| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010169577708285663, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.3898592360952214e-05, | |
| "eval_loss": 1.5521913766860962, | |
| "eval_runtime": 2912.8778, | |
| "eval_samples_per_second": 4.264, | |
| "eval_steps_per_second": 2.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010169577708285663, | |
| "grad_norm": 11.249643325805664, | |
| "learning_rate": 3e-05, | |
| "loss": 5.7115, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00020339155416571327, | |
| "grad_norm": 7.744796276092529, | |
| "learning_rate": 6e-05, | |
| "loss": 6.0804, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002711887388876177, | |
| "eval_loss": 1.517215371131897, | |
| "eval_runtime": 2926.1627, | |
| "eval_samples_per_second": 4.245, | |
| "eval_steps_per_second": 2.123, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003050873312485699, | |
| "grad_norm": 5.9153151512146, | |
| "learning_rate": 9e-05, | |
| "loss": 6.9199, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00040678310833142654, | |
| "grad_norm": 86.80118560791016, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.86, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005084788854142832, | |
| "grad_norm": 1.8858240842819214, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.5372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005423774777752354, | |
| "eval_loss": 1.3532363176345825, | |
| "eval_runtime": 2923.6367, | |
| "eval_samples_per_second": 4.248, | |
| "eval_steps_per_second": 2.124, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006101746624971398, | |
| "grad_norm": 2.218549966812134, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.5828, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007118704395799964, | |
| "grad_norm": 1.8414465188980103, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 5.3067, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0008135662166628531, | |
| "grad_norm": 2.2933406829833984, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 5.2307, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008135662166628531, | |
| "eval_loss": 1.2488714456558228, | |
| "eval_runtime": 2929.3994, | |
| "eval_samples_per_second": 4.24, | |
| "eval_steps_per_second": 2.12, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0009152619937457097, | |
| "grad_norm": 2.308497190475464, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 5.3056, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0010169577708285663, | |
| "grad_norm": 2.603907585144043, | |
| "learning_rate": 0.0, | |
| "loss": 4.5462, | |
| "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": 2.042527481856e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |