| { | |
| "best_metric": 0.27931803464889526, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3401360544217687, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006802721088435374, | |
| "grad_norm": 23.25275421142578, | |
| "learning_rate": 5e-05, | |
| "loss": 18.1545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006802721088435374, | |
| "eval_loss": 19.103919982910156, | |
| "eval_runtime": 20.256, | |
| "eval_samples_per_second": 48.874, | |
| "eval_steps_per_second": 6.122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 27.446414947509766, | |
| "learning_rate": 0.0001, | |
| "loss": 18.6688, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 25.350025177001953, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 17.7764, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 12.311461448669434, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 15.105, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 12.535967826843262, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 13.6968, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 11.613871574401855, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 13.0302, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 14.820775985717773, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 12.3503, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 20.303524017333984, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 9.8871, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 22.571229934692383, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 7.3865, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 25.140674591064453, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.1439, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07482993197278912, | |
| "grad_norm": 33.55000305175781, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.0219, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 40.43766403198242, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.9545, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08843537414965986, | |
| "grad_norm": 29.55443000793457, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.7465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 48.439945220947266, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4023, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 15.316900253295898, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.6828, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 18.673213958740234, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6678, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11564625850340136, | |
| "grad_norm": 21.781675338745117, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.2674, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 19.355789184570312, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1744, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1292517006802721, | |
| "grad_norm": 15.739516258239746, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6757, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 19.030834197998047, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.784, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 22.42937469482422, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5844, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 4.322623252868652, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4223, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1564625850340136, | |
| "grad_norm": 10.439550399780273, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6292, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 14.82199764251709, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1618, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 11.822050094604492, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.838, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "eval_loss": 0.6685309410095215, | |
| "eval_runtime": 20.2384, | |
| "eval_samples_per_second": 48.917, | |
| "eval_steps_per_second": 6.127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17687074829931973, | |
| "grad_norm": 11.028403282165527, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1345, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 7.536412239074707, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7655, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 6.885499000549316, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7078, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19727891156462585, | |
| "grad_norm": 6.023404121398926, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6575, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 4.4944071769714355, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3387, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2108843537414966, | |
| "grad_norm": 4.294863700866699, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.3278, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 2.723747968673706, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3085, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22448979591836735, | |
| "grad_norm": 2.808175563812256, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1762, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23129251700680273, | |
| "grad_norm": 1.71840500831604, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1883, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 1.6521344184875488, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 6.9142913818359375, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5569, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25170068027210885, | |
| "grad_norm": 4.149293422698975, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.6642, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2585034013605442, | |
| "grad_norm": 7.661333084106445, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7672, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "grad_norm": 3.253246784210205, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2413, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 3.304100513458252, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3499, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2789115646258503, | |
| "grad_norm": 3.464125394821167, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2569, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 3.86350154876709, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2346, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2925170068027211, | |
| "grad_norm": 5.176389694213867, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2529, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29931972789115646, | |
| "grad_norm": 5.685366630554199, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2564, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 4.789925575256348, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3129251700680272, | |
| "grad_norm": 3.4090046882629395, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1595, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3197278911564626, | |
| "grad_norm": 1.0902825593948364, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1533, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 1.636353611946106, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2823, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 5.387994289398193, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.6285, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 2.2211647033691406, | |
| "learning_rate": 0.0, | |
| "loss": 0.3492, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 0.27931803464889526, | |
| "eval_runtime": 20.268, | |
| "eval_samples_per_second": 48.845, | |
| "eval_steps_per_second": 6.118, | |
| "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": 2.2961298891341824e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |