| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00475963826749167, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "grad_norm": 0.14505670964717865, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3793, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047596382674916705, | |
| "eval_loss": 10.378437042236328, | |
| "eval_runtime": 2.5061, | |
| "eval_samples_per_second": 353.142, | |
| "eval_steps_per_second": 176.771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009519276534983341, | |
| "grad_norm": 0.1477060616016388, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3778, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014278914802475012, | |
| "grad_norm": 0.1674378216266632, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014278914802475012, | |
| "eval_loss": 10.37828254699707, | |
| "eval_runtime": 2.4122, | |
| "eval_samples_per_second": 366.887, | |
| "eval_steps_per_second": 183.651, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0019038553069966682, | |
| "grad_norm": 0.15274536609649658, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3817, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002379819133745835, | |
| "grad_norm": 0.1628134399652481, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3795, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028557829604950024, | |
| "grad_norm": 0.1442088484764099, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3776, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0028557829604950024, | |
| "eval_loss": 10.37758731842041, | |
| "eval_runtime": 2.476, | |
| "eval_samples_per_second": 357.432, | |
| "eval_steps_per_second": 178.918, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033317467872441696, | |
| "grad_norm": 0.16722121834754944, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3782, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0038077106139933364, | |
| "grad_norm": 0.16152095794677734, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3743, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004283674440742504, | |
| "grad_norm": 0.15844860672950745, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3784, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004283674440742504, | |
| "eval_loss": 10.376397132873535, | |
| "eval_runtime": 2.4685, | |
| "eval_samples_per_second": 358.516, | |
| "eval_steps_per_second": 179.461, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00475963826749167, | |
| "grad_norm": 0.16182802617549896, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3804, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |