Upload 20 files

.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 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2-VL-7B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: BS_riche_lora
+  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. -->
+
+# BS_riche_lora
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct) on the BsKIE3 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,223 @@
+{
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.22.self_attn.o_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.27.mlp.down_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.17.mlp.gate_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.19.self_attn.o_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.21.mlp.up_proj",
+    "model.layers.25.mlp.down_proj",
+    "model.layers.27.mlp.gate_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.23.mlp.up_proj",
+    "model.layers.24.mlp.up_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.26.mlp.down_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.27.mlp.up_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.22.mlp.up_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.22.mlp.down_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.26.self_attn.o_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.23.self_attn.k_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.27.self_attn.o_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.27.self_attn.k_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.19.mlp.gate_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.20.self_attn.o_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.16.mlp.up_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.21.mlp.gate_proj",
+    "model.layers.24.mlp.down_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.22.mlp.gate_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.17.mlp.up_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.18.mlp.gate_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.16.mlp.gate_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.26.mlp.up_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.26.mlp.gate_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.18.self_attn.o_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.23.mlp.gate_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.24.self_attn.o_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.24.mlp.gate_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.21.self_attn.o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2870c56632dfa7eb666926a3b41839b7e17e75a7da0a77fdb8425561928d6bbc
+size 80792096

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": 2.9904761904761905,
+    "num_input_tokens_seen": 8039616,
+    "total_flos": 3.746411207808123e+17,
+    "train_loss": 0.05875852833955716,
+    "train_runtime": 3746.4527,
+    "train_samples_per_second": 0.841,
+    "train_steps_per_second": 0.052
+}

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 %}"
+}

llamaboard_config.yaml

@@ -0,0 +1,78 @@
+top.booster: auto
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Qwen2-VL-7B-Instruct
+top.quantization_bit: none
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: qwen2_vl
+train.additional_target: ''
+train.apollo_rank: 16
+train.apollo_scale: 32
+train.apollo_target: all
+train.apollo_update_interval: 200
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 34114
+train.dataset:
+- BsKIE3
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 2
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to:
+- none
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.swanlab_api_key: ''
+train.swanlab_link: ''
+train.swanlab_mode: cloud
+train.swanlab_project: llamafactory
+train.swanlab_run_name: ''
+train.swanlab_workspace: ''
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_apollo: false
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.use_swanlab: false
+train.val_size: 0
+train.warmup_steps: 0

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
+}

running_log.txt

@@ -0,0 +1,582 @@
+[INFO|2025-03-21 09:41:46] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/config.json
+
+[INFO|2025-03-21 09:41:46] configuration_utils.py:771 >> Model config Qwen2VLConfig {
+  "_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/vocab.json
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/merges.txt
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/tokenizer.json
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/tokenizer_config.json
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-03-21 09:41:49] tokenization_utils_base.py:2313 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-03-21 09:41:49] image_processing_base.py:381 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/preprocessor_config.json
+
+[INFO|2025-03-21 09:41:49] image_processing_base.py:381 >> loading configuration file preprocessor_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/preprocessor_config.json
+
+[WARNING|2025-03-21 09:41:49] logging.py:329 >> Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.48, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
+
+[INFO|2025-03-21 09:41:49] image_processing_base.py:434 >> Image processor Qwen2VLImageProcessor {
+  "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
+}
+
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/vocab.json
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/merges.txt
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/tokenizer.json
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file special_tokens_map.json from cache at None
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/tokenizer_config.json
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2050 >> loading file chat_template.jinja from cache at None
+
+[INFO|2025-03-21 09:41:50] tokenization_utils_base.py:2313 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+[INFO|2025-03-21 09:41:51] processing_utils.py:876 >> Processor Qwen2VLProcessor:
+- image_processor: Qwen2VLImageProcessor {
+  "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
+}
+
+- tokenizer: Qwen2TokenizerFast(name_or_path='Qwen/Qwen2-VL-7B-Instruct', vocab_size=151643, model_max_length=32768, is_fast=True, padding_side='left', truncation_side='right', special_tokens={'eos_token': '<|im_end|>', 'pad_token': '<|endoftext|>', '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|>']}, clean_up_tokenization_spaces=False, added_tokens_decoder={
+	151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151647: AddedToken("<|object_ref_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151648: AddedToken("<|box_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151649: AddedToken("<|box_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151650: AddedToken("<|quad_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151651: AddedToken("<|quad_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151652: AddedToken("<|vision_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151653: AddedToken("<|vision_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151654: AddedToken("<|vision_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151655: AddedToken("<|image_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+	151656: AddedToken("<|video_pad|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True),
+}
+)
+
+{
+  "processor_class": "Qwen2VLProcessor"
+}
+
+
+[INFO|2025-03-21 09:41:51] logging.py:157 >> Add <|im_end|> to stop words.
+
+[INFO|2025-03-21 09:41:51] logging.py:157 >> Loading dataset BsKIE3.json...
+
+[INFO|2025-03-21 09:42:04] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/config.json
+
+[INFO|2025-03-21 09:42:04] configuration_utils.py:771 >> Model config Qwen2VLConfig {
+  "_name_or_path": "Qwen/Qwen2-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-21 09:42:04] modeling_utils.py:3982 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/model.safetensors.index.json
+
+[INFO|2025-03-21 09:43:21] modeling_utils.py:1633 >> Instantiating Qwen2VLForConditionalGeneration model under default dtype torch.bfloat16.
+
+[INFO|2025-03-21 09:43:21] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+[INFO|2025-03-21 09:43:21] modeling_utils.py:1633 >> Instantiating Qwen2VisionTransformerPretrainedModel model under default dtype torch.bfloat16.
+
+[INFO|2025-03-21 09:43:24] modeling_utils.py:4970 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration.
+
+
+[INFO|2025-03-21 09:43:24] modeling_utils.py:4978 >> All the weights of Qwen2VLForConditionalGeneration were initialized from the model checkpoint at Qwen/Qwen2-VL-7B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2VLForConditionalGeneration for predictions without further training.
+
+[INFO|2025-03-21 09:43:24] configuration_utils.py:1095 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/generation_config.json
+
+[INFO|2025-03-21 09:43:24] configuration_utils.py:1140 >> Generate config GenerationConfig {
+  "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
+}
+
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Using torch SDPA for faster training and inference.
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Found linear modules: k_proj,gate_proj,v_proj,o_proj,q_proj,up_proj,down_proj
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Set vision model not trainable: ['visual.patch_embed', 'visual.blocks'].
+
+[INFO|2025-03-21 09:43:24] logging.py:157 >> Set multi model projector not trainable: visual.merger.
+
+[INFO|2025-03-21 09:43:25] logging.py:157 >> trainable params: 20,185,088 || all params: 8,311,560,704 || trainable%: 0.2429
+
+[INFO|2025-03-21 09:43:25] trainer.py:746 >> Using auto half precision backend
+
+[WARNING|2025-03-21 09:43:25] trainer.py:781 >> No label_names provided for model class `PeftModelForCausalLM`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.
+
+[INFO|2025-03-21 09:43:25] trainer.py:2405 >> ***** Running training *****
+
+[INFO|2025-03-21 09:43:25] trainer.py:2406 >>   Num examples = 1,050
+
+[INFO|2025-03-21 09:43:25] trainer.py:2407 >>   Num Epochs = 3
+
+[INFO|2025-03-21 09:43:25] trainer.py:2408 >>   Instantaneous batch size per device = 2
+
+[INFO|2025-03-21 09:43:25] trainer.py:2411 >>   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+[INFO|2025-03-21 09:43:25] trainer.py:2412 >>   Gradient Accumulation steps = 8
+
+[INFO|2025-03-21 09:43:25] trainer.py:2413 >>   Total optimization steps = 195
+
+[INFO|2025-03-21 09:43:25] trainer.py:2414 >>   Number of trainable parameters = 20,185,088
+
+[INFO|2025-03-21 09:45:00] logging.py:157 >> {'loss': 0.2783, 'learning_rate': 4.9919e-05, 'epoch': 0.08, 'throughput': 2222.37}
+
+[INFO|2025-03-21 09:46:36] logging.py:157 >> {'loss': 0.1989, 'learning_rate': 4.9676e-05, 'epoch': 0.15, 'throughput': 2194.13}
+
+[INFO|2025-03-21 09:48:17] logging.py:157 >> {'loss': 0.1331, 'learning_rate': 4.9274e-05, 'epoch': 0.23, 'throughput': 2167.74}
+
+[INFO|2025-03-21 09:49:53] logging.py:157 >> {'loss': 0.1029, 'learning_rate': 4.8713e-05, 'epoch': 0.30, 'throughput': 2159.97}
+
+[INFO|2025-03-21 09:51:29] logging.py:157 >> {'loss': 0.0800, 'learning_rate': 4.7999e-05, 'epoch': 0.38, 'throughput': 2155.84}
+
+[INFO|2025-03-21 09:53:04] logging.py:157 >> {'loss': 0.0767, 'learning_rate': 4.7136e-05, 'epoch': 0.46, 'throughput': 2151.49}
+
+[INFO|2025-03-21 09:54:36] logging.py:157 >> {'loss': 0.0596, 'learning_rate': 4.6130e-05, 'epoch': 0.53, 'throughput': 2154.20}
+
+[INFO|2025-03-21 09:56:13] logging.py:157 >> {'loss': 0.0619, 'learning_rate': 4.4986e-05, 'epoch': 0.61, 'throughput': 2151.53}
+
+[INFO|2025-03-21 09:57:44] logging.py:157 >> {'loss': 0.0585, 'learning_rate': 4.3713e-05, 'epoch': 0.69, 'throughput': 2154.83}
+
+[INFO|2025-03-21 09:59:21] logging.py:157 >> {'loss': 0.0642, 'learning_rate': 4.2318e-05, 'epoch': 0.76, 'throughput': 2151.56}
+
+[INFO|2025-03-21 10:00:58] logging.py:157 >> {'loss': 0.0530, 'learning_rate': 4.0811e-05, 'epoch': 0.84, 'throughput': 2151.91}
+
+[INFO|2025-03-21 10:02:34] logging.py:157 >> {'loss': 0.0566, 'learning_rate': 3.9202e-05, 'epoch': 0.91, 'throughput': 2151.74}
+
+[INFO|2025-03-21 10:04:09] logging.py:157 >> {'loss': 0.0496, 'learning_rate': 3.7500e-05, 'epoch': 0.99, 'throughput': 2152.63}
+
+[INFO|2025-03-21 10:05:52] logging.py:157 >> {'loss': 0.0577, 'learning_rate': 3.5717e-05, 'epoch': 1.08, 'throughput': 2151.34}
+
+[INFO|2025-03-21 10:07:18] logging.py:157 >> {'loss': 0.0442, 'learning_rate': 3.3865e-05, 'epoch': 1.15, 'throughput': 2155.99}
+
+[INFO|2025-03-21 10:08:57] logging.py:157 >> {'loss': 0.0469, 'learning_rate': 3.1955e-05, 'epoch': 1.23, 'throughput': 2152.47}
+
+[INFO|2025-03-21 10:10:36] logging.py:157 >> {'loss': 0.0417, 'learning_rate': 3.0001e-05, 'epoch': 1.30, 'throughput': 2151.23}
+
+[INFO|2025-03-21 10:12:08] logging.py:157 >> {'loss': 0.0451, 'learning_rate': 2.8013e-05, 'epoch': 1.38, 'throughput': 2151.68}
+
+[INFO|2025-03-21 10:13:45] logging.py:157 >> {'loss': 0.0438, 'learning_rate': 2.6007e-05, 'epoch': 1.46, 'throughput': 2150.08}
+
+[INFO|2025-03-21 10:15:23] logging.py:157 >> {'loss': 0.0380, 'learning_rate': 2.3993e-05, 'epoch': 1.53, 'throughput': 2149.01}
+
+[INFO|2025-03-21 10:15:23] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100
+
+[INFO|2025-03-21 10:15:27] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/config.json
+
+[INFO|2025-03-21 10:15:27] configuration_utils.py:771 >> Model config Qwen2VLConfig {
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-21 10:15:27] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100/tokenizer_config.json
+
+[INFO|2025-03-21 10:15:27] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100/special_tokens_map.json
+
+[INFO|2025-03-21 10:15:27] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100/preprocessor_config.json
+
+[INFO|2025-03-21 10:15:27] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100/tokenizer_config.json
+
+[INFO|2025-03-21 10:15:27] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100/special_tokens_map.json
+
+[INFO|2025-03-21 10:15:27] processing_utils.py:638 >> chat template saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-100/chat_template.json
+
+[INFO|2025-03-21 10:17:03] logging.py:157 >> {'loss': 0.0380, 'learning_rate': 2.1987e-05, 'epoch': 1.61, 'throughput': 2144.53}
+
+[INFO|2025-03-21 10:18:43] logging.py:157 >> {'loss': 0.0397, 'learning_rate': 1.9999e-05, 'epoch': 1.69, 'throughput': 2142.88}
+
+[INFO|2025-03-21 10:20:19] logging.py:157 >> {'loss': 0.0404, 'learning_rate': 1.8045e-05, 'epoch': 1.76, 'throughput': 2142.72}
+
+[INFO|2025-03-21 10:21:58] logging.py:157 >> {'loss': 0.0362, 'learning_rate': 1.6135e-05, 'epoch': 1.84, 'throughput': 2142.84}
+
+[INFO|2025-03-21 10:23:28] logging.py:157 >> {'loss': 0.0397, 'learning_rate': 1.4283e-05, 'epoch': 1.91, 'throughput': 2145.15}
+
+[INFO|2025-03-21 10:25:02] logging.py:157 >> {'loss': 0.0343, 'learning_rate': 1.2500e-05, 'epoch': 1.99, 'throughput': 2146.04}
+
+[INFO|2025-03-21 10:26:45] logging.py:157 >> {'loss': 0.0396, 'learning_rate': 1.0798e-05, 'epoch': 2.08, 'throughput': 2145.80}
+
+[INFO|2025-03-21 10:28:14] logging.py:157 >> {'loss': 0.0394, 'learning_rate': 9.1889e-06, 'epoch': 2.15, 'throughput': 2147.67}
+
+[INFO|2025-03-21 10:29:54] logging.py:157 >> {'loss': 0.0311, 'learning_rate': 7.6819e-06, 'epoch': 2.23, 'throughput': 2146.29}
+
+[INFO|2025-03-21 10:31:26] logging.py:157 >> {'loss': 0.0480, 'learning_rate': 6.2872e-06, 'epoch': 2.30, 'throughput': 2147.33}
+
+[INFO|2025-03-21 10:33:00] logging.py:157 >> {'loss': 0.0374, 'learning_rate': 5.0139e-06, 'epoch': 2.38, 'throughput': 2148.07}
+
+[INFO|2025-03-21 10:34:34] logging.py:157 >> {'loss': 0.0334, 'learning_rate': 3.8702e-06, 'epoch': 2.46, 'throughput': 2148.53}
+
+[INFO|2025-03-21 10:36:10] logging.py:157 >> {'loss': 0.0324, 'learning_rate': 2.8636e-06, 'epoch': 2.53, 'throughput': 2148.97}
+
+[INFO|2025-03-21 10:37:44] logging.py:157 >> {'loss': 0.0342, 'learning_rate': 2.0005e-06, 'epoch': 2.61, 'throughput': 2149.31}
+
+[INFO|2025-03-21 10:39:19] logging.py:157 >> {'loss': 0.0384, 'learning_rate': 1.2866e-06, 'epoch': 2.69, 'throughput': 2149.34}
+
+[INFO|2025-03-21 10:40:58] logging.py:157 >> {'loss': 0.0357, 'learning_rate': 7.2645e-07, 'epoch': 2.76, 'throughput': 2148.19}
+
+[INFO|2025-03-21 10:42:43] logging.py:157 >> {'loss': 0.0351, 'learning_rate': 3.2374e-07, 'epoch': 2.84, 'throughput': 2145.47}
+
+[INFO|2025-03-21 10:44:18] logging.py:157 >> {'loss': 0.0324, 'learning_rate': 8.1067e-08, 'epoch': 2.91, 'throughput': 2146.04}
+
+[INFO|2025-03-21 10:45:51] logging.py:157 >> {'loss': 0.0357, 'learning_rate': 0.0000e+00, 'epoch': 2.99, 'throughput': 2146.55}
+
+[INFO|2025-03-21 10:45:51] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195
+
+[INFO|2025-03-21 10:45:51] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/config.json
+
+[INFO|2025-03-21 10:45:51] configuration_utils.py:771 >> Model config Qwen2VLConfig {
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-21 10:45:51] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195/tokenizer_config.json
+
+[INFO|2025-03-21 10:45:51] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195/special_tokens_map.json
+
+[INFO|2025-03-21 10:45:51] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195/preprocessor_config.json
+
+[INFO|2025-03-21 10:45:51] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195/tokenizer_config.json
+
+[INFO|2025-03-21 10:45:51] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195/special_tokens_map.json
+
+[INFO|2025-03-21 10:45:52] processing_utils.py:638 >> chat template saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/checkpoint-195/chat_template.json
+
+[INFO|2025-03-21 10:45:52] trainer.py:2657 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-03-21 10:45:52] image_processing_base.py:261 >> Image processor saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/preprocessor_config.json
+
+[INFO|2025-03-21 10:45:52] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/tokenizer_config.json
+
+[INFO|2025-03-21 10:45:52] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/special_tokens_map.json
+
+[INFO|2025-03-21 10:45:52] processing_utils.py:638 >> chat template saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/chat_template.json
+
+[INFO|2025-03-21 10:45:52] trainer.py:3942 >> Saving model checkpoint to saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora
+
+[INFO|2025-03-21 10:45:52] configuration_utils.py:699 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--Qwen--Qwen2-VL-7B-Instruct/snapshots/eed13092ef92e448dd6875b2a00151bd3f7db0ac/config.json
+
+[INFO|2025-03-21 10:45:52] configuration_utils.py:771 >> Model config Qwen2VLConfig {
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}
+
+
+[INFO|2025-03-21 10:45:52] tokenization_utils_base.py:2500 >> tokenizer config file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/tokenizer_config.json
+
+[INFO|2025-03-21 10:45:52] tokenization_utils_base.py:2509 >> Special tokens file saved in saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora/special_tokens_map.json
+
+[WARNING|2025-03-21 10:45:52] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-03-21 10:45:52] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-03-21 10:45:52] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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 +1,145 @@
+{
+  "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": 34114,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.9904761904761905,
+    "num_input_tokens_seen": 8039616,
+    "total_flos": 3.746411207808123e+17,
+    "train_loss": 0.05875852833955716,
+    "train_runtime": 3746.4527,
+    "train_samples_per_second": 0.841,
+    "train_steps_per_second": 0.052
+}

trainer_log.jsonl

@@ -0,0 +1,40 @@
+{"current_steps": 5, "total_steps": 195, "loss": 0.2783, "lr": 4.9918932703355256e-05, "epoch": 0.0761904761904762, "percentage": 2.56, "elapsed_time": "0:01:35", "remaining_time": "1:00:12", "throughput": 2222.37, "total_tokens": 211280}
+{"current_steps": 10, "total_steps": 195, "loss": 0.1989, "lr": 4.967625656594782e-05, "epoch": 0.1523809523809524, "percentage": 5.13, "elapsed_time": "0:03:11", "remaining_time": "0:58:53", "throughput": 2194.13, "total_tokens": 419136}
+{"current_steps": 15, "total_steps": 195, "loss": 0.1331, "lr": 4.92735454356513e-05, "epoch": 0.22857142857142856, "percentage": 7.69, "elapsed_time": "0:04:51", "remaining_time": "0:58:16", "throughput": 2167.74, "total_tokens": 631632}
+{"current_steps": 20, "total_steps": 195, "loss": 0.1029, "lr": 4.8713411048678635e-05, "epoch": 0.3047619047619048, "percentage": 10.26, "elapsed_time": "0:06:27", "remaining_time": "0:56:30", "throughput": 2159.97, "total_tokens": 836896}
+{"current_steps": 25, "total_steps": 195, "loss": 0.08, "lr": 4.799948609147061e-05, "epoch": 0.38095238095238093, "percentage": 12.82, "elapsed_time": "0:08:03", "remaining_time": "0:54:48", "throughput": 2155.84, "total_tokens": 1042416}
+{"current_steps": 30, "total_steps": 195, "loss": 0.0767, "lr": 4.713640064133025e-05, "epoch": 0.45714285714285713, "percentage": 15.38, "elapsed_time": "0:09:38", "remaining_time": "0:53:01", "throughput": 2151.49, "total_tokens": 1244384}
+{"current_steps": 35, "total_steps": 195, "loss": 0.0596, "lr": 4.6129752138594874e-05, "epoch": 0.5333333333333333, "percentage": 17.95, "elapsed_time": "0:11:10", "remaining_time": "0:51:06", "throughput": 2154.2, "total_tokens": 1445168}
+{"current_steps": 40, "total_steps": 195, "loss": 0.0619, "lr": 4.498606908508754e-05, "epoch": 0.6095238095238096, "percentage": 20.51, "elapsed_time": "0:12:47", "remaining_time": "0:49:34", "throughput": 2151.53, "total_tokens": 1651760}
+{"current_steps": 45, "total_steps": 195, "loss": 0.0585, "lr": 4.371276870427753e-05, "epoch": 0.6857142857142857, "percentage": 23.08, "elapsed_time": "0:14:18", "remaining_time": "0:47:41", "throughput": 2154.83, "total_tokens": 1849920}
+{"current_steps": 50, "total_steps": 195, "loss": 0.0642, "lr": 4.231810883773999e-05, "epoch": 0.7619047619047619, "percentage": 25.64, "elapsed_time": "0:15:55", "remaining_time": "0:46:11", "throughput": 2151.56, "total_tokens": 2056592}
+{"current_steps": 55, "total_steps": 195, "loss": 0.053, "lr": 4.0811134389884433e-05, "epoch": 0.8380952380952381, "percentage": 28.21, "elapsed_time": "0:17:32", "remaining_time": "0:44:39", "throughput": 2151.91, "total_tokens": 2265056}
+{"current_steps": 60, "total_steps": 195, "loss": 0.0566, "lr": 3.920161866827889e-05, "epoch": 0.9142857142857143, "percentage": 30.77, "elapsed_time": "0:19:08", "remaining_time": "0:43:04", "throughput": 2151.74, "total_tokens": 2471328}
+{"current_steps": 65, "total_steps": 195, "loss": 0.0496, "lr": 3.7500000000000003e-05, "epoch": 0.9904761904761905, "percentage": 33.33, "elapsed_time": "0:20:43", "remaining_time": "0:41:26", "throughput": 2152.63, "total_tokens": 2676640}
+{"current_steps": 70, "total_steps": 195, "loss": 0.0577, "lr": 3.5717314035076355e-05, "epoch": 1.0761904761904761, "percentage": 35.9, "elapsed_time": "0:22:26", "remaining_time": "0:40:05", "throughput": 2151.34, "total_tokens": 2897712}
+{"current_steps": 75, "total_steps": 195, "loss": 0.0442, "lr": 3.386512217606339e-05, "epoch": 1.1523809523809523, "percentage": 38.46, "elapsed_time": "0:23:53", "remaining_time": "0:38:12", "throughput": 2155.99, "total_tokens": 3089808}
+{"current_steps": 80, "total_steps": 195, "loss": 0.0469, "lr": 3.195543659791132e-05, "epoch": 1.2285714285714286, "percentage": 41.03, "elapsed_time": "0:25:31", "remaining_time": "0:36:41", "throughput": 2152.47, "total_tokens": 3296576}
+{"current_steps": 85, "total_steps": 195, "loss": 0.0417, "lr": 3.0000642344401113e-05, "epoch": 1.3047619047619048, "percentage": 43.59, "elapsed_time": "0:27:10", "remaining_time": "0:35:10", "throughput": 2151.23, "total_tokens": 3508416}
+{"current_steps": 90, "total_steps": 195, "loss": 0.0451, "lr": 2.8013417006383076e-05, "epoch": 1.380952380952381, "percentage": 46.15, "elapsed_time": "0:28:42", "remaining_time": "0:33:29", "throughput": 2151.68, "total_tokens": 3706512}
+{"current_steps": 95, "total_steps": 195, "loss": 0.0438, "lr": 2.600664850273538e-05, "epoch": 1.457142857142857, "percentage": 48.72, "elapsed_time": "0:30:19", "remaining_time": "0:31:55", "throughput": 2150.08, "total_tokens": 3913120}
+{"current_steps": 100, "total_steps": 195, "loss": 0.038, "lr": 2.399335149726463e-05, "epoch": 1.5333333333333332, "percentage": 51.28, "elapsed_time": "0:31:57", "remaining_time": "0:30:21", "throughput": 2149.01, "total_tokens": 4121248}
+{"current_steps": 105, "total_steps": 195, "loss": 0.038, "lr": 2.1986582993616926e-05, "epoch": 1.6095238095238096, "percentage": 53.85, "elapsed_time": "0:33:38", "remaining_time": "0:28:49", "throughput": 2144.53, "total_tokens": 4327824}
+{"current_steps": 110, "total_steps": 195, "loss": 0.0397, "lr": 1.9999357655598893e-05, "epoch": 1.6857142857142857, "percentage": 56.41, "elapsed_time": "0:35:17", "remaining_time": "0:27:16", "throughput": 2142.88, "total_tokens": 4537936}
+{"current_steps": 115, "total_steps": 195, "loss": 0.0404, "lr": 1.8044563402088684e-05, "epoch": 1.7619047619047619, "percentage": 58.97, "elapsed_time": "0:36:54", "remaining_time": "0:25:40", "throughput": 2142.72, "total_tokens": 4744432}
+{"current_steps": 120, "total_steps": 195, "loss": 0.0362, "lr": 1.613487782393661e-05, "epoch": 1.8380952380952382, "percentage": 61.54, "elapsed_time": "0:38:32", "remaining_time": "0:24:05", "throughput": 2142.84, "total_tokens": 4955296}
+{"current_steps": 125, "total_steps": 195, "loss": 0.0397, "lr": 1.4282685964923642e-05, "epoch": 1.9142857142857141, "percentage": 64.1, "elapsed_time": "0:40:02", "remaining_time": "0:22:25", "throughput": 2145.15, "total_tokens": 5154784}
+{"current_steps": 130, "total_steps": 195, "loss": 0.0343, "lr": 1.2500000000000006e-05, "epoch": 1.9904761904761905, "percentage": 66.67, "elapsed_time": "0:41:36", "remaining_time": "0:20:48", "throughput": 2146.04, "total_tokens": 5358160}
+{"current_steps": 135, "total_steps": 195, "loss": 0.0396, "lr": 1.0798381331721109e-05, "epoch": 2.0761904761904764, "percentage": 69.23, "elapsed_time": "0:43:19", "remaining_time": "0:19:15", "throughput": 2145.8, "total_tokens": 5577808}
+{"current_steps": 140, "total_steps": 195, "loss": 0.0394, "lr": 9.18886561011557e-06, "epoch": 2.1523809523809523, "percentage": 71.79, "elapsed_time": "0:44:49", "remaining_time": "0:17:36", "throughput": 2147.67, "total_tokens": 5775552}
+{"current_steps": 145, "total_steps": 195, "loss": 0.0311, "lr": 7.681891162260015e-06, "epoch": 2.2285714285714286, "percentage": 74.36, "elapsed_time": "0:46:29", "remaining_time": "0:16:01", "throughput": 2146.29, "total_tokens": 5986112}
+{"current_steps": 150, "total_steps": 195, "loss": 0.048, "lr": 6.28723129572247e-06, "epoch": 2.3047619047619046, "percentage": 76.92, "elapsed_time": "0:48:00", "remaining_time": "0:14:24", "throughput": 2147.33, "total_tokens": 6185568}
+{"current_steps": 155, "total_steps": 195, "loss": 0.0374, "lr": 5.013930914912476e-06, "epoch": 2.380952380952381, "percentage": 79.49, "elapsed_time": "0:49:34", "remaining_time": "0:12:47", "throughput": 2148.07, "total_tokens": 6389392}
+{"current_steps": 160, "total_steps": 195, "loss": 0.0334, "lr": 3.8702478614051355e-06, "epoch": 2.4571428571428573, "percentage": 82.05, "elapsed_time": "0:51:09", "remaining_time": "0:11:11", "throughput": 2148.53, "total_tokens": 6594256}
+{"current_steps": 165, "total_steps": 195, "loss": 0.0324, "lr": 2.8635993586697553e-06, "epoch": 2.533333333333333, "percentage": 84.62, "elapsed_time": "0:52:45", "remaining_time": "0:09:35", "throughput": 2148.97, "total_tokens": 6802240}
+{"current_steps": 170, "total_steps": 195, "loss": 0.0342, "lr": 2.0005139085293945e-06, "epoch": 2.6095238095238096, "percentage": 87.18, "elapsed_time": "0:54:19", "remaining_time": "0:07:59", "throughput": 2149.31, "total_tokens": 7004816}
+{"current_steps": 175, "total_steps": 195, "loss": 0.0384, "lr": 1.286588951321363e-06, "epoch": 2.685714285714286, "percentage": 89.74, "elapsed_time": "0:55:53", "remaining_time": "0:06:23", "throughput": 2149.34, "total_tokens": 7208608}
+{"current_steps": 180, "total_steps": 195, "loss": 0.0357, "lr": 7.264545643486997e-07, "epoch": 2.761904761904762, "percentage": 92.31, "elapsed_time": "0:57:33", "remaining_time": "0:04:47", "throughput": 2148.19, "total_tokens": 7418320}
+{"current_steps": 185, "total_steps": 195, "loss": 0.0351, "lr": 3.237434340521789e-07, "epoch": 2.8380952380952382, "percentage": 94.87, "elapsed_time": "0:59:17", "remaining_time": "0:03:12", "throughput": 2145.47, "total_tokens": 7633248}
+{"current_steps": 190, "total_steps": 195, "loss": 0.0324, "lr": 8.106729664475176e-08, "epoch": 2.914285714285714, "percentage": 97.44, "elapsed_time": "1:00:52", "remaining_time": "0:01:36", "throughput": 2146.04, "total_tokens": 7838576}
+{"current_steps": 195, "total_steps": 195, "loss": 0.0357, "lr": 0.0, "epoch": 2.9904761904761905, "percentage": 100.0, "elapsed_time": "1:02:25", "remaining_time": "0:00:00", "throughput": 2146.55, "total_tokens": 8039616}
+{"current_steps": 195, "total_steps": 195, "epoch": 2.9904761904761905, "percentage": 100.0, "elapsed_time": "1:02:26", "remaining_time": "0:00:00", "throughput": 2145.93, "total_tokens": 8039616}

trainer_state.json

@@ -0,0 +1,355 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9904761904761905,
+  "eval_steps": 500,
+  "global_step": 195,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 0.25375691056251526,
+      "learning_rate": 4.9918932703355256e-05,
+      "loss": 0.2783,
+      "num_input_tokens_seen": 211280,
+      "step": 5
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 0.1986791342496872,
+      "learning_rate": 4.967625656594782e-05,
+      "loss": 0.1989,
+      "num_input_tokens_seen": 419136,
+      "step": 10
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.1764397770166397,
+      "learning_rate": 4.92735454356513e-05,
+      "loss": 0.1331,
+      "num_input_tokens_seen": 631632,
+      "step": 15
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.14602281153202057,
+      "learning_rate": 4.8713411048678635e-05,
+      "loss": 0.1029,
+      "num_input_tokens_seen": 836896,
+      "step": 20
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.14543306827545166,
+      "learning_rate": 4.799948609147061e-05,
+      "loss": 0.08,
+      "num_input_tokens_seen": 1042416,
+      "step": 25
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.14905446767807007,
+      "learning_rate": 4.713640064133025e-05,
+      "loss": 0.0767,
+      "num_input_tokens_seen": 1244384,
+      "step": 30
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.12417428195476532,
+      "learning_rate": 4.6129752138594874e-05,
+      "loss": 0.0596,
+      "num_input_tokens_seen": 1445168,
+      "step": 35
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 0.1181894913315773,
+      "learning_rate": 4.498606908508754e-05,
+      "loss": 0.0619,
+      "num_input_tokens_seen": 1651760,
+      "step": 40
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.13109543919563293,
+      "learning_rate": 4.371276870427753e-05,
+      "loss": 0.0585,
+      "num_input_tokens_seen": 1849920,
+      "step": 45
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.1899598389863968,
+      "learning_rate": 4.231810883773999e-05,
+      "loss": 0.0642,
+      "num_input_tokens_seen": 2056592,
+      "step": 50
+    },
+    {
+      "epoch": 0.8380952380952381,
+      "grad_norm": 0.11073227226734161,
+      "learning_rate": 4.0811134389884433e-05,
+      "loss": 0.053,
+      "num_input_tokens_seen": 2265056,
+      "step": 55
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.11537300050258636,
+      "learning_rate": 3.920161866827889e-05,
+      "loss": 0.0566,
+      "num_input_tokens_seen": 2471328,
+      "step": 60
+    },
+    {
+      "epoch": 0.9904761904761905,
+      "grad_norm": 0.1397155374288559,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0496,
+      "num_input_tokens_seen": 2676640,
+      "step": 65
+    },
+    {
+      "epoch": 1.0761904761904761,
+      "grad_norm": 0.1408267617225647,
+      "learning_rate": 3.5717314035076355e-05,
+      "loss": 0.0577,
+      "num_input_tokens_seen": 2897712,
+      "step": 70
+    },
+    {
+      "epoch": 1.1523809523809523,
+      "grad_norm": 0.11563374847173691,
+      "learning_rate": 3.386512217606339e-05,
+      "loss": 0.0442,
+      "num_input_tokens_seen": 3089808,
+      "step": 75
+    },
+    {
+      "epoch": 1.2285714285714286,
+      "grad_norm": 0.1368333101272583,
+      "learning_rate": 3.195543659791132e-05,
+      "loss": 0.0469,
+      "num_input_tokens_seen": 3296576,
+      "step": 80
+    },
+    {
+      "epoch": 1.3047619047619048,
+      "grad_norm": 0.11226939409971237,
+      "learning_rate": 3.0000642344401113e-05,
+      "loss": 0.0417,
+      "num_input_tokens_seen": 3508416,
+      "step": 85
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.12701162695884705,
+      "learning_rate": 2.8013417006383076e-05,
+      "loss": 0.0451,
+      "num_input_tokens_seen": 3706512,
+      "step": 90
+    },
+    {
+      "epoch": 1.457142857142857,
+      "grad_norm": 0.11398270726203918,
+      "learning_rate": 2.600664850273538e-05,
+      "loss": 0.0438,
+      "num_input_tokens_seen": 3913120,
+      "step": 95
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.15226365625858307,
+      "learning_rate": 2.399335149726463e-05,
+      "loss": 0.038,
+      "num_input_tokens_seen": 4121248,
+      "step": 100
+    },
+    {
+      "epoch": 1.6095238095238096,
+      "grad_norm": 0.12406383454799652,
+      "learning_rate": 2.1986582993616926e-05,
+      "loss": 0.038,
+      "num_input_tokens_seen": 4327824,
+      "step": 105
+    },
+    {
+      "epoch": 1.6857142857142857,
+      "grad_norm": 0.11916245520114899,
+      "learning_rate": 1.9999357655598893e-05,
+      "loss": 0.0397,
+      "num_input_tokens_seen": 4537936,
+      "step": 110
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.14286760985851288,
+      "learning_rate": 1.8044563402088684e-05,
+      "loss": 0.0404,
+      "num_input_tokens_seen": 4744432,
+      "step": 115
+    },
+    {
+      "epoch": 1.8380952380952382,
+      "grad_norm": 0.09759990125894547,
+      "learning_rate": 1.613487782393661e-05,
+      "loss": 0.0362,
+      "num_input_tokens_seen": 4955296,
+      "step": 120
+    },
+    {
+      "epoch": 1.9142857142857141,
+      "grad_norm": 0.13581913709640503,
+      "learning_rate": 1.4282685964923642e-05,
+      "loss": 0.0397,
+      "num_input_tokens_seen": 5154784,
+      "step": 125
+    },
+    {
+      "epoch": 1.9904761904761905,
+      "grad_norm": 0.12309057265520096,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0343,
+      "num_input_tokens_seen": 5358160,
+      "step": 130
+    },
+    {
+      "epoch": 2.0761904761904764,
+      "grad_norm": 0.11022833734750748,
+      "learning_rate": 1.0798381331721109e-05,
+      "loss": 0.0396,
+      "num_input_tokens_seen": 5577808,
+      "step": 135
+    },
+    {
+      "epoch": 2.1523809523809523,
+      "grad_norm": 0.10238117724657059,
+      "learning_rate": 9.18886561011557e-06,
+      "loss": 0.0394,
+      "num_input_tokens_seen": 5775552,
+      "step": 140
+    },
+    {
+      "epoch": 2.2285714285714286,
+      "grad_norm": 0.09375017136335373,
+      "learning_rate": 7.681891162260015e-06,
+      "loss": 0.0311,
+      "num_input_tokens_seen": 5986112,
+      "step": 145
+    },
+    {
+      "epoch": 2.3047619047619046,
+      "grad_norm": 0.13229627907276154,
+      "learning_rate": 6.28723129572247e-06,
+      "loss": 0.048,
+      "num_input_tokens_seen": 6185568,
+      "step": 150
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.1364370435476303,
+      "learning_rate": 5.013930914912476e-06,
+      "loss": 0.0374,
+      "num_input_tokens_seen": 6389392,
+      "step": 155
+    },
+    {
+      "epoch": 2.4571428571428573,
+      "grad_norm": 0.11261958628892899,
+      "learning_rate": 3.8702478614051355e-06,
+      "loss": 0.0334,
+      "num_input_tokens_seen": 6594256,
+      "step": 160
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.09721696376800537,
+      "learning_rate": 2.8635993586697553e-06,
+      "loss": 0.0324,
+      "num_input_tokens_seen": 6802240,
+      "step": 165
+    },
+    {
+      "epoch": 2.6095238095238096,
+      "grad_norm": 0.11983498930931091,
+      "learning_rate": 2.0005139085293945e-06,
+      "loss": 0.0342,
+      "num_input_tokens_seen": 7004816,
+      "step": 170
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 0.13199082016944885,
+      "learning_rate": 1.286588951321363e-06,
+      "loss": 0.0384,
+      "num_input_tokens_seen": 7208608,
+      "step": 175
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.10022356361150742,
+      "learning_rate": 7.264545643486997e-07,
+      "loss": 0.0357,
+      "num_input_tokens_seen": 7418320,
+      "step": 180
+    },
+    {
+      "epoch": 2.8380952380952382,
+      "grad_norm": 0.11056291311979294,
+      "learning_rate": 3.237434340521789e-07,
+      "loss": 0.0351,
+      "num_input_tokens_seen": 7633248,
+      "step": 185
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 0.12205488979816437,
+      "learning_rate": 8.106729664475176e-08,
+      "loss": 0.0324,
+      "num_input_tokens_seen": 7838576,
+      "step": 190
+    },
+    {
+      "epoch": 2.9904761904761905,
+      "grad_norm": 0.10819905996322632,
+      "learning_rate": 0.0,
+      "loss": 0.0357,
+      "num_input_tokens_seen": 8039616,
+      "step": 195
+    },
+    {
+      "epoch": 2.9904761904761905,
+      "num_input_tokens_seen": 8039616,
+      "step": 195,
+      "total_flos": 3.746411207808123e+17,
+      "train_loss": 0.05875852833955716,
+      "train_runtime": 3746.4527,
+      "train_samples_per_second": 0.841,
+      "train_steps_per_second": 0.052
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 195,
+  "num_input_tokens_seen": 8039616,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.746411207808123e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228b1695b1c7eda19f24070b43c6f3492403b0468d8e1d5e3d62b239049e3e70
+size 5688

training_args.yaml

@@ -0,0 +1,33 @@
+bf16: true
+cutoff_len: 34114
+dataset: BsKIE3
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen2-VL-7B-Instruct
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2-VL-7B-Instruct/lora/BS_riche_lora
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+report_to: none
+save_steps: 100
+stage: sft
+template: qwen2_vl
+trust_remote_code: true
+warmup_steps: 0