Upload folder using huggingface_hub

'training_args.json

@@ -0,0 +1 @@
+{"output_dir": "outputs", "overwrite_output_dir": true, "do_train": false, "do_eval": false, "do_predict": false, "evaluation_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 4, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 4, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 0.0002, "weight_decay": 0.01, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 2, "max_steps": 75, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 1, "log_level": "passive", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "outputs/runs/Mar12_18-42-25_76bcf0692f4a", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 1, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 500, "save_total_limit": null, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "past_index": -1, "run_name": "outputs", "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, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"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": "paged_adamw_8bit", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["wandb"], "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": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": {"use_reentrant": 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, "dispatch_batches": null, "split_batches": false, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null}

README.md

@@ -1,3 +1,21 @@
 ---
-license: apache-2.0
+library_name: peft
 ---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1166f16f3a7ee05aaa182df525523a4f23340b0ae78ea26c726b4ccee8b4cef4
+size 340327122

optimizer_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff12c0b78f98f955b821346358ca5ce4f9c395898cce1e12fbc33112b9df75b
+size 170961840

scheduler_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a6ac705acf1444d806a81ed3a5df37eb495f15a726c60396089b7d85d1c528
+size 1088