| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07326007326007326, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002442002442002442, | |
| "eval_loss": 1.4053446054458618, | |
| "eval_runtime": 25.0149, | |
| "eval_samples_per_second": 6.916, | |
| "eval_steps_per_second": 3.478, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007326007326007326, | |
| "grad_norm": 1.1817816495895386, | |
| "learning_rate": 3e-05, | |
| "loss": 5.7243, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01221001221001221, | |
| "eval_loss": 1.3982402086257935, | |
| "eval_runtime": 25.0191, | |
| "eval_samples_per_second": 6.915, | |
| "eval_steps_per_second": 3.477, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014652014652014652, | |
| "grad_norm": 1.2069846391677856, | |
| "learning_rate": 6e-05, | |
| "loss": 5.4238, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02197802197802198, | |
| "grad_norm": 1.5348583459854126, | |
| "learning_rate": 9e-05, | |
| "loss": 5.9045, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "eval_loss": 1.3449891805648804, | |
| "eval_runtime": 25.0177, | |
| "eval_samples_per_second": 6.915, | |
| "eval_steps_per_second": 3.478, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029304029304029304, | |
| "grad_norm": 1.2581948041915894, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.2718, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03663003663003663, | |
| "grad_norm": 1.3958145380020142, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.481, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03663003663003663, | |
| "eval_loss": 1.274520754814148, | |
| "eval_runtime": 25.1149, | |
| "eval_samples_per_second": 6.888, | |
| "eval_steps_per_second": 3.464, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04395604395604396, | |
| "grad_norm": 1.4559262990951538, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.8546, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "eval_loss": 1.2311657667160034, | |
| "eval_runtime": 25.1016, | |
| "eval_samples_per_second": 6.892, | |
| "eval_steps_per_second": 3.466, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 1.7523326873779297, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 4.8254, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05860805860805861, | |
| "grad_norm": 1.4057033061981201, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 5.2476, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06105006105006105, | |
| "eval_loss": 1.2100886106491089, | |
| "eval_runtime": 25.1246, | |
| "eval_samples_per_second": 6.886, | |
| "eval_steps_per_second": 3.463, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06593406593406594, | |
| "grad_norm": 2.7432544231414795, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 4.6687, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07326007326007326, | |
| "grad_norm": 1.4368641376495361, | |
| "learning_rate": 0.0, | |
| "loss": 4.8216, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07326007326007326, | |
| "eval_loss": 1.2058435678482056, | |
| "eval_runtime": 25.1068, | |
| "eval_samples_per_second": 6.891, | |
| "eval_steps_per_second": 3.465, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.39606748790784e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |