| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00030028677386904494, | |
| "eval_steps": 5, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0028677386904494e-05, | |
| "eval_loss": 1.0328869819641113, | |
| "eval_runtime": 1647.1723, | |
| "eval_samples_per_second": 8.513, | |
| "eval_steps_per_second": 4.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.008603216071348e-05, | |
| "grad_norm": 0.2662915587425232, | |
| "learning_rate": 3e-05, | |
| "loss": 0.965, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015014338693452247, | |
| "eval_loss": 1.0183448791503906, | |
| "eval_runtime": 1647.4187, | |
| "eval_samples_per_second": 8.511, | |
| "eval_steps_per_second": 4.256, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018017206432142696, | |
| "grad_norm": 0.44537869095802307, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9669, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002702580964821404, | |
| "grad_norm": 0.6517441868782043, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9603, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00030028677386904494, | |
| "eval_loss": 0.8726487159729004, | |
| "eval_runtime": 1647.1028, | |
| "eval_samples_per_second": 8.513, | |
| "eval_steps_per_second": 4.257, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8093431863705600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |