| { | |
| "best_metric": 2.6275486946105957, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.026232948583420776, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013116474291710389, | |
| "eval_loss": 4.575855255126953, | |
| "eval_runtime": 166.0044, | |
| "eval_samples_per_second": 19.337, | |
| "eval_steps_per_second": 4.837, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013116474291710388, | |
| "grad_norm": 3.6807003021240234, | |
| "learning_rate": 5.05e-06, | |
| "loss": 3.5819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0026232948583420775, | |
| "grad_norm": 2.292651891708374, | |
| "learning_rate": 1.01e-05, | |
| "loss": 4.0033, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003934942287513116, | |
| "grad_norm": 3.5651023387908936, | |
| "learning_rate": 9.538888888888889e-06, | |
| "loss": 4.0922, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005246589716684155, | |
| "grad_norm": 5.502660751342773, | |
| "learning_rate": 8.977777777777778e-06, | |
| "loss": 4.2289, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006558237145855194, | |
| "grad_norm": 7.5711565017700195, | |
| "learning_rate": 8.416666666666667e-06, | |
| "loss": 4.1931, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006558237145855194, | |
| "eval_loss": 3.3517510890960693, | |
| "eval_runtime": 165.8751, | |
| "eval_samples_per_second": 19.352, | |
| "eval_steps_per_second": 4.841, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007869884575026232, | |
| "grad_norm": 3.23335337638855, | |
| "learning_rate": 7.855555555555556e-06, | |
| "loss": 2.8308, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009181532004197272, | |
| "grad_norm": 4.3262038230896, | |
| "learning_rate": 7.294444444444444e-06, | |
| "loss": 2.6882, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01049317943336831, | |
| "grad_norm": 4.342103958129883, | |
| "learning_rate": 6.733333333333333e-06, | |
| "loss": 2.9334, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01180482686253935, | |
| "grad_norm": 5.277548789978027, | |
| "learning_rate": 6.172222222222223e-06, | |
| "loss": 2.7713, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.013116474291710388, | |
| "grad_norm": 7.770826816558838, | |
| "learning_rate": 5.611111111111111e-06, | |
| "loss": 2.743, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013116474291710388, | |
| "eval_loss": 2.7597808837890625, | |
| "eval_runtime": 165.1519, | |
| "eval_samples_per_second": 19.437, | |
| "eval_steps_per_second": 4.862, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.014428121720881428, | |
| "grad_norm": 3.34566068649292, | |
| "learning_rate": 5.05e-06, | |
| "loss": 2.6184, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.015739769150052464, | |
| "grad_norm": 3.4692320823669434, | |
| "learning_rate": 4.488888888888889e-06, | |
| "loss": 2.4877, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.017051416579223506, | |
| "grad_norm": 3.4134504795074463, | |
| "learning_rate": 3.927777777777778e-06, | |
| "loss": 2.6637, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.018363064008394544, | |
| "grad_norm": 3.9364752769470215, | |
| "learning_rate": 3.3666666666666665e-06, | |
| "loss": 2.5916, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.019674711437565582, | |
| "grad_norm": 8.155444145202637, | |
| "learning_rate": 2.8055555555555555e-06, | |
| "loss": 2.8924, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.019674711437565582, | |
| "eval_loss": 2.6532483100891113, | |
| "eval_runtime": 165.8277, | |
| "eval_samples_per_second": 19.357, | |
| "eval_steps_per_second": 4.842, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02098635886673662, | |
| "grad_norm": 3.4204041957855225, | |
| "learning_rate": 2.2444444444444445e-06, | |
| "loss": 2.567, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.02229800629590766, | |
| "grad_norm": 3.5250372886657715, | |
| "learning_rate": 1.6833333333333332e-06, | |
| "loss": 2.6192, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0236096537250787, | |
| "grad_norm": 4.614537239074707, | |
| "learning_rate": 1.1222222222222222e-06, | |
| "loss": 2.7407, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.024921301154249738, | |
| "grad_norm": 4.56196403503418, | |
| "learning_rate": 5.611111111111111e-07, | |
| "loss": 2.6979, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.026232948583420776, | |
| "grad_norm": 7.957613468170166, | |
| "learning_rate": 0.0, | |
| "loss": 2.9207, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.026232948583420776, | |
| "eval_loss": 2.6275486946105957, | |
| "eval_runtime": 165.8027, | |
| "eval_samples_per_second": 19.36, | |
| "eval_steps_per_second": 4.843, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.71020323176448e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |