commit de4fac2d6a7346df7550320f23a0e54b86d3d195 Author: ModelHub XC Date: Tue Aug 18 01:23:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: FutureMa/Eva-4B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8799fb9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text + + +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +rng_state_1.pth filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +scheduler.pt filter=lfs diff=lfs merge=lfs -text +rng_state_0.pth filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +optimizer.pt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..3b55cde --- /dev/null +++ b/README.md @@ -0,0 +1,226 @@ +--- +language: +- en +license: apache-2.0 +base_model: +- Qwen/Qwen3-4B-Instruct-2507 +tags: +- finance +- earnings-calls +- financial-nlp +- text-classification +- qwen3 +- llm-as-judge +- distillation +pipeline_tag: text-generation +library_name: transformers +--- + +# Eva-4B: Financial Evasion Detection Model + +Eva-4B is a **4B-parameter** model for detecting **evasive answers** in **earnings call Q&A**. + +## Model Summary + +- **Model name:** Eva-4B +- **Task:** 3-way classification of Q&A pairs into: + - `direct` + - `intermediate` + - `fully_evasive` +- **Base model:** `Qwen/Qwen3-4B-Instruct-2507` +- **Training method:** full-parameter fine-tuning +- **Training data:** EvasionBench training set (30,000 samples; 10,000 per class) + +## Intended Use + +Eva-4B is intended for research and tooling around corporate disclosure quality and evasiveness in earnings call Q&A. + +## Task Definition + +Given an earnings call **Question** (analyst) and **Answer** (management), the model predicts one of: + +- **direct:** answers the core question with specific information +- **intermediate:** provides related information but sidesteps the core question +- **fully_evasive:** does not address the question (refusal, redirection, non-response) + +This taxonomy follows the Rasiah framework referenced in the paper. + +## Dataset: EvasionBench (as reported in the paper) + +### Sources + +- Earnings call transcripts from the **S&P Capital IQ** database. + +### Splits + +- **Training:** 30,000 samples (balanced) + - direct: 10,000 + - intermediate: 10,000 + - fully_evasive: 10,000 +- **Test (Human):** 1,000 samples (natural distribution) + - direct: 412 (41.2%) + - intermediate: 256 (25.6%) + - fully_evasive: 332 (33.2%) + +### Labeling / Construction + +The training set is constructed via a multi-model annotation framework: + +- Two annotators: **Claude Opus 4.5** and **Gemini-3-Flash** +- Agreement cases (~70–80%) are treated as high-confidence +- Disagreement cases (~20–30%) are resolved by an **LLM-as-Judge** protocol using **Claude Opus 4.5** +- Final training mix reported: ~25,000 consensus samples (83.5%) + ~5,000 judge-resolved samples (16.5%) + +### Human validation (test set) + +- A 100-sample subset is double-annotated by two experts. +- Reported inter-annotator agreement: **Cohen’s Kappa = 0.835**. + +## Training Details + +- **Base model:** Qwen3-4B-Instruct-2507 +- **Fine-tuning:** full-parameter fine-tuning +- **Framework:** MS-Swift +- **Hardware:** 2× NVIDIA B200 SXM6 (180GB VRAM each) +- **Epochs:** 2 +- **Learning rate:** 2e-5 (linear warmup; 3% warmup ratio) +- **Batch size:** 8 per GPU +- **Gradient accumulation:** 2 (effective batch size 32) +- **Precision:** bfloat16 +- **Max sequence length:** 2048 +- **Optimizer:** AdamW +- **Gradient checkpointing:** enabled + +## Performance + +### Top-5 models on the 1,000-sample human test set + +| Rank | Model | Accuracy | F1-Macro | +|---:|---|---:|---:| +| 1 | Claude Opus 4.5 | 83.9% | 0.838 | +| 2 | Gemini-3-Flash | 83.7% | 0.833 | +| 3 | GLM-4.7 | 82.6% | 0.809 | +| 4 | **Eva-4B (Ours)** | **81.3%** | **0.807** | +| 5 | GPT-5.2 | 80.5% | 0.805 | + +Note: based on the accuracy values, Eva-4B is **2nd among open-source models**, after GLM-4.7 (82.6%). + +### Per-class F1 (Eva-4B) + +| Class | F1 | +|------:|---:| +| direct | 0.851 | +| intermediate | 0.698 | +| fully_evasive | 0.873 | + +The paper notes most errors are confusion between **direct** and **intermediate**. + +### Ablation (label-source comparison) + +The paper compares Eva-4B training labels (multi-model + judge) vs an Opus-only construction: + +- **Qwen-Opus-Only:** 78.9% accuracy +- **Eva-4B:** 81.3% accuracy (**+2.4%** absolute) + +The paper reports the Opus-only baseline achieves lower training loss but worse generalization. + +## Quick Start + +The prompt below matches `prompts/evasion_rasiah_fine_tuning_minimalist.txt` in this repo. + +````python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_name = "FutureMa/Eva-4B" + +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto", +) + +PROMPT_TEMPLATE = """You are a financial analyst. Your task is to Detect Evasive Answers in Financial Q&A + +Question: {{question}} +Answer: {{answer}} + +Response format: +```json +{"reason": "brief explanation under 100 characters", "label": "direct|intermediate|fully_evasive"} +``` + +Answer in json block content, no other text""" + +question = "What are your revenue expectations for next quarter?" +answer = "We remain optimistic about our business trajectory and will continue to focus on executing our strategic priorities." + +prompt = ( + PROMPT_TEMPLATE + .replace("{{question}}", question) + .replace("{{answer}}", answer) +) + +messages = [{"role": "user", "content": prompt}] +text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer([text], return_tensors="pt").to(model.device) + +with torch.no_grad(): + output_ids = model.generate( + **inputs, + max_new_tokens=128, + temperature=0.7, + do_sample=True, + ) + +generated = output_ids[0][inputs["input_ids"].shape[1]:] +response = tokenizer.decode(generated, skip_special_tokens=True) +print(response) +```` + +Expected output format: + +```json +{"reason": "...", "label": "direct|intermediate|fully_evasive"} +``` + +## Limitations + +- Domain-specific to earnings call Q&A +- English-only evaluation +- Multi-model + judge labeling increases annotation cost (~2.2–2.3× vs single-model) +- Judge position bias risk (no position randomization) +- Potential self-preference concerns (Opus judging its own predictions) +- Subjectivity in the intermediate class (lower agreement) +- Temporal drift (training data spans 2005–2023) + +## Ethics + +Eva-4B is a research artifact and **not financial advice**. Outputs should be used as one signal among many and should be reviewed by humans for high-stakes decisions. + +## Citation + +If you use this model, please cite the accompanying paper: + +```bibtex +@misc{ma2026evasionbenchdetectingevasiveanswers, + title={EvasionBench: Detecting Evasive Answers in Financial Q&A via Multi-Model Consensus and LLM-as-Judge}, + author={Shijian Ma and Yan Lin and Yi Yang}, + year={2026}, + eprint={2601.09142}, + archivePrefix={arXiv}, + primaryClass={cs.LG}, + url={https://arxiv.org/abs/2601.09142}, +} +``` + +Paper: [https://arxiv.org/abs/2601.09142](https://arxiv.org/abs/2601.09142) + +## Author + +- Shijian Ma (mas8069@foxmail.com) + +--- + +Last updated: 2026-01-12 \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/args.json b/args.json new file mode 100644 index 0000000..6bea101 --- /dev/null +++ b/args.json @@ -0,0 +1,353 @@ +{ + "output_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260111-013000", + "overwrite_output_dir": false, + "do_train": false, + "do_eval": false, + "do_predict": false, + "eval_strategy": "no", + "prediction_loss_only": false, + "per_device_train_batch_size": 8, + "per_device_eval_batch_size": 1, + "per_gpu_train_batch_size": null, + "per_gpu_eval_batch_size": null, + "gradient_accumulation_steps": 2, + "eval_accumulation_steps": null, + "eval_delay": 0, + "torch_empty_cache_steps": null, + "learning_rate": 2e-05, + "weight_decay": 0.1, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_epsilon": 1e-08, + "max_grad_norm": 1.0, + "num_train_epochs": 2.0, + "max_steps": -1, + "lr_scheduler_type": "cosine", + "lr_scheduler_kwargs": null, + "warmup_ratio": 0.03, + "warmup_steps": 0, + "log_level": "passive", + "log_level_replica": "warning", + "log_on_each_node": true, + "logging_dir": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/runs", + "logging_strategy": "steps", + "logging_first_step": true, + "logging_steps": 10, + "logging_nan_inf_filter": true, + "save_strategy": "steps", + "save_steps": 500.0, + "save_total_limit": 3, + "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": 42, + "jit_mode_eval": 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": null, + "dataloader_drop_last": false, + "eval_steps": 500.0, + "dataloader_num_workers": 8, + "dataloader_prefetch_factor": null, + "past_index": -1, + "run_name": "/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260111-013000", + "disable_tqdm": null, + "remove_unused_columns": true, + "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": null, + "fsdp_transformer_layer_cls_to_wrap": null, + "accelerator_config": { + "dispatch_batches": false + }, + "parallelism_config": null, + "deepspeed": null, + "label_smoothing_factor": 0.0, + "optim": "adamw_torch_fused", + "optim_args": null, + "adafactor": false, + "group_by_length": false, + "length_column_name": "length", + "report_to": [ + "tensorboard" + ], + "project": "huggingface", + "trackio_space_id": "trackio", + "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": null, + "hub_always_push": false, + "hub_revision": null, + "gradient_checkpointing": true, + "gradient_checkpointing_kwargs": "{\"use_reentrant\": false}", + "include_inputs_for_metrics": false, + "include_for_metrics": [], + "eval_do_concat_batches": true, + "fp16_backend": "auto", + "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": 18000000, + "torch_compile": false, + "torch_compile_backend": null, + "torch_compile_mode": 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, + "liger_kernel_config": null, + "eval_use_gather_object": false, + "average_tokens_across_devices": true, + "sortish_sampler": false, + "predict_with_generate": false, + "generation_max_length": null, + "generation_num_beams": null, + "generation_config": null, + "tuner_backend": "peft", + "vit_gradient_checkpointing": null, + "router_aux_loss_coef": 0.0, + "enable_dft_loss": false, + "enable_channel_loss": false, + "check_model": true, + "acc_strategy": "token", + "train_dataloader_shuffle": true, + "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, + "metric": null, + "eval_use_evalscope": false, + "eval_dataset": [], + "eval_dataset_args": null, + "eval_limit": null, + "eval_generation_config": null, + "extra_eval_args": null, + "use_flash_ckpt": false, + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "FutureMa/Qwen3-4B-Evasion-Exp", + "model_type": "qwen3_nothinking", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_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": "qwen3_nothinking", + "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": [ + "/home/ubuntu/ms-swift/data/balanced_30k_msswift.jsonl" + ], + "val_dataset": [], + "cached_dataset": [], + "cached_val_dataset": [], + "split_dataset_ratio": 0.0, + "dataset_num_proc": 1, + "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, + "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, + "ckpt_dir": null, + "lora_modules": [], + "train_type": "full", + "adapters": [], + "external_plugins": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": false, + "packing_length": null, + "packing_num_proc": 1, + "lazy_tokenize": false, + "custom_register_path": [], + "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": 8, + "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, + "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, + "llamapro_num_new_blocks": 4, + "llamapro_num_groups": null, + "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, + "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_mode": "cloud", + "add_version": true, + "create_checkpoint_symlink": false, + "zero_hpz_partition_size": null, + "deepspeed_autotp_size": null, + "early_stop_interval": null, + "rank": 0, + "global_world_size": 2, + "local_world_size": 2, + "model_suffix": "Qwen3-4B-Evasion-Exp", + "model_info": "ModelInfo(model_type='qwen3_nothinking', model_dir='/home/ubuntu/.cache/huggingface/hub/models--FutureMa--Qwen3-4B-Evasion-Exp/snapshots/a95696b6d485a93ec11814d2976c056d8f567b36', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='qwen3_nothinking', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-30B-A3B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-235B-A22B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='swift/Qwen3-235B-A22B-Instruct-2507-AWQ', hf_model_id=None, model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507', hf_model_id='Qwen/Qwen3-4B-Instruct-2507', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', hf_model_id='Qwen/Qwen3-4B-Instruct-2507-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_nothinking', get_function=, model_arch=None, architectures=['Qwen3MoeForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.51'], tags=[])", + "model_dir": "/home/ubuntu/.cache/huggingface/hub/models--FutureMa--Qwen3-4B-Evasion-Exp/snapshots/a95696b6d485a93ec11814d2976c056d8f567b36", + "_val_dataset_exists": [], + "hub": "", + "evaluation_strategy": "steps", + "training_args": "Seq2SeqTrainingArguments(output_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260111-013000', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=, lr_scheduler_kwargs=None, warmup_ratio=0.03, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/runs', logging_strategy=, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=, save_steps=500, save_total_limit=3, 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=42, jit_mode_eval=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=500.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/home/ubuntu/ms-swift/output/qwen3-4b-evasion-full/v0-20260111-013000', 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), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', 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=, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs={'use_reentrant': False}, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', 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=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, 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, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)" +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..70adff8 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,61 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..39e749e --- /dev/null +++ b/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3dd2c54 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.57.3" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..dcb0691 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4bbb9741e0ee42e2764f57c8d1ecfe62913b8a247d1d0f1b5a114bcfe99c2af +size 4967215360 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..6c01090 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe43af349c73fb6c31d72f68e6f8812494fee13d9e2ab5536b34bb053b8b1f48 +size 3077766632 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b65d806 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,406 @@ +{ + "metadata": { + "total_parameters": 4022468096, + "total_size": 8044936192 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/optimizer.pt b/optimizer.pt new file mode 100644 index 0000000..d82312e --- /dev/null +++ b/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c2310d630b7d441feba634dd2b5890f09bf33ab0e3171aeda62f84a1909a59 +size 16090225449 diff --git a/rng_state_0.pth b/rng_state_0.pth new file mode 100644 index 0000000..870021e --- /dev/null +++ b/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7 +size 14917 diff --git a/rng_state_1.pth b/rng_state_1.pth new file mode 100644 index 0000000..21f20da --- /dev/null +++ b/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e +size 14917 diff --git a/scheduler.pt b/scheduler.pt new file mode 100644 index 0000000..70e7a45 --- /dev/null +++ b/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9a51605f7783f6fc367ac7fc787e622e534a895c2dd8db5311e2d94bf71471 +size 1465 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c9fc122 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 1010000, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..a2bc018 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1538 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500.0, + "global_step": 1876, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0010666666666666667, + "grad_norm": 27.125, + "learning_rate": 3.5087719298245616e-07, + "loss": 1.6233890056610107, + "step": 1, + "token_acc": 0.702493551160791 + }, + { + "epoch": 0.010666666666666666, + "grad_norm": 19.25, + "learning_rate": 3.5087719298245615e-06, + "loss": 1.4475451575385199, + "step": 10, + "token_acc": 0.7265573770491803 + }, + { + "epoch": 0.021333333333333333, + "grad_norm": 12.1875, + "learning_rate": 7.017543859649123e-06, + "loss": 1.2004226684570312, + "step": 20, + "token_acc": 0.7449092613103859 + }, + { + "epoch": 0.032, + "grad_norm": 7.5625, + "learning_rate": 1.0526315789473684e-05, + "loss": 0.9809289932250976, + "step": 30, + "token_acc": 0.7659592602062558 + }, + { + "epoch": 0.042666666666666665, + "grad_norm": 6.1875, + "learning_rate": 1.4035087719298246e-05, + "loss": 0.8323905944824219, + "step": 40, + "token_acc": 0.7854956640027206 + }, + { + "epoch": 0.05333333333333334, + "grad_norm": 6.59375, + "learning_rate": 1.754385964912281e-05, + "loss": 0.7661696434020996, + "step": 50, + "token_acc": 0.7932169071121236 + }, + { + "epoch": 0.064, + "grad_norm": 6.15625, + "learning_rate": 1.9999865771143805e-05, + "loss": 0.7235654354095459, + "step": 60, + "token_acc": 0.8000837871805614 + }, + { + "epoch": 0.07466666666666667, + "grad_norm": 6.5, + "learning_rate": 1.9997479580610527e-05, + "loss": 0.7175994396209717, + "step": 70, + "token_acc": 0.8002734808990685 + }, + { + "epoch": 0.08533333333333333, + "grad_norm": 5.90625, + "learning_rate": 1.9992111345867986e-05, + "loss": 0.6924509048461914, + "step": 80, + "token_acc": 0.8082805238698775 + }, + { + "epoch": 0.096, + "grad_norm": 5.3125, + "learning_rate": 1.9983762668151084e-05, + "loss": 0.6639269828796387, + "step": 90, + "token_acc": 0.814126705163612 + }, + { + "epoch": 0.10666666666666667, + "grad_norm": 5.6875, + "learning_rate": 1.9972436037700082e-05, + "loss": 0.6697088718414307, + "step": 100, + "token_acc": 0.8140579955909785 + }, + { + "epoch": 0.11733333333333333, + "grad_norm": 5.5, + "learning_rate": 1.9958134833017768e-05, + "loss": 0.6650930881500244, + "step": 110, + "token_acc": 0.8157225237449118 + }, + { + "epoch": 0.128, + "grad_norm": 5.5625, + "learning_rate": 1.9940863319861758e-05, + "loss": 0.6610164642333984, + "step": 120, + "token_acc": 0.8128639945186708 + }, + { + "epoch": 0.13866666666666666, + "grad_norm": 6.125, + "learning_rate": 1.992062664997209e-05, + "loss": 0.627209997177124, + "step": 130, + "token_acc": 0.8250212765957446 + }, + { + "epoch": 0.14933333333333335, + "grad_norm": 6.21875, + "learning_rate": 1.9897430859534553e-05, + "loss": 0.6545108795166016, + "step": 140, + "token_acc": 0.8140264586160109 + }, + { + "epoch": 0.16, + "grad_norm": 5.0625, + "learning_rate": 1.9871282867380245e-05, + "loss": 0.6527502536773682, + "step": 150, + "token_acc": 0.8172938078654548 + }, + { + "epoch": 0.17066666666666666, + "grad_norm": 6.09375, + "learning_rate": 1.9842190472921802e-05, + "loss": 0.6138824462890625, + "step": 160, + "token_acc": 0.8251860622462788 + }, + { + "epoch": 0.18133333333333335, + "grad_norm": 5.5, + "learning_rate": 1.9810162353827e-05, + "loss": 0.6213672637939454, + "step": 170, + "token_acc": 0.8211650979394556 + }, + { + "epoch": 0.192, + "grad_norm": 6.0, + "learning_rate": 1.977520806343039e-05, + "loss": 0.5975364685058594, + "step": 180, + "token_acc": 0.8272704146527601 + }, + { + "epoch": 0.20266666666666666, + "grad_norm": 5.59375, + "learning_rate": 1.9737338027883727e-05, + "loss": 0.6315351963043213, + "step": 190, + "token_acc": 0.8185825703628349 + }, + { + "epoch": 0.21333333333333335, + "grad_norm": 5.15625, + "learning_rate": 1.969656354304606e-05, + "loss": 0.6197149276733398, + "step": 200, + "token_acc": 0.8190742151138191 + }, + { + "epoch": 0.224, + "grad_norm": 5.8125, + "learning_rate": 1.9652896771114416e-05, + "loss": 0.6223199367523193, + "step": 210, + "token_acc": 0.8190856560163154 + }, + { + "epoch": 0.23466666666666666, + "grad_norm": 5.03125, + "learning_rate": 1.960635073699605e-05, + "loss": 0.637688159942627, + "step": 220, + "token_acc": 0.8177713409439428 + }, + { + "epoch": 0.24533333333333332, + "grad_norm": 5.8125, + "learning_rate": 1.95569393244234e-05, + "loss": 0.6076653003692627, + "step": 230, + "token_acc": 0.8262690567934328 + }, + { + "epoch": 0.256, + "grad_norm": 5.5, + "learning_rate": 1.950467727181284e-05, + "loss": 0.6383634567260742, + "step": 240, + "token_acc": 0.8165317426501917 + }, + { + "epoch": 0.26666666666666666, + "grad_norm": 5.15625, + "learning_rate": 1.9449580167868506e-05, + "loss": 0.6294333934783936, + "step": 250, + "token_acc": 0.819404255319149 + }, + { + "epoch": 0.2773333333333333, + "grad_norm": 5.34375, + "learning_rate": 1.939166444693252e-05, + "loss": 0.6120997428894043, + "step": 260, + "token_acc": 0.8252212389380531 + }, + { + "epoch": 0.288, + "grad_norm": 5.28125, + "learning_rate": 1.9330947384082957e-05, + "loss": 0.5947658538818359, + "step": 270, + "token_acc": 0.8248434591301405 + }, + { + "epoch": 0.2986666666666667, + "grad_norm": 5.21875, + "learning_rate": 1.9267447089981018e-05, + "loss": 0.5949877738952637, + "step": 280, + "token_acc": 0.8277702473737716 + }, + { + "epoch": 0.30933333333333335, + "grad_norm": 5.28125, + "learning_rate": 1.9201182505469035e-05, + "loss": 0.5923934936523437, + "step": 290, + "token_acc": 0.8287868519146052 + }, + { + "epoch": 0.32, + "grad_norm": 6.71875, + "learning_rate": 1.9132173395920756e-05, + "loss": 0.6005728721618653, + "step": 300, + "token_acc": 0.8250169721656483 + }, + { + "epoch": 0.33066666666666666, + "grad_norm": 5.5625, + "learning_rate": 1.9060440345345762e-05, + "loss": 0.614538049697876, + "step": 310, + "token_acc": 0.8181046916094001 + }, + { + "epoch": 0.3413333333333333, + "grad_norm": 4.71875, + "learning_rate": 1.8986004750249687e-05, + "loss": 0.6015767574310302, + "step": 320, + "token_acc": 0.8247483718176436 + }, + { + "epoch": 0.352, + "grad_norm": 5.5625, + "learning_rate": 1.890888881325205e-05, + "loss": 0.6035000801086425, + "step": 330, + "token_acc": 0.8262050237610319 + }, + { + "epoch": 0.3626666666666667, + "grad_norm": 5.9375, + "learning_rate": 1.8829115536463682e-05, + "loss": 0.5983945846557617, + "step": 340, + "token_acc": 0.8245257452574526 + }, + { + "epoch": 0.37333333333333335, + "grad_norm": 5.8125, + "learning_rate": 1.8746708714625668e-05, + "loss": 0.6272837162017822, + "step": 350, + "token_acc": 0.8214831155608349 + }, + { + "epoch": 0.384, + "grad_norm": 5.75, + "learning_rate": 1.8661692928011858e-05, + "loss": 0.5912134647369385, + "step": 360, + "token_acc": 0.828818151032848 + }, + { + "epoch": 0.39466666666666667, + "grad_norm": 5.65625, + "learning_rate": 1.8574093535097062e-05, + "loss": 0.573200798034668, + "step": 370, + "token_acc": 0.8316343866802582 + }, + { + "epoch": 0.4053333333333333, + "grad_norm": 5.84375, + "learning_rate": 1.8483936664993152e-05, + "loss": 0.5843992233276367, + "step": 380, + "token_acc": 0.8279888315424316 + }, + { + "epoch": 0.416, + "grad_norm": 5.5, + "learning_rate": 1.839124920965527e-05, + "loss": 0.5969943046569824, + "step": 390, + "token_acc": 0.8256973795435334 + }, + { + "epoch": 0.4266666666666667, + "grad_norm": 5.0625, + "learning_rate": 1.829605881586051e-05, + "loss": 0.5709249019622803, + "step": 400, + "token_acc": 0.8314263920671243 + }, + { + "epoch": 0.43733333333333335, + "grad_norm": 5.4375, + "learning_rate": 1.8198393876961446e-05, + "loss": 0.5546571731567382, + "step": 410, + "token_acc": 0.834034515325835 + }, + { + "epoch": 0.448, + "grad_norm": 7.5625, + "learning_rate": 1.8098283524416982e-05, + "loss": 0.5464757919311524, + "step": 420, + "token_acc": 0.8344332135995322 + }, + { + "epoch": 0.45866666666666667, + "grad_norm": 5.3125, + "learning_rate": 1.7995757619103012e-05, + "loss": 0.5686863899230957, + "step": 430, + "token_acc": 0.8333759046402724 + }, + { + "epoch": 0.4693333333333333, + "grad_norm": 5.0, + "learning_rate": 1.7890846742405558e-05, + "loss": 0.575782299041748, + "step": 440, + "token_acc": 0.8317190263623347 + }, + { + "epoch": 0.48, + "grad_norm": 5.53125, + "learning_rate": 1.7783582187098944e-05, + "loss": 0.5736880779266358, + "step": 450, + "token_acc": 0.8315915710125065 + }, + { + "epoch": 0.49066666666666664, + "grad_norm": 5.28125, + "learning_rate": 1.7673995948011807e-05, + "loss": 0.5740520000457764, + "step": 460, + "token_acc": 0.8287811539774668 + }, + { + "epoch": 0.5013333333333333, + "grad_norm": 5.15625, + "learning_rate": 1.75621207124837e-05, + "loss": 0.5786960124969482, + "step": 470, + "token_acc": 0.8299598599368008 + }, + { + "epoch": 0.512, + "grad_norm": 5.375, + "learning_rate": 1.7447989850615114e-05, + "loss": 0.5925831317901611, + "step": 480, + "token_acc": 0.8259212198221093 + }, + { + "epoch": 0.5226666666666666, + "grad_norm": 5.125, + "learning_rate": 1.733163740531386e-05, + "loss": 0.5791446685791015, + "step": 490, + "token_acc": 0.8287425149700599 + }, + { + "epoch": 0.5333333333333333, + "grad_norm": 5.46875, + "learning_rate": 1.7213098082140774e-05, + "loss": 0.5816606521606446, + "step": 500, + "token_acc": 0.8285325856062538 + }, + { + "epoch": 0.544, + "grad_norm": 5.34375, + "learning_rate": 1.7092407238957737e-05, + "loss": 0.5790934562683105, + "step": 510, + "token_acc": 0.8313161235717309 + }, + { + "epoch": 0.5546666666666666, + "grad_norm": 5.15625, + "learning_rate": 1.6969600875381172e-05, + "loss": 0.5422775268554687, + "step": 520, + "token_acc": 0.8432008189728715 + }, + { + "epoch": 0.5653333333333334, + "grad_norm": 5.125, + "learning_rate": 1.684471562204407e-05, + "loss": 0.5492764472961426, + "step": 530, + "token_acc": 0.8374480359718334 + }, + { + "epoch": 0.576, + "grad_norm": 5.1875, + "learning_rate": 1.6717788729669822e-05, + "loss": 0.5672526359558105, + "step": 540, + "token_acc": 0.8343422286639952 + }, + { + "epoch": 0.5866666666666667, + "grad_norm": 5.34375, + "learning_rate": 1.658885805796111e-05, + "loss": 0.5880655288696289, + "step": 550, + "token_acc": 0.828699779623665 + }, + { + "epoch": 0.5973333333333334, + "grad_norm": 5.40625, + "learning_rate": 1.6457962064307104e-05, + "loss": 0.5665912628173828, + "step": 560, + "token_acc": 0.8322487957407251 + }, + { + "epoch": 0.608, + "grad_norm": 5.75, + "learning_rate": 1.6325139792312414e-05, + "loss": 0.5551149368286132, + "step": 570, + "token_acc": 0.8370577281191807 + }, + { + "epoch": 0.6186666666666667, + "grad_norm": 5.3125, + "learning_rate": 1.6190430860151196e-05, + "loss": 0.5558858394622803, + "step": 580, + "token_acc": 0.8377869133264817 + }, + { + "epoch": 0.6293333333333333, + "grad_norm": 5.3125, + "learning_rate": 1.605387544874983e-05, + "loss": 0.5704761505126953, + "step": 590, + "token_acc": 0.83192066451941 + }, + { + "epoch": 0.64, + "grad_norm": 4.9375, + "learning_rate": 1.591551428980179e-05, + "loss": 0.5583576202392578, + "step": 600, + "token_acc": 0.834020358374695 + }, + { + "epoch": 0.6506666666666666, + "grad_norm": 5.71875, + "learning_rate": 1.5775388653618217e-05, + "loss": 0.5596559524536133, + "step": 610, + "token_acc": 0.8347915594441585 + }, + { + "epoch": 0.6613333333333333, + "grad_norm": 5.28125, + "learning_rate": 1.5633540336817804e-05, + "loss": 0.5696552276611329, + "step": 620, + "token_acc": 0.8363047001620746 + }, + { + "epoch": 0.672, + "grad_norm": 5.5, + "learning_rate": 1.549001164985973e-05, + "loss": 0.5665851593017578, + "step": 630, + "token_acc": 0.8350402031316123 + }, + { + "epoch": 0.6826666666666666, + "grad_norm": 5.28125, + "learning_rate": 1.5344845404423313e-05, + "loss": 0.6030998229980469, + "step": 640, + "token_acc": 0.8214255373375244 + }, + { + "epoch": 0.6933333333333334, + "grad_norm": 5.21875, + "learning_rate": 1.5198084900638161e-05, + "loss": 0.557160472869873, + "step": 650, + "token_acc": 0.8347296268088348 + }, + { + "epoch": 0.704, + "grad_norm": 5.78125, + "learning_rate": 1.5049773914168629e-05, + "loss": 0.5760011672973633, + "step": 660, + "token_acc": 0.8304249812139934 + }, + { + "epoch": 0.7146666666666667, + "grad_norm": 5.21875, + "learning_rate": 1.4899956683156413e-05, + "loss": 0.5680459976196289, + "step": 670, + "token_acc": 0.8291992103682088 + }, + { + "epoch": 0.7253333333333334, + "grad_norm": 6.625, + "learning_rate": 1.4748677895025243e-05, + "loss": 0.5647514343261719, + "step": 680, + "token_acc": 0.8340217482930119 + }, + { + "epoch": 0.736, + "grad_norm": 5.53125, + "learning_rate": 1.4595982673151511e-05, + "loss": 0.5595580101013183, + "step": 690, + "token_acc": 0.8372705642420122 + }, + { + "epoch": 0.7466666666666667, + "grad_norm": 5.625, + "learning_rate": 1.444191656340491e-05, + "loss": 0.551822280883789, + "step": 700, + "token_acc": 0.8342021187153187 + }, + { + "epoch": 0.7573333333333333, + "grad_norm": 5.0625, + "learning_rate": 1.4286525520563003e-05, + "loss": 0.5694937705993652, + "step": 710, + "token_acc": 0.8321737654844731 + }, + { + "epoch": 0.768, + "grad_norm": 4.90625, + "learning_rate": 1.4129855894603885e-05, + "loss": 0.5161600112915039, + "step": 720, + "token_acc": 0.8459770114942529 + }, + { + "epoch": 0.7786666666666666, + "grad_norm": 5.0625, + "learning_rate": 1.3971954416880897e-05, + "loss": 0.5634379863739014, + "step": 730, + "token_acc": 0.833432531247343 + }, + { + "epoch": 0.7893333333333333, + "grad_norm": 4.6875, + "learning_rate": 1.3812868186183641e-05, + "loss": 0.5540994644165039, + "step": 740, + "token_acc": 0.8377988807868407 + }, + { + "epoch": 0.8, + "grad_norm": 4.9375, + "learning_rate": 1.3652644654689355e-05, + "loss": 0.5608715057373047, + "step": 750, + "token_acc": 0.8339112050739957 + }, + { + "epoch": 0.8106666666666666, + "grad_norm": 5.40625, + "learning_rate": 1.3491331613808909e-05, + "loss": 0.5746842384338379, + "step": 760, + "token_acc": 0.8306396733582851 + }, + { + "epoch": 0.8213333333333334, + "grad_norm": 5.21875, + "learning_rate": 1.3328977179931595e-05, + "loss": 0.5586155891418457, + "step": 770, + "token_acc": 0.8344169551633877 + }, + { + "epoch": 0.832, + "grad_norm": 5.09375, + "learning_rate": 1.3165629780072991e-05, + "loss": 0.5604053020477295, + "step": 780, + "token_acc": 0.8320225679603351 + }, + { + "epoch": 0.8426666666666667, + "grad_norm": 5.03125, + "learning_rate": 1.3001338137430163e-05, + "loss": 0.549941110610962, + "step": 790, + "token_acc": 0.8354163148116872 + }, + { + "epoch": 0.8533333333333334, + "grad_norm": 5.21875, + "learning_rate": 1.2836151256848562e-05, + "loss": 0.5661550521850586, + "step": 800, + "token_acc": 0.8333191958605479 + }, + { + "epoch": 0.864, + "grad_norm": 5.84375, + "learning_rate": 1.2670118410204819e-05, + "loss": 0.5822794437408447, + "step": 810, + "token_acc": 0.8300913396481732 + }, + { + "epoch": 0.8746666666666667, + "grad_norm": 5.03125, + "learning_rate": 1.250328912171001e-05, + "loss": 0.5514832019805909, + "step": 820, + "token_acc": 0.8363110430491747 + }, + { + "epoch": 0.8853333333333333, + "grad_norm": 5.5, + "learning_rate": 1.2335713153137551e-05, + "loss": 0.5658942222595215, + "step": 830, + "token_acc": 0.8320276303597001 + }, + { + "epoch": 0.896, + "grad_norm": 5.59375, + "learning_rate": 1.2167440488980309e-05, + "loss": 0.5764975547790527, + "step": 840, + "token_acc": 0.8320033599328014 + }, + { + "epoch": 0.9066666666666666, + "grad_norm": 4.71875, + "learning_rate": 1.1998521321541214e-05, + "loss": 0.5525532722473144, + "step": 850, + "token_acc": 0.836985477356707 + }, + { + "epoch": 0.9173333333333333, + "grad_norm": 5.0625, + "learning_rate": 1.1829006035961947e-05, + "loss": 0.5769608974456787, + "step": 860, + "token_acc": 0.832285471537808 + }, + { + "epoch": 0.928, + "grad_norm": 5.8125, + "learning_rate": 1.165894519519407e-05, + "loss": 0.5438988685607911, + "step": 870, + "token_acc": 0.8355040595399188 + }, + { + "epoch": 0.9386666666666666, + "grad_norm": 5.375, + "learning_rate": 1.148838952491712e-05, + "loss": 0.5477108001708985, + "step": 880, + "token_acc": 0.8355240696483441 + }, + { + "epoch": 0.9493333333333334, + "grad_norm": 4.90625, + "learning_rate": 1.1317389898408188e-05, + "loss": 0.5485364913940429, + "step": 890, + "token_acc": 0.832925491519703 + }, + { + "epoch": 0.96, + "grad_norm": 5.5625, + "learning_rate": 1.1145997321367454e-05, + "loss": 0.5587331771850585, + "step": 900, + "token_acc": 0.8355285376561973 + }, + { + "epoch": 0.9706666666666667, + "grad_norm": 5.15625, + "learning_rate": 1.0974262916704223e-05, + "loss": 0.5252433300018311, + "step": 910, + "token_acc": 0.8404669260700389 + }, + { + "epoch": 0.9813333333333333, + "grad_norm": 5.65625, + "learning_rate": 1.0802237909288005e-05, + "loss": 0.5581695079803467, + "step": 920, + "token_acc": 0.838423477222317 + }, + { + "epoch": 0.992, + "grad_norm": 5.71875, + "learning_rate": 1.062997361066918e-05, + "loss": 0.5427685737609863, + "step": 930, + "token_acc": 0.8367765067440669 + }, + { + "epoch": 1.0021333333333333, + "grad_norm": 4.65625, + "learning_rate": 1.0457521403773823e-05, + "loss": 0.5227243900299072, + "step": 940, + "token_acc": 0.8432694901537632 + }, + { + "epoch": 1.0128, + "grad_norm": 4.84375, + "learning_rate": 1.0284932727577203e-05, + "loss": 0.4229020595550537, + "step": 950, + "token_acc": 0.8669341072038238 + }, + { + "epoch": 1.0234666666666667, + "grad_norm": 5.03125, + "learning_rate": 1.0112259061760605e-05, + "loss": 0.43592014312744143, + "step": 960, + "token_acc": 0.8627684964200477 + }, + { + "epoch": 1.0341333333333333, + "grad_norm": 5.46875, + "learning_rate": 9.939551911355979e-06, + "loss": 0.43202896118164064, + "step": 970, + "token_acc": 0.8636055574381566 + }, + { + "epoch": 1.0448, + "grad_norm": 5.15625, + "learning_rate": 9.766862791383054e-06, + "loss": 0.4390109062194824, + "step": 980, + "token_acc": 0.8663960764417385 + }, + { + "epoch": 1.0554666666666668, + "grad_norm": 5.28125, + "learning_rate": 9.59424321148343e-06, + "loss": 0.416988468170166, + "step": 990, + "token_acc": 0.8692489851150202 + }, + { + "epoch": 1.0661333333333334, + "grad_norm": 4.96875, + "learning_rate": 9.42174466055634e-06, + "loss": 0.4186138153076172, + "step": 1000, + "token_acc": 0.8688482570061518 + }, + { + "epoch": 1.0768, + "grad_norm": 5.28125, + "learning_rate": 9.249418591400539e-06, + "loss": 0.4354249954223633, + "step": 1010, + "token_acc": 0.8667799490229396 + }, + { + "epoch": 1.0874666666666666, + "grad_norm": 5.15625, + "learning_rate": 9.07731640536698e-06, + "loss": 0.451226806640625, + "step": 1020, + "token_acc": 0.8601433994095319 + }, + { + "epoch": 1.0981333333333334, + "grad_norm": 5.0, + "learning_rate": 8.90548943702686e-06, + "loss": 0.4429470539093018, + "step": 1030, + "token_acc": 0.8604789908804228 + }, + { + "epoch": 1.1088, + "grad_norm": 5.4375, + "learning_rate": 8.733988938859545e-06, + "loss": 0.435594367980957, + "step": 1040, + "token_acc": 0.8667980126777454 + }, + { + "epoch": 1.1194666666666666, + "grad_norm": 8.3125, + "learning_rate": 8.562866065965013e-06, + "loss": 0.4241774082183838, + "step": 1050, + "token_acc": 0.8683653601963938 + }, + { + "epoch": 1.1301333333333332, + "grad_norm": 5.4375, + "learning_rate": 8.39217186080532e-06, + "loss": 0.42261734008789065, + "step": 1060, + "token_acc": 0.8686390532544379 + }, + { + "epoch": 1.1408, + "grad_norm": 5.03125, + "learning_rate": 8.221957237979686e-06, + "loss": 0.41465024948120116, + "step": 1070, + "token_acc": 0.8682988602785986 + }, + { + "epoch": 1.1514666666666666, + "grad_norm": 5.46875, + "learning_rate": 8.052272969037702e-06, + "loss": 0.4440279006958008, + "step": 1080, + "token_acc": 0.8630967631736272 + }, + { + "epoch": 1.1621333333333332, + "grad_norm": 5.09375, + "learning_rate": 7.88316966733522e-06, + "loss": 0.4302692413330078, + "step": 1090, + "token_acc": 0.8661821291150064 + }, + { + "epoch": 1.1728, + "grad_norm": 5.0, + "learning_rate": 7.71469777293741e-06, + "loss": 0.4230166435241699, + "step": 1100, + "token_acc": 0.8674463937621832 + }, + { + "epoch": 1.1834666666666667, + "grad_norm": 5.03125, + "learning_rate": 7.546907537573529e-06, + "loss": 0.4408688545227051, + "step": 1110, + "token_acc": 0.8641611190696891 + }, + { + "epoch": 1.1941333333333333, + "grad_norm": 5.34375, + "learning_rate": 7.379849009647848e-06, + "loss": 0.43018126487731934, + "step": 1120, + "token_acc": 0.8686655405405406 + }, + { + "epoch": 1.2048, + "grad_norm": 5.3125, + "learning_rate": 7.213572019311235e-06, + "loss": 0.4404290199279785, + "step": 1130, + "token_acc": 0.8649767638360795 + }, + { + "epoch": 1.2154666666666667, + "grad_norm": 6.625, + "learning_rate": 7.04812616359784e-06, + "loss": 0.40485620498657227, + "step": 1140, + "token_acc": 0.8732010559482245 + }, + { + "epoch": 1.2261333333333333, + "grad_norm": 5.46875, + "learning_rate": 6.883560791631307e-06, + "loss": 0.45158863067626953, + "step": 1150, + "token_acc": 0.8618751596695904 + }, + { + "epoch": 1.2368000000000001, + "grad_norm": 5.59375, + "learning_rate": 6.7199249899049435e-06, + "loss": 0.4398628234863281, + "step": 1160, + "token_acc": 0.8650072211366918 + }, + { + "epoch": 1.2474666666666667, + "grad_norm": 5.46875, + "learning_rate": 6.557267567640217e-06, + "loss": 0.4337770462036133, + "step": 1170, + "token_acc": 0.8668418375995931 + }, + { + "epoch": 1.2581333333333333, + "grad_norm": 5.96875, + "learning_rate": 6.3956370422279625e-06, + "loss": 0.4266934394836426, + "step": 1180, + "token_acc": 0.8647713851864349 + }, + { + "epoch": 1.2688, + "grad_norm": 5.59375, + "learning_rate": 6.235081624756629e-06, + "loss": 0.40284242630004885, + "step": 1190, + "token_acc": 0.8689100954294324 + }, + { + "epoch": 1.2794666666666665, + "grad_norm": 5.0625, + "learning_rate": 6.075649205631904e-06, + "loss": 0.43938732147216797, + "step": 1200, + "token_acc": 0.8652512265268144 + }, + { + "epoch": 1.2901333333333334, + "grad_norm": 6.09375, + "learning_rate": 5.917387340291969e-06, + "loss": 0.43057842254638673, + "step": 1210, + "token_acc": 0.8647868184134534 + }, + { + "epoch": 1.3008, + "grad_norm": 5.53125, + "learning_rate": 5.760343235022703e-06, + "loss": 0.43517169952392576, + "step": 1220, + "token_acc": 0.8625830635542682 + }, + { + "epoch": 1.3114666666666666, + "grad_norm": 5.75, + "learning_rate": 5.604563732876989e-06, + "loss": 0.4466823101043701, + "step": 1230, + "token_acc": 0.8609684210526316 + }, + { + "epoch": 1.3221333333333334, + "grad_norm": 5.5625, + "learning_rate": 5.450095299702392e-06, + "loss": 0.44326114654541016, + "step": 1240, + "token_acc": 0.8649106462268146 + }, + { + "epoch": 1.3328, + "grad_norm": 5.59375, + "learning_rate": 5.296984010281367e-06, + "loss": 0.40932507514953614, + "step": 1250, + "token_acc": 0.869938754678462 + }, + { + "epoch": 1.3434666666666666, + "grad_norm": 5.15625, + "learning_rate": 5.145275534588053e-06, + "loss": 0.42442498207092283, + "step": 1260, + "token_acc": 0.8686963177140913 + }, + { + "epoch": 1.3541333333333334, + "grad_norm": 5.125, + "learning_rate": 4.995015124165883e-06, + "loss": 0.42131719589233396, + "step": 1270, + "token_acc": 0.8664903600068248 + }, + { + "epoch": 1.3648, + "grad_norm": 4.90625, + "learning_rate": 4.8462475986299625e-06, + "loss": 0.42685232162475584, + "step": 1280, + "token_acc": 0.8674472267327579 + }, + { + "epoch": 1.3754666666666666, + "grad_norm": 5.46875, + "learning_rate": 4.69901733229828e-06, + "loss": 0.4310049057006836, + "step": 1290, + "token_acc": 0.8657729509587646 + }, + { + "epoch": 1.3861333333333334, + "grad_norm": 5.5, + "learning_rate": 4.5533682409557745e-06, + "loss": 0.42982044219970705, + "step": 1300, + "token_acc": 0.8655927725219467 + }, + { + "epoch": 1.3968, + "grad_norm": 5.25, + "learning_rate": 4.409343768755135e-06, + "loss": 0.41706085205078125, + "step": 1310, + "token_acc": 0.8671621390739792 + }, + { + "epoch": 1.4074666666666666, + "grad_norm": 5.375, + "learning_rate": 4.266986875258299e-06, + "loss": 0.42982168197631837, + "step": 1320, + "token_acc": 0.8655782082734117 + }, + { + "epoch": 1.4181333333333335, + "grad_norm": 5.0, + "learning_rate": 4.126340022622506e-06, + "loss": 0.40945024490356446, + "step": 1330, + "token_acc": 0.8718840088180431 + }, + { + "epoch": 1.4288, + "grad_norm": 5.84375, + "learning_rate": 3.987445162934689e-06, + "loss": 0.4395137786865234, + "step": 1340, + "token_acc": 0.8654642733862616 + }, + { + "epoch": 1.4394666666666667, + "grad_norm": 5.09375, + "learning_rate": 3.850343725698018e-06, + "loss": 0.4194896697998047, + "step": 1350, + "token_acc": 0.8659327530295272 + }, + { + "epoch": 1.4501333333333333, + "grad_norm": 5.40625, + "learning_rate": 3.7150766054743393e-06, + "loss": 0.4344645500183105, + "step": 1360, + "token_acc": 0.8671583587656833 + }, + { + "epoch": 1.4607999999999999, + "grad_norm": 5.71875, + "learning_rate": 3.5816841496861563e-06, + "loss": 0.4192943572998047, + "step": 1370, + "token_acc": 0.8677099367196853 + }, + { + "epoch": 1.4714666666666667, + "grad_norm": 5.1875, + "learning_rate": 3.4502061465818024e-06, + "loss": 0.4389029979705811, + "step": 1380, + "token_acc": 0.8614711328059249 + }, + { + "epoch": 1.4821333333333333, + "grad_norm": 5.25, + "learning_rate": 3.3206818133674478e-06, + "loss": 0.425324821472168, + "step": 1390, + "token_acc": 0.8668295148247979 + }, + { + "epoch": 1.4928, + "grad_norm": 5.25, + "learning_rate": 3.1931497845093753e-06, + "loss": 0.4116145133972168, + "step": 1400, + "token_acc": 0.8701353998126543 + }, + { + "epoch": 1.5034666666666667, + "grad_norm": 8.0625, + "learning_rate": 3.0676481002101223e-06, + "loss": 0.4524849414825439, + "step": 1410, + "token_acc": 0.8596744107173139 + }, + { + "epoch": 1.5141333333333333, + "grad_norm": 6.1875, + "learning_rate": 2.9442141950618762e-06, + "loss": 0.40929403305053713, + "step": 1420, + "token_acc": 0.8705962637550115 + }, + { + "epoch": 1.5248, + "grad_norm": 5.25, + "learning_rate": 2.8228848868804714e-06, + "loss": 0.4273798942565918, + "step": 1430, + "token_acc": 0.8684869739478958 + }, + { + "epoch": 1.5354666666666668, + "grad_norm": 5.71875, + "learning_rate": 2.7036963657234105e-06, + "loss": 0.421265983581543, + "step": 1440, + "token_acc": 0.8716198925189798 + }, + { + "epoch": 1.5461333333333334, + "grad_norm": 5.75, + "learning_rate": 2.5866841830950994e-06, + "loss": 0.4097298622131348, + "step": 1450, + "token_acc": 0.8729807855806836 + }, + { + "epoch": 1.5568, + "grad_norm": 5.84375, + "learning_rate": 2.47188324134255e-06, + "loss": 0.4039015293121338, + "step": 1460, + "token_acc": 0.8734842703298566 + }, + { + "epoch": 1.5674666666666668, + "grad_norm": 5.84375, + "learning_rate": 2.3593277832447405e-06, + "loss": 0.3996889591217041, + "step": 1470, + "token_acc": 0.8748932536293766 + }, + { + "epoch": 1.5781333333333334, + "grad_norm": 6.15625, + "learning_rate": 2.2490513817986757e-06, + "loss": 0.40860567092895506, + "step": 1480, + "token_acc": 0.8692588504966465 + }, + { + "epoch": 1.5888, + "grad_norm": 6.21875, + "learning_rate": 2.141086930205255e-06, + "loss": 0.4375762939453125, + "step": 1490, + "token_acc": 0.8629623316856997 + }, + { + "epoch": 1.5994666666666668, + "grad_norm": 5.1875, + "learning_rate": 2.035466632057905e-06, + "loss": 0.424249267578125, + "step": 1500, + "token_acc": 0.8679070550597744 + }, + { + "epoch": 1.6101333333333332, + "grad_norm": 5.0, + "learning_rate": 1.9322219917369e-06, + "loss": 0.40370688438415525, + "step": 1510, + "token_acc": 0.871133586177834 + }, + { + "epoch": 1.6208, + "grad_norm": 5.28125, + "learning_rate": 1.8313838050122423e-06, + "loss": 0.4515178680419922, + "step": 1520, + "token_acc": 0.8593498005262711 + }, + { + "epoch": 1.6314666666666666, + "grad_norm": 5.0625, + "learning_rate": 1.7329821498579257e-06, + "loss": 0.43173723220825194, + "step": 1530, + "token_acc": 0.8647822765469825 + }, + { + "epoch": 1.6421333333333332, + "grad_norm": 5.125, + "learning_rate": 1.6370463774802759e-06, + "loss": 0.42908735275268556, + "step": 1540, + "token_acc": 0.8682573498082659 + }, + { + "epoch": 1.6528, + "grad_norm": 5.34375, + "learning_rate": 1.5436051035630962e-06, + "loss": 0.4312245845794678, + "step": 1550, + "token_acc": 0.8645736105218498 + }, + { + "epoch": 1.6634666666666666, + "grad_norm": 5.65625, + "learning_rate": 1.4526861997321794e-06, + "loss": 0.4247132301330566, + "step": 1560, + "token_acc": 0.8694854474188976 + }, + { + "epoch": 1.6741333333333333, + "grad_norm": 5.40625, + "learning_rate": 1.3643167852417894e-06, + "loss": 0.4231447219848633, + "step": 1570, + "token_acc": 0.8674972640794679 + }, + { + "epoch": 1.6848, + "grad_norm": 5.4375, + "learning_rate": 1.278523218885518e-06, + "loss": 0.40172972679138186, + "step": 1580, + "token_acc": 0.8752116491703352 + }, + { + "epoch": 1.6954666666666667, + "grad_norm": 5.3125, + "learning_rate": 1.1953310911340165e-06, + "loss": 0.4114649295806885, + "step": 1590, + "token_acc": 0.8714602524735585 + }, + { + "epoch": 1.7061333333333333, + "grad_norm": 5.1875, + "learning_rate": 1.1147652165018597e-06, + "loss": 0.40552978515625, + "step": 1600, + "token_acc": 0.8678014905149052 + }, + { + "epoch": 1.7168, + "grad_norm": 5.53125, + "learning_rate": 1.0368496261459004e-06, + "loss": 0.4324502944946289, + "step": 1610, + "token_acc": 0.862758329818642 + }, + { + "epoch": 1.7274666666666667, + "grad_norm": 5.46875, + "learning_rate": 9.616075606972597e-07, + "loss": 0.4126314163208008, + "step": 1620, + "token_acc": 0.8694481830417228 + }, + { + "epoch": 1.7381333333333333, + "grad_norm": 5.75, + "learning_rate": 8.890614633291095e-07, + "loss": 0.43532743453979494, + "step": 1630, + "token_acc": 0.8601766904519198 + }, + { + "epoch": 1.7488000000000001, + "grad_norm": 5.15625, + "learning_rate": 8.192329730623471e-07, + "loss": 0.4172046661376953, + "step": 1640, + "token_acc": 0.8675934559633806 + }, + { + "epoch": 1.7594666666666665, + "grad_norm": 5.34375, + "learning_rate": 7.521429183111139e-07, + "loss": 0.4211602687835693, + "step": 1650, + "token_acc": 0.869084099421178 + }, + { + "epoch": 1.7701333333333333, + "grad_norm": 5.3125, + "learning_rate": 6.878113106700946e-07, + "loss": 0.4197425842285156, + "step": 1660, + "token_acc": 0.8680926916221033 + }, + { + "epoch": 1.7808000000000002, + "grad_norm": 5.28125, + "learning_rate": 6.262573389454773e-07, + "loss": 0.43222551345825194, + "step": 1670, + "token_acc": 0.8637358935489304 + }, + { + "epoch": 1.7914666666666665, + "grad_norm": 6.09375, + "learning_rate": 5.674993634313242e-07, + "loss": 0.4256401062011719, + "step": 1680, + "token_acc": 0.8653747652381766 + }, + { + "epoch": 1.8021333333333334, + "grad_norm": 5.03125, + "learning_rate": 5.115549104330575e-07, + "loss": 0.39786996841430666, + "step": 1690, + "token_acc": 0.8736002714625043 + }, + { + "epoch": 1.8128, + "grad_norm": 7.09375, + "learning_rate": 4.5844066703973676e-07, + "loss": 0.42459850311279296, + "step": 1700, + "token_acc": 0.8695799745439118 + }, + { + "epoch": 1.8234666666666666, + "grad_norm": 5.59375, + "learning_rate": 4.081724761466288e-07, + "loss": 0.44160709381103513, + "step": 1710, + "token_acc": 0.8608688288593446 + }, + { + "epoch": 1.8341333333333334, + "grad_norm": 5.5, + "learning_rate": 3.6076533172959895e-07, + "loss": 0.4103675842285156, + "step": 1720, + "token_acc": 0.8672603545324709 + }, + { + "epoch": 1.8448, + "grad_norm": 5.5625, + "learning_rate": 3.1623337437272084e-07, + "loss": 0.43485474586486816, + "step": 1730, + "token_acc": 0.8642153532608695 + }, + { + "epoch": 1.8554666666666666, + "grad_norm": 5.4375, + "learning_rate": 2.745898870504116e-07, + "loss": 0.4110551357269287, + "step": 1740, + "token_acc": 0.8730118009235506 + }, + { + "epoch": 1.8661333333333334, + "grad_norm": 5.21875, + "learning_rate": 2.3584729116541305e-07, + "loss": 0.41416378021240235, + "step": 1750, + "token_acc": 0.86998136540742 + }, + { + "epoch": 1.8768, + "grad_norm": 5.34375, + "learning_rate": 2.0001714284372253e-07, + "loss": 0.43006277084350586, + "step": 1760, + "token_acc": 0.8696650229552797 + }, + { + "epoch": 1.8874666666666666, + "grad_norm": 5.78125, + "learning_rate": 1.6711012948764426e-07, + "loss": 0.40975046157836914, + "step": 1770, + "token_acc": 0.8725116476069462 + }, + { + "epoch": 1.8981333333333335, + "grad_norm": 5.625, + "learning_rate": 1.371360665879584e-07, + "loss": 0.406182861328125, + "step": 1780, + "token_acc": 0.8718765721952038 + }, + { + "epoch": 1.9088, + "grad_norm": 5.25, + "learning_rate": 1.1010389479615302e-07, + "loss": 0.4136258602142334, + "step": 1790, + "token_acc": 0.870780770542107 + }, + { + "epoch": 1.9194666666666667, + "grad_norm": 6.4375, + "learning_rate": 8.60216772576139e-08, + "loss": 0.4269017219543457, + "step": 1800, + "token_acc": 0.8661390519955748 + }, + { + "epoch": 1.9301333333333335, + "grad_norm": 5.6875, + "learning_rate": 6.489659720655295e-08, + "loss": 0.42894792556762695, + "step": 1810, + "token_acc": 0.8644270122783083 + }, + { + "epoch": 1.9407999999999999, + "grad_norm": 5.34375, + "learning_rate": 4.673495582339649e-08, + "loss": 0.42904911041259763, + "step": 1820, + "token_acc": 0.8654405474764756 + }, + { + "epoch": 1.9514666666666667, + "grad_norm": 5.375, + "learning_rate": 3.154217035526874e-08, + "loss": 0.42716250419616697, + "step": 1830, + "token_acc": 0.869757174392936 + }, + { + "epoch": 1.9621333333333333, + "grad_norm": 5.28125, + "learning_rate": 1.932277250014214e-08, + "loss": 0.42876396179199217, + "step": 1840, + "token_acc": 0.8661888701517707 + }, + { + "epoch": 1.9727999999999999, + "grad_norm": 5.5625, + "learning_rate": 1.008040705511748e-08, + "loss": 0.44731903076171875, + "step": 1850, + "token_acc": 0.8617075232459848 + }, + { + "epoch": 1.9834666666666667, + "grad_norm": 5.40625, + "learning_rate": 3.8178308292624585e-09, + "loss": 0.4366297721862793, + "step": 1860, + "token_acc": 0.8642533936651584 + }, + { + "epoch": 1.9941333333333333, + "grad_norm": 5.59375, + "learning_rate": 5.369118213094382e-10, + "loss": 0.4206860542297363, + "step": 1870, + "token_acc": 0.8676668914362778 + } + ], + "logging_steps": 10, + "max_steps": 1876, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 8.012174212254925e+17, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..bcb295c --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cdf8cebbd77f195e00b8a3ab06b991da57afbdcc88a2b676402363dc1798fb +size 7057 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833