| { | |
| "best_metric": 1.2535191774368286, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3472222222222222, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006944444444444444, | |
| "grad_norm": 3.476346254348755, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006944444444444444, | |
| "eval_loss": 4.7398810386657715, | |
| "eval_runtime": 29.857, | |
| "eval_samples_per_second": 32.488, | |
| "eval_steps_per_second": 4.086, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013888888888888888, | |
| "grad_norm": 3.7576146125793457, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5563, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020833333333333332, | |
| "grad_norm": 3.2495226860046387, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.4202, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 2.8715317249298096, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7515, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.034722222222222224, | |
| "grad_norm": 3.1827681064605713, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1039, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 3.257744789123535, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4059, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04861111111111111, | |
| "grad_norm": 3.1038901805877686, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.8887, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 3.184278726577759, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5376, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 2.082414150238037, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.3516, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06944444444444445, | |
| "grad_norm": 1.6695497035980225, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3557, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0763888888888889, | |
| "grad_norm": 1.8141134977340698, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4042, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.9131998419761658, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3845, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09027777777777778, | |
| "grad_norm": 8.301287651062012, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.0785, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09722222222222222, | |
| "grad_norm": 1.9383556842803955, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2627, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10416666666666667, | |
| "grad_norm": 1.2070971727371216, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2195, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.8308581709861755, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1975, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11805555555555555, | |
| "grad_norm": 0.7211664319038391, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1921, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.5430946946144104, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2082, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13194444444444445, | |
| "grad_norm": 1.2237274646759033, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2241, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 0.4934002757072449, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14583333333333334, | |
| "grad_norm": 0.44239938259124756, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2009, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1527777777777778, | |
| "grad_norm": 0.3797169625759125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2146, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1597222222222222, | |
| "grad_norm": 0.38971444964408875, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2059, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 1.097565770149231, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.26, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1736111111111111, | |
| "grad_norm": 0.7389172911643982, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2768, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1736111111111111, | |
| "eval_loss": 1.315967321395874, | |
| "eval_runtime": 30.0845, | |
| "eval_samples_per_second": 32.243, | |
| "eval_steps_per_second": 4.055, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18055555555555555, | |
| "grad_norm": 4.528706073760986, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2754, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 1.2604354619979858, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1671, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19444444444444445, | |
| "grad_norm": 1.2874277830123901, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.193, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2013888888888889, | |
| "grad_norm": 0.8460001349449158, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1593, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 0.30335867404937744, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2152777777777778, | |
| "grad_norm": 1.150852084159851, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1991, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 1.0014760494232178, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2075, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22916666666666666, | |
| "grad_norm": 1.1253355741500854, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2038, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2361111111111111, | |
| "grad_norm": 0.4158329665660858, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2013, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24305555555555555, | |
| "grad_norm": 0.3990498483181, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.179, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.34036171436309814, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1811, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2569444444444444, | |
| "grad_norm": 0.3939284384250641, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2234, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2638888888888889, | |
| "grad_norm": 2.1086604595184326, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.2966, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2708333333333333, | |
| "grad_norm": 0.648451566696167, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1439, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.5881859660148621, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2847222222222222, | |
| "grad_norm": 0.5503454208374023, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1291, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2916666666666667, | |
| "grad_norm": 0.5237451791763306, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1538, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2986111111111111, | |
| "grad_norm": 0.6803749799728394, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.176, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3055555555555556, | |
| "grad_norm": 0.4073289930820465, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1751, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.397196501493454, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1962, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3194444444444444, | |
| "grad_norm": 0.447818398475647, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1877, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3263888888888889, | |
| "grad_norm": 0.34394121170043945, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1707, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.34709423780441284, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1682, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3402777777777778, | |
| "grad_norm": 0.2884080410003662, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1722, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3472222222222222, | |
| "grad_norm": 0.35996749997138977, | |
| "learning_rate": 0.0, | |
| "loss": 1.2179, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3472222222222222, | |
| "eval_loss": 1.2535191774368286, | |
| "eval_runtime": 29.8222, | |
| "eval_samples_per_second": 32.526, | |
| "eval_steps_per_second": 4.091, | |
| "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": 5.805082167402824e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |