Upload folder using huggingface_hub

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77160a64e08f6464de6b139897892d443cb98c7672066843a2b134a824b9fc9
+oid sha256:d094eec375253e7a02e0ef6325eee1379f3223fbca55268204fd05c60ee76630
 size 4949453792

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c67a64120dee4b553d682a97db8a2b3294c97efc31bba241e067c389ee5bc6
+oid sha256:d54442a4905e28a83a89f76faa0c958b577c5b756ba026d4b23ecf1ee31c3f3e
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21946a9f73b60f96801bb956b8e88b16b4955858b9651772fb1778b7342a5f58
+oid sha256:06d744b227f8ed7a3a96014035dfd7ea8419bb567903a03a8c7a0349c45d731b
 size 4546807800

sft_args.json

@@ -10,7 +10,7 @@
   "additional_trainable_parameters": [],
   "tuner_backend": "peft",
   "template_type": "llama",
-  "output_dir": "/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0103_model/mistral-7b-instruct-v3/v0-20250103-203956",
+  "output_dir": "/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0112_model_no_path_POSCAR/mistral-7b-instruct-v3/v1-20250112-162032",
   "add_output_dir_suffix": true,
   "ddp_backend": null,
   "ddp_find_unused_parameters": null,
@@ -30,7 +30,7 @@
   "model_kwargs": null,
   "loss_name": null,
   "dataset": [
-    "/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/data/origin_data_0103/0103_merged_metal_alloy.json"
+    "/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/data/0112_all_product/merged_metal_alloy_molecule_POSCAR_0112.json"
   ],
   "val_dataset": [],
   "dataset_seed": 42,
@@ -132,7 +132,7 @@
   "batch_size": 1,
   "eval_batch_size": 1,
   "auto_find_batch_size": false,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "max_steps": -1,
   "optim": "adamw_torch",
   "adam_beta1": 0.9,
@@ -168,7 +168,7 @@
   "use_flash_attn": null,
   "ignore_args_error": false,
   "check_model_is_latest": true,
-  "logging_dir": "/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0103_model/mistral-7b-instruct-v3/v0-20250103-203956/runs",
+  "logging_dir": "/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0112_model_no_path_POSCAR/mistral-7b-instruct-v3/v1-20250112-162032/runs",
   "report_to": [
     "tensorboard"
   ],
@@ -244,5 +244,5 @@
   "load_in_4bit": false,
   "load_in_8bit": false,
   "train_sampler_random": true,
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0103_model/mistral-7b-instruct-v3/v0-20250103-203956', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=3, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0103_model/mistral-7b-instruct-v3/v0-20250103-203956/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, 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=None, jit_mode_eval=False, use_ipex=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=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0103_model/mistral-7b-instruct-v3/v0-20250103-203956', 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), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], 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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, eval_use_gather_object=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"bos_token_id\": 1,\n  \"eos_token_id\": 2,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 2\n}\n, train_sampler_random=True, acc_strategy='token', loss_name=None, additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
+  "training_args": "Seq2SeqTrainingArguments(output_dir='/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0112_model_no_path_POSCAR/mistral-7b-instruct-v3/v1-20250112-162032', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=2, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0112_model_no_path_POSCAR/mistral-7b-instruct-v3/v1-20250112-162032/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=2, 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=None, jit_mode_eval=False, use_ipex=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=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/nesi/nobackup/uoa04081/wxy/computational_gpt/final_manuscript/3.3/model/0112_model_no_path_POSCAR/mistral-7b-instruct-v3/v1-20250112-162032', 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), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], 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=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, eval_use_gather_object=False, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n  \"bos_token_id\": 1,\n  \"eos_token_id\": 2,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 2\n}\n, train_sampler_random=True, acc_strategy='token', loss_name=None, additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
 }