| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07601672367920942, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015203344735841885, | |
| "eval_loss": 2.2542741298675537, | |
| "eval_runtime": 35.0676, | |
| "eval_samples_per_second": 7.899, | |
| "eval_steps_per_second": 3.964, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007601672367920942, | |
| "grad_norm": 1.3452098369598389, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2456, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015203344735841885, | |
| "grad_norm": 1.3729311227798462, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0814, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015203344735841885, | |
| "eval_loss": 2.0321643352508545, | |
| "eval_runtime": 35.3391, | |
| "eval_samples_per_second": 7.838, | |
| "eval_steps_per_second": 3.933, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02280501710376283, | |
| "grad_norm": 1.9186620712280273, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03040668947168377, | |
| "grad_norm": 2.302685499191284, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.714, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03040668947168377, | |
| "eval_loss": 1.6984518766403198, | |
| "eval_runtime": 35.5062, | |
| "eval_samples_per_second": 7.801, | |
| "eval_steps_per_second": 3.915, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03800836183960471, | |
| "grad_norm": 1.996578574180603, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8536, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04561003420752566, | |
| "grad_norm": 2.080104351043701, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04561003420752566, | |
| "eval_loss": 1.656833291053772, | |
| "eval_runtime": 35.495, | |
| "eval_samples_per_second": 7.804, | |
| "eval_steps_per_second": 3.916, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0532117065754466, | |
| "grad_norm": 1.8273946046829224, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.56, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06081337894336754, | |
| "grad_norm": 1.7108153104782104, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5956, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06081337894336754, | |
| "eval_loss": 1.6338121891021729, | |
| "eval_runtime": 35.5531, | |
| "eval_samples_per_second": 7.791, | |
| "eval_steps_per_second": 3.91, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06841505131128849, | |
| "grad_norm": 1.9220895767211914, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6862, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07601672367920942, | |
| "grad_norm": 1.6117706298828125, | |
| "learning_rate": 0.0, | |
| "loss": 1.6049, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07601672367920942, | |
| "eval_loss": 1.6271249055862427, | |
| "eval_runtime": 35.5454, | |
| "eval_samples_per_second": 7.793, | |
| "eval_steps_per_second": 3.91, | |
| "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": 1.844940337525555e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |