| { | |
| "best_metric": 10.349431037902832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.54421768707483, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010884353741496598, | |
| "grad_norm": 0.29789671301841736, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010884353741496598, | |
| "eval_loss": 10.38390064239502, | |
| "eval_runtime": 0.6508, | |
| "eval_samples_per_second": 951.109, | |
| "eval_steps_per_second": 119.849, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021768707482993196, | |
| "grad_norm": 0.2871239483356476, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3839, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0326530612244898, | |
| "grad_norm": 0.29564058780670166, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3841, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04353741496598639, | |
| "grad_norm": 0.297428697347641, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3827, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 0.30088019371032715, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3804, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0653061224489796, | |
| "grad_norm": 0.2966240346431732, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.38, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0761904761904762, | |
| "grad_norm": 0.30285754799842834, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3788, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08707482993197278, | |
| "grad_norm": 0.3085600435733795, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3783, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09795918367346938, | |
| "grad_norm": 0.3070805072784424, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3761, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 0.3117634952068329, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11972789115646258, | |
| "grad_norm": 0.33045291900634766, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3738, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1306122448979592, | |
| "grad_norm": 0.331281840801239, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.372, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1414965986394558, | |
| "grad_norm": 0.32997581362724304, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3734, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "grad_norm": 0.3284686803817749, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3721, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.34724903106689453, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3708, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17414965986394557, | |
| "grad_norm": 0.35911825299263, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3689, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18503401360544217, | |
| "grad_norm": 0.3483351469039917, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3674, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19591836734693877, | |
| "grad_norm": 0.35687845945358276, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3663, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20680272108843537, | |
| "grad_norm": 0.3608298897743225, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3649, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21768707482993196, | |
| "grad_norm": 0.36443498730659485, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3643, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.3776651620864868, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3623, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23945578231292516, | |
| "grad_norm": 0.37512120604515076, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3611, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2503401360544218, | |
| "grad_norm": 0.3709583580493927, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3608, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2612244897959184, | |
| "grad_norm": 0.3929137885570526, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3592, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "grad_norm": 0.370810866355896, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3597, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.272108843537415, | |
| "eval_loss": 10.358575820922852, | |
| "eval_runtime": 0.6466, | |
| "eval_samples_per_second": 957.305, | |
| "eval_steps_per_second": 120.63, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2829931972789116, | |
| "grad_norm": 0.42081892490386963, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3586, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2938775510204082, | |
| "grad_norm": 0.40955573320388794, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3587, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "grad_norm": 0.4053417146205902, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3575, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.31564625850340133, | |
| "grad_norm": 0.4076749384403229, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3567, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.40912002325057983, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3548, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.33741496598639453, | |
| "grad_norm": 0.41830697655677795, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3538, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.34829931972789113, | |
| "grad_norm": 0.41212475299835205, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.35918367346938773, | |
| "grad_norm": 0.4229467809200287, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3524, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37006802721088433, | |
| "grad_norm": 0.40772733092308044, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3524, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.41412273049354553, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3522, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39183673469387753, | |
| "grad_norm": 0.41297608613967896, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3526, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.40272108843537413, | |
| "grad_norm": 0.38842713832855225, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3519, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.41360544217687073, | |
| "grad_norm": 0.4429492652416229, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3524, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.42448979591836733, | |
| "grad_norm": 0.44514551758766174, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3516, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.43537414965986393, | |
| "grad_norm": 0.4472653865814209, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3509, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44625850340136053, | |
| "grad_norm": 0.44553062319755554, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3499, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.433199018239975, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3501, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.46802721088435373, | |
| "grad_norm": 0.4309545159339905, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3486, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.47891156462585033, | |
| "grad_norm": 0.43892306089401245, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3485, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.43471524119377136, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.35, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5006802721088436, | |
| "grad_norm": 0.4365433156490326, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3491, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5115646258503401, | |
| "grad_norm": 0.40179312229156494, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3504, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5224489795918368, | |
| "grad_norm": 0.4212394654750824, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3486, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.4362102150917053, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.348, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "grad_norm": 0.4109918475151062, | |
| "learning_rate": 0.0, | |
| "loss": 10.3504, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54421768707483, | |
| "eval_loss": 10.349431037902832, | |
| "eval_runtime": 0.6456, | |
| "eval_samples_per_second": 958.852, | |
| "eval_steps_per_second": 120.825, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |