758,
+      "learning_rate": 4.226463637535429e-05,
+      "loss": 0.8094,
+      "num_input_tokens_seen": 4269232,
+      "step": 910
+    },
+    {
+      "epoch": 0.5173144876325089,
+      "grad_norm": 1.889750361442566,
+      "learning_rate": 4.218414391188353e-05,
+      "loss": 0.697,
+      "num_input_tokens_seen": 4292688,
+      "step": 915
+    },
+    {
+      "epoch": 0.5201413427561837,
+      "grad_norm": 2.302185535430908,
+      "learning_rate": 4.2103312336982734e-05,
+      "loss": 0.8087,
+      "num_input_tokens_seen": 4316192,
+      "step": 920
+    },
+    {
+      "epoch": 0.5229681978798587,
+      "grad_norm": 3.6521856784820557,
+      "learning_rate": 4.2022143245779996e-05,
+      "loss": 0.7683,
+      "num_input_tokens_seen": 4340016,
+      "step": 925
+    },
+    {
+      "epoch": 0.5257950530035336,
+      "grad_norm": 1.4392321109771729,
+      "learning_rate": 4.194063824006397e-05,
+      "loss": 0.7393,
+      "num_input_tokens_seen": 4364048,
+      "step": 930
+    },
+    {
+      "epoch": 0.5286219081272084,
+      "grad_norm": 1.6422187089920044,
+      "learning_rate": 4.185879892825222e-05,
+      "loss": 0.8686,
+      "num_input_tokens_seen": 4387456,
+      "step": 935
+    },
+    {
+      "epoch": 0.5314487632508834,
+      "grad_norm": 2.241570472717285,
+      "learning_rate": 4.177662692535952e-05,
+      "loss": 0.7628,
+      "num_input_tokens_seen": 4410768,
+      "step": 940
+    },
+    {
+      "epoch": 0.5342756183745583,
+      "grad_norm": 2.3923139572143555,
+      "learning_rate": 4.1694123852965926e-05,
+      "loss": 0.6928,
+      "num_input_tokens_seen": 4434064,
+      "step": 945
+    },
+    {
+      "epoch": 0.5371024734982333,
+      "grad_norm": 2.7285265922546387,
+      "learning_rate": 4.161129133918485e-05,
+      "loss": 0.7368,
+      "num_input_tokens_seen": 4457760,
+      "step": 950
+    },
+    {
+      "epoch": 0.5399293286219081,
+      "grad_norm": 2.306457757949829,
+      "learning_rate": 4.152813101863087e-05,
+      "loss": 0.7434,
+      "num_input_tokens_seen": 4480688,
+      "step": 955
+    },
+    {
+      "epoch": 0.542756183745583,
+      "grad_norm": 1.9828684329986572,
+      "learning_rate": 4.144464453238748e-05,
+      "loss": 0.7868,
+      "num_input_tokens_seen": 4504496,
+      "step": 960
+    },
+    {
+      "epoch": 0.545583038869258,
+      "grad_norm": 2.1162819862365723,
+      "learning_rate": 4.136083352797476e-05,
+      "loss": 0.8646,
+      "num_input_tokens_seen": 4527600,
+      "step": 965
+    },
+    {
+      "epoch": 0.5484098939929328,
+      "grad_norm": 1.9256089925765991,
+      "learning_rate": 4.1276699659316787e-05,
+      "loss": 0.7628,
+      "num_input_tokens_seen": 4551600,
+      "step": 970
+    },
+    {
+      "epoch": 0.5512367491166078,
+      "grad_norm": 2.933058738708496,
+      "learning_rate": 4.119224458670905e-05,
+      "loss": 0.7804,
+      "num_input_tokens_seen": 4575408,
+      "step": 975
+    },
+    {
+      "epoch": 0.5540636042402827,
+      "grad_norm": 2.9193356037139893,
+      "learning_rate": 4.110746997678565e-05,
+      "loss": 0.7821,
+      "num_input_tokens_seen": 4598912,
+      "step": 980
+    },
+    {
+      "epoch": 0.5568904593639576,
+      "grad_norm": 2.562621831893921,
+      "learning_rate": 4.102237750248645e-05,
+      "loss": 0.6505,
+      "num_input_tokens_seen": 4622416,
+      "step": 985
+    },
+    {
+      "epoch": 0.5597173144876325,
+      "grad_norm": 1.7989310026168823,
+      "learning_rate": 4.093696884302404e-05,
+      "loss": 0.7531,
+      "num_input_tokens_seen": 4646032,
+      "step": 990
+    },
+    {
+      "epoch": 0.5625441696113074,
+      "grad_norm": 2.9085874557495117,
+      "learning_rate": 4.085124568385057e-05,
+      "loss": 0.7638,
+      "num_input_tokens_seen": 4669584,
+      "step": 995
+    },
+    {
+      "epoch": 0.5653710247349824,
+      "grad_norm": 2.0637929439544678,
+      "learning_rate": 4.076520971662455e-05,
+      "loss": 0.5917,
+      "num_input_tokens_seen": 4693296,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5681978798586572,
+      "grad_norm": 2.630014181137085,
+      "learning_rate": 4.067886263917743e-05,
+      "loss": 0.7581,
+      "num_input_tokens_seen": 4716592,
+      "step": 1005
+    },
+    {
+      "epoch": 0.5710247349823322,
+      "grad_norm": 2.239084243774414,
+      "learning_rate": 4.059220615548008e-05,
+      "loss": 0.7985,
+      "num_input_tokens_seen": 4740368,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5738515901060071,
+      "grad_norm": 1.7670809030532837,
+      "learning_rate": 4.0505241975609206e-05,
+      "loss": 0.7224,
+      "num_input_tokens_seen": 4763712,
+      "step": 1015
+    },
+    {
+      "epoch": 0.5766784452296819,
+      "grad_norm": 1.740500569343567,
+      "learning_rate": 4.0417971815713584e-05,
+      "loss": 0.7639,
+      "num_input_tokens_seen": 4787232,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5795053003533569,
+      "grad_norm": 2.05525803565979,
+      "learning_rate": 4.0330397397980166e-05,
+      "loss": 0.7884,
+      "num_input_tokens_seen": 4810608,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5823321554770318,
+      "grad_norm": 2.364126443862915,
+      "learning_rate": 4.024252045060015e-05,
+      "loss": 0.5888,
+      "num_input_tokens_seen": 4834192,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5851590106007067,
+      "grad_norm": 2.007268190383911,
+      "learning_rate": 4.0154342707734846e-05,
+      "loss": 0.7096,
+      "num_input_tokens_seen": 4857152,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5879858657243816,
+      "grad_norm": 2.7187740802764893,
+      "learning_rate": 4.0065865909481417e-05,
+      "loss": 0.8011,
+      "num_input_tokens_seen": 4880768,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5908127208480566,
+      "grad_norm": 2.1375982761383057,
+      "learning_rate": 3.9977091801838606e-05,
+      "loss": 0.7042,
+      "num_input_tokens_seen": 4903840,
+      "step": 1045
+    },
+    {
+      "epoch": 0.5936395759717314,
+      "grad_norm": 1.724465012550354,
+      "learning_rate": 3.988802213667225e-05,
+      "loss": 0.8065,
+      "num_input_tokens_seen": 4927392,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5964664310954063,
+      "grad_norm": 3.0985677242279053,
+      "learning_rate": 3.979865867168071e-05,
+      "loss": 0.7548,
+      "num_input_tokens_seen": 4950544,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5992932862190813,
+      "grad_norm": 2.9757890701293945,
+      "learning_rate": 3.9709003170360176e-05,
+      "loss": 0.8626,
+      "num_input_tokens_seen": 4973616,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6021201413427562,
+      "grad_norm": 2.467498302459717,
+      "learning_rate": 3.9619057401969884e-05,
+      "loss": 0.7873,
+      "num_input_tokens_seen": 4996416,
+      "step": 1065
+    },
+    {
+      "epoch": 0.6049469964664311,
+      "grad_norm": 1.9884438514709473,
+      "learning_rate": 3.952882314149718e-05,
+      "loss": 0.5953,
+      "num_input_tokens_seen": 5019712,
+      "step": 1070
+    },
+    {
+      "epoch": 0.607773851590106,
+      "grad_norm": 2.4566147327423096,
+      "learning_rate": 3.943830216962253e-05,
+      "loss": 0.716,
+      "num_input_tokens_seen": 5043312,
+      "step": 1075
+    },
+    {
+      "epoch": 0.610600706713781,
+      "grad_norm": 2.359757661819458,
+      "learning_rate": 3.9347496272684325e-05,
+      "loss": 0.692,
+      "num_input_tokens_seen": 5066400,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6134275618374558,
+      "grad_norm": 1.6109179258346558,
+      "learning_rate": 3.925640724264368e-05,
+      "loss": 0.7852,
+      "num_input_tokens_seen": 5090576,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6162544169611307,
+      "grad_norm": 2.8359413146972656,
+      "learning_rate": 3.916503687704903e-05,
+      "loss": 0.6898,
+      "num_input_tokens_seen": 5114112,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6190812720848057,
+      "grad_norm": 1.5688904523849487,
+      "learning_rate": 3.9073386979000714e-05,
+      "loss": 0.7576,
+      "num_input_tokens_seen": 5138080,
+      "step": 1095
+    },
+    {
+      "epoch": 0.6219081272084805,
+      "grad_norm": 3.030547857284546,
+      "learning_rate": 3.8981459357115325e-05,
+      "loss": 0.6537,
+      "num_input_tokens_seen": 5161488,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 3536,
+  "num_input_tokens_seen": 5161488,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.146849984628326e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cbc94a713da9a44fc659b7c77cb3a54484d5d6762cafa7efa3cea0c036c9ff
+size 5432