| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18691588785046728, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 0.9504849910736084, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0864, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "eval_loss": 2.4634759426116943, | |
| "eval_runtime": 1.9807, | |
| "eval_samples_per_second": 11.612, | |
| "eval_steps_per_second": 6.059, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 1.128625512123108, | |
| "learning_rate": 4e-05, | |
| "loss": 2.052, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 1.1591551303863525, | |
| "learning_rate": 6e-05, | |
| "loss": 2.0881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "eval_loss": 2.4596502780914307, | |
| "eval_runtime": 0.7432, | |
| "eval_samples_per_second": 30.947, | |
| "eval_steps_per_second": 16.146, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 1.0428029298782349, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0578, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 1.082016944885254, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9756, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 1.079058289527893, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1077, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "eval_loss": 2.4028377532958984, | |
| "eval_runtime": 0.7562, | |
| "eval_samples_per_second": 30.415, | |
| "eval_steps_per_second": 15.868, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 1.3398456573486328, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3719, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 1.376936912536621, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7642, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 1.6025842428207397, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9801, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "eval_loss": 2.127096652984619, | |
| "eval_runtime": 0.7449, | |
| "eval_samples_per_second": 30.878, | |
| "eval_steps_per_second": 16.11, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 1.239439845085144, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8532, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1895803354349568.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |