delete

README.md

@@ -1,3 +0,0 @@
----
-license: apache-2.0
----

adapter_config.json

@@ -1,20 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/home/vmagent/app/dataset/mpt-7b",
-  "bias": "none",
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "revision": null,
-  "target_modules": [
-    "Wqkv"
-  ],
-  "task_type": "CAUSAL_LM"
-}

adapter_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:55b11dd03bbca4cc535ff26657feb93f34dbf3a8361c4b2bb6fa98a6e5d2c73d
-size 16799089

all_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 1.0,
-    "eval_loss": 1.0701578855514526,
-    "eval_runtime": 3713.8306,
-    "eval_samples": 15601,
-    "eval_samples_per_second": 4.201,
-    "eval_steps_per_second": 0.525,
-    "eval_tokens": 1722455
-}

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 1.0,
-    "eval_loss": 1.0701578855514526,
-    "eval_runtime": 3713.8306,
-    "eval_samples": 15601,
-    "eval_samples_per_second": 4.201,
-    "eval_steps_per_second": 0.525,
-    "eval_tokens": 1722455
-}

mpt-lora-run-1epoch.log

@@ -1,159 +0,0 @@
-07/25/2023 13:42:21 - WARNING - __main__ -   Process rank: 0, device: cpu
-distributed training: True, 16-bits training: True
-07/25/2023 13:42:21 - INFO - __main__ -   Training/evaluation parameters TrainingArguments(
-_n_gpu=0,
-adafactor=False,
-adam_beta1=0.9,
-adam_beta2=0.999,
-adam_epsilon=1e-08,
-auto_find_batch_size=False,
-bf16=True,
-bf16_full_eval=False,
-data_seed=None,
-dataloader_drop_last=False,
-dataloader_num_workers=0,
-dataloader_pin_memory=True,
-ddp_backend=None,
-ddp_broadcast_buffers=None,
-ddp_bucket_cap_mb=None,
-ddp_find_unused_parameters=None,
-ddp_timeout=1800,
-debug=[],
-deepspeed=None,
-disable_tqdm=False,
-do_eval=True,
-do_predict=False,
-do_train=True,
-eval_accumulation_steps=None,
-eval_delay=0,
-eval_steps=None,
-evaluation_strategy=no,
-fp16=False,
-fp16_backend=auto,
-fp16_full_eval=False,
-fp16_opt_level=O1,
-fsdp=[],
-fsdp_config={'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
-fsdp_min_num_params=0,
-fsdp_transformer_layer_cls_to_wrap=None,
-full_determinism=False,
-gradient_accumulation_steps=1,
-gradient_checkpointing=False,
-greater_is_better=None,
-group_by_length=False,
-half_precision_backend=auto,
-hub_model_id=None,
-hub_private_repo=False,
-hub_strategy=every_save,
-hub_token=<HUB_TOKEN>,
-ignore_data_skip=False,
-include_inputs_for_metrics=False,
-jit_mode_eval=False,
-label_names=None,
-label_smoothing_factor=0.0,
-learning_rate=0.0001,
-length_column_name=length,
-load_best_model_at_end=False,
-local_rank=0,
-log_level=info,
-log_level_replica=warning,
-log_on_each_node=True,
-logging_dir=./mpt_peft_finetuned_model/runs/Jul25_13-42-21_a4bf019308e9,
-logging_first_step=False,
-logging_nan_inf_filter=True,
-logging_steps=100,
-logging_strategy=steps,
-lr_scheduler_type=linear,
-max_grad_norm=1.0,
-max_steps=-1,
-metric_for_best_model=None,
-mp_parameters=,
-no_cuda=True,
-num_train_epochs=1.0,
-optim=adamw_hf,
-optim_args=None,
-output_dir=./mpt_peft_finetuned_model,
-overwrite_output_dir=False,
-past_index=-1,
-per_device_eval_batch_size=8,
-per_device_train_batch_size=8,
-prediction_loss_only=False,
-push_to_hub=False,
-push_to_hub_model_id=None,
-push_to_hub_organization=None,
-push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
-ray_scope=last,
-remove_unused_columns=True,
-report_to=['wandb'],
-resume_from_checkpoint=None,
-run_name=./mpt_peft_finetuned_model,
-save_on_each_node=False,
-save_safetensors=False,
-save_steps=500,
-save_strategy=epoch,
-save_total_limit=1,
-seed=42,
-sharded_ddp=[],
-skip_memory_metrics=True,
-tf32=None,
-torch_compile=False,
-torch_compile_backend=None,
-torch_compile_mode=None,
-torchdynamo=None,
-tpu_metrics_debug=False,
-tpu_num_cores=None,
-use_ipex=False,
-use_legacy_prediction_loop=False,
-use_mps_device=False,
-warmup_ratio=0.0,
-warmup_steps=0,
-weight_decay=0.0,
-xpu_backend=None,
-)
-07/25/2023 13:42:21 - WARNING - datasets.builder -   Found cached dataset json (/root/.cache/huggingface/datasets/json/default-5bec83249d5e85ed/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
-07/25/2023 13:42:22 - WARNING - datasets.builder -   Found cached dataset json (/root/.cache/huggingface/datasets/json/default-5bec83249d5e85ed/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
-07/25/2023 13:42:22 - WARNING - datasets.builder -   Found cached dataset json (/root/.cache/huggingface/datasets/json/default-5bec83249d5e85ed/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
-You are using config.init_device='cpu', but you can also use config.init_device="meta" with Composer + FSDP for fast initialization.
-07/25/2023 13:42:30 - WARNING - datasets.arrow_dataset -   Loading cached processed dataset at /root/.cache/huggingface/datasets/json/default-5bec83249d5e85ed/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-100c7c6f488a1310.arrow
-07/25/2023 13:42:37 - INFO - __main__ -   Using data collator of type DataCollatorForSeq2Seq
-trainable params: 4,194,304 || all params: 6,653,480,960 || trainable%: 0.0630392425441013
-07/25/2023 13:42:49 - INFO - __main__ -   *** Training ***
-huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
-To disable this warning, you can either:
-	- Avoid using `tokenizers` before the fork if possible
-	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
-huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
-To disable this warning, you can either:
-	- Avoid using `tokenizers` before the fork if possible
-	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
-huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
-To disable this warning, you can either:
-	- Avoid using `tokenizers` before the fork if possible
-	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
-huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
-To disable this warning, you can either:
-	- Avoid using `tokenizers` before the fork if possible
-	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
-huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
-To disable this warning, you can either:
-	- Avoid using `tokenizers` before the fork if possible
-	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
-{'loss': 1.197, 'learning_rate': 8.984771573604062e-05, 'epoch': 0.1}
-{'loss': 1.0836, 'learning_rate': 7.969543147208121e-05, 'epoch': 0.2}
-{'loss': 1.0757, 'learning_rate': 6.954314720812183e-05, 'epoch': 0.3}
-{'loss': 1.0668, 'learning_rate': 5.939086294416244e-05, 'epoch': 0.41}
-{'loss': 1.0582, 'learning_rate': 4.9238578680203045e-05, 'epoch': 0.51}
-{'loss': 1.0494, 'learning_rate': 3.9086294416243655e-05, 'epoch': 0.61}
-{'loss': 1.0502, 'learning_rate': 2.8934010152284264e-05, 'epoch': 0.71}
-{'loss': 1.0407, 'learning_rate': 1.8781725888324874e-05, 'epoch': 0.81}
-{'loss': 1.0421, 'learning_rate': 8.629441624365483e-06, 'epoch': 0.91}
-{'train_runtime': 34313.0928, 'train_samples_per_second': 0.23, 'train_steps_per_second': 0.029, 'train_loss': 1.0698003004045051, 'epoch': 1.0}
-07/25/2023 23:14:42 - INFO - __main__ -   *** Evaluate ***
-***** eval metrics *****
-  epoch                   =        1.0
-  eval_loss               =     1.0702
-  eval_runtime            = 1:01:53.83
-  eval_samples            =      15601
-  eval_samples_per_second =      4.201
-  eval_steps_per_second   =      0.525
-  eval_tokens             =    1722455

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:55b11dd03bbca4cc535ff26657feb93f34dbf3a8361c4b2bb6fa98a6e5d2c73d
-size 16799089