Initial model upload

README.md

@@ -36,13 +36,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 1
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1.0
+- num_epochs: 10.0
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -19,7 +19,7 @@
   "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "^(?!.*visual).*(?:q_proj|v_proj|down_proj|o_proj|k_proj|up_proj|gate_proj).*",
+  "target_modules": "^(?!.*visual).*(?:v_proj|o_proj|down_proj|gate_proj|k_proj|up_proj|q_proj).*",
   "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15be91fb58ade897afaeafe11f5b1e404d89dc498e9505b1df77b5b1f2d5cfe6
+oid sha256:d8cd4557de62011d00d0129f372984c93946f97bcccf5653f59dd83e0933f99b
 size 80792096

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "total_flos": 1253709718659072.0,
-    "train_loss": 1.1837843036651612,
-    "train_runtime": 1511.658,
-    "train_samples_per_second": 0.066,
-    "train_steps_per_second": 0.066
+    "epoch": 10.0,
+    "total_flos": 1.1283387467931648e+16,
+    "train_loss": 0.3623817192316055,
+    "train_runtime": 5832.4394,
+    "train_samples_per_second": 0.171,
+    "train_steps_per_second": 0.086
 }

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:v_proj|o_proj|down_proj|gate_proj|k_proj|up_proj|q_proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cd4557de62011d00d0129f372984c93946f97bcccf5653f59dd83e0933f99b
+size 80792096

checkpoint-500/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-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31b791db3aa6196fd68138a3de6f12343891e33e72e49b4eb69f86607580998
+size 161810538

checkpoint-500/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-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db153df6a267d4d428174749933eed3d7b65f025a851ca2ce2a038fb8c797683
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4617a9e3219086c0277ec0ef4bd3c0449bbfde6f7e39345b351d4003923694b
+size 1064

checkpoint-500/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-500/tokenizer.json

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

checkpoint-500/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-500/trainer_state.json

@@ -0,0 +1,383 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.4489102363586426,
+      "learning_rate": 2e-05,
+      "loss": 1.8047,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.8422876596450806,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.3832,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.1532328128814697,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.1404,
+      "step": 30
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.9095581769943237,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.068,
+      "step": 40
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.4410550594329834,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 1.014,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.7899439334869385,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.1168,
+      "step": 60
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.6681783199310303,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.9987,
+      "step": 70
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.2320525646209717,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 1.198,
+      "step": 80
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.1953657865524292,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 1.0336,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.67486572265625,
+      "learning_rate": 0.0,
+      "loss": 1.0806,
+      "step": 100
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.0614951848983765,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.9586,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1396006345748901,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.9822,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.8257782459259033,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.9798,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 3.6675124168395996,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.9642,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.7332773208618164,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.0019,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.2114962339401245,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.8493,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 5.460783004760742,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.8319,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 3.551159620285034,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.7986,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 4.315650463104248,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.7908,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.731149673461914,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8207,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 2.3099749088287354,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.8045,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 5.100424766540527,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.6337,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 4.819253444671631,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5244,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 5.7660675048828125,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.5807,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.9891021251678467,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.6353,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 3.6858391761779785,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.4776,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 9.160813331604004,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.323,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 7.0403313636779785,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.4799,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 7.419447898864746,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.5816,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.421180009841919,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4278,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 4.215754985809326,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.3721,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 6.3047308921813965,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.2973,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 14.362757682800293,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.2589,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 7.351701736450195,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.2718,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 8.06631851196289,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3159,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 5.070101261138916,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.2075,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 7.613597869873047,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.1164,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 6.611764907836914,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.2217,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 12.279210090637207,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.1475,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 14.093499183654785,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.2752,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 2.3949663639068604,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.1019,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 3.969956159591675,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.1754,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 8.477439880371094,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.1174,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 2.671515464782715,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.1461,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.29233822226524353,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.1105,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 3.0615086555480957,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.1009,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 1.1887454986572266,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.1134,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 13.041033744812012,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.1092,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 5.9538798332214355,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.0799,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.9380784034729004,
+      "learning_rate": 0.0,
+      "loss": 0.1335,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "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": 1.1283387467931648e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ac5c77361865dee62f3686a14dbb3f3cbb2a06b7fa1d162335e35f9298c002
+size 5368

runs/Nov16_14-06-13_LAB12-PC43/events.out.tfevents.1731747996.LAB12-PC43.13616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d4f584f815f2c42f7f4a8a653835a270c01b99c667171f47a4af1e46c428c4
+size 14374

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "total_flos": 1253709718659072.0,
-    "train_loss": 1.1837843036651612,
-    "train_runtime": 1511.658,
-    "train_samples_per_second": 0.066,
-    "train_steps_per_second": 0.066
+    "epoch": 10.0,
+    "total_flos": 1.1283387467931648e+16,
+    "train_loss": 0.3623817192316055,
+    "train_runtime": 5832.4394,
+    "train_samples_per_second": 0.171,
+    "train_steps_per_second": 0.086
 }

trainer_log.jsonl

@@ -9,3 +9,44 @@
 {"current_steps": 90, "total_steps": 100, "loss": 1.0336, "learning_rate": 6.030737921409169e-07, "epoch": 0.9, "percentage": 90.0, "elapsed_time": "0:22:33", "remaining_time": "0:02:30"}
 {"current_steps": 100, "total_steps": 100, "loss": 1.0806, "learning_rate": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:25:05", "remaining_time": "0:00:00"}
 {"current_steps": 100, "total_steps": 100, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:25:07", "remaining_time": "0:00:00"}
+{"current_steps": 110, "total_steps": 500, "loss": 0.9586, "learning_rate": 1.913545457642601e-05, "epoch": 2.2, "percentage": 22.0, "elapsed_time": "0:02:25", "remaining_time": "0:08:37"}
+{"current_steps": 120, "total_steps": 500, "loss": 0.9822, "learning_rate": 1.8829475928589272e-05, "epoch": 2.4, "percentage": 24.0, "elapsed_time": "0:05:07", "remaining_time": "0:16:15"}
+{"current_steps": 130, "total_steps": 500, "loss": 0.9798, "learning_rate": 1.848048096156426e-05, "epoch": 2.6, "percentage": 26.0, "elapsed_time": "0:07:52", "remaining_time": "0:22:24"}
+{"current_steps": 140, "total_steps": 500, "loss": 0.9642, "learning_rate": 1.8090169943749477e-05, "epoch": 2.8, "percentage": 28.0, "elapsed_time": "0:10:10", "remaining_time": "0:26:10"}
+{"current_steps": 150, "total_steps": 500, "loss": 1.0019, "learning_rate": 1.766044443118978e-05, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:12:29", "remaining_time": "0:29:09"}
+{"current_steps": 160, "total_steps": 500, "loss": 0.8493, "learning_rate": 1.7193398003386514e-05, "epoch": 3.2, "percentage": 32.0, "elapsed_time": "0:14:49", "remaining_time": "0:31:30"}
+{"current_steps": 170, "total_steps": 500, "loss": 0.8319, "learning_rate": 1.6691306063588583e-05, "epoch": 3.4, "percentage": 34.0, "elapsed_time": "0:17:07", "remaining_time": "0:33:15"}
+{"current_steps": 180, "total_steps": 500, "loss": 0.7986, "learning_rate": 1.6156614753256583e-05, "epoch": 3.6, "percentage": 36.0, "elapsed_time": "0:19:41", "remaining_time": "0:35:00"}
+{"current_steps": 190, "total_steps": 500, "loss": 0.7908, "learning_rate": 1.5591929034707468e-05, "epoch": 3.8, "percentage": 38.0, "elapsed_time": "0:22:17", "remaining_time": "0:36:22"}
+{"current_steps": 200, "total_steps": 500, "loss": 0.8207, "learning_rate": 1.5000000000000002e-05, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:24:53", "remaining_time": "0:37:20"}
+{"current_steps": 210, "total_steps": 500, "loss": 0.8045, "learning_rate": 1.4383711467890776e-05, "epoch": 4.2, "percentage": 42.0, "elapsed_time": "0:27:29", "remaining_time": "0:37:58"}
+{"current_steps": 220, "total_steps": 500, "loss": 0.6337, "learning_rate": 1.3746065934159123e-05, "epoch": 4.4, "percentage": 44.0, "elapsed_time": "0:30:05", "remaining_time": "0:38:18"}
+{"current_steps": 230, "total_steps": 500, "loss": 0.5244, "learning_rate": 1.3090169943749475e-05, "epoch": 4.6, "percentage": 46.0, "elapsed_time": "0:32:41", "remaining_time": "0:38:22"}
+{"current_steps": 240, "total_steps": 500, "loss": 0.5807, "learning_rate": 1.2419218955996677e-05, "epoch": 4.8, "percentage": 48.0, "elapsed_time": "0:35:16", "remaining_time": "0:38:13"}
+{"current_steps": 250, "total_steps": 500, "loss": 0.6353, "learning_rate": 1.1736481776669307e-05, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:37:53", "remaining_time": "0:37:53"}
+{"current_steps": 260, "total_steps": 500, "loss": 0.4776, "learning_rate": 1.1045284632676535e-05, "epoch": 5.2, "percentage": 52.0, "elapsed_time": "0:40:29", "remaining_time": "0:37:22"}
+{"current_steps": 270, "total_steps": 500, "loss": 0.323, "learning_rate": 1.0348994967025012e-05, "epoch": 5.4, "percentage": 54.0, "elapsed_time": "0:43:05", "remaining_time": "0:36:42"}
+{"current_steps": 280, "total_steps": 500, "loss": 0.4799, "learning_rate": 9.651005032974994e-06, "epoch": 5.6, "percentage": 56.0, "elapsed_time": "0:45:35", "remaining_time": "0:35:49"}
+{"current_steps": 290, "total_steps": 500, "loss": 0.5816, "learning_rate": 8.954715367323468e-06, "epoch": 5.8, "percentage": 58.0, "elapsed_time": "0:47:55", "remaining_time": "0:34:42"}
+{"current_steps": 300, "total_steps": 500, "loss": 0.4278, "learning_rate": 8.263518223330698e-06, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:50:14", "remaining_time": "0:33:29"}
+{"current_steps": 310, "total_steps": 500, "loss": 0.3721, "learning_rate": 7.580781044003324e-06, "epoch": 6.2, "percentage": 62.0, "elapsed_time": "0:52:35", "remaining_time": "0:32:14"}
+{"current_steps": 320, "total_steps": 500, "loss": 0.2973, "learning_rate": 6.909830056250527e-06, "epoch": 6.4, "percentage": 64.0, "elapsed_time": "0:54:54", "remaining_time": "0:30:53"}
+{"current_steps": 330, "total_steps": 500, "loss": 0.2589, "learning_rate": 6.25393406584088e-06, "epoch": 6.6, "percentage": 66.0, "elapsed_time": "0:57:13", "remaining_time": "0:29:28"}
+{"current_steps": 340, "total_steps": 500, "loss": 0.2718, "learning_rate": 5.616288532109225e-06, "epoch": 6.8, "percentage": 68.0, "elapsed_time": "0:59:31", "remaining_time": "0:28:00"}
+{"current_steps": 350, "total_steps": 500, "loss": 0.3159, "learning_rate": 5.000000000000003e-06, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "1:01:53", "remaining_time": "0:26:31"}
+{"current_steps": 360, "total_steps": 500, "loss": 0.2075, "learning_rate": 4.408070965292534e-06, "epoch": 7.2, "percentage": 72.0, "elapsed_time": "1:04:13", "remaining_time": "0:24:58"}
+{"current_steps": 370, "total_steps": 500, "loss": 0.1164, "learning_rate": 3.8433852467434175e-06, "epoch": 7.4, "percentage": 74.0, "elapsed_time": "1:06:32", "remaining_time": "0:23:22"}
+{"current_steps": 380, "total_steps": 500, "loss": 0.2217, "learning_rate": 3.308693936411421e-06, "epoch": 7.6, "percentage": 76.0, "elapsed_time": "1:08:53", "remaining_time": "0:21:45"}
+{"current_steps": 390, "total_steps": 500, "loss": 0.1475, "learning_rate": 2.8066019966134907e-06, "epoch": 7.8, "percentage": 78.0, "elapsed_time": "1:11:14", "remaining_time": "0:20:05"}
+{"current_steps": 400, "total_steps": 500, "loss": 0.2752, "learning_rate": 2.339555568810221e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "1:13:36", "remaining_time": "0:18:24"}
+{"current_steps": 410, "total_steps": 500, "loss": 0.1019, "learning_rate": 1.9098300562505266e-06, "epoch": 8.2, "percentage": 82.0, "elapsed_time": "1:15:58", "remaining_time": "0:16:40"}
+{"current_steps": 420, "total_steps": 500, "loss": 0.1754, "learning_rate": 1.5195190384357405e-06, "epoch": 8.4, "percentage": 84.0, "elapsed_time": "1:18:19", "remaining_time": "0:14:55"}
+{"current_steps": 430, "total_steps": 500, "loss": 0.1174, "learning_rate": 1.1705240714107301e-06, "epoch": 8.6, "percentage": 86.0, "elapsed_time": "1:20:41", "remaining_time": "0:13:08"}
+{"current_steps": 440, "total_steps": 500, "loss": 0.1461, "learning_rate": 8.645454235739903e-07, "epoch": 8.8, "percentage": 88.0, "elapsed_time": "1:23:02", "remaining_time": "0:11:19"}
+{"current_steps": 450, "total_steps": 500, "loss": 0.1105, "learning_rate": 6.030737921409169e-07, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "1:25:23", "remaining_time": "0:09:29"}
+{"current_steps": 460, "total_steps": 500, "loss": 0.1009, "learning_rate": 3.8738304061681107e-07, "epoch": 9.2, "percentage": 92.0, "elapsed_time": "1:27:44", "remaining_time": "0:07:37"}
+{"current_steps": 470, "total_steps": 500, "loss": 0.1134, "learning_rate": 2.1852399266194312e-07, "epoch": 9.4, "percentage": 94.0, "elapsed_time": "1:30:06", "remaining_time": "0:05:45"}
+{"current_steps": 480, "total_steps": 500, "loss": 0.1092, "learning_rate": 9.731931258429638e-08, "epoch": 9.6, "percentage": 96.0, "elapsed_time": "1:32:28", "remaining_time": "0:03:51"}
+{"current_steps": 490, "total_steps": 500, "loss": 0.0799, "learning_rate": 2.4359497401758026e-08, "epoch": 9.8, "percentage": 98.0, "elapsed_time": "1:34:48", "remaining_time": "0:01:56"}
+{"current_steps": 500, "total_steps": 500, "loss": 0.1335, "learning_rate": 0.0, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "1:37:09", "remaining_time": "0:00:00"}
+{"current_steps": 500, "total_steps": 500, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "1:37:10", "remaining_time": "0:00:00"}

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,19 +79,299 @@
       "step": 100
     },
     {
-      "epoch": 1.0,
-      "step": 100,
-      "total_flos": 1253709718659072.0,
-      "train_loss": 1.1837843036651612,
-      "train_runtime": 1511.658,
-      "train_samples_per_second": 0.066,
-      "train_steps_per_second": 0.066
+      "epoch": 2.2,
+      "grad_norm": 1.0614951848983765,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.9586,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.1396006345748901,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.9822,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 1.8257782459259033,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.9798,
+      "step": 130
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 3.6675124168395996,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.9642,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.7332773208618164,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.0019,
+      "step": 150
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.2114962339401245,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.8493,
+      "step": 160
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 5.460783004760742,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.8319,
+      "step": 170
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 3.551159620285034,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.7986,
+      "step": 180
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 4.315650463104248,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.7908,
+      "step": 190
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.731149673461914,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8207,
+      "step": 200
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 2.3099749088287354,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.8045,
+      "step": 210
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 5.100424766540527,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.6337,
+      "step": 220
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 4.819253444671631,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.5244,
+      "step": 230
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 5.7660675048828125,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.5807,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.9891021251678467,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.6353,
+      "step": 250
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 3.6858391761779785,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.4776,
+      "step": 260
+    },
+    {
+      "epoch": 5.4,
+      "grad_norm": 9.160813331604004,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.323,
+      "step": 270
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 7.0403313636779785,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.4799,
+      "step": 280
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 7.419447898864746,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.5816,
+      "step": 290
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.421180009841919,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4278,
+      "step": 300
+    },
+    {
+      "epoch": 6.2,
+      "grad_norm": 4.215754985809326,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.3721,
+      "step": 310
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 6.3047308921813965,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.2973,
+      "step": 320
+    },
+    {
+      "epoch": 6.6,
+      "grad_norm": 14.362757682800293,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.2589,
+      "step": 330
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 7.351701736450195,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.2718,
+      "step": 340
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 8.06631851196289,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.3159,
+      "step": 350
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 5.070101261138916,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.2075,
+      "step": 360
+    },
+    {
+      "epoch": 7.4,
+      "grad_norm": 7.613597869873047,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.1164,
+      "step": 370
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 6.611764907836914,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.2217,
+      "step": 380
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 12.279210090637207,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.1475,
+      "step": 390
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 14.093499183654785,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.2752,
+      "step": 400
+    },
+    {
+      "epoch": 8.2,
+      "grad_norm": 2.3949663639068604,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.1019,
+      "step": 410
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 3.969956159591675,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.1754,
+      "step": 420
+    },
+    {
+      "epoch": 8.6,
+      "grad_norm": 8.477439880371094,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.1174,
+      "step": 430
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 2.671515464782715,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.1461,
+      "step": 440
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.29233822226524353,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.1105,
+      "step": 450
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 3.0615086555480957,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.1009,
+      "step": 460
+    },
+    {
+      "epoch": 9.4,
+      "grad_norm": 1.1887454986572266,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.1134,
+      "step": 470
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 13.041033744812012,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.1092,
+      "step": 480
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 5.9538798332214355,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.0799,
+      "step": 490
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.9380784034729004,
+      "learning_rate": 0.0,
+      "loss": 0.1335,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "step": 500,
+      "total_flos": 1.1283387467931648e+16,
+      "train_loss": 0.3623817192316055,
+      "train_runtime": 5832.4394,
+      "train_samples_per_second": 0.171,
+      "train_steps_per_second": 0.086
     }
   ],
   "logging_steps": 10,
-  "max_steps": 100,
+  "max_steps": 500,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 10,
   "save_steps": 1000,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -105,7 +385,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1253709718659072.0,
+  "total_flos": 1.1283387467931648e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea5dac8d603112133ba04cc7f152bd315d118dde0adf33514551718b87e8ebb
+oid sha256:91ac5c77361865dee62f3686a14dbb3f3cbb2a06b7fa1d162335e35f9298c002
 size 5368