| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "/kaggle/working/new_downloads22/checkpoint-317", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 317, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07886435331230283, | |
| "grad_norm": 8.923051834106445, | |
| "learning_rate": 1.75e-05, | |
| "loss": 9.5858, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15772870662460567, | |
| "grad_norm": 7.801741600036621, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 7.4178, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23659305993690852, | |
| "grad_norm": 6.98698091506958, | |
| "learning_rate": 5.916666666666667e-05, | |
| "loss": 6.5061, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.31545741324921134, | |
| "grad_norm": 15.704840660095215, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3719, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3943217665615142, | |
| "grad_norm": 18.519981384277344, | |
| "learning_rate": 9.9983922829582e-05, | |
| "loss": 6.2496, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.47318611987381703, | |
| "grad_norm": 5.073540210723877, | |
| "learning_rate": 9.958199356913184e-05, | |
| "loss": 6.1319, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5520504731861199, | |
| "grad_norm": 5.464381217956543, | |
| "learning_rate": 9.918006430868168e-05, | |
| "loss": 6.0139, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6309148264984227, | |
| "grad_norm": 7.70945405960083, | |
| "learning_rate": 9.877813504823152e-05, | |
| "loss": 5.8082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7097791798107256, | |
| "grad_norm": 10.696139335632324, | |
| "learning_rate": 9.837620578778135e-05, | |
| "loss": 5.4794, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.7886435331230284, | |
| "grad_norm": 11.641499519348145, | |
| "learning_rate": 9.79742765273312e-05, | |
| "loss": 5.0549, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8675078864353313, | |
| "grad_norm": 9.7868013381958, | |
| "learning_rate": 9.757234726688104e-05, | |
| "loss": 4.5482, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.9463722397476341, | |
| "grad_norm": 8.010425567626953, | |
| "learning_rate": 9.717041800643088e-05, | |
| "loss": 4.0112, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_cer": 1.0, | |
| "eval_loss": 3.591109037399292, | |
| "eval_runtime": 822.2984, | |
| "eval_samples_per_second": 2.674, | |
| "eval_steps_per_second": 0.022, | |
| "eval_wer": 1.0, | |
| "step": 317 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 6340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2485467588608e+18, | |
| "train_batch_size": 160, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |