| { | |
| "best_metric": 1.3382925987243652, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06685050555694827, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013370101111389655, | |
| "grad_norm": 45.61884689331055, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013370101111389655, | |
| "eval_loss": 2.1031837463378906, | |
| "eval_runtime": 144.5887, | |
| "eval_samples_per_second": 34.851, | |
| "eval_steps_per_second": 4.357, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002674020222277931, | |
| "grad_norm": 61.574256896972656, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8337, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004011030333416896, | |
| "grad_norm": 47.025516510009766, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7141, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005348040444555862, | |
| "grad_norm": 42.46583938598633, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5738, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0066850505556948275, | |
| "grad_norm": 38.542701721191406, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3803, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008022060666833792, | |
| "grad_norm": 38.241188049316406, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4181, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009359070777972758, | |
| "grad_norm": 37.101680755615234, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010696080889111724, | |
| "grad_norm": 36.86508560180664, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3025, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01203309100025069, | |
| "grad_norm": 35.759864807128906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4198, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013370101111389655, | |
| "grad_norm": 37.84111404418945, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3385, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01470711122252862, | |
| "grad_norm": 42.640438079833984, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2823, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016044121333667585, | |
| "grad_norm": 44.959407806396484, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3878, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01738113144480655, | |
| "grad_norm": 45.82082748413086, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5677, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018718141555945516, | |
| "grad_norm": 28.606582641601562, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6885, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02005515166708448, | |
| "grad_norm": 23.147939682006836, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4806, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021392161778223447, | |
| "grad_norm": 23.436861038208008, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4649, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022729171889362413, | |
| "grad_norm": 26.963802337646484, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3901, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02406618200050138, | |
| "grad_norm": 28.463054656982422, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3727, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025403192111640344, | |
| "grad_norm": 28.883792877197266, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1623, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02674020222277931, | |
| "grad_norm": 30.714143753051758, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3107, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028077212333918276, | |
| "grad_norm": 32.90729522705078, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3789, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02941422244505724, | |
| "grad_norm": 33.87862014770508, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3426, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030751232556196207, | |
| "grad_norm": 34.535404205322266, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2615, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03208824266733517, | |
| "grad_norm": 45.40268325805664, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3269, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033425252778474135, | |
| "grad_norm": 45.20197296142578, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033425252778474135, | |
| "eval_loss": 1.3706095218658447, | |
| "eval_runtime": 145.5182, | |
| "eval_samples_per_second": 34.628, | |
| "eval_steps_per_second": 4.329, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0347622628896131, | |
| "grad_norm": 25.990808486938477, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5636, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.036099273000752066, | |
| "grad_norm": 22.69860076904297, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5672, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03743628311189103, | |
| "grad_norm": 22.71676254272461, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.43, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03877329322303, | |
| "grad_norm": 23.096960067749023, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4142, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04011030333416896, | |
| "grad_norm": 23.61298942565918, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04144731344530793, | |
| "grad_norm": 25.191864013671875, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3509, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.042784323556446895, | |
| "grad_norm": 25.648237228393555, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.333, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04412133366758586, | |
| "grad_norm": 27.153898239135742, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3001, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045458343778724826, | |
| "grad_norm": 28.19595718383789, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4561, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04679535388986379, | |
| "grad_norm": 29.54447364807129, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3213, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04813236400100276, | |
| "grad_norm": 31.437786102294922, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1158, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04946937411214172, | |
| "grad_norm": 37.75790023803711, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2325, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05080638422328069, | |
| "grad_norm": 31.451086044311523, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3948, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.052143394334419654, | |
| "grad_norm": 19.551162719726562, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5541, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05348040444555862, | |
| "grad_norm": 20.893918991088867, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5098, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.054817414556697586, | |
| "grad_norm": 21.392484664916992, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4131, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05615442466783655, | |
| "grad_norm": 21.886232376098633, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.348, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05749143477897552, | |
| "grad_norm": 22.548765182495117, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2932, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05882844489011448, | |
| "grad_norm": 24.45055389404297, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2246, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06016545500125345, | |
| "grad_norm": 25.212177276611328, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2447, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.061502465112392414, | |
| "grad_norm": 25.975236892700195, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2924, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06283947522353138, | |
| "grad_norm": 28.950206756591797, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.317, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06417648533467034, | |
| "grad_norm": 29.081235885620117, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.136, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06551349544580931, | |
| "grad_norm": 33.672969818115234, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2239, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06685050555694827, | |
| "grad_norm": 46.237857818603516, | |
| "learning_rate": 0.0, | |
| "loss": 1.2762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06685050555694827, | |
| "eval_loss": 1.3382925987243652, | |
| "eval_runtime": 292.4772, | |
| "eval_samples_per_second": 17.229, | |
| "eval_steps_per_second": 2.154, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |