| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06587615283267458, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013175230566534915, | |
| "eval_loss": 2.429551601409912, | |
| "eval_runtime": 34.1229, | |
| "eval_samples_per_second": 9.378, | |
| "eval_steps_per_second": 4.689, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006587615283267457, | |
| "grad_norm": 1.0831778049468994, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1113, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013175230566534914, | |
| "grad_norm": 0.8124720454216003, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9417, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013175230566534914, | |
| "eval_loss": 1.9890544414520264, | |
| "eval_runtime": 34.7293, | |
| "eval_samples_per_second": 9.214, | |
| "eval_steps_per_second": 4.607, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019762845849802372, | |
| "grad_norm": 0.7260387539863586, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5863, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026350461133069828, | |
| "grad_norm": 0.6288080811500549, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4501, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026350461133069828, | |
| "eval_loss": 1.3593571186065674, | |
| "eval_runtime": 34.6864, | |
| "eval_samples_per_second": 9.226, | |
| "eval_steps_per_second": 4.613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03293807641633729, | |
| "grad_norm": 0.6772316694259644, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2137, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039525691699604744, | |
| "grad_norm": 0.6072627902030945, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.039525691699604744, | |
| "eval_loss": 1.1616449356079102, | |
| "eval_runtime": 34.7532, | |
| "eval_samples_per_second": 9.208, | |
| "eval_steps_per_second": 4.604, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0461133069828722, | |
| "grad_norm": 0.6614992618560791, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0897, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "grad_norm": 0.5868863463401794, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "eval_loss": 1.061147928237915, | |
| "eval_runtime": 34.8273, | |
| "eval_samples_per_second": 9.188, | |
| "eval_steps_per_second": 4.594, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05928853754940711, | |
| "grad_norm": 0.5653367638587952, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0647, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06587615283267458, | |
| "grad_norm": 0.5659787654876709, | |
| "learning_rate": 0.0, | |
| "loss": 1.1004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06587615283267458, | |
| "eval_loss": 1.0537097454071045, | |
| "eval_runtime": 34.7012, | |
| "eval_samples_per_second": 9.222, | |
| "eval_steps_per_second": 4.611, | |
| "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": 1.64316422602752e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |