| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0011633791510822335, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.326758302164467e-05, | |
| "eval_loss": 5.18183708190918, | |
| "eval_runtime": 1103.9859, | |
| "eval_samples_per_second": 16.392, | |
| "eval_steps_per_second": 8.197, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011633791510822335, | |
| "grad_norm": 3.286332368850708, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002326758302164467, | |
| "grad_norm": 4.80321741104126, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9456, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002326758302164467, | |
| "eval_loss": 4.540585517883301, | |
| "eval_runtime": 1107.4278, | |
| "eval_samples_per_second": 16.341, | |
| "eval_steps_per_second": 8.171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00034901374532467005, | |
| "grad_norm": 4.00037956237793, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.947, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004653516604328934, | |
| "grad_norm": 3.7681870460510254, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.3056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004653516604328934, | |
| "eval_loss": 2.6043853759765625, | |
| "eval_runtime": 1107.0056, | |
| "eval_samples_per_second": 16.348, | |
| "eval_steps_per_second": 8.174, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005816895755411168, | |
| "grad_norm": 2.936751365661621, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2767, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0006980274906493401, | |
| "grad_norm": 3.392641544342041, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5175, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006980274906493401, | |
| "eval_loss": 2.222399950027466, | |
| "eval_runtime": 1102.8097, | |
| "eval_samples_per_second": 16.41, | |
| "eval_steps_per_second": 8.205, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008143654057575635, | |
| "grad_norm": 3.994202136993408, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.5334, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0009307033208657868, | |
| "grad_norm": 3.685447931289673, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.5459, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009307033208657868, | |
| "eval_loss": 2.1419756412506104, | |
| "eval_runtime": 1106.9783, | |
| "eval_samples_per_second": 16.348, | |
| "eval_steps_per_second": 8.175, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010470412359740102, | |
| "grad_norm": 2.698432683944702, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.04, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0011633791510822335, | |
| "grad_norm": 3.505143404006958, | |
| "learning_rate": 0.0, | |
| "loss": 1.8153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0011633791510822335, | |
| "eval_loss": 2.1304948329925537, | |
| "eval_runtime": 1105.9958, | |
| "eval_samples_per_second": 16.363, | |
| "eval_steps_per_second": 8.182, | |
| "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": 8486288055336960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |