| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010311670232785956, | |
| "eval_steps": 5, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.577917558196489e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.7556, | |
| "eval_samples_per_second": 29.077, | |
| "eval_steps_per_second": 7.27, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.733752674589467e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012889587790982445, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.3721, | |
| "eval_samples_per_second": 29.097, | |
| "eval_steps_per_second": 7.275, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015467505349178935, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000232012580237684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002577917558196489, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.1935, | |
| "eval_samples_per_second": 29.106, | |
| "eval_steps_per_second": 7.277, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003093501069835787, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00038668763372947334, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00038668763372947334, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.2254, | |
| "eval_samples_per_second": 29.104, | |
| "eval_steps_per_second": 7.277, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000464025160475368, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005155835116392978, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.2671, | |
| "eval_samples_per_second": 29.102, | |
| "eval_steps_per_second": 7.276, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005413626872212626, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0006187002139671574, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006444793895491222, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.203, | |
| "eval_samples_per_second": 29.105, | |
| "eval_steps_per_second": 7.277, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000696037740713052, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0007733752674589467, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007733752674589467, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.1702, | |
| "eval_samples_per_second": 29.107, | |
| "eval_steps_per_second": 7.278, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008507127942048413, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0009022711453687711, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.1363, | |
| "eval_samples_per_second": 29.109, | |
| "eval_steps_per_second": 7.278, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.000928050320950736, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0010053878476966307, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0010311670232785956, | |
| "eval_loss": NaN, | |
| "eval_runtime": 561.1451, | |
| "eval_samples_per_second": 29.108, | |
| "eval_steps_per_second": 7.278, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3682706084855808.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |