| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0042387848816672555, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001412928293889085, | |
| "grad_norm": 0.9927595257759094, | |
| "learning_rate": 2e-05, | |
| "loss": 44.2813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "eval_loss": 11.076643943786621, | |
| "eval_runtime": 1.1279, | |
| "eval_samples_per_second": 264.206, | |
| "eval_steps_per_second": 132.103, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "grad_norm": 0.9892200827598572, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3553, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "grad_norm": 0.9895350933074951, | |
| "learning_rate": 6e-05, | |
| "loss": 44.2978, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "eval_loss": 11.07655143737793, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 466.764, | |
| "eval_steps_per_second": 233.382, | |
| "step": 3 | |
| } | |
| ], | |
| "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": 2241331200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |