| { | |
| "best_metric": 0.28741422295570374, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.15628052353975386, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003125610470795077, | |
| "grad_norm": 93.13221740722656, | |
| "learning_rate": 5e-05, | |
| "loss": 11.63, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003125610470795077, | |
| "eval_loss": 12.39339542388916, | |
| "eval_runtime": 56.8328, | |
| "eval_samples_per_second": 37.936, | |
| "eval_steps_per_second": 4.751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006251220941590154, | |
| "grad_norm": 92.16307067871094, | |
| "learning_rate": 0.0001, | |
| "loss": 11.6224, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009376831412385232, | |
| "grad_norm": 57.949501037597656, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.4543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012502441883180308, | |
| "grad_norm": 35.27203369140625, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.9361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015628052353975387, | |
| "grad_norm": 46.797607421875, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.7793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018753662824770465, | |
| "grad_norm": 5.431611061096191, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4571, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02187927329556554, | |
| "grad_norm": 11.085064888000488, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.621, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.025004883766360616, | |
| "grad_norm": 1.893434762954712, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3611, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028130494237155693, | |
| "grad_norm": 7.700344085693359, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5145, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031256104707950774, | |
| "grad_norm": 5.926100730895996, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4401, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03438171517874585, | |
| "grad_norm": 2.6263937950134277, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.3748, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03750732564954093, | |
| "grad_norm": 3.012312173843384, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3842, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.040632936120336006, | |
| "grad_norm": 0.493480384349823, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3416, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04375854659113108, | |
| "grad_norm": 1.6048505306243896, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3589, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.046884157061926154, | |
| "grad_norm": 1.7863847017288208, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05000976753272123, | |
| "grad_norm": 0.7475451827049255, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.327, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05313537800351631, | |
| "grad_norm": 1.7667124271392822, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3417, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05626098847431139, | |
| "grad_norm": 1.4262945652008057, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3278, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.059386598945106464, | |
| "grad_norm": 2.850707769393921, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3398, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06251220941590155, | |
| "grad_norm": 4.376528739929199, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3879, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06563781988669662, | |
| "grad_norm": 1.0391062498092651, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3205, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0687634303574917, | |
| "grad_norm": 1.0256831645965576, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2882, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07188904082828677, | |
| "grad_norm": 0.9023930430412292, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2855, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07501465129908186, | |
| "grad_norm": 1.717550277709961, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3136, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07814026176987693, | |
| "grad_norm": 2.4976720809936523, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3448, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07814026176987693, | |
| "eval_loss": 0.3386324644088745, | |
| "eval_runtime": 56.931, | |
| "eval_samples_per_second": 37.87, | |
| "eval_steps_per_second": 4.743, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08126587224067201, | |
| "grad_norm": 2.45245623588562, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3774, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08439148271146708, | |
| "grad_norm": 1.5845011472702026, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3466, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08751709318226215, | |
| "grad_norm": 0.8654233813285828, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2892, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09064270365305724, | |
| "grad_norm": 1.2370487451553345, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3171, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09376831412385231, | |
| "grad_norm": 1.3261559009552002, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.3282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0968939245946474, | |
| "grad_norm": 1.2208430767059326, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2933, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10001953506544246, | |
| "grad_norm": 1.0844453573226929, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3098, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10314514553623755, | |
| "grad_norm": 0.9611645936965942, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2733, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10627075600703262, | |
| "grad_norm": 1.1155072450637817, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3004, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1093963664778277, | |
| "grad_norm": 1.0913764238357544, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3093, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11252197694862277, | |
| "grad_norm": 0.7945312261581421, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2808, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11564758741941786, | |
| "grad_norm": 1.0648337602615356, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2536, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11877319789021293, | |
| "grad_norm": 0.7629750967025757, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3224, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12189880836100801, | |
| "grad_norm": 1.1458991765975952, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2724, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1250244188318031, | |
| "grad_norm": 2.066157579421997, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3444, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12815002930259817, | |
| "grad_norm": 2.434628963470459, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3555, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13127563977339324, | |
| "grad_norm": 1.6599045991897583, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3035, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1344012502441883, | |
| "grad_norm": 1.7663042545318604, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.3589, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1375268607149834, | |
| "grad_norm": 1.3124494552612305, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3243, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14065247118577848, | |
| "grad_norm": 0.9794068336486816, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2703, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14377808165657355, | |
| "grad_norm": 1.0024210214614868, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2816, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14690369212736862, | |
| "grad_norm": 1.1213816404342651, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2952, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15002930259816372, | |
| "grad_norm": 1.1528414487838745, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2853, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1531549130689588, | |
| "grad_norm": 0.7072805762290955, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2796, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15628052353975386, | |
| "grad_norm": 0.8989966511726379, | |
| "learning_rate": 0.0, | |
| "loss": 0.2968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15628052353975386, | |
| "eval_loss": 0.28741422295570374, | |
| "eval_runtime": 56.9261, | |
| "eval_samples_per_second": 37.874, | |
| "eval_steps_per_second": 4.743, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |