| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010256410256410256, | |
| "eval_steps": 2, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006837606837606838, | |
| "grad_norm": 0.01459360308945179, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3793, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006837606837606838, | |
| "eval_loss": 10.37917423248291, | |
| "eval_runtime": 3.5837, | |
| "eval_samples_per_second": 171.888, | |
| "eval_steps_per_second": 85.944, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013675213675213675, | |
| "grad_norm": 0.013831038028001785, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3799, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013675213675213675, | |
| "eval_loss": 10.379171371459961, | |
| "eval_runtime": 3.5514, | |
| "eval_samples_per_second": 173.452, | |
| "eval_steps_per_second": 86.726, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020512820512820513, | |
| "grad_norm": 0.014491274021565914, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3789, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002735042735042735, | |
| "grad_norm": 0.01442716270685196, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3815, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002735042735042735, | |
| "eval_loss": 10.379145622253418, | |
| "eval_runtime": 3.5666, | |
| "eval_samples_per_second": 172.711, | |
| "eval_steps_per_second": 86.356, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003418803418803419, | |
| "grad_norm": 0.01321357674896717, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3781, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0041025641025641026, | |
| "grad_norm": 0.012160197831690311, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3803, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0041025641025641026, | |
| "eval_loss": 10.379097938537598, | |
| "eval_runtime": 3.6086, | |
| "eval_samples_per_second": 170.703, | |
| "eval_steps_per_second": 85.352, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004786324786324786, | |
| "grad_norm": 0.01298796571791172, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3767, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00547008547008547, | |
| "grad_norm": 0.012850708328187466, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3795, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00547008547008547, | |
| "eval_loss": 10.379048347473145, | |
| "eval_runtime": 3.5895, | |
| "eval_samples_per_second": 171.61, | |
| "eval_steps_per_second": 85.805, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006153846153846154, | |
| "grad_norm": 0.013943369500339031, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3819, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006837606837606838, | |
| "grad_norm": 0.017278488725423813, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3765, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006837606837606838, | |
| "eval_loss": 10.379008293151855, | |
| "eval_runtime": 3.566, | |
| "eval_samples_per_second": 172.744, | |
| "eval_steps_per_second": 86.372, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007521367521367521, | |
| "grad_norm": 0.01218665111809969, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 10.3796, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008205128205128205, | |
| "grad_norm": 0.014596718363463879, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.3781, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008205128205128205, | |
| "eval_loss": 10.378983497619629, | |
| "eval_runtime": 3.7412, | |
| "eval_samples_per_second": 164.654, | |
| "eval_steps_per_second": 82.327, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008888888888888889, | |
| "grad_norm": 0.016098329797387123, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3813, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009572649572649573, | |
| "grad_norm": 0.0119888074696064, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 10.3783, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009572649572649573, | |
| "eval_loss": 10.378974914550781, | |
| "eval_runtime": 3.5778, | |
| "eval_samples_per_second": 172.173, | |
| "eval_steps_per_second": 86.086, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.010256410256410256, | |
| "grad_norm": 0.015922540798783302, | |
| "learning_rate": 0.0, | |
| "loss": 10.3789, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 775854489600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |