second model upload

.gitattributes

@@ -33,3 +33,5 @@ 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-620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: other
+base_model: saim1212/penguin2-checkpoint2
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2vl_lora_16lr_7b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2vl_lora_16lr_7b
+
+This model is a fine-tuned version of [saim1212/penguin2-checkpoint2](https://huggingface.co/saim1212/penguin2-checkpoint2) on the talk2car dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.0
+- Transformers 4.50.0
+- Pytorch 2.4.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "saim1212/penguin2-checkpoint2",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9898f0fb3424a02fe4ed0e1717139a80d63a4ec5a0625710780a01a90b0947d
+size 91374880

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.848,
+    "total_flos": 2.117785669819433e+17,
+    "train_loss": 0.48659542481745444,
+    "train_runtime": 31064.4118,
+    "train_samples_per_second": 0.644,
+    "train_steps_per_second": 0.02
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-620/README.md

@@ -0,0 +1,202 @@
+---
+base_model: saim1212/penguin2-checkpoint2
+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 0.15.0

checkpoint-620/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "saim1212/penguin2-checkpoint2",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-620/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9898f0fb3424a02fe4ed0e1717139a80d63a4ec5a0625710780a01a90b0947d
+size 91374880

checkpoint-620/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-620/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-620/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6117ba44e69c112d4f961b02428f07a70be2a3e54d1cb4654e497a4626bea3
+size 183102410

checkpoint-620/preprocessor_config.json

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

checkpoint-620/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b074bf97f241c2662caa5ce956b03d1249c3cc0713b6aef7796673362754f98
+size 14512

checkpoint-620/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58aed9e8d78903cb12015375021c729c3f6c5fd1a1e19e7aee6ddde57c3310b9
+size 14512

checkpoint-620/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1288836bdb58704d4d6759b9121ca31491cf01f58a8498305dcb334bf5481a77
+size 988

checkpoint-620/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8495dbb29c37ec643988e8063dd15232603beffb07a639805fe64236fc006bee
+size 1064

checkpoint-620/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-620/tokenizer.json

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

checkpoint-620/tokenizer_config.json

@@ -0,0 +1,148 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-620/trainer_state.json

@@ -0,0 +1,468 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.848,
+  "eval_steps": 500,
+  "global_step": 620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 12.881609916687012,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 2.0828,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 7.486210823059082,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 1.4787,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.486098289489746,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 1.3156,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.403397083282471,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 1.1692,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.133569240570068,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 1.1055,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.2612862586975098,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 1.0751,
+      "step": 60
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 2.8362364768981934,
+      "learning_rate": 1.9989858366670475e-05,
+      "loss": 0.9454,
+      "step": 70
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 2.404646396636963,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 0.9386,
+      "step": 80
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 2.6535897254943848,
+      "learning_rate": 1.9876001099813018e-05,
+      "loss": 0.9624,
+      "step": 90
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 2.9908246994018555,
+      "learning_rate": 1.977201232274814e-05,
+      "loss": 0.9408,
+      "step": 100
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 2.08085298538208,
+      "learning_rate": 1.963705643889941e-05,
+      "loss": 0.9316,
+      "step": 110
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 2.0934102535247803,
+      "learning_rate": 1.947156111793487e-05,
+      "loss": 0.9286,
+      "step": 120
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 2.122586727142334,
+      "learning_rate": 1.9276050807747878e-05,
+      "loss": 0.8039,
+      "step": 130
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 2.289278268814087,
+      "learning_rate": 1.9051145072503216e-05,
+      "loss": 0.7758,
+      "step": 140
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 2.2588486671447754,
+      "learning_rate": 1.8797556629263603e-05,
+      "loss": 0.7719,
+      "step": 150
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 2.52738356590271,
+      "learning_rate": 1.851608908941855e-05,
+      "loss": 0.7735,
+      "step": 160
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 2.1543173789978027,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 0.7807,
+      "step": 170
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 2.3994810581207275,
+      "learning_rate": 1.7873170077464285e-05,
+      "loss": 0.7859,
+      "step": 180
+    },
+    {
+      "epoch": 3.016,
+      "grad_norm": 2.4878721237182617,
+      "learning_rate": 1.7513755989369636e-05,
+      "loss": 0.6971,
+      "step": 190
+    },
+    {
+      "epoch": 3.176,
+      "grad_norm": 2.379432439804077,
+      "learning_rate": 1.7130531116312202e-05,
+      "loss": 0.619,
+      "step": 200
+    },
+    {
+      "epoch": 3.336,
+      "grad_norm": 2.209932565689087,
+      "learning_rate": 1.6724709882217606e-05,
+      "loss": 0.5998,
+      "step": 210
+    },
+    {
+      "epoch": 3.496,
+      "grad_norm": 2.7859106063842773,
+      "learning_rate": 1.6297578317954025e-05,
+      "loss": 0.6066,
+      "step": 220
+    },
+    {
+      "epoch": 3.656,
+      "grad_norm": 2.6925034523010254,
+      "learning_rate": 1.5850489985953076e-05,
+      "loss": 0.6351,
+      "step": 230
+    },
+    {
+      "epoch": 3.816,
+      "grad_norm": 2.7933480739593506,
+      "learning_rate": 1.538486169082589e-05,
+      "loss": 0.6003,
+      "step": 240
+    },
+    {
+      "epoch": 3.976,
+      "grad_norm": 2.7974672317504883,
+      "learning_rate": 1.4902168989567335e-05,
+      "loss": 0.6382,
+      "step": 250
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 2.982576608657837,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 0.4597,
+      "step": 260
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 2.571833610534668,
+      "learning_rate": 1.3891758131310329e-05,
+      "loss": 0.444,
+      "step": 270
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 2.4135894775390625,
+      "learning_rate": 1.3367241924934715e-05,
+      "loss": 0.4541,
+      "step": 280
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 2.8163669109344482,
+      "learning_rate": 1.283205506682304e-05,
+      "loss": 0.4532,
+      "step": 290
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 2.9105963706970215,
+      "learning_rate": 1.2287893542207122e-05,
+      "loss": 0.4454,
+      "step": 300
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 2.6453466415405273,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4547,
+      "step": 310
+    },
+    {
+      "epoch": 5.08,
+      "grad_norm": 3.0081467628479004,
+      "learning_rate": 1.1179567171508463e-05,
+      "loss": 0.3733,
+      "step": 320
+    },
+    {
+      "epoch": 5.24,
+      "grad_norm": 3.0316622257232666,
+      "learning_rate": 1.061891456629682e-05,
+      "loss": 0.2988,
+      "step": 330
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 2.4374618530273438,
+      "learning_rate": 1.0056300646175661e-05,
+      "loss": 0.3001,
+      "step": 340
+    },
+    {
+      "epoch": 5.5600000000000005,
+      "grad_norm": 2.4697585105895996,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 0.2894,
+      "step": 350
+    },
+    {
+      "epoch": 5.72,
+      "grad_norm": 2.9103164672851562,
+      "learning_rate": 8.932321028464412e-06,
+      "loss": 0.2931,
+      "step": 360
+    },
+    {
+      "epoch": 5.88,
+      "grad_norm": 2.7394156455993652,
+      "learning_rate": 8.374517176244038e-06,
+      "loss": 0.3003,
+      "step": 370
+    },
+    {
+      "epoch": 6.032,
+      "grad_norm": 2.1789660453796387,
+      "learning_rate": 7.821864412511485e-06,
+      "loss": 0.2594,
+      "step": 380
+    },
+    {
+      "epoch": 6.192,
+      "grad_norm": 3.0000176429748535,
+      "learning_rate": 7.276114071238069e-06,
+      "loss": 0.1877,
+      "step": 390
+    },
+    {
+      "epoch": 6.352,
+      "grad_norm": 2.3748111724853516,
+      "learning_rate": 6.7389956129010516e-06,
+      "loss": 0.1846,
+      "step": 400
+    },
+    {
+      "epoch": 6.5120000000000005,
+      "grad_norm": 2.3044967651367188,
+      "learning_rate": 6.21221114389424e-06,
+      "loss": 0.1728,
+      "step": 410
+    },
+    {
+      "epoch": 6.672,
+      "grad_norm": 2.2465269565582275,
+      "learning_rate": 5.697430022622542e-06,
+      "loss": 0.1726,
+      "step": 420
+    },
+    {
+      "epoch": 6.832,
+      "grad_norm": 2.356623888015747,
+      "learning_rate": 5.1962835693735506e-06,
+      "loss": 0.1707,
+      "step": 430
+    },
+    {
+      "epoch": 6.992,
+      "grad_norm": 2.5909860134124756,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 0.1764,
+      "step": 440
+    },
+    {
+      "epoch": 7.144,
+      "grad_norm": 1.7320761680603027,
+      "learning_rate": 4.241198876907936e-06,
+      "loss": 0.0992,
+      "step": 450
+    },
+    {
+      "epoch": 7.304,
+      "grad_norm": 1.5438932180404663,
+      "learning_rate": 3.790287261960953e-06,
+      "loss": 0.0986,
+      "step": 460
+    },
+    {
+      "epoch": 7.464,
+      "grad_norm": 1.8166850805282593,
+      "learning_rate": 3.3590539723276083e-06,
+      "loss": 0.1039,
+      "step": 470
+    },
+    {
+      "epoch": 7.624,
+      "grad_norm": 1.8122446537017822,
+      "learning_rate": 2.9488655686392086e-06,
+      "loss": 0.1062,
+      "step": 480
+    },
+    {
+      "epoch": 7.784,
+      "grad_norm": 1.9146348237991333,
+      "learning_rate": 2.56102192114549e-06,
+      "loss": 0.1029,
+      "step": 490
+    },
+    {
+      "epoch": 7.944,
+      "grad_norm": 1.5483825206756592,
+      "learning_rate": 2.196752090479083e-06,
+      "loss": 0.0997,
+      "step": 500
+    },
+    {
+      "epoch": 8.096,
+      "grad_norm": 0.9715578556060791,
+      "learning_rate": 1.8572104328126738e-06,
+      "loss": 0.0687,
+      "step": 510
+    },
+    {
+      "epoch": 8.256,
+      "grad_norm": 1.1563620567321777,
+      "learning_rate": 1.5434729417516049e-06,
+      "loss": 0.0625,
+      "step": 520
+    },
+    {
+      "epoch": 8.416,
+      "grad_norm": 1.2092530727386475,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 0.0647,
+      "step": 530
+    },
+    {
+      "epoch": 8.576,
+      "grad_norm": 1.2118881940841675,
+      "learning_rate": 9.973024214852567e-07,
+      "loss": 0.0659,
+      "step": 540
+    },
+    {
+      "epoch": 8.736,
+      "grad_norm": 1.1171401739120483,
+      "learning_rate": 7.666001842872639e-07,
+      "loss": 0.0648,
+      "step": 550
+    },
+    {
+      "epoch": 8.896,
+      "grad_norm": 1.0178390741348267,
+      "learning_rate": 5.651582129001987e-07,
+      "loss": 0.0628,
+      "step": 560
+    },
+    {
+      "epoch": 9.048,
+      "grad_norm": 0.854426383972168,
+      "learning_rate": 3.936148686802077e-07,
+      "loss": 0.0579,
+      "step": 570
+    },
+    {
+      "epoch": 9.208,
+      "grad_norm": 0.9751760363578796,
+      "learning_rate": 2.525137654586185e-07,
+      "loss": 0.0508,
+      "step": 580
+    },
+    {
+      "epoch": 9.368,
+      "grad_norm": 0.9072787165641785,
+      "learning_rate": 1.4230204685196202e-07,
+      "loss": 0.0516,
+      "step": 590
+    },
+    {
+      "epoch": 9.528,
+      "grad_norm": 1.0727787017822266,
+      "learning_rate": 6.332896928217258e-08,
+      "loss": 0.0517,
+      "step": 600
+    },
+    {
+      "epoch": 9.688,
+      "grad_norm": 0.8716169595718384,
+      "learning_rate": 1.5844795197285102e-08,
+      "loss": 0.0518,
+      "step": 610
+    },
+    {
+      "epoch": 9.848,
+      "grad_norm": 0.9439557790756226,
+      "learning_rate": 0.0,
+      "loss": 0.0527,
+      "step": 620
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.117785669819433e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-620/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8679129aad6efc54177edfebfe7b8f12c2a44794d1347f1d72c78ddfc60b1a3a
+size 5688

preprocessor_config.json

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

runs/Apr03_09-55-08_2a3956608003/events.out.tfevents.1743674368.2a3956608003.152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d6e8b6ed621bb084ad4c5597cfd14492ef52815460c21ab4c3e8f04997b66e
+size 19962

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,148 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.848,
+    "total_flos": 2.117785669819433e+17,
+    "train_loss": 0.48659542481745444,
+    "train_runtime": 31064.4118,
+    "train_samples_per_second": 0.644,
+    "train_steps_per_second": 0.02
+}

trainer_log.jsonl

@@ -0,0 +1,63 @@
+{"current_steps": 10, "total_steps": 620, "loss": 2.0828, "lr": 3.225806451612903e-06, "epoch": 0.16, "percentage": 1.61, "elapsed_time": "0:08:11", "remaining_time": "8:19:30"}
+{"current_steps": 20, "total_steps": 620, "loss": 1.4787, "lr": 6.451612903225806e-06, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:16:36", "remaining_time": "8:18:02"}
+{"current_steps": 30, "total_steps": 620, "loss": 1.3156, "lr": 9.67741935483871e-06, "epoch": 0.48, "percentage": 4.84, "elapsed_time": "0:25:00", "remaining_time": "8:11:50"}
+{"current_steps": 40, "total_steps": 620, "loss": 1.1692, "lr": 1.2903225806451613e-05, "epoch": 0.64, "percentage": 6.45, "elapsed_time": "0:33:26", "remaining_time": "8:04:47"}
+{"current_steps": 50, "total_steps": 620, "loss": 1.1055, "lr": 1.6129032258064517e-05, "epoch": 0.8, "percentage": 8.06, "elapsed_time": "0:41:51", "remaining_time": "7:57:14"}
+{"current_steps": 60, "total_steps": 620, "loss": 1.0751, "lr": 1.935483870967742e-05, "epoch": 0.96, "percentage": 9.68, "elapsed_time": "0:50:16", "remaining_time": "7:49:14"}
+{"current_steps": 70, "total_steps": 620, "loss": 0.9454, "lr": 1.9989858366670475e-05, "epoch": 1.112, "percentage": 11.29, "elapsed_time": "0:58:16", "remaining_time": "7:37:51"}
+{"current_steps": 80, "total_steps": 620, "loss": 0.9386, "lr": 1.994869323391895e-05, "epoch": 1.272, "percentage": 12.9, "elapsed_time": "1:06:41", "remaining_time": "7:30:10"}
+{"current_steps": 90, "total_steps": 620, "loss": 0.9624, "lr": 1.9876001099813018e-05, "epoch": 1.432, "percentage": 14.52, "elapsed_time": "1:15:06", "remaining_time": "7:22:17"}
+{"current_steps": 100, "total_steps": 620, "loss": 0.9408, "lr": 1.977201232274814e-05, "epoch": 1.592, "percentage": 16.13, "elapsed_time": "1:23:31", "remaining_time": "7:14:19"}
+{"current_steps": 110, "total_steps": 620, "loss": 0.9316, "lr": 1.963705643889941e-05, "epoch": 1.752, "percentage": 17.74, "elapsed_time": "1:31:56", "remaining_time": "7:06:15"}
+{"current_steps": 120, "total_steps": 620, "loss": 0.9286, "lr": 1.947156111793487e-05, "epoch": 1.912, "percentage": 19.35, "elapsed_time": "1:40:20", "remaining_time": "6:58:06"}
+{"current_steps": 130, "total_steps": 620, "loss": 0.8039, "lr": 1.9276050807747878e-05, "epoch": 2.064, "percentage": 20.97, "elapsed_time": "1:48:19", "remaining_time": "6:48:19"}
+{"current_steps": 140, "total_steps": 620, "loss": 0.7758, "lr": 1.9051145072503216e-05, "epoch": 2.224, "percentage": 22.58, "elapsed_time": "1:56:44", "remaining_time": "6:40:14"}
+{"current_steps": 150, "total_steps": 620, "loss": 0.7719, "lr": 1.8797556629263603e-05, "epoch": 2.384, "percentage": 24.19, "elapsed_time": "2:05:09", "remaining_time": "6:32:10"}
+{"current_steps": 160, "total_steps": 620, "loss": 0.7735, "lr": 1.851608908941855e-05, "epoch": 2.544, "percentage": 25.81, "elapsed_time": "2:13:34", "remaining_time": "6:24:01"}
+{"current_steps": 170, "total_steps": 620, "loss": 0.7807, "lr": 1.8207634412072765e-05, "epoch": 2.7039999999999997, "percentage": 27.42, "elapsed_time": "2:21:59", "remaining_time": "6:15:51"}
+{"current_steps": 180, "total_steps": 620, "loss": 0.7859, "lr": 1.7873170077464285e-05, "epoch": 2.864, "percentage": 29.03, "elapsed_time": "2:30:23", "remaining_time": "6:07:38"}
+{"current_steps": 190, "total_steps": 620, "loss": 0.6971, "lr": 1.7513755989369636e-05, "epoch": 3.016, "percentage": 30.65, "elapsed_time": "2:38:23", "remaining_time": "5:58:28"}
+{"current_steps": 200, "total_steps": 620, "loss": 0.619, "lr": 1.7130531116312202e-05, "epoch": 3.176, "percentage": 32.26, "elapsed_time": "2:46:48", "remaining_time": "5:50:17"}
+{"current_steps": 210, "total_steps": 620, "loss": 0.5998, "lr": 1.6724709882217606e-05, "epoch": 3.336, "percentage": 33.87, "elapsed_time": "2:55:13", "remaining_time": "5:42:05"}
+{"current_steps": 220, "total_steps": 620, "loss": 0.6066, "lr": 1.6297578317954025e-05, "epoch": 3.496, "percentage": 35.48, "elapsed_time": "3:03:37", "remaining_time": "5:33:52"}
+{"current_steps": 230, "total_steps": 620, "loss": 0.6351, "lr": 1.5850489985953076e-05, "epoch": 3.656, "percentage": 37.1, "elapsed_time": "3:12:02", "remaining_time": "5:25:37"}
+{"current_steps": 240, "total_steps": 620, "loss": 0.6003, "lr": 1.538486169082589e-05, "epoch": 3.816, "percentage": 38.71, "elapsed_time": "3:20:27", "remaining_time": "5:17:23"}
+{"current_steps": 250, "total_steps": 620, "loss": 0.6382, "lr": 1.4902168989567335e-05, "epoch": 3.976, "percentage": 40.32, "elapsed_time": "3:28:51", "remaining_time": "5:09:06"}
+{"current_steps": 260, "total_steps": 620, "loss": 0.4597, "lr": 1.4403941515576344e-05, "epoch": 4.128, "percentage": 41.94, "elapsed_time": "3:36:50", "remaining_time": "5:00:15"}
+{"current_steps": 270, "total_steps": 620, "loss": 0.444, "lr": 1.3891758131310329e-05, "epoch": 4.288, "percentage": 43.55, "elapsed_time": "3:45:14", "remaining_time": "4:51:59"}
+{"current_steps": 280, "total_steps": 620, "loss": 0.4541, "lr": 1.3367241924934715e-05, "epoch": 4.448, "percentage": 45.16, "elapsed_time": "3:53:39", "remaining_time": "4:43:43"}
+{"current_steps": 290, "total_steps": 620, "loss": 0.4532, "lr": 1.283205506682304e-05, "epoch": 4.608, "percentage": 46.77, "elapsed_time": "4:02:04", "remaining_time": "4:35:27"}
+{"current_steps": 300, "total_steps": 620, "loss": 0.4454, "lr": 1.2287893542207122e-05, "epoch": 4.768, "percentage": 48.39, "elapsed_time": "4:10:29", "remaining_time": "4:27:11"}
+{"current_steps": 310, "total_steps": 620, "loss": 0.4547, "lr": 1.1736481776669307e-05, "epoch": 4.928, "percentage": 50.0, "elapsed_time": "4:18:54", "remaining_time": "4:18:54"}
+{"current_steps": 320, "total_steps": 620, "loss": 0.3733, "lr": 1.1179567171508463e-05, "epoch": 5.08, "percentage": 51.61, "elapsed_time": "4:26:54", "remaining_time": "4:10:13"}
+{"current_steps": 330, "total_steps": 620, "loss": 0.2988, "lr": 1.061891456629682e-05, "epoch": 5.24, "percentage": 53.23, "elapsed_time": "4:35:19", "remaining_time": "4:01:56"}
+{"current_steps": 340, "total_steps": 620, "loss": 0.3001, "lr": 1.0056300646175661e-05, "epoch": 5.4, "percentage": 54.84, "elapsed_time": "4:43:44", "remaining_time": "3:53:40"}
+{"current_steps": 350, "total_steps": 620, "loss": 0.2894, "lr": 9.493508311612874e-06, "epoch": 5.5600000000000005, "percentage": 56.45, "elapsed_time": "4:52:09", "remaining_time": "3:45:22"}
+{"current_steps": 360, "total_steps": 620, "loss": 0.2931, "lr": 8.932321028464412e-06, "epoch": 5.72, "percentage": 58.06, "elapsed_time": "5:00:34", "remaining_time": "3:37:04"}
+{"current_steps": 370, "total_steps": 620, "loss": 0.3003, "lr": 8.374517176244038e-06, "epoch": 5.88, "percentage": 59.68, "elapsed_time": "5:08:59", "remaining_time": "3:28:46"}
+{"current_steps": 380, "total_steps": 620, "loss": 0.2594, "lr": 7.821864412511485e-06, "epoch": 6.032, "percentage": 61.29, "elapsed_time": "5:16:58", "remaining_time": "3:20:11"}
+{"current_steps": 390, "total_steps": 620, "loss": 0.1877, "lr": 7.276114071238069e-06, "epoch": 6.192, "percentage": 62.9, "elapsed_time": "5:25:23", "remaining_time": "3:11:54"}
+{"current_steps": 400, "total_steps": 620, "loss": 0.1846, "lr": 6.7389956129010516e-06, "epoch": 6.352, "percentage": 64.52, "elapsed_time": "5:33:48", "remaining_time": "3:03:35"}
+{"current_steps": 410, "total_steps": 620, "loss": 0.1728, "lr": 6.21221114389424e-06, "epoch": 6.5120000000000005, "percentage": 66.13, "elapsed_time": "5:42:13", "remaining_time": "2:55:16"}
+{"current_steps": 420, "total_steps": 620, "loss": 0.1726, "lr": 5.697430022622542e-06, "epoch": 6.672, "percentage": 67.74, "elapsed_time": "5:50:38", "remaining_time": "2:46:58"}
+{"current_steps": 430, "total_steps": 620, "loss": 0.1707, "lr": 5.1962835693735506e-06, "epoch": 6.832, "percentage": 69.35, "elapsed_time": "5:59:03", "remaining_time": "2:38:39"}
+{"current_steps": 440, "total_steps": 620, "loss": 0.1764, "lr": 4.710359896730379e-06, "epoch": 6.992, "percentage": 70.97, "elapsed_time": "6:07:29", "remaining_time": "2:30:20"}
+{"current_steps": 450, "total_steps": 620, "loss": 0.0992, "lr": 4.241198876907936e-06, "epoch": 7.144, "percentage": 72.58, "elapsed_time": "6:15:30", "remaining_time": "2:21:51"}
+{"current_steps": 460, "total_steps": 620, "loss": 0.0986, "lr": 3.790287261960953e-06, "epoch": 7.304, "percentage": 74.19, "elapsed_time": "6:23:54", "remaining_time": "2:13:32"}
+{"current_steps": 470, "total_steps": 620, "loss": 0.1039, "lr": 3.3590539723276083e-06, "epoch": 7.464, "percentage": 75.81, "elapsed_time": "6:32:19", "remaining_time": "2:05:12"}
+{"current_steps": 480, "total_steps": 620, "loss": 0.1062, "lr": 2.9488655686392086e-06, "epoch": 7.624, "percentage": 77.42, "elapsed_time": "6:40:43", "remaining_time": "1:56:52"}
+{"current_steps": 490, "total_steps": 620, "loss": 0.1029, "lr": 2.56102192114549e-06, "epoch": 7.784, "percentage": 79.03, "elapsed_time": "6:49:08", "remaining_time": "1:48:32"}
+{"current_steps": 500, "total_steps": 620, "loss": 0.0997, "lr": 2.196752090479083e-06, "epoch": 7.944, "percentage": 80.65, "elapsed_time": "6:57:34", "remaining_time": "1:40:12"}
+{"current_steps": 510, "total_steps": 620, "loss": 0.0687, "lr": 1.8572104328126738e-06, "epoch": 8.096, "percentage": 82.26, "elapsed_time": "7:05:34", "remaining_time": "1:31:47"}
+{"current_steps": 520, "total_steps": 620, "loss": 0.0625, "lr": 1.5434729417516049e-06, "epoch": 8.256, "percentage": 83.87, "elapsed_time": "7:13:59", "remaining_time": "1:23:27"}
+{"current_steps": 530, "total_steps": 620, "loss": 0.0647, "lr": 1.2565338385541792e-06, "epoch": 8.416, "percentage": 85.48, "elapsed_time": "7:22:24", "remaining_time": "1:15:07"}
+{"current_steps": 540, "total_steps": 620, "loss": 0.0659, "lr": 9.973024214852567e-07, "epoch": 8.576, "percentage": 87.1, "elapsed_time": "7:30:49", "remaining_time": "1:06:47"}
+{"current_steps": 550, "total_steps": 620, "loss": 0.0648, "lr": 7.666001842872639e-07, "epoch": 8.736, "percentage": 88.71, "elapsed_time": "7:39:14", "remaining_time": "0:58:26"}
+{"current_steps": 560, "total_steps": 620, "loss": 0.0628, "lr": 5.651582129001987e-07, "epoch": 8.896, "percentage": 90.32, "elapsed_time": "7:47:38", "remaining_time": "0:50:06"}
+{"current_steps": 570, "total_steps": 620, "loss": 0.0579, "lr": 3.936148686802077e-07, "epoch": 9.048, "percentage": 91.94, "elapsed_time": "7:55:37", "remaining_time": "0:41:43"}
+{"current_steps": 580, "total_steps": 620, "loss": 0.0508, "lr": 2.525137654586185e-07, "epoch": 9.208, "percentage": 93.55, "elapsed_time": "8:04:02", "remaining_time": "0:33:22"}
+{"current_steps": 590, "total_steps": 620, "loss": 0.0516, "lr": 1.4230204685196202e-07, "epoch": 9.368, "percentage": 95.16, "elapsed_time": "8:12:27", "remaining_time": "0:25:02"}
+{"current_steps": 600, "total_steps": 620, "loss": 0.0517, "lr": 6.332896928217258e-08, "epoch": 9.528, "percentage": 96.77, "elapsed_time": "8:20:51", "remaining_time": "0:16:41"}
+{"current_steps": 610, "total_steps": 620, "loss": 0.0518, "lr": 1.5844795197285102e-08, "epoch": 9.688, "percentage": 98.39, "elapsed_time": "8:29:16", "remaining_time": "0:08:20"}
+{"current_steps": 620, "total_steps": 620, "loss": 0.0527, "lr": 0.0, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "8:37:41", "remaining_time": "0:00:00"}
+{"current_steps": 620, "total_steps": 620, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "8:37:43", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,477 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.848,
+  "eval_steps": 500,
+  "global_step": 620,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 12.881609916687012,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 2.0828,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 7.486210823059082,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 1.4787,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.486098289489746,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 1.3156,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.403397083282471,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 1.1692,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.133569240570068,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 1.1055,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.2612862586975098,
+      "learning_rate": 1.935483870967742e-05,
+      "loss": 1.0751,
+      "step": 60
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 2.8362364768981934,
+      "learning_rate": 1.9989858366670475e-05,
+      "loss": 0.9454,
+      "step": 70
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 2.404646396636963,
+      "learning_rate": 1.994869323391895e-05,
+      "loss": 0.9386,
+      "step": 80
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 2.6535897254943848,
+      "learning_rate": 1.9876001099813018e-05,
+      "loss": 0.9624,
+      "step": 90
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 2.9908246994018555,
+      "learning_rate": 1.977201232274814e-05,
+      "loss": 0.9408,
+      "step": 100
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 2.08085298538208,
+      "learning_rate": 1.963705643889941e-05,
+      "loss": 0.9316,
+      "step": 110
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 2.0934102535247803,
+      "learning_rate": 1.947156111793487e-05,
+      "loss": 0.9286,
+      "step": 120
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 2.122586727142334,
+      "learning_rate": 1.9276050807747878e-05,
+      "loss": 0.8039,
+      "step": 130
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 2.289278268814087,
+      "learning_rate": 1.9051145072503216e-05,
+      "loss": 0.7758,
+      "step": 140
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 2.2588486671447754,
+      "learning_rate": 1.8797556629263603e-05,
+      "loss": 0.7719,
+      "step": 150
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 2.52738356590271,
+      "learning_rate": 1.851608908941855e-05,
+      "loss": 0.7735,
+      "step": 160
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 2.1543173789978027,
+      "learning_rate": 1.8207634412072765e-05,
+      "loss": 0.7807,
+      "step": 170
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 2.3994810581207275,
+      "learning_rate": 1.7873170077464285e-05,
+      "loss": 0.7859,
+      "step": 180
+    },
+    {
+      "epoch": 3.016,
+      "grad_norm": 2.4878721237182617,
+      "learning_rate": 1.7513755989369636e-05,
+      "loss": 0.6971,
+      "step": 190
+    },
+    {
+      "epoch": 3.176,
+      "grad_norm": 2.379432439804077,
+      "learning_rate": 1.7130531116312202e-05,
+      "loss": 0.619,
+      "step": 200
+    },
+    {
+      "epoch": 3.336,
+      "grad_norm": 2.209932565689087,
+      "learning_rate": 1.6724709882217606e-05,
+      "loss": 0.5998,
+      "step": 210
+    },
+    {
+      "epoch": 3.496,
+      "grad_norm": 2.7859106063842773,
+      "learning_rate": 1.6297578317954025e-05,
+      "loss": 0.6066,
+      "step": 220
+    },
+    {
+      "epoch": 3.656,
+      "grad_norm": 2.6925034523010254,
+      "learning_rate": 1.5850489985953076e-05,
+      "loss": 0.6351,
+      "step": 230
+    },
+    {
+      "epoch": 3.816,
+      "grad_norm": 2.7933480739593506,
+      "learning_rate": 1.538486169082589e-05,
+      "loss": 0.6003,
+      "step": 240
+    },
+    {
+      "epoch": 3.976,
+      "grad_norm": 2.7974672317504883,
+      "learning_rate": 1.4902168989567335e-05,
+      "loss": 0.6382,
+      "step": 250
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 2.982576608657837,
+      "learning_rate": 1.4403941515576344e-05,
+      "loss": 0.4597,
+      "step": 260
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 2.571833610534668,
+      "learning_rate": 1.3891758131310329e-05,
+      "loss": 0.444,
+      "step": 270
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 2.4135894775390625,
+      "learning_rate": 1.3367241924934715e-05,
+      "loss": 0.4541,
+      "step": 280
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 2.8163669109344482,
+      "learning_rate": 1.283205506682304e-05,
+      "loss": 0.4532,
+      "step": 290
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 2.9105963706970215,
+      "learning_rate": 1.2287893542207122e-05,
+      "loss": 0.4454,
+      "step": 300
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 2.6453466415405273,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.4547,
+      "step": 310
+    },
+    {
+      "epoch": 5.08,
+      "grad_norm": 3.0081467628479004,
+      "learning_rate": 1.1179567171508463e-05,
+      "loss": 0.3733,
+      "step": 320
+    },
+    {
+      "epoch": 5.24,
+      "grad_norm": 3.0316622257232666,
+      "learning_rate": 1.061891456629682e-05,
+      "loss": 0.2988,
+      "step": 330
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 2.4374618530273438,
+      "learning_rate": 1.0056300646175661e-05,
+      "loss": 0.3001,
+      "step": 340
+    },
+    {
+      "epoch": 5.5600000000000005,
+      "grad_norm": 2.4697585105895996,
+      "learning_rate": 9.493508311612874e-06,
+      "loss": 0.2894,
+      "step": 350
+    },
+    {
+      "epoch": 5.72,
+      "grad_norm": 2.9103164672851562,
+      "learning_rate": 8.932321028464412e-06,
+      "loss": 0.2931,
+      "step": 360
+    },
+    {
+      "epoch": 5.88,
+      "grad_norm": 2.7394156455993652,
+      "learning_rate": 8.374517176244038e-06,
+      "loss": 0.3003,
+      "step": 370
+    },
+    {
+      "epoch": 6.032,
+      "grad_norm": 2.1789660453796387,
+      "learning_rate": 7.821864412511485e-06,
+      "loss": 0.2594,
+      "step": 380
+    },
+    {
+      "epoch": 6.192,
+      "grad_norm": 3.0000176429748535,
+      "learning_rate": 7.276114071238069e-06,
+      "loss": 0.1877,
+      "step": 390
+    },
+    {
+      "epoch": 6.352,
+      "grad_norm": 2.3748111724853516,
+      "learning_rate": 6.7389956129010516e-06,
+      "loss": 0.1846,
+      "step": 400
+    },
+    {
+      "epoch": 6.5120000000000005,
+      "grad_norm": 2.3044967651367188,
+      "learning_rate": 6.21221114389424e-06,
+      "loss": 0.1728,
+      "step": 410
+    },
+    {
+      "epoch": 6.672,
+      "grad_norm": 2.2465269565582275,
+      "learning_rate": 5.697430022622542e-06,
+      "loss": 0.1726,
+      "step": 420
+    },
+    {
+      "epoch": 6.832,
+      "grad_norm": 2.356623888015747,
+      "learning_rate": 5.1962835693735506e-06,
+      "loss": 0.1707,
+      "step": 430
+    },
+    {
+      "epoch": 6.992,
+      "grad_norm": 2.5909860134124756,
+      "learning_rate": 4.710359896730379e-06,
+      "loss": 0.1764,
+      "step": 440
+    },
+    {
+      "epoch": 7.144,
+      "grad_norm": 1.7320761680603027,
+      "learning_rate": 4.241198876907936e-06,
+      "loss": 0.0992,
+      "step": 450
+    },
+    {
+      "epoch": 7.304,
+      "grad_norm": 1.5438932180404663,
+      "learning_rate": 3.790287261960953e-06,
+      "loss": 0.0986,
+      "step": 460
+    },
+    {
+      "epoch": 7.464,
+      "grad_norm": 1.8166850805282593,
+      "learning_rate": 3.3590539723276083e-06,
+      "loss": 0.1039,
+      "step": 470
+    },
+    {
+      "epoch": 7.624,
+      "grad_norm": 1.8122446537017822,
+      "learning_rate": 2.9488655686392086e-06,
+      "loss": 0.1062,
+      "step": 480
+    },
+    {
+      "epoch": 7.784,
+      "grad_norm": 1.9146348237991333,
+      "learning_rate": 2.56102192114549e-06,
+      "loss": 0.1029,
+      "step": 490
+    },
+    {
+      "epoch": 7.944,
+      "grad_norm": 1.5483825206756592,
+      "learning_rate": 2.196752090479083e-06,
+      "loss": 0.0997,
+      "step": 500
+    },
+    {
+      "epoch": 8.096,
+      "grad_norm": 0.9715578556060791,
+      "learning_rate": 1.8572104328126738e-06,
+      "loss": 0.0687,
+      "step": 510
+    },
+    {
+      "epoch": 8.256,
+      "grad_norm": 1.1563620567321777,
+      "learning_rate": 1.5434729417516049e-06,
+      "loss": 0.0625,
+      "step": 520
+    },
+    {
+      "epoch": 8.416,
+      "grad_norm": 1.2092530727386475,
+      "learning_rate": 1.2565338385541792e-06,
+      "loss": 0.0647,
+      "step": 530
+    },
+    {
+      "epoch": 8.576,
+      "grad_norm": 1.2118881940841675,
+      "learning_rate": 9.973024214852567e-07,
+      "loss": 0.0659,
+      "step": 540
+    },
+    {
+      "epoch": 8.736,
+      "grad_norm": 1.1171401739120483,
+      "learning_rate": 7.666001842872639e-07,
+      "loss": 0.0648,
+      "step": 550
+    },
+    {
+      "epoch": 8.896,
+      "grad_norm": 1.0178390741348267,
+      "learning_rate": 5.651582129001987e-07,
+      "loss": 0.0628,
+      "step": 560
+    },
+    {
+      "epoch": 9.048,
+      "grad_norm": 0.854426383972168,
+      "learning_rate": 3.936148686802077e-07,
+      "loss": 0.0579,
+      "step": 570
+    },
+    {
+      "epoch": 9.208,
+      "grad_norm": 0.9751760363578796,
+      "learning_rate": 2.525137654586185e-07,
+      "loss": 0.0508,
+      "step": 580
+    },
+    {
+      "epoch": 9.368,
+      "grad_norm": 0.9072787165641785,
+      "learning_rate": 1.4230204685196202e-07,
+      "loss": 0.0516,
+      "step": 590
+    },
+    {
+      "epoch": 9.528,
+      "grad_norm": 1.0727787017822266,
+      "learning_rate": 6.332896928217258e-08,
+      "loss": 0.0517,
+      "step": 600
+    },
+    {
+      "epoch": 9.688,
+      "grad_norm": 0.8716169595718384,
+      "learning_rate": 1.5844795197285102e-08,
+      "loss": 0.0518,
+      "step": 610
+    },
+    {
+      "epoch": 9.848,
+      "grad_norm": 0.9439557790756226,
+      "learning_rate": 0.0,
+      "loss": 0.0527,
+      "step": 620
+    },
+    {
+      "epoch": 9.848,
+      "step": 620,
+      "total_flos": 2.117785669819433e+17,
+      "train_loss": 0.48659542481745444,
+      "train_runtime": 31064.4118,
+      "train_samples_per_second": 0.644,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 620,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.117785669819433e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8679129aad6efc54177edfebfe7b8f12c2a44794d1347f1d72c78ddfc60b1a3a
+size 5688