| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0035871865695734835, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.174373139146967e-05, | |
| "eval_loss": 0.29852578043937683, | |
| "eval_runtime": 1099.318, | |
| "eval_samples_per_second": 5.339, | |
| "eval_steps_per_second": 2.67, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035871865695734833, | |
| "grad_norm": 3.126492500305176, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1413, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007174373139146967, | |
| "grad_norm": 1.8165031671524048, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8714, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007174373139146967, | |
| "eval_loss": 0.16495029628276825, | |
| "eval_runtime": 1118.9908, | |
| "eval_samples_per_second": 5.245, | |
| "eval_steps_per_second": 2.623, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001076155970872045, | |
| "grad_norm": 2.5322368144989014, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5411, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014348746278293933, | |
| "grad_norm": 2.760817050933838, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014348746278293933, | |
| "eval_loss": 0.10688852518796921, | |
| "eval_runtime": 1119.5877, | |
| "eval_samples_per_second": 5.242, | |
| "eval_steps_per_second": 2.622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0017935932847867417, | |
| "grad_norm": 1.9835935831069946, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3953, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00215231194174409, | |
| "grad_norm": 1.234115719795227, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3368, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00215231194174409, | |
| "eval_loss": 0.0884622186422348, | |
| "eval_runtime": 1123.6058, | |
| "eval_samples_per_second": 5.223, | |
| "eval_steps_per_second": 2.612, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025110305987014383, | |
| "grad_norm": 1.4333447217941284, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3364, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0028697492556587867, | |
| "grad_norm": 3.595264434814453, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.385, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0028697492556587867, | |
| "eval_loss": 0.08297457545995712, | |
| "eval_runtime": 1126.3993, | |
| "eval_samples_per_second": 5.21, | |
| "eval_steps_per_second": 2.606, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003228467912616135, | |
| "grad_norm": 1.4879796504974365, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3122, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0035871865695734835, | |
| "grad_norm": 1.9949724674224854, | |
| "learning_rate": 0.0, | |
| "loss": 0.3348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035871865695734835, | |
| "eval_loss": 0.08217484503984451, | |
| "eval_runtime": 1119.4208, | |
| "eval_samples_per_second": 5.243, | |
| "eval_steps_per_second": 2.622, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.75267179921408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |