| { | |
| "best_metric": 0.7348595261573792, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.081441922563418, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021361815754339118, | |
| "grad_norm": 1.6046092510223389, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021361815754339118, | |
| "eval_loss": 5.955810070037842, | |
| "eval_runtime": 3.9169, | |
| "eval_samples_per_second": 80.676, | |
| "eval_steps_per_second": 10.212, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042723631508678236, | |
| "grad_norm": 2.5250778198242188, | |
| "learning_rate": 0.0001, | |
| "loss": 4.313, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06408544726301736, | |
| "grad_norm": 2.5050735473632812, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.7944, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08544726301735647, | |
| "grad_norm": 3.702223539352417, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.2291, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1068090787716956, | |
| "grad_norm": 5.475708961486816, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.4467, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12817089452603472, | |
| "grad_norm": 7.406168460845947, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.2887, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 7.808836936950684, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.0059, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17089452603471295, | |
| "grad_norm": 7.647904396057129, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.19225634178905207, | |
| "grad_norm": 7.238813400268555, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.5267, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2136181575433912, | |
| "grad_norm": 7.758616924285889, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9833, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2349799732977303, | |
| "grad_norm": 9.739021301269531, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.8584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25634178905206945, | |
| "grad_norm": 4.0756707191467285, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.91, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.27770360480640854, | |
| "grad_norm": 4.203242301940918, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 4.677343845367432, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9641, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3204272363150868, | |
| "grad_norm": 5.733473300933838, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9235, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3417890520694259, | |
| "grad_norm": 2.1184158325195312, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.979, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36315086782376504, | |
| "grad_norm": 2.2146058082580566, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8419, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.38451268357810414, | |
| "grad_norm": 1.4407413005828857, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7433, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.40587449933244324, | |
| "grad_norm": 2.29788875579834, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8774, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4272363150867824, | |
| "grad_norm": 1.3592867851257324, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 2.1214427947998047, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.654, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4699599465954606, | |
| "grad_norm": 1.5212901830673218, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5561, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.49132176234979974, | |
| "grad_norm": 2.9649057388305664, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6371, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5126835781041389, | |
| "grad_norm": 0.8475658893585205, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2951, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5340453938584779, | |
| "grad_norm": 2.3448703289031982, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7157, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5340453938584779, | |
| "eval_loss": 0.8425735235214233, | |
| "eval_runtime": 3.9279, | |
| "eval_samples_per_second": 80.451, | |
| "eval_steps_per_second": 10.184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5554072096128171, | |
| "grad_norm": 2.1120316982269287, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7252, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5767690253671562, | |
| "grad_norm": 1.448875069618225, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6728, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5981308411214953, | |
| "grad_norm": 0.9731662273406982, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5703, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6194926568758344, | |
| "grad_norm": 1.6093170642852783, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6493, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6408544726301736, | |
| "grad_norm": 1.569778323173523, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6615, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6622162883845126, | |
| "grad_norm": 1.0836259126663208, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6269, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6835781041388518, | |
| "grad_norm": 0.8956681489944458, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5857, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7049399198931909, | |
| "grad_norm": 1.2497748136520386, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4974, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7263017356475301, | |
| "grad_norm": 1.2253942489624023, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5433, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "grad_norm": 0.5431591272354126, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2895, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7690253671562083, | |
| "grad_norm": 1.2693477869033813, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.6153, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7903871829105474, | |
| "grad_norm": 1.342617392539978, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7099, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8117489986648865, | |
| "grad_norm": 0.7940839529037476, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5316, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8331108144192256, | |
| "grad_norm": 1.0928740501403809, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6798, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8544726301735648, | |
| "grad_norm": 1.2615504264831543, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5477, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8758344459279038, | |
| "grad_norm": 0.9154185056686401, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6583, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.8197636008262634, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.549, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9185580774365821, | |
| "grad_norm": 0.6741806268692017, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5017, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9399198931909212, | |
| "grad_norm": 0.8679367899894714, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5409, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9612817089452603, | |
| "grad_norm": 0.7181217670440674, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4768, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9826435246995995, | |
| "grad_norm": 1.0969020128250122, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.49, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0173564753004005, | |
| "grad_norm": 2.3091795444488525, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2256, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0387182910547397, | |
| "grad_norm": 1.3182036876678467, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5804, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0600801068090788, | |
| "grad_norm": 1.2283663749694824, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5296, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.081441922563418, | |
| "grad_norm": 1.7760813236236572, | |
| "learning_rate": 0.0, | |
| "loss": 0.5364, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.081441922563418, | |
| "eval_loss": 0.7348595261573792, | |
| "eval_runtime": 3.9346, | |
| "eval_samples_per_second": 80.314, | |
| "eval_steps_per_second": 10.166, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.0648340363267277e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |