| { | |
| "best_metric": 2.830770969390869, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010379365820748353, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004151746328299341, | |
| "grad_norm": 377.5227966308594, | |
| "learning_rate": 5e-05, | |
| "loss": 128.8738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004151746328299341, | |
| "eval_loss": 9.024163246154785, | |
| "eval_runtime": 678.47, | |
| "eval_samples_per_second": 23.917, | |
| "eval_steps_per_second": 2.991, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008303492656598682, | |
| "grad_norm": 409.34124755859375, | |
| "learning_rate": 0.0001, | |
| "loss": 141.3958, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012455238984898022, | |
| "grad_norm": 312.35101318359375, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 127.1079, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016606985313197364, | |
| "grad_norm": 672.0693969726562, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 101.7809, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020758731641496706, | |
| "grad_norm": 431.4256591796875, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 182.7217, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0024910477969796044, | |
| "grad_norm": 1824.4056396484375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 86.9111, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029062224298095386, | |
| "grad_norm": 123.24996948242188, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 49.6599, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003321397062639473, | |
| "grad_norm": 35.04706954956055, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 47.4024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037365716954694066, | |
| "grad_norm": 46.73086166381836, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 47.2966, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004151746328299341, | |
| "grad_norm": 13.349804878234863, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 46.118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004566920961129275, | |
| "grad_norm": 32.715354919433594, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 46.5278, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004982095593959209, | |
| "grad_norm": 1636.382568359375, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 118.1171, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005397270226789143, | |
| "grad_norm": 923.6768188476562, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 89.8615, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005812444859619077, | |
| "grad_norm": 432.9980773925781, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 47.3111, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0062276194924490115, | |
| "grad_norm": 636.610595703125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 48.9343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006642794125278946, | |
| "grad_norm": 1527.2369384765625, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 56.1184, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00705796875810888, | |
| "grad_norm": 286.00689697265625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 47.9084, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007473143390938813, | |
| "grad_norm": 39.90363311767578, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 46.906, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007888318023768747, | |
| "grad_norm": 16.350696563720703, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 46.0326, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008303492656598683, | |
| "grad_norm": 18.461915969848633, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 45.4721, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008718667289428616, | |
| "grad_norm": 34.859214782714844, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 44.6744, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00913384192225855, | |
| "grad_norm": 42.21925354003906, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 43.6556, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009549016555088484, | |
| "grad_norm": 54.80242156982422, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 42.6972, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009964191187918418, | |
| "grad_norm": 102.70449829101562, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 45.8084, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010379365820748353, | |
| "grad_norm": 1259.2509765625, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 115.2336, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010379365820748353, | |
| "eval_loss": 2.830770969390869, | |
| "eval_runtime": 389.2434, | |
| "eval_samples_per_second": 41.689, | |
| "eval_steps_per_second": 5.213, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.629552387915776e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |