| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05052631578947368, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 14.417243957519531, | |
| "eval_runtime": 24.0885, | |
| "eval_samples_per_second": 10.378, | |
| "eval_steps_per_second": 5.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 23.87982177734375, | |
| "learning_rate": 6e-05, | |
| "loss": 11.5088, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "eval_loss": 11.165465354919434, | |
| "eval_runtime": 24.4388, | |
| "eval_samples_per_second": 10.23, | |
| "eval_steps_per_second": 5.115, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 25.36711311340332, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8775, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 33.61933135986328, | |
| "learning_rate": 0.00018, | |
| "loss": 7.2912, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "eval_loss": 3.2156097888946533, | |
| "eval_runtime": 24.5491, | |
| "eval_samples_per_second": 10.184, | |
| "eval_steps_per_second": 5.092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020210526315789474, | |
| "grad_norm": 14.489277839660645, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.086, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "grad_norm": 4.496290683746338, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.2389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02526315789473684, | |
| "eval_loss": 2.3330087661743164, | |
| "eval_runtime": 24.5945, | |
| "eval_samples_per_second": 10.165, | |
| "eval_steps_per_second": 5.082, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03031578947368421, | |
| "grad_norm": 2.6100714206695557, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2098, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03368421052631579, | |
| "eval_loss": 2.2271230220794678, | |
| "eval_runtime": 24.609, | |
| "eval_samples_per_second": 10.159, | |
| "eval_steps_per_second": 5.079, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03536842105263158, | |
| "grad_norm": 2.528639078140259, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.0081, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04042105263157895, | |
| "grad_norm": 2.648385763168335, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.2642, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 2.166091203689575, | |
| "eval_runtime": 24.6075, | |
| "eval_samples_per_second": 10.16, | |
| "eval_steps_per_second": 5.08, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04547368421052632, | |
| "grad_norm": 3.181828498840332, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.2066, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "grad_norm": 2.4813320636749268, | |
| "learning_rate": 0.0, | |
| "loss": 1.7934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05052631578947368, | |
| "eval_loss": 2.1476662158966064, | |
| "eval_runtime": 24.6276, | |
| "eval_samples_per_second": 10.151, | |
| "eval_steps_per_second": 5.076, | |
| "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": 1.150341542313984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |