| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021178588447080004, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.05952948236e-05, | |
| "eval_loss": 2.7068030834198, | |
| "eval_runtime": 669.1483, | |
| "eval_samples_per_second": 8.914, | |
| "eval_steps_per_second": 4.458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021178588447080002, | |
| "grad_norm": 1.047041416168213, | |
| "learning_rate": 6e-05, | |
| "loss": 10.7511, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00042357176894160004, | |
| "grad_norm": 1.577899694442749, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8091, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005647623585888, | |
| "eval_loss": 2.5358192920684814, | |
| "eval_runtime": 669.5429, | |
| "eval_samples_per_second": 8.909, | |
| "eval_steps_per_second": 4.455, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006353576534124001, | |
| "grad_norm": 1.0739885568618774, | |
| "learning_rate": 0.00018, | |
| "loss": 10.5286, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008471435378832001, | |
| "grad_norm": 1.0982314348220825, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.1016, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010589294223540002, | |
| "grad_norm": 1.1774293184280396, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 9.434, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011295247171776, | |
| "eval_loss": 2.345432758331299, | |
| "eval_runtime": 669.4827, | |
| "eval_samples_per_second": 8.91, | |
| "eval_steps_per_second": 4.456, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012707153068248001, | |
| "grad_norm": 1.3145077228546143, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.158, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0014825011912956002, | |
| "grad_norm": 1.2306267023086548, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 9.464, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016942870757664001, | |
| "grad_norm": 1.0889095067977905, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 9.4374, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016942870757664001, | |
| "eval_loss": 2.303675889968872, | |
| "eval_runtime": 669.5487, | |
| "eval_samples_per_second": 8.909, | |
| "eval_steps_per_second": 4.455, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0019060729602372003, | |
| "grad_norm": 0.9970927238464355, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 8.9337, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0021178588447080004, | |
| "grad_norm": 1.0527116060256958, | |
| "learning_rate": 0.0, | |
| "loss": 9.2766, | |
| "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": 1.90434898870272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |