| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014665982254161472, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029331964508322946, | |
| "eval_loss": 1.800489902496338, | |
| "eval_runtime": 49.0759, | |
| "eval_samples_per_second": 29.261, | |
| "eval_steps_per_second": 14.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014665982254161473, | |
| "grad_norm": 1.0147321224212646, | |
| "learning_rate": 5e-05, | |
| "loss": 1.847, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0029331964508322946, | |
| "grad_norm": 0.6598513722419739, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8272, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0029331964508322946, | |
| "eval_loss": 1.7177491188049316, | |
| "eval_runtime": 47.9652, | |
| "eval_samples_per_second": 29.938, | |
| "eval_steps_per_second": 14.969, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004399794676248442, | |
| "grad_norm": 0.576564371585846, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005866392901664589, | |
| "grad_norm": 0.6612115502357483, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6475, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005866392901664589, | |
| "eval_loss": 1.6254923343658447, | |
| "eval_runtime": 47.7129, | |
| "eval_samples_per_second": 30.097, | |
| "eval_steps_per_second": 15.048, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007332991127080736, | |
| "grad_norm": 0.5590262413024902, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6559, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008799589352496884, | |
| "grad_norm": 2.4237823486328125, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7524, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008799589352496884, | |
| "eval_loss": 1.596480131149292, | |
| "eval_runtime": 47.8654, | |
| "eval_samples_per_second": 30.001, | |
| "eval_steps_per_second": 15.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010266187577913031, | |
| "grad_norm": 0.6278929710388184, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6188, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.011732785803329178, | |
| "grad_norm": 0.6061598658561707, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7754, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011732785803329178, | |
| "eval_loss": 1.586182951927185, | |
| "eval_runtime": 47.7566, | |
| "eval_samples_per_second": 30.069, | |
| "eval_steps_per_second": 15.035, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013199384028745325, | |
| "grad_norm": 0.5589456558227539, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5946, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014665982254161472, | |
| "grad_norm": 0.8638172745704651, | |
| "learning_rate": 0.0, | |
| "loss": 1.5911, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014665982254161472, | |
| "eval_loss": 1.584321141242981, | |
| "eval_runtime": 47.47, | |
| "eval_samples_per_second": 30.251, | |
| "eval_steps_per_second": 15.125, | |
| "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": 389373298212864.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |