| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004220121539500338, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.440243079000676e-05, | |
| "eval_loss": 3.1470351219177246, | |
| "eval_runtime": 319.5056, | |
| "eval_samples_per_second": 15.615, | |
| "eval_steps_per_second": 7.809, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00042201215395003375, | |
| "grad_norm": 35.62696075439453, | |
| "learning_rate": 5e-05, | |
| "loss": 12.3903, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008440243079000675, | |
| "grad_norm": 19.322917938232422, | |
| "learning_rate": 0.0001, | |
| "loss": 9.2821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008440243079000675, | |
| "eval_loss": 1.8441649675369263, | |
| "eval_runtime": 319.4554, | |
| "eval_samples_per_second": 15.617, | |
| "eval_steps_per_second": 7.81, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012660364618501012, | |
| "grad_norm": 13.528854370117188, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.2452, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001688048615800135, | |
| "grad_norm": 18.941818237304688, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.5938, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001688048615800135, | |
| "eval_loss": 1.389623999595642, | |
| "eval_runtime": 321.1448, | |
| "eval_samples_per_second": 15.535, | |
| "eval_steps_per_second": 7.769, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002110060769750169, | |
| "grad_norm": 16.26671600341797, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.5765, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0025320729237002025, | |
| "grad_norm": 12.967823028564453, | |
| "learning_rate": 5e-05, | |
| "loss": 4.7227, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025320729237002025, | |
| "eval_loss": 1.2695437669754028, | |
| "eval_runtime": 319.4343, | |
| "eval_samples_per_second": 15.618, | |
| "eval_steps_per_second": 7.811, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029540850776502365, | |
| "grad_norm": 11.24402141571045, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.567, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00337609723160027, | |
| "grad_norm": 14.4766845703125, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.9867, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00337609723160027, | |
| "eval_loss": 1.2205829620361328, | |
| "eval_runtime": 321.1482, | |
| "eval_samples_per_second": 15.535, | |
| "eval_steps_per_second": 7.769, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003798109385550304, | |
| "grad_norm": 17.95623207092285, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.583, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004220121539500338, | |
| "grad_norm": 12.699307441711426, | |
| "learning_rate": 0.0, | |
| "loss": 4.8422, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.004220121539500338, | |
| "eval_loss": 1.208472728729248, | |
| "eval_runtime": 317.7638, | |
| "eval_samples_per_second": 15.7, | |
| "eval_steps_per_second": 7.852, | |
| "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": 8763348929740800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |