| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.888888888888889, | |
| "eval_steps": 500, | |
| "global_step": 42, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 22.339479446411133, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 72.1042, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 23.86441421508789, | |
| "learning_rate": 9.047619047619048e-05, | |
| "loss": 70.3059, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 27.62677001953125, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 66.5863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.126984126984127, | |
| "grad_norm": 57.27507781982422, | |
| "learning_rate": 8.095238095238096e-05, | |
| "loss": 82.8912, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 38.90316390991211, | |
| "learning_rate": 7.619047619047618e-05, | |
| "loss": 57.8037, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.6349206349206349, | |
| "grad_norm": 28.1763916015625, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 52.8797, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 30.55934715270996, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 52.8374, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.253968253968254, | |
| "grad_norm": 26.450092315673828, | |
| "learning_rate": 6.19047619047619e-05, | |
| "loss": 69.0564, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.507936507936508, | |
| "grad_norm": 34.066776275634766, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 46.8763, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 24.209619522094727, | |
| "learning_rate": 5.2380952380952384e-05, | |
| "loss": 46.5825, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.126984126984127, | |
| "grad_norm": 35.07560729980469, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 62.4426, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.380952380952381, | |
| "grad_norm": 14.254531860351562, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 43.6682, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.634920634920635, | |
| "grad_norm": 10.83181095123291, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 44.4259, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.888888888888889, | |
| "grad_norm": 15.05122184753418, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 43.1349, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 4.253968253968254, | |
| "grad_norm": 10.117740631103516, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 58.7522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.507936507936508, | |
| "grad_norm": 12.624483108520508, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 41.6464, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 8.7578125, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 41.2899, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 5.1269841269841265, | |
| "grad_norm": 14.106217384338379, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 58.7284, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 5.380952380952381, | |
| "grad_norm": 11.060308456420898, | |
| "learning_rate": 9.523809523809523e-06, | |
| "loss": 39.9459, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 5.634920634920634, | |
| "grad_norm": 11.781099319458008, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 43.8549, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.888888888888889, | |
| "grad_norm": 8.562162399291992, | |
| "learning_rate": 0.0, | |
| "loss": 42.2842, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 5.888888888888889, | |
| "step": 42, | |
| "total_flos": 674107298249544.0, | |
| "train_loss": 54.19509578886486, | |
| "train_runtime": 1597.8044, | |
| "train_samples_per_second": 0.473, | |
| "train_steps_per_second": 0.026 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 42, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 674107298249544.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |