Initial model upload

checkpoint-45/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /root/.cache/modelscope/hub/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-45/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/modelscope/hub/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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(model)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-45/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b24dad4ce65e32a16a510881666a4aa74fa48770db8d2b62a33b89c4d254c30
+size 80792096

checkpoint-45/additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

checkpoint-45/configuration.json

@@ -0,0 +1,14 @@
+{
+    "framework": "pytorch",
+    "task": "image-text-to-text",
+    "allow_remote": true,
+    "adapter_cfg": {
+        "model_id_or_path": "qwen/Qwen2-VL-7B-Instruct",
+        "model_revision": "master",
+        "sft_type": "lora",
+        "tuner_backend": "peft",
+        "template_type": "qwen2-vl",
+        "dtype": "bf16",
+        "system": "You are a helpful assistant."
+    }
+}

checkpoint-45/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.45.0.dev0"
+}

checkpoint-45/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44696fdb374fb59a8a79d721c49d62887579b41b57b0ec18cede3d69f284529a
+size 161810282

checkpoint-45/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef27693e8c6e3e442c7ede4fb192233f1699444a12fc9bcac9d2639636e2f5e
+size 14244

checkpoint-45/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e263c1ebbfad3b137dc95d038c7d450a9c91a9eea444a4a6b3bd99ae958ae3a
+size 1064

checkpoint-45/sft_args.json

@@ -0,0 +1,244 @@
+{
+  "model_type": "qwen2-vl-7b-instruct",
+  "model_id_or_path": "qwen/Qwen2-VL-7B-Instruct",
+  "model_revision": "master",
+  "full_determinism": false,
+  "sft_type": "lora",
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
+  "additional_trainable_parameters": [],
+  "tuner_backend": "peft",
+  "template_type": "qwen2-vl",
+  "output_dir": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714",
+  "add_output_dir_suffix": true,
+  "ddp_backend": null,
+  "ddp_find_unused_parameters": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
+  "seed": 42,
+  "resume_from_checkpoint": null,
+  "resume_only_model": false,
+  "ignore_data_skip": false,
+  "dtype": "bf16",
+  "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
+  "model_kwargs": null,
+  "loss_name": null,
+  "dataset": [
+    "/content/HebQwen.jsonl"
+  ],
+  "val_dataset": [],
+  "dataset_seed": 42,
+  "dataset_test_ratio": 0.01,
+  "use_loss_scale": false,
+  "loss_scale_config_path": "/content/swift/swift/llm/agent/default_loss_scale_config.json",
+  "system": "You are a helpful assistant.",
+  "tools_prompt": "react_en",
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "check_dataset_strategy": "none",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
+  "model_name": [
+    null,
+    null
+  ],
+  "model_author": [
+    null,
+    null
+  ],
+  "quant_method": null,
+  "quantization_bit": 0,
+  "hqq_axis": 0,
+  "hqq_dynamic_config_path": null,
+  "bnb_4bit_comp_dtype": "bf16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "rescale_image": -1,
+  "target_modules": "^(model)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias_trainable": "none",
+  "lora_dtype": null,
+  "lora_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "init_lora_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "rope_scaling": null,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "ia3_feedforward_modules": [],
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "neftune_noise_alpha": null,
+  "neftune_backend": "transformers",
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "use_liger": false,
+  "gradient_checkpointing": true,
+  "deepspeed": null,
+  "batch_size": 1,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 1,
+  "max_steps": -1,
+  "optim": "adamw_torch",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "learning_rate": 0.0001,
+  "weight_decay": 0.1,
+  "gradient_accumulation_steps": 16,
+  "max_grad_norm": 1,
+  "predict_with_generate": false,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "eval_steps": 50,
+  "save_steps": 50,
+  "save_only_model": false,
+  "save_total_limit": 2,
+  "logging_steps": 5,
+  "acc_steps": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_drop_last": false,
+  "push_to_hub": false,
+  "hub_model_id": null,
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_strategy": "every_save",
+  "test_oom_error": false,
+  "disable_tqdm": false,
+  "lazy_tokenize": true,
+  "preprocess_num_proc": 1,
+  "use_flash_attn": null,
+  "ignore_args_error": false,
+  "check_model_is_latest": true,
+  "logging_dir": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/runs",
+  "report_to": [
+    "tensorboard"
+  ],
+  "acc_strategy": "token",
+  "save_on_each_node": false,
+  "evaluation_strategy": "steps",
+  "save_strategy": "steps",
+  "save_safetensors": true,
+  "gpu_memory_fraction": null,
+  "include_num_input_tokens_seen": false,
+  "local_repo_path": null,
+  "custom_register_path": null,
+  "custom_dataset_info": null,
+  "device_map_config": null,
+  "device_max_memory": [],
+  "max_new_tokens": 2048,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "fsdp": "",
+  "fsdp_config": null,
+  "sequence_parallel_size": 1,
+  "model_layer_cls_name": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "per_device_train_batch_size": null,
+  "per_device_eval_batch_size": null,
+  "eval_strategy": null,
+  "self_cognition_sample": 0,
+  "train_dataset_mix_ratio": 0.0,
+  "train_dataset_mix_ds": [
+    "ms-bench"
+  ],
+  "train_dataset_sample": -1,
+  "val_dataset_sample": null,
+  "safe_serialization": null,
+  "only_save_model": null,
+  "neftune_alpha": null,
+  "deepspeed_config_path": null,
+  "model_cache_dir": null,
+  "lora_dropout_p": null,
+  "lora_target_modules": [],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
+  "custom_train_dataset_path": [],
+  "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
+  "use_self_cognition": false,
+  "is_multimodal": true,
+  "is_vision": true,
+  "lora_use_embedding": false,
+  "lora_use_all": false,
+  "lora_m2s_use_embedding": false,
+  "lora_m2s_use_ln": false,
+  "torch_dtype": "torch.bfloat16",
+  "fp16": false,
+  "bf16": true,
+  "rank": -1,
+  "local_rank": -1,
+  "world_size": 1,
+  "local_world_size": 1,
+  "bnb_4bit_compute_dtype": "torch.bfloat16",
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "train_sampler_random": true,
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/content/output/qwen2-vl-7b-instruct/v2-20240909-100714', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/content/output/qwen2-vl-7b-instruct/v2-20240909-100714', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"bos_token_id\": 151643,\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.01,\n  \"top_k\": 1,\n  \"top_p\": 0.001\n}\n, train_sampler_random=True, acc_strategy='token', loss_name=None, additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
+}

checkpoint-45/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": 0.50872844,
+  "best_model_checkpoint": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/checkpoint-45",
+  "epoch": 0.993103448275862,
+  "eval_steps": 50,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "acc": 0.61398816,
+      "epoch": 0.022068965517241378,
+      "grad_norm": 7.717197895050049,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.87438893,
+      "memory(GiB)": 20.29,
+      "step": 1,
+      "train_speed(iter/s)": 0.066629
+    },
+    {
+      "acc": 0.62096363,
+      "epoch": 0.1103448275862069,
+      "grad_norm": 8.616560935974121,
+      "learning_rate": 9.944154131125642e-05,
+      "loss": 2.60930538,
+      "memory(GiB)": 22.58,
+      "step": 5,
+      "train_speed(iter/s)": 0.075138
+    },
+    {
+      "acc": 0.80472717,
+      "epoch": 0.2206896551724138,
+      "grad_norm": 3.399202346801758,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.68508205,
+      "memory(GiB)": 23.35,
+      "step": 10,
+      "train_speed(iter/s)": 0.076348
+    },
+    {
+      "acc": 0.81436024,
+      "epoch": 0.3310344827586207,
+      "grad_norm": 5.226686477661133,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 0.69332366,
+      "memory(GiB)": 24.12,
+      "step": 15,
+      "train_speed(iter/s)": 0.076737
+    },
+    {
+      "acc": 0.86372032,
+      "epoch": 0.4413793103448276,
+      "grad_norm": 3.478239059448242,
+      "learning_rate": 6.473775872054521e-05,
+      "loss": 0.57136168,
+      "memory(GiB)": 24.12,
+      "step": 20,
+      "train_speed(iter/s)": 0.076946
+    },
+    {
+      "acc": 0.85740089,
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.1063661575317383,
+      "learning_rate": 4.626349532067879e-05,
+      "loss": 0.51958747,
+      "memory(GiB)": 24.91,
+      "step": 25,
+      "train_speed(iter/s)": 0.077061
+    },
+    {
+      "acc": 0.85881948,
+      "epoch": 0.6620689655172414,
+      "grad_norm": 2.6917998790740967,
+      "learning_rate": 2.8305813044122097e-05,
+      "loss": 0.51737795,
+      "memory(GiB)": 24.91,
+      "step": 30,
+      "train_speed(iter/s)": 0.077142
+    },
+    {
+      "acc": 0.84086313,
+      "epoch": 0.7724137931034483,
+      "grad_norm": 7.916348934173584,
+      "learning_rate": 1.3347406408508695e-05,
+      "loss": 0.72901492,
+      "memory(GiB)": 24.91,
+      "step": 35,
+      "train_speed(iter/s)": 0.077198
+    },
+    {
+      "acc": 0.86680059,
+      "epoch": 0.8827586206896552,
+      "grad_norm": 2.948944568634033,
+      "learning_rate": 3.4563125677897932e-06,
+      "loss": 0.43249173,
+      "memory(GiB)": 24.91,
+      "step": 40,
+      "train_speed(iter/s)": 0.077243
+    },
+    {
+      "acc": 0.91657734,
+      "epoch": 0.993103448275862,
+      "grad_norm": 2.6367099285125732,
+      "learning_rate": 0.0,
+      "loss": 0.34231672,
+      "memory(GiB)": 24.91,
+      "step": 45,
+      "train_speed(iter/s)": 0.077273
+    },
+    {
+      "epoch": 0.993103448275862,
+      "eval_acc": 0.8181818181818182,
+      "eval_loss": 0.5087284445762634,
+      "eval_runtime": 3.4104,
+      "eval_samples_per_second": 2.053,
+      "eval_steps_per_second": 2.053,
+      "step": 45
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.488065503664026e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-45/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2508c7a374e9d5d3ede8c60e5ae128e7478c0510497c08865f6c3e3591a412
+size 7288

logging.jsonl

@@ -0,0 +1,13 @@
+{"loss": 2.87438893, "acc": 0.61398816, "grad_norm": 7.7171979, "learning_rate": 3.333e-05, "memory(GiB)": 20.29, "train_speed(iter/s)": 0.066629, "epoch": 0.02206897, "global_step/max_steps": "1/45", "percentage": "2.22%", "elapsed_time": "14s", "remaining_time": "10m 38s"}
+{"loss": 2.60930538, "acc": 0.62096363, "grad_norm": 8.61656094, "learning_rate": 9.944e-05, "memory(GiB)": 22.58, "train_speed(iter/s)": 0.075138, "epoch": 0.11034483, "global_step/max_steps": "5/45", "percentage": "11.11%", "elapsed_time": "1m 6s", "remaining_time": "8m 48s"}
+{"loss": 0.68508205, "acc": 0.80472717, "grad_norm": 3.39920235, "learning_rate": 9.33e-05, "memory(GiB)": 23.35, "train_speed(iter/s)": 0.076348, "epoch": 0.22068966, "global_step/max_steps": "10/45", "percentage": "22.22%", "elapsed_time": "2m 10s", "remaining_time": "7m 36s"}
+{"loss": 0.69332366, "acc": 0.81436024, "grad_norm": 5.22668648, "learning_rate": 8.117e-05, "memory(GiB)": 24.12, "train_speed(iter/s)": 0.076737, "epoch": 0.33103448, "global_step/max_steps": "15/45", "percentage": "33.33%", "elapsed_time": "3m 14s", "remaining_time": "6m 29s"}
+{"loss": 0.57136168, "acc": 0.86372032, "grad_norm": 3.47823906, "learning_rate": 6.474e-05, "memory(GiB)": 24.12, "train_speed(iter/s)": 0.076946, "epoch": 0.44137931, "global_step/max_steps": "20/45", "percentage": "44.44%", "elapsed_time": "4m 19s", "remaining_time": "5m 24s"}
+{"loss": 0.51958747, "acc": 0.85740089, "grad_norm": 2.10636616, "learning_rate": 4.626e-05, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077061, "epoch": 0.55172414, "global_step/max_steps": "25/45", "percentage": "55.56%", "elapsed_time": "5m 23s", "remaining_time": "4m 19s"}
+{"loss": 0.51737795, "acc": 0.85881948, "grad_norm": 2.69179988, "learning_rate": 2.831e-05, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077142, "epoch": 0.66206897, "global_step/max_steps": "30/45", "percentage": "66.67%", "elapsed_time": "6m 28s", "remaining_time": "3m 14s"}
+{"loss": 0.72901492, "acc": 0.84086313, "grad_norm": 7.91634893, "learning_rate": 1.335e-05, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077198, "epoch": 0.77241379, "global_step/max_steps": "35/45", "percentage": "77.78%", "elapsed_time": "7m 32s", "remaining_time": "2m 9s"}
+{"loss": 0.43249173, "acc": 0.86680059, "grad_norm": 2.94894457, "learning_rate": 3.46e-06, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077243, "epoch": 0.88275862, "global_step/max_steps": "40/45", "percentage": "88.89%", "elapsed_time": "8m 37s", "remaining_time": "1m 4s"}
+{"loss": 0.34231672, "acc": 0.91657734, "grad_norm": 2.63670993, "learning_rate": 0.0, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077273, "epoch": 0.99310345, "global_step/max_steps": "45/45", "percentage": "100.00%", "elapsed_time": "9m 41s", "remaining_time": "0s"}
+{"eval_loss": 0.50872844, "eval_acc": 0.81818182, "eval_runtime": 3.4104, "eval_samples_per_second": 2.053, "eval_steps_per_second": 2.053, "epoch": 0.99310345, "global_step/max_steps": "45/45", "percentage": "100.00%", "elapsed_time": "9m 45s", "remaining_time": "0s"}
+{"train_runtime": 585.8499, "train_samples_per_second": 1.238, "train_steps_per_second": 0.077, "total_flos": 4.488065503664026e+16, "train_loss": 0.79476425, "epoch": 0.99310345, "global_step/max_steps": "45/45", "percentage": "100.00%", "elapsed_time": "9m 45s", "remaining_time": "0s"}
+{"memory": {"cuda": "24.91GiB"}, "last_model_checkpoint": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/checkpoint-45", "best_model_checkpoint": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/checkpoint-45", "best_metric": 0.50872844, "global_step": 45, "log_history": [{"loss": 2.87438893, "acc": 0.61398816, "grad_norm": 7.717197895050049, "learning_rate": 3.3333333333333335e-05, "memory(GiB)": 20.29, "train_speed(iter/s)": 0.066629, "epoch": 0.022068965517241378, "step": 1}, {"loss": 2.60930538, "acc": 0.62096363, "grad_norm": 8.616560935974121, "learning_rate": 9.944154131125642e-05, "memory(GiB)": 22.58, "train_speed(iter/s)": 0.075138, "epoch": 0.1103448275862069, "step": 5}, {"loss": 0.68508205, "acc": 0.80472717, "grad_norm": 3.399202346801758, "learning_rate": 9.330127018922194e-05, "memory(GiB)": 23.35, "train_speed(iter/s)": 0.076348, "epoch": 0.2206896551724138, "step": 10}, {"loss": 0.69332366, "acc": 0.81436024, "grad_norm": 5.226686477661133, "learning_rate": 8.117449009293668e-05, "memory(GiB)": 24.12, "train_speed(iter/s)": 0.076737, "epoch": 0.3310344827586207, "step": 15}, {"loss": 0.57136168, "acc": 0.86372032, "grad_norm": 3.478239059448242, "learning_rate": 6.473775872054521e-05, "memory(GiB)": 24.12, "train_speed(iter/s)": 0.076946, "epoch": 0.4413793103448276, "step": 20}, {"loss": 0.51958747, "acc": 0.85740089, "grad_norm": 2.1063661575317383, "learning_rate": 4.626349532067879e-05, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077061, "epoch": 0.5517241379310345, "step": 25}, {"loss": 0.51737795, "acc": 0.85881948, "grad_norm": 2.6917998790740967, "learning_rate": 2.8305813044122097e-05, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077142, "epoch": 0.6620689655172414, "step": 30}, {"loss": 0.72901492, "acc": 0.84086313, "grad_norm": 7.916348934173584, "learning_rate": 1.3347406408508695e-05, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077198, "epoch": 0.7724137931034483, "step": 35}, {"loss": 0.43249173, "acc": 0.86680059, "grad_norm": 2.948944568634033, "learning_rate": 3.4563125677897932e-06, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077243, "epoch": 0.8827586206896552, "step": 40}, {"loss": 0.34231672, "acc": 0.91657734, "grad_norm": 2.6367099285125732, "learning_rate": 0.0, "memory(GiB)": 24.91, "train_speed(iter/s)": 0.077273, "epoch": 0.993103448275862, "step": 45}, {"eval_loss": 0.5087284445762634, "eval_acc": 0.8181818181818182, "eval_runtime": 3.4104, "eval_samples_per_second": 2.053, "eval_steps_per_second": 2.053, "epoch": 0.993103448275862, "step": 45}, {"train_runtime": 585.8499, "train_samples_per_second": 1.238, "train_steps_per_second": 0.077, "total_flos": 4.488065503664026e+16, "train_loss": 0.7947642538282607, "epoch": 0.993103448275862, "step": 45}], "model_info": "PeftModelForCausalLM: 8311.5607M Params (20.1851M Trainable [0.2429%]), 0.0019M Buffers.", "dataset_info": null, "train_time": {"train_runtime": 585.8499, "n_train_samples": 725, "train_samples_per_second": 1.2375183472763245}}

runs/events.out.tfevents.1725876447.8e952411ac7f.14553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e57eafa0306c03db3b7cc3ba4bf4ff599a994f44cb3a38480e8f860ce128a7
+size 12057

sft_args.json

@@ -0,0 +1,244 @@
+{
+  "model_type": "qwen2-vl-7b-instruct",
+  "model_id_or_path": "qwen/Qwen2-VL-7B-Instruct",
+  "model_revision": "master",
+  "full_determinism": false,
+  "sft_type": "lora",
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
+  "additional_trainable_parameters": [],
+  "tuner_backend": "peft",
+  "template_type": "qwen2-vl",
+  "output_dir": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714",
+  "add_output_dir_suffix": true,
+  "ddp_backend": null,
+  "ddp_find_unused_parameters": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
+  "seed": 42,
+  "resume_from_checkpoint": null,
+  "resume_only_model": false,
+  "ignore_data_skip": false,
+  "dtype": "bf16",
+  "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
+  "model_kwargs": null,
+  "loss_name": null,
+  "dataset": [
+    "/content/HebQwen.jsonl"
+  ],
+  "val_dataset": [],
+  "dataset_seed": 42,
+  "dataset_test_ratio": 0.01,
+  "use_loss_scale": false,
+  "loss_scale_config_path": "/content/swift/swift/llm/agent/default_loss_scale_config.json",
+  "system": "You are a helpful assistant.",
+  "tools_prompt": "react_en",
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "check_dataset_strategy": "none",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
+  "model_name": [
+    null,
+    null
+  ],
+  "model_author": [
+    null,
+    null
+  ],
+  "quant_method": null,
+  "quantization_bit": 0,
+  "hqq_axis": 0,
+  "hqq_dynamic_config_path": null,
+  "bnb_4bit_comp_dtype": "bf16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "rescale_image": -1,
+  "target_modules": "^(model)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias_trainable": "none",
+  "lora_dtype": null,
+  "lora_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "init_lora_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "rope_scaling": null,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "ia3_feedforward_modules": [],
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "neftune_noise_alpha": null,
+  "neftune_backend": "transformers",
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "use_liger": false,
+  "gradient_checkpointing": true,
+  "deepspeed": null,
+  "batch_size": 1,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 1,
+  "max_steps": -1,
+  "optim": "adamw_torch",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "learning_rate": 0.0001,
+  "weight_decay": 0.1,
+  "gradient_accumulation_steps": 16,
+  "max_grad_norm": 1,
+  "predict_with_generate": false,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "eval_steps": 50,
+  "save_steps": 50,
+  "save_only_model": false,
+  "save_total_limit": 2,
+  "logging_steps": 5,
+  "acc_steps": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_drop_last": false,
+  "push_to_hub": false,
+  "hub_model_id": null,
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_strategy": "every_save",
+  "test_oom_error": false,
+  "disable_tqdm": false,
+  "lazy_tokenize": true,
+  "preprocess_num_proc": 1,
+  "use_flash_attn": null,
+  "ignore_args_error": false,
+  "check_model_is_latest": true,
+  "logging_dir": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/runs",
+  "report_to": [
+    "tensorboard"
+  ],
+  "acc_strategy": "token",
+  "save_on_each_node": false,
+  "evaluation_strategy": "steps",
+  "save_strategy": "steps",
+  "save_safetensors": true,
+  "gpu_memory_fraction": null,
+  "include_num_input_tokens_seen": false,
+  "local_repo_path": null,
+  "custom_register_path": null,
+  "custom_dataset_info": null,
+  "device_map_config": null,
+  "device_max_memory": [],
+  "max_new_tokens": 2048,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "fsdp": "",
+  "fsdp_config": null,
+  "sequence_parallel_size": 1,
+  "model_layer_cls_name": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "per_device_train_batch_size": null,
+  "per_device_eval_batch_size": null,
+  "eval_strategy": null,
+  "self_cognition_sample": 0,
+  "train_dataset_mix_ratio": 0.0,
+  "train_dataset_mix_ds": [
+    "ms-bench"
+  ],
+  "train_dataset_sample": -1,
+  "val_dataset_sample": null,
+  "safe_serialization": null,
+  "only_save_model": null,
+  "neftune_alpha": null,
+  "deepspeed_config_path": null,
+  "model_cache_dir": null,
+  "lora_dropout_p": null,
+  "lora_target_modules": [],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
+  "custom_train_dataset_path": [],
+  "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
+  "use_self_cognition": false,
+  "is_multimodal": true,
+  "is_vision": true,
+  "lora_use_embedding": false,
+  "lora_use_all": false,
+  "lora_m2s_use_embedding": false,
+  "lora_m2s_use_ln": false,
+  "torch_dtype": "torch.bfloat16",
+  "fp16": false,
+  "bf16": true,
+  "rank": -1,
+  "local_rank": -1,
+  "world_size": 1,
+  "local_world_size": 1,
+  "bnb_4bit_compute_dtype": "torch.bfloat16",
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "train_sampler_random": true,
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/content/output/qwen2-vl-7b-instruct/v2-20240909-100714', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=None, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/content/output/qwen2-vl-7b-instruct/v2-20240909-100714', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"bos_token_id\": 151643,\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.01,\n  \"top_k\": 1,\n  \"top_p\": 0.001\n}\n, train_sampler_random=True, acc_strategy='token', loss_name=None, additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
+}

training_args.json

@@ -0,0 +1,153 @@
+{
+  "output_dir": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 1,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 16,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 0.0001,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1,
+  "num_train_epochs": 1,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.05,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714/runs",
+  "logging_strategy": "steps",
+  "logging_first_step": true,
+  "logging_steps": 5,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 50,
+  "save_total_limit": 2,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": 50,
+  "dataloader_num_workers": 1,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "/content/output/qwen2-vl-7b-instruct/v2-20240909-100714",
+  "disable_tqdm": false,
+  "remove_unused_columns": false,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "tensorboard"
+  ],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_always_push": false,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "include_inputs_for_metrics": false,
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "evaluation_strategy": null,
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": null,
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "dispatch_batches": null,
+  "split_batches": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "eval_use_gather_object": false,
+  "sortish_sampler": true,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": "GenerationConfig {\n  \"bos_token_id\": 151643,\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.01,\n  \"top_k\": 1,\n  \"top_p\": 0.001\n}\n",
+  "train_sampler_random": true,
+  "acc_strategy": "token",
+  "loss_name": null,
+  "additional_saved_files": [],
+  "metric_warmup_step": 0,
+  "train_dataset_sample": -1,
+  "distributed_state": "Distributed environment: NO\nNum processes: 1\nProcess index: 0\nLocal process index: 0\nDevice: cuda\n",
+  "_n_gpu": 1,
+  "__cached__setup_devices": "device(type='cuda', index=0)",
+  "deepspeed_plugin": null
+}