| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00474293302978562, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.485866059571239e-05, | |
| "eval_loss": 2.415705919265747, | |
| "eval_runtime": 51.375, | |
| "eval_samples_per_second": 86.404, | |
| "eval_steps_per_second": 43.212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009485866059571238, | |
| "grad_norm": 1.2573297023773193, | |
| "learning_rate": 0.0001, | |
| "loss": 9.4553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012331625877442611, | |
| "eval_loss": 2.3920791149139404, | |
| "eval_runtime": 51.16, | |
| "eval_samples_per_second": 86.767, | |
| "eval_steps_per_second": 43.393, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0018971732119142477, | |
| "grad_norm": 1.9926952123641968, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.419, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0024663251754885223, | |
| "eval_loss": 2.3714699745178223, | |
| "eval_runtime": 51.1351, | |
| "eval_samples_per_second": 86.809, | |
| "eval_steps_per_second": 43.414, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0028457598178713715, | |
| "grad_norm": 1.8926585912704468, | |
| "learning_rate": 5e-05, | |
| "loss": 9.4168, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003699487763232783, | |
| "eval_loss": 2.3647139072418213, | |
| "eval_runtime": 51.0728, | |
| "eval_samples_per_second": 86.915, | |
| "eval_steps_per_second": 43.467, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0037943464238284954, | |
| "grad_norm": 1.7808252573013306, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 9.6828, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00474293302978562, | |
| "grad_norm": 1.7304259538650513, | |
| "learning_rate": 0.0, | |
| "loss": 9.6331, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 2226846582177792.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |