| { | |
| "best_metric": 1.0260274410247803, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0255427841634739, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020434227330779056, | |
| "grad_norm": 7.360929489135742, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 17.3749, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020434227330779056, | |
| "eval_loss": 1.138229489326477, | |
| "eval_runtime": 21.2669, | |
| "eval_samples_per_second": 7.759, | |
| "eval_steps_per_second": 1.975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04086845466155811, | |
| "grad_norm": 6.317312717437744, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 17.9715, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06130268199233716, | |
| "grad_norm": 6.0731658935546875, | |
| "learning_rate": 1.5e-06, | |
| "loss": 16.5836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08173690932311622, | |
| "grad_norm": 5.645073413848877, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 16.209, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10217113665389528, | |
| "grad_norm": 7.367918014526367, | |
| "learning_rate": 2.5e-06, | |
| "loss": 17.2826, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12260536398467432, | |
| "grad_norm": 6.8022966384887695, | |
| "learning_rate": 3e-06, | |
| "loss": 16.758, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14303959131545338, | |
| "grad_norm": 6.725194931030273, | |
| "learning_rate": 3.5000000000000004e-06, | |
| "loss": 19.0619, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16347381864623245, | |
| "grad_norm": 6.638408660888672, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 17.6671, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1839080459770115, | |
| "grad_norm": 5.699502468109131, | |
| "learning_rate": 4.5e-06, | |
| "loss": 17.215, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20434227330779056, | |
| "grad_norm": 6.1157097816467285, | |
| "learning_rate": 5e-06, | |
| "loss": 18.4525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2247765006385696, | |
| "grad_norm": 5.536643981933594, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 15.6788, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24521072796934865, | |
| "grad_norm": 7.206900596618652, | |
| "learning_rate": 6e-06, | |
| "loss": 17.0678, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2656449553001277, | |
| "grad_norm": 5.241375923156738, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 18.2783, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.28607918263090676, | |
| "grad_norm": 5.224916934967041, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 18.9804, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3065134099616858, | |
| "grad_norm": 4.611645698547363, | |
| "learning_rate": 7.5e-06, | |
| "loss": 18.8118, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3269476372924649, | |
| "grad_norm": 5.321063995361328, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 16.1292, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.34738186462324394, | |
| "grad_norm": 4.779561519622803, | |
| "learning_rate": 8.500000000000002e-06, | |
| "loss": 17.0707, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.367816091954023, | |
| "grad_norm": 4.141415119171143, | |
| "learning_rate": 9e-06, | |
| "loss": 19.2067, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.388250319284802, | |
| "grad_norm": 4.518102645874023, | |
| "learning_rate": 9.5e-06, | |
| "loss": 16.8985, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4086845466155811, | |
| "grad_norm": 4.083268165588379, | |
| "learning_rate": 1e-05, | |
| "loss": 18.5685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42911877394636017, | |
| "grad_norm": 4.17296028137207, | |
| "learning_rate": 1.05e-05, | |
| "loss": 16.5411, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4495530012771392, | |
| "grad_norm": 3.7888073921203613, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 16.498, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46998722860791825, | |
| "grad_norm": 3.7531864643096924, | |
| "learning_rate": 1.1500000000000002e-05, | |
| "loss": 15.8281, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4904214559386973, | |
| "grad_norm": 3.5403201580047607, | |
| "learning_rate": 1.2e-05, | |
| "loss": 16.5056, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5108556832694764, | |
| "grad_norm": 3.830643653869629, | |
| "learning_rate": 1.25e-05, | |
| "loss": 16.6906, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5108556832694764, | |
| "eval_loss": 1.084327220916748, | |
| "eval_runtime": 21.5708, | |
| "eval_samples_per_second": 7.649, | |
| "eval_steps_per_second": 1.947, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5312899106002554, | |
| "grad_norm": 3.512051582336426, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 17.1562, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 3.581163167953491, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 15.3294, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5721583652618135, | |
| "grad_norm": 3.7532386779785156, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 18.2124, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 3.3712620735168457, | |
| "learning_rate": 1.45e-05, | |
| "loss": 15.1985, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6130268199233716, | |
| "grad_norm": 3.74042010307312, | |
| "learning_rate": 1.5e-05, | |
| "loss": 16.3185, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6334610472541508, | |
| "grad_norm": 3.747729778289795, | |
| "learning_rate": 1.55e-05, | |
| "loss": 18.091, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6538952745849298, | |
| "grad_norm": 3.3717548847198486, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 15.5985, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6743295019157088, | |
| "grad_norm": 3.1136016845703125, | |
| "learning_rate": 1.65e-05, | |
| "loss": 16.1861, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6947637292464879, | |
| "grad_norm": 2.9378445148468018, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 15.428, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7151979565772669, | |
| "grad_norm": 3.0630242824554443, | |
| "learning_rate": 1.75e-05, | |
| "loss": 15.6852, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.735632183908046, | |
| "grad_norm": 3.5427470207214355, | |
| "learning_rate": 1.8e-05, | |
| "loss": 15.8646, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.756066411238825, | |
| "grad_norm": 3.6774771213531494, | |
| "learning_rate": 1.85e-05, | |
| "loss": 15.4281, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.776500638569604, | |
| "grad_norm": 3.539029836654663, | |
| "learning_rate": 1.9e-05, | |
| "loss": 16.3628, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7969348659003831, | |
| "grad_norm": 3.6181910037994385, | |
| "learning_rate": 1.9500000000000003e-05, | |
| "loss": 16.0907, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8173690932311622, | |
| "grad_norm": 3.2122557163238525, | |
| "learning_rate": 2e-05, | |
| "loss": 16.8239, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8378033205619413, | |
| "grad_norm": 3.049232006072998, | |
| "learning_rate": 2.05e-05, | |
| "loss": 17.2511, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8582375478927203, | |
| "grad_norm": 3.254066228866577, | |
| "learning_rate": 2.1e-05, | |
| "loss": 16.2736, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8786717752234994, | |
| "grad_norm": 3.0137479305267334, | |
| "learning_rate": 2.15e-05, | |
| "loss": 16.5703, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8991060025542784, | |
| "grad_norm": 3.380715847015381, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 16.8219, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9195402298850575, | |
| "grad_norm": 2.935159921646118, | |
| "learning_rate": 2.25e-05, | |
| "loss": 16.5484, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9399744572158365, | |
| "grad_norm": 2.9660491943359375, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 15.6773, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9604086845466155, | |
| "grad_norm": 2.7908406257629395, | |
| "learning_rate": 2.35e-05, | |
| "loss": 15.7697, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9808429118773946, | |
| "grad_norm": 3.0066637992858887, | |
| "learning_rate": 2.4e-05, | |
| "loss": 17.0586, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0051085568326947, | |
| "grad_norm": 3.090890645980835, | |
| "learning_rate": 2.45e-05, | |
| "loss": 19.5984, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0255427841634739, | |
| "grad_norm": 2.8104114532470703, | |
| "learning_rate": 2.5e-05, | |
| "loss": 16.0491, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0255427841634739, | |
| "eval_loss": 1.0260274410247803, | |
| "eval_runtime": 21.5925, | |
| "eval_samples_per_second": 7.642, | |
| "eval_steps_per_second": 1.945, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6709702668294554e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |