| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02820476660555634, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005640953321111268, | |
| "eval_loss": 3.325026750564575, | |
| "eval_runtime": 53.1499, | |
| "eval_samples_per_second": 14.055, | |
| "eval_steps_per_second": 7.037, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028204766605556338, | |
| "grad_norm": 0.7551614046096802, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3613, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0056409533211112676, | |
| "grad_norm": 1.139972448348999, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3191, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0056409533211112676, | |
| "eval_loss": 3.2550063133239746, | |
| "eval_runtime": 55.9381, | |
| "eval_samples_per_second": 13.354, | |
| "eval_steps_per_second": 6.686, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008461429981666902, | |
| "grad_norm": 1.1269532442092896, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0919, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011281906642222535, | |
| "grad_norm": 1.5638645887374878, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0077, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011281906642222535, | |
| "eval_loss": 2.887854814529419, | |
| "eval_runtime": 56.3579, | |
| "eval_samples_per_second": 13.255, | |
| "eval_steps_per_second": 6.636, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01410238330277817, | |
| "grad_norm": 1.5099170207977295, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.878, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016922859963333804, | |
| "grad_norm": 1.288618803024292, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8783, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016922859963333804, | |
| "eval_loss": 2.770209312438965, | |
| "eval_runtime": 56.3307, | |
| "eval_samples_per_second": 13.261, | |
| "eval_steps_per_second": 6.639, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019743336623889437, | |
| "grad_norm": 1.306066870689392, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.7098, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02256381328444507, | |
| "grad_norm": 1.313513159751892, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.7063, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02256381328444507, | |
| "eval_loss": 2.7314085960388184, | |
| "eval_runtime": 56.3595, | |
| "eval_samples_per_second": 13.254, | |
| "eval_steps_per_second": 6.636, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025384289945000704, | |
| "grad_norm": 1.1740163564682007, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8209, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02820476660555634, | |
| "grad_norm": 1.3812577724456787, | |
| "learning_rate": 0.0, | |
| "loss": 2.773, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02820476660555634, | |
| "eval_loss": 2.724761724472046, | |
| "eval_runtime": 56.5648, | |
| "eval_samples_per_second": 13.206, | |
| "eval_steps_per_second": 6.612, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8143670712729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |