| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2777777777777778, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009259259259259259, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.9024, | |
| "eval_samples_per_second": 3.087, | |
| "eval_steps_per_second": 1.543, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.046296296296296294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.3922, | |
| "eval_samples_per_second": 3.196, | |
| "eval_steps_per_second": 1.598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.3825, | |
| "eval_samples_per_second": 3.198, | |
| "eval_steps_per_second": 1.599, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.3595, | |
| "eval_samples_per_second": 3.203, | |
| "eval_steps_per_second": 1.602, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.3293, | |
| "eval_samples_per_second": 3.21, | |
| "eval_steps_per_second": 1.605, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19444444444444445, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23148148148148148, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.3328, | |
| "eval_samples_per_second": 3.209, | |
| "eval_steps_per_second": 1.605, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.3292, | |
| "eval_samples_per_second": 3.21, | |
| "eval_steps_per_second": 1.605, | |
| "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": 2.06763800395776e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |