| { | |
| "best_metric": 5.745617389678955, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15561174868702587, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031122349737405172, | |
| "grad_norm": 12.367483139038086, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031122349737405172, | |
| "eval_loss": 14.697776794433594, | |
| "eval_runtime": 51.2827, | |
| "eval_samples_per_second": 42.217, | |
| "eval_steps_per_second": 5.284, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0062244699474810344, | |
| "grad_norm": 18.720218658447266, | |
| "learning_rate": 0.0001, | |
| "loss": 11.1734, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009336704921221552, | |
| "grad_norm": 22.912841796875, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 12.0145, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012448939894962069, | |
| "grad_norm": 18.14128303527832, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.5955, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015561174868702588, | |
| "grad_norm": 15.235579490661621, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.9424, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018673409842443103, | |
| "grad_norm": 17.73942756652832, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.4111, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02178564481618362, | |
| "grad_norm": 19.625747680664062, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.4535, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.024897879789924138, | |
| "grad_norm": 21.149904251098633, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.6805, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028010114763664655, | |
| "grad_norm": 22.261550903320312, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.6755, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031122349737405176, | |
| "grad_norm": 23.148033142089844, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 8.4377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03423458471114569, | |
| "grad_norm": 82.3243179321289, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 16.8757, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03734681968488621, | |
| "grad_norm": 89.35270690917969, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 17.371, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.040459054658626724, | |
| "grad_norm": 36.61917495727539, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 9.4905, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04357128963236724, | |
| "grad_norm": 39.98612976074219, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.9403, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04668352460610776, | |
| "grad_norm": 16.919132232666016, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 7.5666, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.049795759579848276, | |
| "grad_norm": 11.894121170043945, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.7462, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05290799455358879, | |
| "grad_norm": 9.204946517944336, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.3437, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05602022952732931, | |
| "grad_norm": 9.868268966674805, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.4335, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.059132464501069834, | |
| "grad_norm": 15.351909637451172, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.7056, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06224469947481035, | |
| "grad_norm": 12.843435287475586, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.4079, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06535693444855087, | |
| "grad_norm": 9.099300384521484, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.023, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06846916942229138, | |
| "grad_norm": 7.443927764892578, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.0051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0715814043960319, | |
| "grad_norm": 39.088592529296875, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 8.9596, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07469363936977241, | |
| "grad_norm": 61.89222717285156, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.8615, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07780587434351294, | |
| "grad_norm": 66.38684844970703, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.2523, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07780587434351294, | |
| "eval_loss": 7.096124172210693, | |
| "eval_runtime": 49.7838, | |
| "eval_samples_per_second": 43.488, | |
| "eval_steps_per_second": 5.444, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08091810931725345, | |
| "grad_norm": 36.23772048950195, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1879, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08403034429099397, | |
| "grad_norm": 28.252685546875, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 8.9334, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08714257926473448, | |
| "grad_norm": 21.92393684387207, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 7.6344, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.090254814238475, | |
| "grad_norm": 19.237417221069336, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 7.2, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09336704921221552, | |
| "grad_norm": 19.00653839111328, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.7892, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09647928418595604, | |
| "grad_norm": 9.482794761657715, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.8281, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09959151915969655, | |
| "grad_norm": 7.041558742523193, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.985, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10270375413343708, | |
| "grad_norm": 7.1093878746032715, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.0649, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10581598910717759, | |
| "grad_norm": 7.380600929260254, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.0434, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10892822408091811, | |
| "grad_norm": 11.326904296875, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.7365, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11204045905465862, | |
| "grad_norm": 67.85647583007812, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 9.864, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11515269402839914, | |
| "grad_norm": 68.0254135131836, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 9.6725, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11826492900213967, | |
| "grad_norm": 13.48176383972168, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.5964, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12137716397588018, | |
| "grad_norm": 14.436902046203613, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.5174, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1244893989496207, | |
| "grad_norm": 11.990131378173828, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 6.0007, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1276016339233612, | |
| "grad_norm": 7.9069085121154785, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 5.5727, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13071386889710174, | |
| "grad_norm": 7.264441013336182, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 5.4522, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13382610387084226, | |
| "grad_norm": 6.674943923950195, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 5.0556, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13693833884458276, | |
| "grad_norm": 9.692429542541504, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.0145, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14005057381832328, | |
| "grad_norm": 9.313735961914062, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.9252, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1431628087920638, | |
| "grad_norm": 9.679069519042969, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.9762, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14627504376580433, | |
| "grad_norm": 9.562905311584473, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.1521, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14938727873954483, | |
| "grad_norm": 15.053668022155762, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.0278, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15249951371328535, | |
| "grad_norm": 66.99755859375, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 9.3966, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15561174868702587, | |
| "grad_norm": 68.58241271972656, | |
| "learning_rate": 0.0, | |
| "loss": 9.256, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15561174868702587, | |
| "eval_loss": 5.745617389678955, | |
| "eval_runtime": 51.0026, | |
| "eval_samples_per_second": 42.449, | |
| "eval_steps_per_second": 5.313, | |
| "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 | |
| } | |