Model save

.gitattributes

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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: transformers
+model_name: Qwen2-VL-2B-Instruct-SFT_v2
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2-VL-2B-Instruct-SFT_v2
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="BleachNick/Qwen2-VL-2B-Instruct-SFT_v2", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/haozhezhao/huggingface/runs/pc94incy) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1+cu124
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9938398357289527,
+    "total_flos": 2.6292398538830643e+17,
+    "train_loss": 0.28410920734740486,
+    "train_runtime": 8398.4302,
+    "train_samples": 70000,
+    "train_samples_per_second": 8.335,
+    "train_steps_per_second": 0.014
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "attn_implementation": null,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c4308bdadc91e9f6dcf661911ce98052900d85033c9b3747959e90a046a190
+size 4884798456

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 sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9938398357289527,
+    "total_flos": 2.6292398538830643e+17,
+    "train_loss": 0.28410920734740486,
+    "train_runtime": 8398.4302,
+    "train_samples": 70000,
+    "train_samples_per_second": 8.335,
+    "train_steps_per_second": 0.014
+}

trainer_state.json

@@ -0,0 +1,210 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9938398357289527,
+  "eval_steps": 500,
+  "global_step": 121,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04106776180698152,
+      "grad_norm": 30.744543075561523,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 2.5793,
+      "step": 5
+    },
+    {
+      "epoch": 0.08213552361396304,
+      "grad_norm": 9.884822845458984,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.9277,
+      "step": 10
+    },
+    {
+      "epoch": 0.12320328542094455,
+      "grad_norm": 3.679464101791382,
+      "learning_rate": 1.9983081582712684e-05,
+      "loss": 0.4308,
+      "step": 15
+    },
+    {
+      "epoch": 0.16427104722792607,
+      "grad_norm": 3.9533257484436035,
+      "learning_rate": 1.9793406217655516e-05,
+      "loss": 0.2932,
+      "step": 20
+    },
+    {
+      "epoch": 0.2053388090349076,
+      "grad_norm": 3.831698179244995,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.2669,
+      "step": 25
+    },
+    {
+      "epoch": 0.2464065708418891,
+      "grad_norm": 3.2703301906585693,
+      "learning_rate": 1.880201391180111e-05,
+      "loss": 0.2244,
+      "step": 30
+    },
+    {
+      "epoch": 0.2874743326488706,
+      "grad_norm": 2.6521003246307373,
+      "learning_rate": 1.802123192755044e-05,
+      "loss": 0.1853,
+      "step": 35
+    },
+    {
+      "epoch": 0.32854209445585214,
+      "grad_norm": 3.0814249515533447,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.1587,
+      "step": 40
+    },
+    {
+      "epoch": 0.36960985626283366,
+      "grad_norm": 1.3627839088439941,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.1369,
+      "step": 45
+    },
+    {
+      "epoch": 0.4106776180698152,
+      "grad_norm": 1.0753473043441772,
+      "learning_rate": 1.4746003697476406e-05,
+      "loss": 0.1231,
+      "step": 50
+    },
+    {
+      "epoch": 0.4517453798767967,
+      "grad_norm": 0.8766598701477051,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.1167,
+      "step": 55
+    },
+    {
+      "epoch": 0.4928131416837782,
+      "grad_norm": 0.8106464743614197,
+      "learning_rate": 1.2022175723320382e-05,
+      "loss": 0.1141,
+      "step": 60
+    },
+    {
+      "epoch": 0.5338809034907598,
+      "grad_norm": 0.6666741967201233,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.1119,
+      "step": 65
+    },
+    {
+      "epoch": 0.5749486652977412,
+      "grad_norm": 0.6863110065460205,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.11,
+      "step": 70
+    },
+    {
+      "epoch": 0.6160164271047228,
+      "grad_norm": 0.4802115261554718,
+      "learning_rate": 7.6938412925756e-06,
+      "loss": 0.1093,
+      "step": 75
+    },
+    {
+      "epoch": 0.6570841889117043,
+      "grad_norm": 0.40680229663848877,
+      "learning_rate": 6.3079385268731575e-06,
+      "loss": 0.1086,
+      "step": 80
+    },
+    {
+      "epoch": 0.6981519507186859,
+      "grad_norm": 0.3752386271953583,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1073,
+      "step": 85
+    },
+    {
+      "epoch": 0.7392197125256673,
+      "grad_norm": 0.3691989481449127,
+      "learning_rate": 3.797645087317401e-06,
+      "loss": 0.1072,
+      "step": 90
+    },
+    {
+      "epoch": 0.7802874743326489,
+      "grad_norm": 0.4962676763534546,
+      "learning_rate": 2.726263584269513e-06,
+      "loss": 0.1075,
+      "step": 95
+    },
+    {
+      "epoch": 0.8213552361396304,
+      "grad_norm": 0.5959629416465759,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.1077,
+      "step": 100
+    },
+    {
+      "epoch": 0.8624229979466119,
+      "grad_norm": 0.29346510767936707,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.1065,
+      "step": 105
+    },
+    {
+      "epoch": 0.9034907597535934,
+      "grad_norm": 0.29161593317985535,
+      "learning_rate": 5.075735642696611e-07,
+      "loss": 0.1069,
+      "step": 110
+    },
+    {
+      "epoch": 0.944558521560575,
+      "grad_norm": 0.32137367129325867,
+      "learning_rate": 1.519224698779198e-07,
+      "loss": 0.1066,
+      "step": 115
+    },
+    {
+      "epoch": 0.9856262833675564,
+      "grad_norm": 0.23854857683181763,
+      "learning_rate": 4.230499177994007e-09,
+      "loss": 0.1071,
+      "step": 120
+    },
+    {
+      "epoch": 0.9938398357289527,
+      "step": 121,
+      "total_flos": 2.6292398538830643e+17,
+      "train_loss": 0.28410920734740486,
+      "train_runtime": 8398.4302,
+      "train_samples_per_second": 8.335,
+      "train_steps_per_second": 0.014
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 121,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6292398538830643e+17,
+  "train_batch_size": 18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54e1422894f243b4b2f1dfc9a61806b6890ab99a863bdc07e1c457767195db5
+size 7160