| { | |
| "best_metric": 1.5668654441833496, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.40526849037487334, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008105369807497468, | |
| "grad_norm": 7.904720783233643, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4502, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008105369807497468, | |
| "eval_loss": 3.2280056476593018, | |
| "eval_runtime": 23.8854, | |
| "eval_samples_per_second": 34.791, | |
| "eval_steps_per_second": 4.354, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016210739614994935, | |
| "grad_norm": 8.790853500366211, | |
| "learning_rate": 0.0001, | |
| "loss": 2.439, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0243161094224924, | |
| "grad_norm": 4.56343412399292, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.4184, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03242147922998987, | |
| "grad_norm": 4.2467732429504395, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.040526849037487336, | |
| "grad_norm": 1.8644218444824219, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8382, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 1.9568532705307007, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.8509, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": 1.110546350479126, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.8251, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06484295845997974, | |
| "grad_norm": 1.1750296354293823, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9507, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0729483282674772, | |
| "grad_norm": 1.0463156700134277, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9353, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08105369807497467, | |
| "grad_norm": 0.6957851648330688, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08915906788247213, | |
| "grad_norm": 1.9994052648544312, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0345, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0972644376899696, | |
| "grad_norm": 1.3627257347106934, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.3265, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10536980749746708, | |
| "grad_norm": 0.2764863073825836, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5045, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": 0.2644999921321869, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.392, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12158054711246201, | |
| "grad_norm": 0.22837163507938385, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2861, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12968591691995948, | |
| "grad_norm": 0.22888338565826416, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.2934, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13779128672745694, | |
| "grad_norm": 0.21393026411533356, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3441, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1458966565349544, | |
| "grad_norm": 0.17430530488491058, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3398, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1540020263424519, | |
| "grad_norm": 0.21894441545009613, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4612, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16210739614994935, | |
| "grad_norm": 0.2172875702381134, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5441, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": 0.22415199875831604, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6691, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17831813576494426, | |
| "grad_norm": 0.33313316106796265, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.763, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18642350557244175, | |
| "grad_norm": 0.26398777961730957, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.873, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1945288753799392, | |
| "grad_norm": 0.3155348300933838, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0692, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20263424518743667, | |
| "grad_norm": 0.5277456641197205, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.3044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20263424518743667, | |
| "eval_loss": 1.598935842514038, | |
| "eval_runtime": 23.8955, | |
| "eval_samples_per_second": 34.776, | |
| "eval_steps_per_second": 4.352, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21073961499493415, | |
| "grad_norm": 0.250800222158432, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4023, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2188449848024316, | |
| "grad_norm": 0.24198980629444122, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3362, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": 0.18812240660190582, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3514, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23505572441742653, | |
| "grad_norm": 0.2894032597541809, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2495, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24316109422492402, | |
| "grad_norm": 0.21906958520412445, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.444, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2512664640324215, | |
| "grad_norm": 0.2103070467710495, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.5269, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.25937183383991896, | |
| "grad_norm": 0.2812809646129608, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4841, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2674772036474164, | |
| "grad_norm": 0.24371977150440216, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.664, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2755825734549139, | |
| "grad_norm": 0.26612022519111633, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6387, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": 0.21530385315418243, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.7245, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2917933130699088, | |
| "grad_norm": 0.2958863377571106, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.9309, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2998986828774063, | |
| "grad_norm": 0.4526556730270386, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.8786, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3080040526849038, | |
| "grad_norm": 0.14817576110363007, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4305, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3161094224924012, | |
| "grad_norm": 0.12831979990005493, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.2881, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3242147922998987, | |
| "grad_norm": 0.15420038998126984, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.2267, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3323201621073962, | |
| "grad_norm": 0.12769393622875214, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2373, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 0.13905879855155945, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3497, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3485309017223911, | |
| "grad_norm": 0.13880909979343414, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.3607, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3566362715298885, | |
| "grad_norm": 0.12389617413282394, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4539, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.364741641337386, | |
| "grad_norm": 0.1297137439250946, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3728470111448835, | |
| "grad_norm": 0.16556890308856964, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6069, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.15601517260074615, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6373, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3890577507598784, | |
| "grad_norm": 0.16503740847110748, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.7971, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3971631205673759, | |
| "grad_norm": 0.21679052710533142, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.9231, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.40526849037487334, | |
| "grad_norm": 0.39398708939552307, | |
| "learning_rate": 0.0, | |
| "loss": 2.1675, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40526849037487334, | |
| "eval_loss": 1.5668654441833496, | |
| "eval_runtime": 23.9003, | |
| "eval_samples_per_second": 34.769, | |
| "eval_steps_per_second": 4.351, | |
| "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": 5.305284264198144e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |