| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026041666666666668, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005208333333333333, | |
| "eval_loss": 3.025148868560791, | |
| "eval_runtime": 71.3194, | |
| "eval_samples_per_second": 11.343, | |
| "eval_steps_per_second": 5.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026041666666666665, | |
| "grad_norm": 3.64170503616333, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005208333333333333, | |
| "grad_norm": 4.330460548400879, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6031, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005208333333333333, | |
| "eval_loss": 2.3286690711975098, | |
| "eval_runtime": 71.7462, | |
| "eval_samples_per_second": 11.276, | |
| "eval_steps_per_second": 5.645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0078125, | |
| "grad_norm": 6.281655788421631, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0724, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010416666666666666, | |
| "grad_norm": 5.416592597961426, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010416666666666666, | |
| "eval_loss": 1.7252271175384521, | |
| "eval_runtime": 71.9068, | |
| "eval_samples_per_second": 11.251, | |
| "eval_steps_per_second": 5.632, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013020833333333334, | |
| "grad_norm": 5.787356853485107, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6041, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015625, | |
| "grad_norm": 4.985279560089111, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7145, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015625, | |
| "eval_loss": 1.5758812427520752, | |
| "eval_runtime": 71.8838, | |
| "eval_samples_per_second": 11.254, | |
| "eval_steps_per_second": 5.634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018229166666666668, | |
| "grad_norm": 6.2775092124938965, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6066, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 4.507986068725586, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "eval_loss": 1.5156272649765015, | |
| "eval_runtime": 71.8116, | |
| "eval_samples_per_second": 11.266, | |
| "eval_steps_per_second": 5.64, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0234375, | |
| "grad_norm": 3.982529878616333, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5871, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026041666666666668, | |
| "grad_norm": 4.551398754119873, | |
| "learning_rate": 0.0, | |
| "loss": 1.5938, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026041666666666668, | |
| "eval_loss": 1.5064769983291626, | |
| "eval_runtime": 71.7963, | |
| "eval_samples_per_second": 11.268, | |
| "eval_steps_per_second": 5.641, | |
| "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": 1.017656179163136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |