Init

adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "openlm-research/open_llama_3b_v2",
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa0394a9bafd4015b5d26d7da327811524d63a317c6c23e9c7d250011af39bd
+size 5361901

checkpoint-53500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812d45ff9000d037ea1b1438461bfbc695842e5cdf68947cabb1fb19ed9ac3b0
+size 10736709

checkpoint-53500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be99df93c65c64af89fc1d135a2fdda61f3fd44d07b70a43f904b2f16ec35fe
+size 5361901

checkpoint-53500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fdadfa42e325068d0a2240c5e69fedf12896ae96f94f3319cd032e71e35b0c0
+size 14575

checkpoint-53500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c10e85608f0060eca8d21c7596fce64d15ec83ba66cdaa48c094cd8b1525298
+size 557

checkpoint-53500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7462c7717f86e9e32e0ea74c7c53a04bf2926a5063419d01d5d4bb53aef63e7
+size 627

checkpoint-53500/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-53500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
+size 511574

checkpoint-53500/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-53500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f77695c4c715a980d6c21668550d6992d5fc2d87548441ca3f4724bf1d46a9
+size 3643

finetune_args.json

@@ -0,0 +1,27 @@
+{
+  "micro_batch_size": 1,
+  "gradient_accumulation_steps": 1,
+  "num_train_epochs": 2,
+  "learning_rate": 0.0003,
+  "cutoff_len": 512,
+  "val_set_size": 0,
+  "lora_r": 4,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "lora_modules_to_save": [],
+  "train_on_inputs": true,
+  "group_by_length": false,
+  "load_in_8bit": false,
+  "fp16": true,
+  "bf16": false,
+  "gradient_checkpointing": false,
+  "save_steps": 500,
+  "save_total_limit": 5,
+  "logging_steps": 10,
+  "additional_training_arguments": null,
+  "additional_lora_config": null
+}

info.json

@@ -0,0 +1,9 @@
+{
+  "base_model": "openlm-research/open_llama_3b_v2",
+  "prompt_template": "alpaca",
+  "dataset_name": "N/A (from text input)",
+  "dataset_rows": 26981,
+  "trained_on_machine": "d8cc48c8fbe1",
+  "timestamp": 1689869784.2048044,
+  "tuner_version": "06c08436"
+}

train_output.json

@@ -0,0 +1,11 @@
+[
+  53962,
+  0.6364423901274552,
+  {
+    "train_runtime": 6417.4177,
+    "train_samples_per_second": 8.409,
+    "train_steps_per_second": 8.409,
+    "train_loss": 0.6364423901274552,
+    "epoch": 2.0
+  }
+]

trainer_args.json

@@ -0,0 +1,113 @@
+{
+  "output_dir": "/root/LLaMA-LoRA-Tuner/lora_models/ru-llama-3b",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": false,
+  "do_predict": false,
+  "evaluation_strategy": "no",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 1,
+  "per_device_eval_batch_size": 8,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 1,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "learning_rate": 0.0003,
+  "weight_decay": 0.0,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 2,
+  "max_steps": -1,
+  "lr_scheduler_type": "linear",
+  "warmup_ratio": 0.0,
+  "warmup_steps": 100,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "/root/LLaMA-LoRA-Tuner/lora_models/ru-llama-3b/runs/Jul20_16-21-42_d8cc48c8fbe1",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 10,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 500,
+  "save_total_limit": 5,
+  "save_safetensors": false,
+  "save_on_each_node": false,
+  "no_cuda": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": false,
+  "fp16": true,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "cuda_amp",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": -1,
+  "xpu_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": null,
+  "dataloader_num_workers": 0,
+  "past_index": -1,
+  "run_name": "/root/LLaMA-LoRA-Tuner/lora_models/ru-llama-3b",
+  "disable_tqdm": false,
+  "remove_unused_columns": true,
+  "label_names": null,
+  "load_best_model_at_end": false,
+  "metric_for_best_model": null,
+  "greater_is_better": null,
+  "ignore_data_skip": false,
+  "sharded_ddp": [],
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "fsdp_min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [],
+  "ddp_find_unused_parameters": null,
+  "ddp_bucket_cap_mb": null,
+  "dataloader_pin_memory": true,
+  "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": "<HUB_TOKEN>",
+  "hub_private_repo": false,
+  "gradient_checkpointing": false,
+  "include_inputs_for_metrics": false,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null
+}