| { | |
| "best_metric": 0.9987742304801941, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.606425702811245, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0321285140562249, | |
| "grad_norm": 0.32158681750297546, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0321285140562249, | |
| "eval_loss": 1.3230139017105103, | |
| "eval_runtime": 5.9411, | |
| "eval_samples_per_second": 35.347, | |
| "eval_steps_per_second": 4.545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0642570281124498, | |
| "grad_norm": 0.35555076599121094, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 0.3009185194969177, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1027, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1285140562248996, | |
| "grad_norm": 0.3456253707408905, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1433, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1606425702811245, | |
| "grad_norm": 0.3506094217300415, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2594, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 0.4312651753425598, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.387, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2248995983935743, | |
| "grad_norm": 0.6198199987411499, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3969, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2570281124497992, | |
| "grad_norm": 0.3235548436641693, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9537, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 0.46262267231941223, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.947, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.321285140562249, | |
| "grad_norm": 0.4304946959018707, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3534136546184739, | |
| "grad_norm": 0.3087094724178314, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9636, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 0.23648039996623993, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0569, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41767068273092367, | |
| "grad_norm": 0.3179496228694916, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.2459, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4497991967871486, | |
| "grad_norm": 0.31749600172042847, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3157, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 0.4612431228160858, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2573, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5140562248995983, | |
| "grad_norm": 0.20168350636959076, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8247, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5461847389558233, | |
| "grad_norm": 0.17371076345443726, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.87, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 0.19454284012317657, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.9399, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6104417670682731, | |
| "grad_norm": 0.1993064284324646, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9209, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.642570281124498, | |
| "grad_norm": 0.18901658058166504, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6746987951807228, | |
| "grad_norm": 0.2547932267189026, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1466, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7068273092369478, | |
| "grad_norm": 0.33584922552108765, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1172, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7389558232931727, | |
| "grad_norm": 0.3578781485557556, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.191, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 0.1538023203611374, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.8221, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8032128514056225, | |
| "grad_norm": 0.17102853953838348, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.868, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8032128514056225, | |
| "eval_loss": 1.0288419723510742, | |
| "eval_runtime": 5.9425, | |
| "eval_samples_per_second": 35.339, | |
| "eval_steps_per_second": 4.544, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8353413654618473, | |
| "grad_norm": 0.17465923726558685, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9016, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8674698795180723, | |
| "grad_norm": 0.1872902363538742, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8917, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8995983935742972, | |
| "grad_norm": 0.18722985684871674, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.0243, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9317269076305221, | |
| "grad_norm": 0.2619907855987549, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1796, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 0.31004104018211365, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9959839357429718, | |
| "grad_norm": 0.6074375510215759, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1173, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0281124497991967, | |
| "grad_norm": 0.514019787311554, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7883, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0602409638554218, | |
| "grad_norm": 0.23374691605567932, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8339, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0923694779116466, | |
| "grad_norm": 0.2548729479312897, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8329, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1244979919678715, | |
| "grad_norm": 0.2810096740722656, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.9055, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1566265060240963, | |
| "grad_norm": 0.355925977230072, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0052, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1887550200803212, | |
| "grad_norm": 0.4292905330657959, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1282, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2208835341365463, | |
| "grad_norm": 0.49879974126815796, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0253, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2530120481927711, | |
| "grad_norm": 0.27068158984184265, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6199, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.285140562248996, | |
| "grad_norm": 0.260896772146225, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9507, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3172690763052208, | |
| "grad_norm": 0.26006272435188293, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8103, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3493975903614457, | |
| "grad_norm": 0.27475443482398987, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8499, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3815261044176708, | |
| "grad_norm": 0.3011744022369385, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9216, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4136546184738956, | |
| "grad_norm": 0.37961646914482117, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0301, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4457831325301205, | |
| "grad_norm": 0.4721483886241913, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1092, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4779116465863453, | |
| "grad_norm": 0.5502549409866333, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.066, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5100401606425704, | |
| "grad_norm": 0.28434449434280396, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7651, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.2478226125240326, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8829, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5742971887550201, | |
| "grad_norm": 0.25373923778533936, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8507, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.606425702811245, | |
| "grad_norm": 0.2824363708496094, | |
| "learning_rate": 0.0, | |
| "loss": 0.8463, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.606425702811245, | |
| "eval_loss": 0.9987742304801941, | |
| "eval_runtime": 5.9338, | |
| "eval_samples_per_second": 35.391, | |
| "eval_steps_per_second": 4.55, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |