Upload 13 files

.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1733296685

README.md

@@ -0,0 +1,202 @@
+---
+base_model: OpenGVLab/InternVL2-8B
+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

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "OpenGVLab/InternVL2-8B",
+  "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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(language_model|mlp1)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "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 sha256:7d39598d1bb26f37137fdf1a6f6662dc6086aee910b68b5a496b7a08c3791bfb
+size 304135344

additional_config.json

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

configuration.json

@@ -0,0 +1,13 @@
+{
+    "framework": "Pytorch",
+    "task": "visual-question-answering",
+    "adapter_cfg": {
+        "model_id_or_path": "OpenGVLab/InternVL2-8B",
+        "model_revision": "master",
+        "sft_type": "lora",
+        "tuner_backend": "peft",
+        "template_type": "internvl2",
+        "dtype": "bf16",
+        "system": "你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。"
+    }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "do_sample": true,
+  "eos_token_id": 92542,
+  "max_new_tokens": 2048,
+  "pad_token_id": 2,
+  "temperature": 0.3,
+  "top_k": 20,
+  "top_p": 0.7,
+  "transformers_version": "4.42.4"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977eafe730cc774275d4bede3ea42829e42a41c29d493f5c2872316523e38593
+size 604247218

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5300550d983dfe14e9250d237ab24b102afbe30cfa064b715cbf67139cd43ee7
+size 14168

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ccfb671b3bcf0ec000da201187d640680707b6126e070560a47081cd755f42
+size 1056

sft_args.json

@@ -0,0 +1,231 @@
+{
+  "model_type": "internvl2-8b",
+  "model_id_or_path": "OpenGVLab/InternVL2-8B",
+  "model_revision": "master",
+  "full_determinism": false,
+  "sft_type": "lora",
+  "freeze_parameters": 0.0,
+  "additional_trainable_parameters": [],
+  "tuner_backend": "peft",
+  "template_type": "internvl2",
+  "output_dir": "/public1/home/stu52275901020/swift/model_output/高神经质/internvl2-8b/v36-20241204-000354",
+  "add_output_dir_suffix": true,
+  "ddp_backend": null,
+  "ddp_find_unused_parameters": null,
+  "ddp_broadcast_buffers": null,
+  "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,
+  "dataset": [
+    "/public1/home/stu52275901020/swift/dataset/updata_data/微调指令数据集数据/json/高神经质_output.json"
+  ],
+  "val_dataset": [],
+  "dataset_seed": 42,
+  "dataset_test_ratio": 0.01,
+  "use_loss_scale": false,
+  "loss_scale_config_path": "/public1/home/stu52275901020/swift/swift/llm/agent/default_loss_scale_config.json",
+  "system": "你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。",
+  "tools_prompt": "react_en",
+  "max_length": 4096,
+  "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": "^(language_model|mlp1)(?!.*(lm_head|output|emb|wte|shared)).*",
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "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,
+  "gradient_checkpointing": true,
+  "deepspeed": null,
+  "batch_size": 1,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 3,
+  "max_steps": -1,
+  "optim": "adamw_torch",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "learning_rate": 0.0001,
+  "weight_decay": 0.01,
+  "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,
+  "push_hub_strategy": "push_best",
+  "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": "/public1/home/stu52275901020/swift/model_output/高神经质/internvl2-8b/v36-20241204-000354/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_path": null,
+  "device_max_memory": [],
+  "max_new_tokens": 2048,
+  "do_sample": true,
+  "temperature": 0.3,
+  "top_k": 20,
+  "top_p": 0.7,
+  "repetition_penalty": 1.0,
+  "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": [],
+  "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='/public1/home/stu52275901020/swift/model_output/高神经质/internvl2-8b/v36-20241204-000354', 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, learning_rate=0.0001, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=3, 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='/public1/home/stu52275901020/swift/model_output/高神经质/internvl2-8b/v36-20241204-000354/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='/public1/home/stu52275901020/swift/model_output/高神经质/internvl2-8b/v36-20241204-000354', 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, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"do_sample\": true,\n  \"eos_token_id\": 92542,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 2,\n  \"temperature\": 0.3,\n  \"top_k\": 20,\n  \"top_p\": 0.7\n}\n, train_sampler_random=True, push_hub_strategy='push_best', acc_strategy='token', additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
+}

trainer_state.json

@@ -0,0 +1,370 @@
+{
+  "best_metric": 1.84548545,
+  "best_model_checkpoint": "/public1/home/stu52275901020/swift/model_output/\u9ad8\u795e\u7ecf\u8d28/internvl2-8b/v36-20241204-000354/checkpoint-150",
+  "epoch": 1.702127659574468,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "acc": 0.4818837,
+      "epoch": 0.011347517730496455,
+      "grad_norm": 1.6654787063598633,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 2.21617293,
+      "memory(GiB)": 21.82,
+      "step": 1,
+      "train_speed(iter/s)": 0.047704
+    },
+    {
+      "acc": 0.50631422,
+      "epoch": 0.05673758865248227,
+      "grad_norm": 1.5600533485412598,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 2.20940375,
+      "memory(GiB)": 23.14,
+      "step": 5,
+      "train_speed(iter/s)": 0.099488
+    },
+    {
+      "acc": 0.51391821,
+      "epoch": 0.11347517730496454,
+      "grad_norm": 1.7131439447402954,
+      "learning_rate": 7.142857142857143e-05,
+      "loss": 2.04298916,
+      "memory(GiB)": 23.14,
+      "step": 10,
+      "train_speed(iter/s)": 0.114765
+    },
+    {
+      "acc": 0.55212674,
+      "epoch": 0.1702127659574468,
+      "grad_norm": 1.686623215675354,
+      "learning_rate": 9.999605221019081e-05,
+      "loss": 1.88184052,
+      "memory(GiB)": 24.5,
+      "step": 15,
+      "train_speed(iter/s)": 0.12107
+    },
+    {
+      "acc": 0.53304815,
+      "epoch": 0.22695035460992907,
+      "grad_norm": 1.0942801237106323,
+      "learning_rate": 9.98579450130307e-05,
+      "loss": 1.94336758,
+      "memory(GiB)": 24.5,
+      "step": 20,
+      "train_speed(iter/s)": 0.124439
+    },
+    {
+      "acc": 0.56079154,
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.9606024622917175,
+      "learning_rate": 9.952307128483256e-05,
+      "loss": 1.77457695,
+      "memory(GiB)": 24.5,
+      "step": 25,
+      "train_speed(iter/s)": 0.126437
+    },
+    {
+      "acc": 0.55825844,
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.922258198261261,
+      "learning_rate": 9.899275261921234e-05,
+      "loss": 1.84706001,
+      "memory(GiB)": 24.5,
+      "step": 30,
+      "train_speed(iter/s)": 0.127904
+    },
+    {
+      "acc": 0.56207647,
+      "epoch": 0.3971631205673759,
+      "grad_norm": 1.0378409624099731,
+      "learning_rate": 9.82690819416637e-05,
+      "loss": 1.753508,
+      "memory(GiB)": 24.5,
+      "step": 35,
+      "train_speed(iter/s)": 0.128886
+    },
+    {
+      "acc": 0.57356367,
+      "epoch": 0.45390070921985815,
+      "grad_norm": 1.1508853435516357,
+      "learning_rate": 9.735491524973722e-05,
+      "loss": 1.75303555,
+      "memory(GiB)": 24.5,
+      "step": 40,
+      "train_speed(iter/s)": 0.129863
+    },
+    {
+      "acc": 0.55143838,
+      "epoch": 0.5106382978723404,
+      "grad_norm": 1.2086931467056274,
+      "learning_rate": 9.62538603417229e-05,
+      "loss": 1.85968819,
+      "memory(GiB)": 25.91,
+      "step": 45,
+      "train_speed(iter/s)": 0.130489
+    },
+    {
+      "acc": 0.55636163,
+      "epoch": 0.5673758865248227,
+      "grad_norm": 1.0430564880371094,
+      "learning_rate": 9.497026257831855e-05,
+      "loss": 1.7241251,
+      "memory(GiB)": 25.91,
+      "step": 50,
+      "train_speed(iter/s)": 0.131006
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "eval_acc": 0.5656192236598891,
+      "eval_loss": 1.916869044303894,
+      "eval_runtime": 2.4464,
+      "eval_samples_per_second": 5.723,
+      "eval_steps_per_second": 5.723,
+      "step": 50
+    },
+    {
+      "acc": 0.54153261,
+      "epoch": 0.624113475177305,
+      "grad_norm": 1.2167576551437378,
+      "learning_rate": 9.35091877334763e-05,
+      "loss": 1.82617283,
+      "memory(GiB)": 26.3,
+      "step": 55,
+      "train_speed(iter/s)": 0.129776
+    },
+    {
+      "acc": 0.56068554,
+      "epoch": 0.6808510638297872,
+      "grad_norm": 1.3103394508361816,
+      "learning_rate": 9.18764020021071e-05,
+      "loss": 1.67511196,
+      "memory(GiB)": 26.3,
+      "step": 60,
+      "train_speed(iter/s)": 0.130279
+    },
+    {
+      "acc": 0.58310304,
+      "epoch": 0.7375886524822695,
+      "grad_norm": 1.0143637657165527,
+      "learning_rate": 9.007834924354383e-05,
+      "loss": 1.67270927,
+      "memory(GiB)": 26.3,
+      "step": 65,
+      "train_speed(iter/s)": 0.130674
+    },
+    {
+      "acc": 0.57467747,
+      "epoch": 0.7943262411347518,
+      "grad_norm": 1.3850369453430176,
+      "learning_rate": 8.81221255505724e-05,
+      "loss": 1.70278339,
+      "memory(GiB)": 26.3,
+      "step": 70,
+      "train_speed(iter/s)": 0.131012
+    },
+    {
+      "acc": 0.5916081,
+      "epoch": 0.851063829787234,
+      "grad_norm": 1.0732088088989258,
+      "learning_rate": 8.601545124439535e-05,
+      "loss": 1.63483982,
+      "memory(GiB)": 26.3,
+      "step": 75,
+      "train_speed(iter/s)": 0.131314
+    },
+    {
+      "acc": 0.56617246,
+      "epoch": 0.9078014184397163,
+      "grad_norm": 1.084026575088501,
+      "learning_rate": 8.376664040605122e-05,
+      "loss": 1.73948345,
+      "memory(GiB)": 26.3,
+      "step": 80,
+      "train_speed(iter/s)": 0.131575
+    },
+    {
+      "acc": 0.54482946,
+      "epoch": 0.9645390070921985,
+      "grad_norm": 1.0596380233764648,
+      "learning_rate": 8.138456806453503e-05,
+      "loss": 1.84302387,
+      "memory(GiB)": 26.3,
+      "step": 85,
+      "train_speed(iter/s)": 0.131746
+    },
+    {
+      "acc": 0.60235672,
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.9688817858695984,
+      "learning_rate": 7.887863517111338e-05,
+      "loss": 1.53876371,
+      "memory(GiB)": 26.3,
+      "step": 90,
+      "train_speed(iter/s)": 0.131937
+    },
+    {
+      "acc": 0.61323328,
+      "epoch": 1.0780141843971631,
+      "grad_norm": 1.1411057710647583,
+      "learning_rate": 7.62587314980648e-05,
+      "loss": 1.45239391,
+      "memory(GiB)": 26.3,
+      "step": 95,
+      "train_speed(iter/s)": 0.132127
+    },
+    {
+      "acc": 0.59773045,
+      "epoch": 1.1347517730496455,
+      "grad_norm": 1.1101690530776978,
+      "learning_rate": 7.353519660826665e-05,
+      "loss": 1.54209366,
+      "memory(GiB)": 26.3,
+      "step": 100,
+      "train_speed(iter/s)": 0.132289
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "eval_acc": 0.5360443622920518,
+      "eval_loss": 1.8874558210372925,
+      "eval_runtime": 2.3721,
+      "eval_samples_per_second": 5.902,
+      "eval_steps_per_second": 5.902,
+      "step": 100
+    },
+    {
+      "acc": 0.61074128,
+      "epoch": 1.1914893617021276,
+      "grad_norm": 1.1275923252105713,
+      "learning_rate": 7.071877904966423e-05,
+      "loss": 1.45454111,
+      "memory(GiB)": 26.3,
+      "step": 105,
+      "train_speed(iter/s)": 0.131567
+    },
+    {
+      "acc": 0.60273228,
+      "epoch": 1.24822695035461,
+      "grad_norm": 1.3083913326263428,
+      "learning_rate": 6.782059393566253e-05,
+      "loss": 1.48250647,
+      "memory(GiB)": 26.3,
+      "step": 110,
+      "train_speed(iter/s)": 0.13177
+    },
+    {
+      "acc": 0.62370677,
+      "epoch": 1.3049645390070923,
+      "grad_norm": 1.0839005708694458,
+      "learning_rate": 6.485207907885175e-05,
+      "loss": 1.46015568,
+      "memory(GiB)": 26.3,
+      "step": 115,
+      "train_speed(iter/s)": 0.131889
+    },
+    {
+      "acc": 0.61979499,
+      "epoch": 1.3617021276595744,
+      "grad_norm": 1.2509405612945557,
+      "learning_rate": 6.182494985118624e-05,
+      "loss": 1.45815115,
+      "memory(GiB)": 26.3,
+      "step": 120,
+      "train_speed(iter/s)": 0.132091
+    },
+    {
+      "acc": 0.61155128,
+      "epoch": 1.4184397163120568,
+      "grad_norm": 1.4081703424453735,
+      "learning_rate": 5.875115294876381e-05,
+      "loss": 1.44713774,
+      "memory(GiB)": 26.3,
+      "step": 125,
+      "train_speed(iter/s)": 0.132225
+    },
+    {
+      "acc": 0.61849551,
+      "epoch": 1.475177304964539,
+      "grad_norm": 1.3654893636703491,
+      "learning_rate": 5.564281924367408e-05,
+      "loss": 1.39691505,
+      "memory(GiB)": 26.3,
+      "step": 130,
+      "train_speed(iter/s)": 0.132372
+    },
+    {
+      "acc": 0.62567844,
+      "epoch": 1.5319148936170213,
+      "grad_norm": 1.5169520378112793,
+      "learning_rate": 5.2512215908988484e-05,
+      "loss": 1.41729832,
+      "memory(GiB)": 26.3,
+      "step": 135,
+      "train_speed(iter/s)": 0.132474
+    },
+    {
+      "acc": 0.63134012,
+      "epoch": 1.5886524822695036,
+      "grad_norm": 1.4038567543029785,
+      "learning_rate": 4.9371698005832365e-05,
+      "loss": 1.37339115,
+      "memory(GiB)": 26.3,
+      "step": 140,
+      "train_speed(iter/s)": 0.132568
+    },
+    {
+      "acc": 0.61558661,
+      "epoch": 1.645390070921986,
+      "grad_norm": 1.513599157333374,
+      "learning_rate": 4.623365972360337e-05,
+      "loss": 1.44473677,
+      "memory(GiB)": 26.3,
+      "step": 145,
+      "train_speed(iter/s)": 0.132637
+    },
+    {
+      "acc": 0.62634563,
+      "epoch": 1.702127659574468,
+      "grad_norm": 1.3617616891860962,
+      "learning_rate": 4.31104854657681e-05,
+      "loss": 1.38092842,
+      "memory(GiB)": 26.3,
+      "step": 150,
+      "train_speed(iter/s)": 0.13276
+    },
+    {
+      "epoch": 1.702127659574468,
+      "eval_acc": 0.5489833641404805,
+      "eval_loss": 1.8454854488372803,
+      "eval_runtime": 2.5064,
+      "eval_samples_per_second": 5.586,
+      "eval_steps_per_second": 5.586,
+      "step": 150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 264,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858706d8f3c54ad15f422bdde72ec7ac07e7a6a1854048f372d99d1dcec8c89b
+size 7264