| { | |
| "best_metric": 0.5340929627418518, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9259259259259259, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 0.5647748708724976, | |
| "learning_rate": 5e-05, | |
| "loss": 1.097, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "eval_loss": 1.6396740674972534, | |
| "eval_runtime": 4.1727, | |
| "eval_samples_per_second": 87.234, | |
| "eval_steps_per_second": 11.024, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 0.704931914806366, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.7352797985076904, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.2515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.6545394062995911, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.228, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 0.6046964526176453, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2025, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.5980863571166992, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.131, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12962962962962962, | |
| "grad_norm": 0.5863988399505615, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.0939, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.5570467114448547, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0675, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.5377064943313599, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.976, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 0.593476414680481, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9628, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2037037037037037, | |
| "grad_norm": 0.561056911945343, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9599, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.560419499874115, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9372, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.24074074074074073, | |
| "grad_norm": 0.25102630257606506, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6954, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25925925925925924, | |
| "grad_norm": 0.21997065842151642, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6822, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.2169683426618576, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.23189207911491394, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6494, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3148148148148148, | |
| "grad_norm": 0.24518410861492157, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6537, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.24312365055084229, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6322, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.35185185185185186, | |
| "grad_norm": 0.2416844218969345, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6625, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 0.26255324482917786, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6631, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.26637887954711914, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6135, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4074074074074074, | |
| "grad_norm": 0.2723131775856018, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5994, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.42592592592592593, | |
| "grad_norm": 0.2862944006919861, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5824, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.3188299238681793, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6065, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "grad_norm": 0.4002661406993866, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6144, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "eval_loss": 0.576792299747467, | |
| "eval_runtime": 4.1618, | |
| "eval_samples_per_second": 87.462, | |
| "eval_steps_per_second": 11.053, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.48148148148148145, | |
| "grad_norm": 0.16417062282562256, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5861, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.1619228571653366, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5484, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5185185185185185, | |
| "grad_norm": 0.17447136342525482, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5745, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5370370370370371, | |
| "grad_norm": 0.18351832032203674, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5973, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.1494884341955185, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5367, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5740740740740741, | |
| "grad_norm": 0.16889017820358276, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5395, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.1729159951210022, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.16859622299671173, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5238, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6296296296296297, | |
| "grad_norm": 0.18731187283992767, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5243, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6481481481481481, | |
| "grad_norm": 0.19786499440670013, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5568, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.20120374858379364, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5174, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6851851851851852, | |
| "grad_norm": 0.24167144298553467, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.543, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7037037037037037, | |
| "grad_norm": 0.15936322510242462, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5167, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.14347104728221893, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5224, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.15032237768173218, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5412, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7592592592592593, | |
| "grad_norm": 0.14347581565380096, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5128, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.15086627006530762, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5582, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7962962962962963, | |
| "grad_norm": 0.13948625326156616, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4918, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8148148148148148, | |
| "grad_norm": 0.1540198177099228, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5425, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.15320159494876862, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5285, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8518518518518519, | |
| "grad_norm": 0.16808032989501953, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.493, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8703703703703703, | |
| "grad_norm": 0.17464371025562286, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.525, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.18388594686985016, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5178, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9074074074074074, | |
| "grad_norm": 0.20205292105674744, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5219, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "grad_norm": 0.3138573467731476, | |
| "learning_rate": 0.0, | |
| "loss": 0.4853, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9259259259259259, | |
| "eval_loss": 0.5340929627418518, | |
| "eval_runtime": 4.1714, | |
| "eval_samples_per_second": 87.26, | |
| "eval_steps_per_second": 11.027, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |