| { | |
| "best_metric": 0.006335424259305, | |
| "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": 8.384090423583984, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1569, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006802721088435374, | |
| "eval_loss": 7.6087327003479, | |
| "eval_runtime": 19.4438, | |
| "eval_samples_per_second": 50.916, | |
| "eval_steps_per_second": 6.377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 9.042967796325684, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3495, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 7.906692028045654, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.1599, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 7.033726215362549, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.2656, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 7.941586494445801, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.3318, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 8.245903968811035, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0846, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 8.305931091308594, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3041, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 6.832699775695801, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5622, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 4.221113204956055, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.1772, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 2.9281857013702393, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07482993197278912, | |
| "grad_norm": 3.394575357437134, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9967, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 5.905345439910889, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1588, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08843537414965986, | |
| "grad_norm": 4.155373573303223, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7795, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 2.751556634902954, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1565, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 1.0200952291488647, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1343, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 0.6103468537330627, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0584, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11564625850340136, | |
| "grad_norm": 0.23342931270599365, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0042, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 1.3207299709320068, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.017, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1292517006802721, | |
| "grad_norm": 0.262893944978714, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0029, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 0.7945185303688049, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0357, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.5545347929000854, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0314, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 0.06888148933649063, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.001, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1564625850340136, | |
| "grad_norm": 0.6578580737113953, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0213, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.9135988354682922, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0296, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 1.6072754859924316, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0584, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "eval_loss": 0.03923076018691063, | |
| "eval_runtime": 17.9785, | |
| "eval_samples_per_second": 55.066, | |
| "eval_steps_per_second": 6.897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17687074829931973, | |
| "grad_norm": 0.8757835030555725, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0741, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 0.6202448010444641, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0278, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.2728913724422455, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0152, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.19727891156462585, | |
| "grad_norm": 0.35162627696990967, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0054, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 0.26197877526283264, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0038, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2108843537414966, | |
| "grad_norm": 0.02254539169371128, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0002, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 0.5768834948539734, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0592, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22448979591836735, | |
| "grad_norm": 0.03499084711074829, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0004, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23129251700680273, | |
| "grad_norm": 0.11083720624446869, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.001, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 0.09705158323049545, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0009, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.25740352272987366, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0076, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.25170068027210885, | |
| "grad_norm": 0.5679620504379272, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0165, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2585034013605442, | |
| "grad_norm": 0.4646860659122467, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0172, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "grad_norm": 0.19410698115825653, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.004, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 0.2193833589553833, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2789115646258503, | |
| "grad_norm": 0.6219828724861145, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.014, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.018709324300289154, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0003, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2925170068027211, | |
| "grad_norm": 0.037566523998975754, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0003, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.29931972789115646, | |
| "grad_norm": 0.37556684017181396, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0064, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 0.027847126126289368, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0002, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3129251700680272, | |
| "grad_norm": 0.015570895746350288, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0003, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3197278911564626, | |
| "grad_norm": 0.3432367146015167, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.005, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.11973174661397934, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0015, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.04032721742987633, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0005, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "grad_norm": 0.1603790819644928, | |
| "learning_rate": 0.0, | |
| "loss": 0.0019, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3401360544217687, | |
| "eval_loss": 0.006335424259305, | |
| "eval_runtime": 18.3293, | |
| "eval_samples_per_second": 54.012, | |
| "eval_steps_per_second": 6.765, | |
| "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": 2.234825437211525e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |