| { | |
| "best_metric": 10.367974281311035, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5625, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03125, | |
| "grad_norm": 0.040279604494571686, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03125, | |
| "eval_loss": 10.373767852783203, | |
| "eval_runtime": 0.262, | |
| "eval_samples_per_second": 824.323, | |
| "eval_steps_per_second": 103.04, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.03447087109088898, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3742, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 0.03469149395823479, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3747, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.03095581755042076, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3746, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15625, | |
| "grad_norm": 0.03302657604217529, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.374, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 0.03392250835895538, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3745, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21875, | |
| "grad_norm": 0.03197386488318443, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.372, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.03758975863456726, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3707, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 0.03830201178789139, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3728, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.03908096253871918, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34375, | |
| "grad_norm": 0.04030102491378784, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3727, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.037071190774440765, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3719, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.40625, | |
| "grad_norm": 0.04191800206899643, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3721, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 0.04097755625844002, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.372, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 0.03519574925303459, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3715, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.03910599648952484, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3698, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.53125, | |
| "grad_norm": 0.0498882494866848, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3707, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 0.048532191663980484, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3717, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.59375, | |
| "grad_norm": 0.045430682599544525, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3719, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.044642332941293716, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3713, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 0.0460655577480793, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3706, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 0.04527508467435837, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3708, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.71875, | |
| "grad_norm": 0.04004138708114624, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3708, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.04607178643345833, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "grad_norm": 0.053999096155166626, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3693, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.78125, | |
| "eval_loss": 10.369440078735352, | |
| "eval_runtime": 0.2582, | |
| "eval_samples_per_second": 836.422, | |
| "eval_steps_per_second": 104.553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 0.05605136603116989, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3698, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 0.05612441152334213, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3702, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 0.04707453399896622, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3698, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.90625, | |
| "grad_norm": 0.057319339364767075, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3695, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.04838840290904045, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.37, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.96875, | |
| "grad_norm": 0.0468837209045887, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3696, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.049436602741479874, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3676, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.03125, | |
| "grad_norm": 0.058732643723487854, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3685, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 0.06249787285923958, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3687, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.09375, | |
| "grad_norm": 0.05789044126868248, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3686, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 0.053412776440382004, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3685, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.15625, | |
| "grad_norm": 0.0577046163380146, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3683, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1875, | |
| "grad_norm": 0.05308849364519119, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3691, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.21875, | |
| "grad_norm": 0.04882021248340607, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3681, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.0544765368103981, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3675, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.28125, | |
| "grad_norm": 0.0665287971496582, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3675, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "grad_norm": 0.06518158316612244, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3685, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.34375, | |
| "grad_norm": 0.06472929567098618, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.369, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 0.056068893522024155, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.40625, | |
| "grad_norm": 0.0575835295021534, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3694, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 0.05884500592947006, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3679, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.46875, | |
| "grad_norm": 0.05084865540266037, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3684, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.05442655831575394, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3669, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.53125, | |
| "grad_norm": 0.06957589834928513, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3675, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 0.06302504986524582, | |
| "learning_rate": 0.0, | |
| "loss": 10.3681, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "eval_loss": 10.367974281311035, | |
| "eval_runtime": 0.2568, | |
| "eval_samples_per_second": 841.105, | |
| "eval_steps_per_second": 105.138, | |
| "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": 44438686924800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |