| { | |
| "best_metric": 10.371206283569336, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.4545454545454546, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02909090909090909, | |
| "grad_norm": 0.04542732611298561, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3755, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02909090909090909, | |
| "eval_loss": 10.378427505493164, | |
| "eval_runtime": 0.2157, | |
| "eval_samples_per_second": 1075.713, | |
| "eval_steps_per_second": 134.464, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05818181818181818, | |
| "grad_norm": 0.044699184596538544, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3757, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08727272727272728, | |
| "grad_norm": 0.04836718365550041, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3797, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11636363636363636, | |
| "grad_norm": 0.04853840544819832, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3785, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.04985123127698898, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17454545454545456, | |
| "grad_norm": 0.05220064893364906, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3776, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20363636363636364, | |
| "grad_norm": 0.054472118616104126, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3783, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.23272727272727273, | |
| "grad_norm": 0.06365810334682465, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3777, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26181818181818184, | |
| "grad_norm": 0.0501365028321743, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3754, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.048848334699869156, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3747, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.04923773556947708, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3744, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3490909090909091, | |
| "grad_norm": 0.04974054545164108, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3749, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3781818181818182, | |
| "grad_norm": 0.05604294314980507, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4072727272727273, | |
| "grad_norm": 0.05577346310019493, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3788, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 0.06580042093992233, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.46545454545454545, | |
| "grad_norm": 0.06522443145513535, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3795, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.49454545454545457, | |
| "grad_norm": 0.08119519799947739, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3759, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5236363636363637, | |
| "grad_norm": 0.056983832269907, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3713, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5527272727272727, | |
| "grad_norm": 0.052240677177906036, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3741, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5818181818181818, | |
| "grad_norm": 0.06199200823903084, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3755, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.610909090909091, | |
| "grad_norm": 0.06343241035938263, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3748, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.07450269907712936, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.374, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6690909090909091, | |
| "grad_norm": 0.0749194473028183, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3728, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6981818181818182, | |
| "grad_norm": 0.08099077641963959, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.373, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.08432656526565552, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3731, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "eval_loss": 10.373350143432617, | |
| "eval_runtime": 0.212, | |
| "eval_samples_per_second": 1094.239, | |
| "eval_steps_per_second": 136.78, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7563636363636363, | |
| "grad_norm": 0.07291626930236816, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3713, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7854545454545454, | |
| "grad_norm": 0.06883475184440613, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.37, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8145454545454546, | |
| "grad_norm": 0.07164252549409866, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3727, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8436363636363636, | |
| "grad_norm": 0.07420614361763, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3716, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8727272727272727, | |
| "grad_norm": 0.07898180931806564, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3718, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9018181818181819, | |
| "grad_norm": 0.08564016222953796, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3744, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9309090909090909, | |
| "grad_norm": 0.08289813995361328, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3717, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.10542256385087967, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.37, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9890909090909091, | |
| "grad_norm": 0.11940684914588928, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3709, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.018181818181818, | |
| "grad_norm": 0.14024017751216888, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 17.4511, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0472727272727274, | |
| "grad_norm": 0.06805068999528885, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 9.9872, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0763636363636364, | |
| "grad_norm": 0.08220560103654861, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3888, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1054545454545455, | |
| "grad_norm": 0.10088109970092773, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3326, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1345454545454545, | |
| "grad_norm": 0.09310103207826614, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.332, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.1636363636363636, | |
| "grad_norm": 0.09103864431381226, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.4093, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1927272727272726, | |
| "grad_norm": 0.09932649880647659, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.4759, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.221818181818182, | |
| "grad_norm": 0.12177771329879761, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.4992, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.250909090909091, | |
| "grad_norm": 0.06674141436815262, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 7.3741, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.104917012155056, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 13.2692, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.309090909090909, | |
| "grad_norm": 0.07617160677909851, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.2841, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3381818181818181, | |
| "grad_norm": 0.08638501167297363, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3278, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.3672727272727272, | |
| "grad_norm": 0.09070190787315369, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3126, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3963636363636365, | |
| "grad_norm": 0.08757533878087997, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.4069, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4254545454545455, | |
| "grad_norm": 0.10536868870258331, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.4002, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.08869392424821854, | |
| "learning_rate": 0.0, | |
| "loss": 10.4616, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "eval_loss": 10.371206283569336, | |
| "eval_runtime": 0.2127, | |
| "eval_samples_per_second": 1090.833, | |
| "eval_steps_per_second": 136.354, | |
| "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": 42768059596800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |