| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 100, | |
| "global_step": 355, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.408450704225352, | |
| "grad_norm": 0.15238748490810394, | |
| "learning_rate": 4.218676994605295e-05, | |
| "loss": 0.202, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "eval_loss": 0.04926154389977455, | |
| "eval_runtime": 68.6551, | |
| "eval_samples_per_second": 8.273, | |
| "eval_steps_per_second": 4.137, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "grad_norm": 0.1673239916563034, | |
| "learning_rate": 2.11342453729918e-05, | |
| "loss": 0.04, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "eval_loss": 0.04269786551594734, | |
| "eval_runtime": 68.6662, | |
| "eval_samples_per_second": 8.272, | |
| "eval_steps_per_second": 4.136, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.225352112676056, | |
| "grad_norm": 0.23441216349601746, | |
| "learning_rate": 3.0879348275879488e-06, | |
| "loss": 0.0289, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.225352112676056, | |
| "eval_loss": 0.043623749166727066, | |
| "eval_runtime": 68.6214, | |
| "eval_samples_per_second": 8.277, | |
| "eval_steps_per_second": 4.139, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 355, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.30529991585153e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |