| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002246559955068801, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.493119910137602e-05, | |
| "eval_loss": 4.334721088409424, | |
| "eval_runtime": 611.3447, | |
| "eval_samples_per_second": 15.33, | |
| "eval_steps_per_second": 7.665, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002246559955068801, | |
| "grad_norm": 5.346963882446289, | |
| "learning_rate": 5e-05, | |
| "loss": 4.319, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004493119910137602, | |
| "grad_norm": 6.329273700714111, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2676, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004493119910137602, | |
| "eval_loss": 3.843945026397705, | |
| "eval_runtime": 609.9274, | |
| "eval_samples_per_second": 15.366, | |
| "eval_steps_per_second": 7.683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006739679865206403, | |
| "grad_norm": 7.640130043029785, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7507, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008986239820275204, | |
| "grad_norm": 5.644228458404541, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008986239820275204, | |
| "eval_loss": 3.3383829593658447, | |
| "eval_runtime": 609.2979, | |
| "eval_samples_per_second": 15.382, | |
| "eval_steps_per_second": 7.691, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011232799775344005, | |
| "grad_norm": 6.619650840759277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.1767, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013479359730412806, | |
| "grad_norm": 5.7096476554870605, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2471, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013479359730412806, | |
| "eval_loss": 3.1682851314544678, | |
| "eval_runtime": 611.281, | |
| "eval_samples_per_second": 15.332, | |
| "eval_steps_per_second": 7.666, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0015725919685481606, | |
| "grad_norm": 7.731268882751465, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.3125, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017972479640550407, | |
| "grad_norm": 5.792168140411377, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9318, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017972479640550407, | |
| "eval_loss": 3.112304925918579, | |
| "eval_runtime": 610.8208, | |
| "eval_samples_per_second": 15.343, | |
| "eval_steps_per_second": 7.672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020219039595619206, | |
| "grad_norm": 7.447405815124512, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.0419, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002246559955068801, | |
| "grad_norm": 5.79746150970459, | |
| "learning_rate": 0.0, | |
| "loss": 3.0246, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002246559955068801, | |
| "eval_loss": 3.1021504402160645, | |
| "eval_runtime": 609.5075, | |
| "eval_samples_per_second": 15.376, | |
| "eval_steps_per_second": 7.688, | |
| "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": 4662275981967360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |