| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006385614487682149, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2771228975364299e-05, | |
| "eval_loss": 3.492058038711548, | |
| "eval_runtime": 514.169, | |
| "eval_samples_per_second": 64.121, | |
| "eval_steps_per_second": 32.061, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.38561448768215e-05, | |
| "grad_norm": 1.112701416015625, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3946, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000127712289753643, | |
| "grad_norm": 0.9742205739021301, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000127712289753643, | |
| "eval_loss": 3.4140679836273193, | |
| "eval_runtime": 512.3057, | |
| "eval_samples_per_second": 64.354, | |
| "eval_steps_per_second": 32.178, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001915684346304645, | |
| "grad_norm": 1.1488938331604004, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000255424579507286, | |
| "grad_norm": 1.0554172992706299, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000255424579507286, | |
| "eval_loss": 3.1005325317382812, | |
| "eval_runtime": 505.3648, | |
| "eval_samples_per_second": 65.238, | |
| "eval_steps_per_second": 32.62, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00031928072438410746, | |
| "grad_norm": 1.1332489252090454, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0394, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.000383136869260929, | |
| "grad_norm": 1.2555519342422485, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8423, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000383136869260929, | |
| "eval_loss": 2.883232831954956, | |
| "eval_runtime": 505.1532, | |
| "eval_samples_per_second": 65.265, | |
| "eval_steps_per_second": 32.634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00044699301413775045, | |
| "grad_norm": 1.251326560974121, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.762, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.000510849159014572, | |
| "grad_norm": 1.1709085702896118, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.8656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.000510849159014572, | |
| "eval_loss": 2.7841124534606934, | |
| "eval_runtime": 506.134, | |
| "eval_samples_per_second": 65.139, | |
| "eval_steps_per_second": 32.57, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005747053038913935, | |
| "grad_norm": 1.371285319328308, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8135, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0006385614487682149, | |
| "grad_norm": 1.164176106452942, | |
| "learning_rate": 0.0, | |
| "loss": 2.8105, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0006385614487682149, | |
| "eval_loss": 2.7675223350524902, | |
| "eval_runtime": 505.1815, | |
| "eval_samples_per_second": 65.262, | |
| "eval_steps_per_second": 32.632, | |
| "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": 171463252377600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |