Download trainer_state.json from Dongkkka/PATs_upload_test_model: direct link, hf CLI and curl.
- Browser
- Download file 2.15 kB
-
https://huggingface.co/Dongkkka/PATs_upload_test_model/resolve/main/trainer_state.json
- Command line
-
hf download hf://Dongkkka/PATs_upload_test_model/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Dongkkka/PATs_upload_test_model/resolve/main/trainer_state.json
2.15 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "grad_norm": 0.29096701741218567, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.2375, | |
| "step": 10 | |
| }, | |
| { | |
| "grad_norm": 0.16030608117580414, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.1952, | |
| "step": 20 | |
| }, | |
| { | |
| "grad_norm": 0.13103239238262177, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.2002, | |
| "step": 30 | |
| }, | |
| { | |
| "grad_norm": 0.11081837117671967, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.191, | |
| "step": 40 | |
| }, | |
| { | |
| "grad_norm": 0.15927913784980774, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 1.194, | |
| "step": 50 | |
| }, | |
| { | |
| "grad_norm": 0.2992898225784302, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 1.1546, | |
| "step": 60 | |
| }, | |
| { | |
| "grad_norm": 0.402879923582077, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 1.1042, | |
| "step": 70 | |
| }, | |
| { | |
| "grad_norm": 0.3662746846675873, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 1.091, | |
| "step": 80 | |
| }, | |
| { | |
| "grad_norm": 0.31836211681365967, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 1.0746, | |
| "step": 90 | |
| }, | |
| { | |
| "grad_norm": 0.2885839641094208, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 1.0781, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |