| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006191471248355391, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010319118747258984, | |
| "grad_norm": 2.7657470703125, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010319118747258984, | |
| "eval_loss": NaN, | |
| "eval_runtime": 317.8218, | |
| "eval_samples_per_second": 12.841, | |
| "eval_steps_per_second": 6.422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020638237494517968, | |
| "grad_norm": 2.364863395690918, | |
| "learning_rate": 4e-05, | |
| "loss": 1.576, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00030957356241776953, | |
| "grad_norm": 3.7804818153381348, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5991, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00030957356241776953, | |
| "eval_loss": NaN, | |
| "eval_runtime": 315.7114, | |
| "eval_samples_per_second": 12.926, | |
| "eval_steps_per_second": 6.465, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00041276474989035937, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5043, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005159559373629492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006191471248355391, | |
| "grad_norm": 3.124617099761963, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8695, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006191471248355391, | |
| "eval_loss": NaN, | |
| "eval_runtime": 315.8984, | |
| "eval_samples_per_second": 12.919, | |
| "eval_steps_per_second": 6.461, | |
| "step": 6 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3135477657894912.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |