| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04678362573099415, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015594541910331384, | |
| "eval_loss": 1.508385419845581, | |
| "eval_runtime": 26.969, | |
| "eval_samples_per_second": 10.049, | |
| "eval_steps_per_second": 5.043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 0.39213576912879944, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5605, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "eval_loss": 1.4978253841400146, | |
| "eval_runtime": 26.4506, | |
| "eval_samples_per_second": 10.246, | |
| "eval_steps_per_second": 5.142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 0.36995622515678406, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 0.3752123713493347, | |
| "learning_rate": 9e-05, | |
| "loss": 1.3854, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "eval_loss": 1.4332730770111084, | |
| "eval_runtime": 26.4493, | |
| "eval_samples_per_second": 10.246, | |
| "eval_steps_per_second": 5.142, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 0.3255695104598999, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.3539, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.2485169768333435, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3517, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "eval_loss": 1.3882832527160645, | |
| "eval_runtime": 26.4826, | |
| "eval_samples_per_second": 10.233, | |
| "eval_steps_per_second": 5.135, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 0.3311094343662262, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.4781, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "eval_loss": 1.3644858598709106, | |
| "eval_runtime": 26.4672, | |
| "eval_samples_per_second": 10.239, | |
| "eval_steps_per_second": 5.138, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03274853801169591, | |
| "grad_norm": 0.25635430216789246, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.3608, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 0.25514256954193115, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.3215, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "eval_loss": 1.3476552963256836, | |
| "eval_runtime": 26.484, | |
| "eval_samples_per_second": 10.233, | |
| "eval_steps_per_second": 5.135, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.20033127069473267, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.4183, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 0.21877515316009521, | |
| "learning_rate": 0.0, | |
| "loss": 1.2605, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "eval_loss": 1.345063328742981, | |
| "eval_runtime": 26.458, | |
| "eval_samples_per_second": 10.243, | |
| "eval_steps_per_second": 5.14, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7888418277097472e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |