| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.029354207436399216, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009784735812133072, | |
| "eval_loss": 7.14760684967041, | |
| "eval_runtime": 84.0888, | |
| "eval_samples_per_second": 5.126, | |
| "eval_steps_per_second": 2.569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029354207436399216, | |
| "grad_norm": 19.590736389160156, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2867, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005870841487279843, | |
| "grad_norm": 14.517230987548828, | |
| "learning_rate": 0.00012, | |
| "loss": 5.7847, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007827788649706457, | |
| "eval_loss": 2.2990779876708984, | |
| "eval_runtime": 85.1101, | |
| "eval_samples_per_second": 5.064, | |
| "eval_steps_per_second": 2.538, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008806262230919765, | |
| "grad_norm": 10.66134262084961, | |
| "learning_rate": 0.00018, | |
| "loss": 2.4597, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011741682974559686, | |
| "grad_norm": 9.743139266967773, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7441, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014677103718199608, | |
| "grad_norm": 11.344720840454102, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.5078, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015655577299412915, | |
| "eval_loss": 2.035311222076416, | |
| "eval_runtime": 85.1668, | |
| "eval_samples_per_second": 5.061, | |
| "eval_steps_per_second": 2.536, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01761252446183953, | |
| "grad_norm": 11.525131225585938, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.3631, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02054794520547945, | |
| "grad_norm": 7.393858909606934, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.7479, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "grad_norm": 9.101008415222168, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.7406, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.023483365949119372, | |
| "eval_loss": 1.9797108173370361, | |
| "eval_runtime": 85.184, | |
| "eval_samples_per_second": 5.06, | |
| "eval_steps_per_second": 2.536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.026418786692759294, | |
| "grad_norm": 10.545234680175781, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.1363, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029354207436399216, | |
| "grad_norm": 8.334158897399902, | |
| "learning_rate": 0.0, | |
| "loss": 1.6207, | |
| "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": 1.235418813038592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |