LoRA adapter + training metadata

lora/README.md

@@ -0,0 +1,207 @@
+---
+base_model: openbmb/MiniCPM-V-4.6
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:openbmb/MiniCPM-V-4.6
+- lora
+- transformers
+---
+
+# 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 0.19.1

lora/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/huggingface/hub/models--openbmb--MiniCPM-V-4.6/snapshots/d7f5ed8d15462c508d4f9d9ce5a0cf1fe8d87bcc",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(model\\.language_model(?=\\.).*\\.(in_proj_b|in_proj_qkv|gate_proj|v_proj|k_proj|o_proj|up_proj|in_proj_z|in_proj_a|out_proj|down_proj|q_proj))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5a9f1c7c5113044e20167e8960b44c7f2425c295ee03cbaa818431aa405268
+size 43346432

lora/additional_config.json

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

lora/args.json

@@ -0,0 +1,348 @@
+{
+  "output_dir": "/root/outputs/rune-goblin-vision-lora/v2-20260607-171815",
+  "per_device_train_batch_size": 16,
+  "num_train_epochs": 3.0,
+  "max_steps": -1,
+  "learning_rate": 0.0001,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": null,
+  "warmup_steps": 0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "weight_decay": 0.1,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "optim_target_modules": null,
+  "gradient_accumulation_steps": 1,
+  "average_tokens_across_devices": true,
+  "max_grad_norm": 1.0,
+  "label_smoothing_factor": 0.0,
+  "bf16": true,
+  "fp16": false,
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": null,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "use_cache": false,
+  "neftune_noise_alpha": null,
+  "torch_empty_cache_steps": null,
+  "auto_find_batch_size": false,
+  "logging_strategy": "steps",
+  "logging_steps": 10,
+  "logging_first_step": true,
+  "log_on_each_node": true,
+  "logging_nan_inf_filter": true,
+  "include_num_input_tokens_seen": false,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "disable_tqdm": null,
+  "report_to": [
+    "wandb"
+  ],
+  "run_name": "/root/outputs/rune-goblin-vision-lora/v2-20260607-171815",
+  "project": "huggingface",
+  "trackio_space_id": null,
+  "trackio_bucket_id": null,
+  "trackio_static_space_id": null,
+  "eval_strategy": "steps",
+  "eval_steps": 200.0,
+  "eval_delay": 0,
+  "per_device_eval_batch_size": 1,
+  "prediction_loss_only": false,
+  "eval_on_start": false,
+  "eval_do_concat_batches": true,
+  "eval_use_gather_object": false,
+  "eval_accumulation_steps": null,
+  "include_for_metrics": [],
+  "batch_eval_metrics": false,
+  "save_only_model": false,
+  "save_strategy": "steps",
+  "save_steps": 200.0,
+  "save_on_each_node": false,
+  "save_total_limit": 2,
+  "enable_jit_checkpoint": false,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_private_repo": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_always_push": false,
+  "hub_revision": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": "loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "restore_callback_states_from_checkpoint": false,
+  "full_determinism": false,
+  "seed": 42,
+  "data_seed": 42,
+  "use_cpu": false,
+  "accelerator_config": {
+    "dispatch_batches": false
+  },
+  "parallelism_config": null,
+  "dataloader_drop_last": false,
+  "dataloader_num_workers": 8,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "dataloader_prefetch_factor": null,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "train_sampling_strategy": "random",
+  "length_column_name": "length",
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_static_graph": null,
+  "ddp_backend": null,
+  "ddp_timeout": 18000000,
+  "fsdp": [],
+  "fsdp_config": null,
+  "deepspeed": null,
+  "debug": null,
+  "skip_memory_metrics": true,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "resume_from_checkpoint": null,
+  "warmup_ratio": 0.03,
+  "logging_dir": "/root/outputs/rune-goblin-vision-lora/v2-20260607-171815/runs",
+  "local_rank": -1,
+  "sortish_sampler": false,
+  "predict_with_generate": false,
+  "generation_max_length": null,
+  "generation_num_beams": null,
+  "generation_config": null,
+  "tuner_backend": "peft",
+  "vit_gradient_checkpointing": false,
+  "router_aux_loss_coef": 0.0,
+  "enable_dft_loss": false,
+  "enable_channel_loss": false,
+  "safe_serialization": true,
+  "max_shard_size": "5GB",
+  "check_model": true,
+  "acc_strategy": "token",
+  "train_dataloader_shuffle": true,
+  "group_by_length": false,
+  "max_epochs": null,
+  "aligner_lr": null,
+  "vit_lr": null,
+  "use_logits_to_keep": null,
+  "ds3_gather_for_generation": true,
+  "resume_only_model": false,
+  "optimizer": null,
+  "loss_type": null,
+  "eval_metric": null,
+  "callbacks": [],
+  "early_stop_interval": null,
+  "eval_use_evalscope": false,
+  "eval_dataset": [],
+  "eval_dataset_args": null,
+  "eval_limit": null,
+  "eval_generation_config": null,
+  "extra_eval_args": null,
+  "tuner_type": "lora",
+  "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,
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "use_flash_ckpt": false,
+  "use_ray": false,
+  "ray_exp_name": null,
+  "device_groups": null,
+  "model": "openbmb/MiniCPM-V-4.6",
+  "model_type": "minicpmv4_6",
+  "model_revision": null,
+  "task_type": "causal_lm",
+  "torch_dtype": "bfloat16",
+  "attn_impl": "sdpa",
+  "experts_impl": null,
+  "new_special_tokens": [],
+  "num_labels": null,
+  "problem_type": null,
+  "rope_scaling": null,
+  "device_map": null,
+  "max_memory": {},
+  "max_model_len": null,
+  "local_repo_path": null,
+  "init_strategy": null,
+  "template": "minicpmv4_6",
+  "system": null,
+  "max_length": 2048,
+  "truncation_strategy": "delete",
+  "max_pixels": null,
+  "agent_template": null,
+  "norm_bbox": null,
+  "use_chat_template": true,
+  "padding_side": "right",
+  "padding_free": false,
+  "loss_scale": "default",
+  "sequence_parallel_size": 1,
+  "template_backend": "swift",
+  "response_prefix": null,
+  "enable_thinking": null,
+  "add_non_thinking_prefix": true,
+  "dataset": [
+    "rg_swift_train.jsonl"
+  ],
+  "val_dataset": [
+    "rg_swift_val.jsonl"
+  ],
+  "cached_dataset": [],
+  "cached_val_dataset": [],
+  "split_dataset_ratio": 0.0,
+  "dataset_num_proc": 8,
+  "load_from_cache_file": false,
+  "dataset_shuffle": true,
+  "val_dataset_shuffle": false,
+  "streaming": false,
+  "interleave_prob": null,
+  "stopping_strategy": "first_exhausted",
+  "shuffle_buffer_size": 1000,
+  "download_mode": "reuse_dataset_if_exists",
+  "columns": {},
+  "strict": false,
+  "disable_auto_column_mapping": false,
+  "model_name": null,
+  "model_author": null,
+  "custom_dataset_info": [],
+  "quant_method": null,
+  "quant_bits": null,
+  "hqq_axis": null,
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "max_new_tokens": 64,
+  "temperature": 0.0,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "stream": false,
+  "stop_words": [],
+  "logprobs": false,
+  "top_logprobs": null,
+  "structured_outputs_regex": null,
+  "adapters": [],
+  "external_plugins": [],
+  "custom_register_path": [],
+  "model_kwargs": {},
+  "enable_npu_model_patch": true,
+  "load_args": false,
+  "load_data_args": false,
+  "packing": false,
+  "packing_length": null,
+  "packing_num_proc": 1,
+  "lazy_tokenize": true,
+  "use_hf": true,
+  "ignore_args_error": false,
+  "use_swift_lora": false,
+  "freeze_parameters": [],
+  "freeze_parameters_regex": null,
+  "freeze_parameters_ratio": 0.0,
+  "trainable_parameters": [],
+  "trainable_parameters_regex": null,
+  "freeze_llm": false,
+  "freeze_vit": true,
+  "freeze_aligner": true,
+  "target_modules": [
+    "all-linear"
+  ],
+  "target_regex": null,
+  "target_parameters": null,
+  "modules_to_save": [],
+  "lora_rank": 16,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_dtype": null,
+  "lorap_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "lora_ga_batch_size": 2,
+  "lora_ga_iters": 2,
+  "lora_ga_max_length": 1024,
+  "lora_ga_direction": "ArB2r",
+  "lora_ga_scale": "stable",
+  "lora_ga_stable_gamma": 16,
+  "init_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "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,
+  "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,
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "swanlab_token": null,
+  "swanlab_project": "ms-swift",
+  "swanlab_workspace": null,
+  "swanlab_exp_name": null,
+  "swanlab_notification_method": null,
+  "swanlab_webhook_url": null,
+  "swanlab_secret": null,
+  "swanlab_sender_email": null,
+  "swanlab_receiver_email": null,
+  "swanlab_smtp_server": null,
+  "swanlab_smtp_port": null,
+  "swanlab_email_language": "zh",
+  "swanlab_mode": "cloud",
+  "add_version": true,
+  "create_checkpoint_symlink": false,
+  "zero_hpz_partition_size": null,
+  "deepspeed_autotp_size": null,
+  "swift_version": "4.2.3",
+  "ckpt_dir": null,
+  "rank": -1,
+  "global_world_size": 1,
+  "local_world_size": 1,
+  "model_suffix": "MiniCPM-V-4.6",
+  "model_info": "ModelInfo(model_type='minicpmv4_6', model_dir='/root/.cache/huggingface/hub/models--openbmb--MiniCPM-V-4.6/snapshots/d7f5ed8d15462c508d4f9d9ce5a0cf1fe8d87bcc', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
+  "model_meta": "ModelMeta(model_type='minicpmv4_6', model_groups=[ModelGroup(models=[Model(ms_model_id='OpenBMB/MiniCPM-V-4.6', hf_model_id='openbmb/MiniCPM-V-4.6', model_path=None, ms_revision=None, hf_revision=None)], template=None, ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.minicpm.MiniCPMV4_6Loader'>, template='minicpmv4_6', model_arch=MultiModelKeys(arch_name='minicpmv4_6', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.merger'], vision_tower=['model.vision_tower'], generator=[]), mcore_model_type=None, architectures=['MiniCPMV4_6ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.7.0'], tags=[])",
+  "model_dir": "/root/.cache/huggingface/hub/models--openbmb--MiniCPM-V-4.6/snapshots/d7f5ed8d15462c508d4f9d9ce5a0cf1fe8d87bcc",
+  "template_meta": "ChatmlTemplateMeta(template_type='minicpmv4_6', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.minicpm.MiniCPMV4_6Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=True, stop_words=[], agent_template='react_en', is_thinking=True, thinking_prefix='<think>\\n', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', history_thinking_prefix='')",
+  "_val_dataset_exists": true,
+  "hub": "<class 'swift.hub.hub.HFHub'>",
+  "evaluation_strategy": "steps",
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/root/outputs/rune-goblin-vision-lora/v2-20260607-171815', per_device_train_batch_size=16, num_train_epochs=3.0, max_steps=-1, learning_rate=0.0001, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=0.03, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=1, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=10, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['wandb'], run_name='/root/outputs/rune-goblin-vision-lora/v2-20260607-171815', project='huggingface', trackio_space_id=None, trackio_bucket_id=None, trackio_static_space_id=None, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, eval_steps=200, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=False, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=200, save_on_each_node=False, save_total_limit=2, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, 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), parallelism_config=None, dataloader_drop_last=False, dataloader_num_workers=8, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_static_graph=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, deepspeed=None, debug=[], skip_memory_metrics=True, do_train=False, do_eval=True, do_predict=False, resume_from_checkpoint=None, warmup_ratio=0.03, logging_dir='/root/outputs/rune-goblin-vision-lora/v2-20260607-171815/runs', local_rank=-1, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='lora', use_galore=False, galore_target_modules=None, 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, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
+}

lora/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984b78595ea57860f859959981b4531b247129679458708b08c0a0f0e37a29fb
+size 86899135

lora/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858514dc6cb54559a8f1a3ee289ea2ebab35a4d94d2dcdcefe7f41a324d5eb7a
+size 14645

lora/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e97fb1ffd942fa42e3daeba6d24c25f44cad62992c926a1bb4cfa2dd355f8f0
+size 1465

lora/trainer_state.json

@@ -0,0 +1,759 @@
+{
+  "best_global_step": 846,
+  "best_metric": 0.11049881,
+  "best_model_checkpoint": "/root/outputs/rune-goblin-vision-lora/v2-20260607-171815/checkpoint-846",
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 846,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0035460992907801418,
+      "grad_norm": 26.47808074951172,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 4.957160472869873,
+      "step": 1,
+      "token_acc": 0.32794774836713647
+    },
+    {
+      "epoch": 0.03546099290780142,
+      "grad_norm": 6.980465412139893,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 4.304361979166667,
+      "step": 10,
+      "token_acc": 0.371801140994295
+    },
+    {
+      "epoch": 0.07092198581560284,
+      "grad_norm": 2.8949131965637207,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 2.537805938720703,
+      "step": 20,
+      "token_acc": 0.5499852876268942
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 2.3080947399139404,
+      "learning_rate": 9.999412884518409e-05,
+      "loss": 1.4758130073547364,
+      "step": 30,
+      "token_acc": 0.719080560740822
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 1.9129527807235718,
+      "learning_rate": 9.992809418734932e-05,
+      "loss": 0.8724543571472168,
+      "step": 40,
+      "token_acc": 0.8118754734677681
+    },
+    {
+      "epoch": 0.1773049645390071,
+      "grad_norm": 1.6698404550552368,
+      "learning_rate": 9.978878316629133e-05,
+      "loss": 0.6030772686004638,
+      "step": 50,
+      "token_acc": 0.857075642417662
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 1.4783146381378174,
+      "learning_rate": 9.957640024014426e-05,
+      "loss": 0.4381204605102539,
+      "step": 60,
+      "token_acc": 0.8833357600465929
+    },
+    {
+      "epoch": 0.24822695035460993,
+      "grad_norm": 1.3394635915756226,
+      "learning_rate": 9.929125711013952e-05,
+      "loss": 0.36449878215789794,
+      "step": 70,
+      "token_acc": 0.9001910219675263
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 1.8082902431488037,
+      "learning_rate": 9.893377226314113e-05,
+      "loss": 0.3078165054321289,
+      "step": 80,
+      "token_acc": 0.9116833988069256
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 1.3050870895385742,
+      "learning_rate": 9.850447035745866e-05,
+      "loss": 0.2708670854568481,
+      "step": 90,
+      "token_acc": 0.9215828380924772
+    },
+    {
+      "epoch": 0.3546099290780142,
+      "grad_norm": 1.157996654510498,
+      "learning_rate": 9.800398145283874e-05,
+      "loss": 0.2403315305709839,
+      "step": 100,
+      "token_acc": 0.9257353477848332
+    },
+    {
+      "epoch": 0.3900709219858156,
+      "grad_norm": 1.1475191116333008,
+      "learning_rate": 9.74330400857655e-05,
+      "loss": 0.2249774932861328,
+      "step": 110,
+      "token_acc": 0.9299674267100977
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 1.1834532022476196,
+      "learning_rate": 9.679248419142703e-05,
+      "loss": 0.21108412742614746,
+      "step": 120,
+      "token_acc": 0.9321722859918679
+    },
+    {
+      "epoch": 0.46099290780141844,
+      "grad_norm": 1.025472640991211,
+      "learning_rate": 9.608325387392986e-05,
+      "loss": 0.1984718918800354,
+      "step": 130,
+      "token_acc": 0.9349572712000584
+    },
+    {
+      "epoch": 0.49645390070921985,
+      "grad_norm": 1.3528136014938354,
+      "learning_rate": 9.530639002656665e-05,
+      "loss": 0.18717693090438842,
+      "step": 140,
+      "token_acc": 0.9383361356824329
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 0.9476079344749451,
+      "learning_rate": 9.446303280416168e-05,
+      "loss": 0.18122910261154174,
+      "step": 150,
+      "token_acc": 0.939964093357271
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "grad_norm": 1.1301629543304443,
+      "learning_rate": 9.35544199497364e-05,
+      "loss": 0.17390866279602052,
+      "step": 160,
+      "token_acc": 0.9416140097490522
+    },
+    {
+      "epoch": 0.6028368794326241,
+      "grad_norm": 0.9774699211120605,
+      "learning_rate": 9.258188497795093e-05,
+      "loss": 0.1724635124206543,
+      "step": 170,
+      "token_acc": 0.9417198946266826
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.9606502652168274,
+      "learning_rate": 9.154685521798736e-05,
+      "loss": 0.16570632457733153,
+      "step": 180,
+      "token_acc": 0.9430933137398971
+    },
+    {
+      "epoch": 0.6737588652482269,
+      "grad_norm": 0.7653209567070007,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.16216459274291992,
+      "step": 190,
+      "token_acc": 0.945176232177752
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": 0.8915665149688721,
+      "learning_rate": 8.929547701943848e-05,
+      "loss": 0.16271411180496215,
+      "step": 200,
+      "token_acc": 0.942606371451275
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "eval_loss": 0.15719343721866608,
+      "eval_runtime": 201.5815,
+      "eval_samples_per_second": 2.48,
+      "eval_steps_per_second": 2.48,
+      "eval_token_acc": 0.945529659545907,
+      "step": 200
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.8328582644462585,
+      "learning_rate": 8.808243278882094e-05,
+      "loss": 0.1601296544075012,
+      "step": 210,
+      "token_acc": 0.9429678447276941
+    },
+    {
+      "epoch": 0.7801418439716312,
+      "grad_norm": 0.6964325308799744,
+      "learning_rate": 8.681349733658002e-05,
+      "loss": 0.156463623046875,
+      "step": 220,
+      "token_acc": 0.944890562819784
+    },
+    {
+      "epoch": 0.8156028368794326,
+      "grad_norm": 0.7970917820930481,
+      "learning_rate": 8.549053300047603e-05,
+      "loss": 0.1498551845550537,
+      "step": 230,
+      "token_acc": 0.9467647380111422
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.8542683720588684,
+      "learning_rate": 8.411548141310682e-05,
+      "loss": 0.150161075592041,
+      "step": 240,
+      "token_acc": 0.9477524382195498
+    },
+    {
+      "epoch": 0.8865248226950354,
+      "grad_norm": 1.1433733701705933,
+      "learning_rate": 8.269036065229427e-05,
+      "loss": 0.14733513593673705,
+      "step": 250,
+      "token_acc": 0.9477655677655678
+    },
+    {
+      "epoch": 0.9219858156028369,
+      "grad_norm": 0.8125953674316406,
+      "learning_rate": 8.121726227927671e-05,
+      "loss": 0.14813485145568847,
+      "step": 260,
+      "token_acc": 0.9468073573519314
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.6343769431114197,
+      "learning_rate": 7.96983482690544e-05,
+      "loss": 0.14432573318481445,
+      "step": 270,
+      "token_acc": 0.9457151129125652
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 0.6489441990852356,
+      "learning_rate": 7.813584783739314e-05,
+      "loss": 0.14110009670257567,
+      "step": 280,
+      "token_acc": 0.9487638198146624
+    },
+    {
+      "epoch": 1.0283687943262412,
+      "grad_norm": 0.6926689743995667,
+      "learning_rate": 7.653205416914267e-05,
+      "loss": 0.13882286548614503,
+      "step": 290,
+      "token_acc": 0.9491290028173485
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.6307562589645386,
+      "learning_rate": 7.48893210526717e-05,
+      "loss": 0.13428436517715453,
+      "step": 300,
+      "token_acc": 0.9507825962090752
+    },
+    {
+      "epoch": 1.099290780141844,
+      "grad_norm": 0.6745529770851135,
+      "learning_rate": 7.32100594253589e-05,
+      "loss": 0.13728001117706298,
+      "step": 310,
+      "token_acc": 0.9503636828831463
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 0.6265084743499756,
+      "learning_rate": 7.149673383520977e-05,
+      "loss": 0.1338452696800232,
+      "step": 320,
+      "token_acc": 0.9483374653638618
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.7385435104370117,
+      "learning_rate": 6.975185882379271e-05,
+      "loss": 0.1393455147743225,
+      "step": 330,
+      "token_acc": 0.9486471763210459
+    },
+    {
+      "epoch": 1.2056737588652482,
+      "grad_norm": 0.5905711650848389,
+      "learning_rate": 6.79779952358024e-05,
+      "loss": 0.13502193689346315,
+      "step": 340,
+      "token_acc": 0.9485331772624186
+    },
+    {
+      "epoch": 1.2411347517730495,
+      "grad_norm": 0.7370989322662354,
+      "learning_rate": 6.617774646066712e-05,
+      "loss": 0.13421342372894288,
+      "step": 350,
+      "token_acc": 0.9494764589587757
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.5736089944839478,
+      "learning_rate": 6.43537546117158e-05,
+      "loss": 0.13304685354232787,
+      "step": 360,
+      "token_acc": 0.9498352251922373
+    },
+    {
+      "epoch": 1.3120567375886525,
+      "grad_norm": 0.5789754986763,
+      "learning_rate": 6.250869664851227e-05,
+      "loss": 0.13168127536773683,
+      "step": 370,
+      "token_acc": 0.9499291450165328
+    },
+    {
+      "epoch": 1.3475177304964538,
+      "grad_norm": 0.5693713426589966,
+      "learning_rate": 6.0645280448048044e-05,
+      "loss": 0.12925996780395507,
+      "step": 380,
+      "token_acc": 0.9515637471881576
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.7503437399864197,
+      "learning_rate": 5.876624083055939e-05,
+      "loss": 0.1295076847076416,
+      "step": 390,
+      "token_acc": 0.9505007983742197
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 0.6699873805046082,
+      "learning_rate": 5.687433554580147e-05,
+      "loss": 0.12774388790130614,
+      "step": 400,
+      "token_acc": 0.9517989761338236
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "eval_loss": 0.1278059333562851,
+      "eval_runtime": 202.2442,
+      "eval_samples_per_second": 2.472,
+      "eval_steps_per_second": 2.472,
+      "eval_token_acc": 0.9520795241511792,
+      "step": 400
+    },
+    {
+      "epoch": 1.4539007092198581,
+      "grad_norm": 0.5635619163513184,
+      "learning_rate": 5.4972341225670354e-05,
+      "loss": 0.1255749225616455,
+      "step": 410,
+      "token_acc": 0.9524740290295726
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.7221083641052246,
+      "learning_rate": 5.306304930911278e-05,
+      "loss": 0.12711741924285888,
+      "step": 420,
+      "token_acc": 0.9516117426967909
+    },
+    {
+      "epoch": 1.524822695035461,
+      "grad_norm": 0.5900425314903259,
+      "learning_rate": 5.1149261945304526e-05,
+      "loss": 0.1292075514793396,
+      "step": 430,
+      "token_acc": 0.9518457901436624
+    },
+    {
+      "epoch": 1.5602836879432624,
+      "grad_norm": 0.6121543645858765,
+      "learning_rate": 4.923378788111019e-05,
+      "loss": 0.12657049894332886,
+      "step": 440,
+      "token_acc": 0.9530577088716624
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.5986051559448242,
+      "learning_rate": 4.731943833885973e-05,
+      "loss": 0.12117983102798462,
+      "step": 450,
+      "token_acc": 0.9550748752079867
+    },
+    {
+      "epoch": 1.6312056737588652,
+      "grad_norm": 0.5218138694763184,
+      "learning_rate": 4.54090228904921e-05,
+      "loss": 0.12389755249023438,
+      "step": 460,
+      "token_acc": 0.9530423518405239
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.6366024017333984,
+      "learning_rate": 4.350534533412097e-05,
+      "loss": 0.12183566093444824,
+      "step": 470,
+      "token_acc": 0.9533030027297543
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.631432056427002,
+      "learning_rate": 4.16111995790744e-05,
+      "loss": 0.1201132893562317,
+      "step": 480,
+      "token_acc": 0.9545209419378033
+    },
+    {
+      "epoch": 1.7375886524822695,
+      "grad_norm": 0.6317788362503052,
+      "learning_rate": 3.9729365545447514e-05,
+      "loss": 0.12237818241119384,
+      "step": 490,
+      "token_acc": 0.9546474590994644
+    },
+    {
+      "epoch": 1.773049645390071,
+      "grad_norm": 0.5718140006065369,
+      "learning_rate": 3.786260508418655e-05,
+      "loss": 0.124367356300354,
+      "step": 500,
+      "token_acc": 0.9517145369284877
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.6416216492652893,
+      "learning_rate": 3.601365792369161e-05,
+      "loss": 0.12365785837173462,
+      "step": 510,
+      "token_acc": 0.9522010751125962
+    },
+    {
+      "epoch": 1.8439716312056738,
+      "grad_norm": 0.5563585758209229,
+      "learning_rate": 3.418523764888758e-05,
+      "loss": 0.11884108781814576,
+      "step": 520,
+      "token_acc": 0.9552927391893377
+    },
+    {
+      "epoch": 1.8794326241134751,
+      "grad_norm": 0.6853976249694824,
+      "learning_rate": 3.238002771866391e-05,
+      "loss": 0.11873785257339478,
+      "step": 530,
+      "token_acc": 0.9553233651594307
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.64034104347229,
+      "learning_rate": 3.060067752752874e-05,
+      "loss": 0.1139642357826233,
+      "step": 540,
+      "token_acc": 0.9571830173718734
+    },
+    {
+      "epoch": 1.950354609929078,
+      "grad_norm": 0.5898419618606567,
+      "learning_rate": 2.8849798517257065e-05,
+      "loss": 0.11692265272140503,
+      "step": 550,
+      "token_acc": 0.9547944708486014
+    },
+    {
+      "epoch": 1.9858156028368794,
+      "grad_norm": 0.5608242750167847,
+      "learning_rate": 2.7129960344239824e-05,
+      "loss": 0.11538001298904418,
+      "step": 560,
+      "token_acc": 0.9559320788003528
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.6120197772979736,
+      "learning_rate": 2.5443687108158836e-05,
+      "loss": 0.11315921545028687,
+      "step": 570,
+      "token_acc": 0.9558374442095372
+    },
+    {
+      "epoch": 2.0567375886524824,
+      "grad_norm": 0.5597257018089294,
+      "learning_rate": 2.379345364752239e-05,
+      "loss": 0.11295346021652222,
+      "step": 580,
+      "token_acc": 0.9562364842575963
+    },
+    {
+      "epoch": 2.0921985815602837,
+      "grad_norm": 0.4704679846763611,
+      "learning_rate": 2.2181681907498502e-05,
+      "loss": 0.10958367586135864,
+      "step": 590,
+      "token_acc": 0.9576675281185164
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.534522294998169,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.11023097038269043,
+      "step": 600,
+      "token_acc": 0.9576889723948547
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.11636195331811905,
+      "eval_runtime": 201.0697,
+      "eval_samples_per_second": 2.487,
+      "eval_steps_per_second": 2.487,
+      "eval_token_acc": 0.9559214942023283,
+      "step": 600
+    },
+    {
+      "epoch": 2.1631205673758864,
+      "grad_norm": 0.4464743733406067,
+      "learning_rate": 1.9082925658872853e-05,
+      "loss": 0.10994529724121094,
+      "step": 610,
+      "token_acc": 0.9586940836940837
+    },
+    {
+      "epoch": 2.198581560283688,
+      "grad_norm": 0.5795279741287231,
+      "learning_rate": 1.7600489002379443e-05,
+      "loss": 0.11219470500946045,
+      "step": 620,
+      "token_acc": 0.9579232995658467
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "grad_norm": 0.43980446457862854,
+      "learning_rate": 1.6165603096115107e-05,
+      "loss": 0.10888147354125977,
+      "step": 630,
+      "token_acc": 0.9575937589464644
+    },
+    {
+      "epoch": 2.269503546099291,
+      "grad_norm": 0.5029824376106262,
+      "learning_rate": 1.4780373833015737e-05,
+      "loss": 0.10863748788833619,
+      "step": 640,
+      "token_acc": 0.9594982078853047
+    },
+    {
+      "epoch": 2.3049645390070923,
+      "grad_norm": 0.5658282041549683,
+      "learning_rate": 1.3446834228045812e-05,
+      "loss": 0.10928837060928345,
+      "step": 650,
+      "token_acc": 0.9579486439699942
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 0.5395434498786926,
+      "learning_rate": 1.216694143446857e-05,
+      "loss": 0.10922106504440307,
+      "step": 660,
+      "token_acc": 0.9575124269801532
+    },
+    {
+      "epoch": 2.375886524822695,
+      "grad_norm": 0.5449179410934448,
+      "learning_rate": 1.0942573871453733e-05,
+      "loss": 0.1074299693107605,
+      "step": 670,
+      "token_acc": 0.9578538497840056
+    },
+    {
+      "epoch": 2.4113475177304964,
+      "grad_norm": 0.5345823168754578,
+      "learning_rate": 9.775528467238327e-06,
+      "loss": 0.10802021026611328,
+      "step": 680,
+      "token_acc": 0.9587758112094396
+    },
+    {
+      "epoch": 2.4468085106382977,
+      "grad_norm": 0.5855720639228821,
+      "learning_rate": 8.6675180218867e-06,
+      "loss": 0.10763558149337768,
+      "step": 690,
+      "token_acc": 0.9585245065909257
+    },
+    {
+      "epoch": 2.482269503546099,
+      "grad_norm": 0.5211033821105957,
+      "learning_rate": 7.62016869352028e-06,
+      "loss": 0.1050539493560791,
+      "step": 700,
+      "token_acc": 0.9588449213264681
+    },
+    {
+      "epoch": 2.5177304964539005,
+      "grad_norm": 0.5373179912567139,
+      "learning_rate": 6.6350176117061845e-06,
+      "loss": 0.10771543979644775,
+      "step": 710,
+      "token_acc": 0.9592036553524804
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.5263897180557251,
+      "learning_rate": 5.7135106215077335e-06,
+      "loss": 0.10759412050247193,
+      "step": 720,
+      "token_acc": 0.9581606835099556
+    },
+    {
+      "epoch": 2.5886524822695036,
+      "grad_norm": 0.46306130290031433,
+      "learning_rate": 4.857000161507353e-06,
+      "loss": 0.10637538433074951,
+      "step": 730,
+      "token_acc": 0.9585609205447527
+    },
+    {
+      "epoch": 2.624113475177305,
+      "grad_norm": 0.5812863707542419,
+      "learning_rate": 4.0667432789165075e-06,
+      "loss": 0.10533280372619629,
+      "step": 740,
+      "token_acc": 0.9585522263686098
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 0.6535531878471375,
+      "learning_rate": 3.3438997846855393e-06,
+      "loss": 0.10743522644042969,
+      "step": 750,
+      "token_acc": 0.9587139335943163
+    },
+    {
+      "epoch": 2.6950354609929077,
+      "grad_norm": 0.5804023742675781,
+      "learning_rate": 2.689530551321179e-06,
+      "loss": 0.10793532133102417,
+      "step": 760,
+      "token_acc": 0.9582205746061168
+    },
+    {
+      "epoch": 2.7304964539007095,
+      "grad_norm": 0.6999026536941528,
+      "learning_rate": 2.104595955909844e-06,
+      "loss": 0.10848350524902343,
+      "step": 770,
+      "token_acc": 0.957983193277311
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 0.5102624297142029,
+      "learning_rate": 1.5899544706318381e-06,
+      "loss": 0.1073201060295105,
+      "step": 780,
+      "token_acc": 0.958284841431481
+    },
+    {
+      "epoch": 2.801418439716312,
+      "grad_norm": 0.6007110476493835,
+      "learning_rate": 1.1463614028350389e-06,
+      "loss": 0.1058308243751526,
+      "step": 790,
+      "token_acc": 0.9592070831989102
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "grad_norm": 0.5462249517440796,
+      "learning_rate": 7.744677865171967e-07,
+      "loss": 0.1059834361076355,
+      "step": 800,
+      "token_acc": 0.9579558070407908
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "eval_loss": 0.11057131737470627,
+      "eval_runtime": 216.6008,
+      "eval_samples_per_second": 2.308,
+      "eval_steps_per_second": 2.308,
+      "eval_token_acc": 0.957229152683593,
+      "step": 800
+    },
+    {
+      "epoch": 2.872340425531915,
+      "grad_norm": 0.4730088412761688,
+      "learning_rate": 4.7481942684378113e-07,
+      "loss": 0.10582698583602905,
+      "step": 810,
+      "token_acc": 0.9595293603380446
+    },
+    {
+      "epoch": 2.9078014184397163,
+      "grad_norm": 0.47516319155693054,
+      "learning_rate": 2.478560991036383e-07,
+      "loss": 0.10610353946685791,
+      "step": 820,
+      "token_acc": 0.9585180379860886
+    },
+    {
+      "epoch": 2.9432624113475176,
+      "grad_norm": 0.459794819355011,
+      "learning_rate": 9.391090327811048e-08,
+      "loss": 0.10496950149536133,
+      "step": 830,
+      "token_acc": 0.9590602804589328
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 0.5275819897651672,
+      "learning_rate": 1.3209775170852645e-08,
+      "loss": 0.10786118507385253,
+      "step": 840,
+      "token_acc": 0.9574242977015688
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.110498808324337,
+      "eval_runtime": 200.6458,
+      "eval_samples_per_second": 2.492,
+      "eval_steps_per_second": 2.492,
+      "eval_token_acc": 0.9572985858772884,
+      "step": 846
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 846,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.56432289067704e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

lora/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f492cc2114f0a9b43b9b81711ed249c6970e112484dacb3a7811adaa65d58bfa
+size 6737