| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007704753833115032, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015409507666230065, | |
| "eval_loss": 3.6128110885620117, | |
| "eval_runtime": 142.396, | |
| "eval_samples_per_second": 19.193, | |
| "eval_steps_per_second": 9.6, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007704753833115032, | |
| "grad_norm": 16.850940704345703, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7844, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015409507666230063, | |
| "grad_norm": 13.494234085083008, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2671, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015409507666230063, | |
| "eval_loss": 1.1115665435791016, | |
| "eval_runtime": 131.5497, | |
| "eval_samples_per_second": 20.775, | |
| "eval_steps_per_second": 10.392, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00231142614993451, | |
| "grad_norm": 4.364719390869141, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030819015332460126, | |
| "grad_norm": 12.563011169433594, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030819015332460126, | |
| "eval_loss": 0.036739639937877655, | |
| "eval_runtime": 120.7226, | |
| "eval_samples_per_second": 22.639, | |
| "eval_steps_per_second": 11.323, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003852376916557516, | |
| "grad_norm": 0.7028213739395142, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0257, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00462285229986902, | |
| "grad_norm": 1.7384469509124756, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0451, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00462285229986902, | |
| "eval_loss": 0.02767186053097248, | |
| "eval_runtime": 91.0793, | |
| "eval_samples_per_second": 30.007, | |
| "eval_steps_per_second": 15.009, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005393327683180522, | |
| "grad_norm": 2.4048991203308105, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0619, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006163803066492025, | |
| "grad_norm": 3.614093065261841, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0491, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006163803066492025, | |
| "eval_loss": 0.028665006160736084, | |
| "eval_runtime": 88.966, | |
| "eval_samples_per_second": 30.72, | |
| "eval_steps_per_second": 15.365, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006934278449803529, | |
| "grad_norm": 0.4157285690307617, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0091, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007704753833115032, | |
| "grad_norm": 0.2494722455739975, | |
| "learning_rate": 0.0, | |
| "loss": 0.006, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007704753833115032, | |
| "eval_loss": 0.028482932597398758, | |
| "eval_runtime": 90.914, | |
| "eval_samples_per_second": 30.061, | |
| "eval_steps_per_second": 15.036, | |
| "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": 445190819020800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |