| { | |
| "best_metric": 1.3707951307296753, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7699115044247788, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.035398230088495575, | |
| "grad_norm": 0.48062071204185486, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5641, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.035398230088495575, | |
| "eval_loss": 1.5635976791381836, | |
| "eval_runtime": 2.222, | |
| "eval_samples_per_second": 85.507, | |
| "eval_steps_per_second": 10.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07079646017699115, | |
| "grad_norm": 0.5046669244766235, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5219, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10619469026548672, | |
| "grad_norm": 0.3963252007961273, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.5175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1415929203539823, | |
| "grad_norm": 0.3819900453090668, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4488, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17699115044247787, | |
| "grad_norm": 0.40185779333114624, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.4642, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "grad_norm": 0.42010143399238586, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4739, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24778761061946902, | |
| "grad_norm": 0.38947638869285583, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5526, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2831858407079646, | |
| "grad_norm": 0.28739336133003235, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4553, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3185840707964602, | |
| "grad_norm": 0.2647819221019745, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4806, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 0.2436285763978958, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3893805309734513, | |
| "grad_norm": 0.21143852174282074, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4264, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": 0.2090560495853424, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4301, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.46017699115044247, | |
| "grad_norm": 0.21220526099205017, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4801, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.49557522123893805, | |
| "grad_norm": 0.29451966285705566, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5158, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5309734513274337, | |
| "grad_norm": 0.20719057321548462, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4301, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5663716814159292, | |
| "grad_norm": 0.20236384868621826, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.407, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6017699115044248, | |
| "grad_norm": 0.2062968909740448, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "grad_norm": 0.18799862265586853, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3724, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.672566371681416, | |
| "grad_norm": 0.19302979111671448, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4243, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 0.1935189813375473, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7433628318584071, | |
| "grad_norm": 0.24287334084510803, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4691, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7787610619469026, | |
| "grad_norm": 0.19274497032165527, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4141, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8141592920353983, | |
| "grad_norm": 0.2027171105146408, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4203, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": 0.19442526996135712, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.382, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "grad_norm": 0.18337927758693695, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3655, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "eval_loss": 1.3890187740325928, | |
| "eval_runtime": 2.2206, | |
| "eval_samples_per_second": 85.563, | |
| "eval_steps_per_second": 10.808, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9203539823008849, | |
| "grad_norm": 0.2022041529417038, | |
| "learning_rate": 5e-05, | |
| "loss": 1.385, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9557522123893806, | |
| "grad_norm": 0.19861751794815063, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4019, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9911504424778761, | |
| "grad_norm": 0.2385483831167221, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3938, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0265486725663717, | |
| "grad_norm": 0.4870010316371918, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.4318, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0619469026548674, | |
| "grad_norm": 0.3053165674209595, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3394, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0973451327433628, | |
| "grad_norm": 0.2962687015533447, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3852, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1327433628318584, | |
| "grad_norm": 0.3027305006980896, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3173, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.168141592920354, | |
| "grad_norm": 0.33227747678756714, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3647, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2035398230088497, | |
| "grad_norm": 0.3296235203742981, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4011, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.238938053097345, | |
| "grad_norm": 0.39872992038726807, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4346, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.2743362831858407, | |
| "grad_norm": 0.3268812298774719, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.3378, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3097345132743363, | |
| "grad_norm": 0.3023950755596161, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.3331, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3451327433628317, | |
| "grad_norm": 0.32276710867881775, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3421, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3805309734513274, | |
| "grad_norm": 0.31279733777046204, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3191, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.415929203539823, | |
| "grad_norm": 0.32816168665885925, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3224, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4513274336283186, | |
| "grad_norm": 0.32745441794395447, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3618, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4867256637168142, | |
| "grad_norm": 0.3378945291042328, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3688, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5221238938053099, | |
| "grad_norm": 0.3114747405052185, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.3884, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5575221238938053, | |
| "grad_norm": 0.32342156767845154, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3411, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.592920353982301, | |
| "grad_norm": 0.3232678174972534, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.3715, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6283185840707963, | |
| "grad_norm": 0.3243681490421295, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.3108, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.663716814159292, | |
| "grad_norm": 0.33341413736343384, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4022, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6991150442477876, | |
| "grad_norm": 0.33767956495285034, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.3355, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7345132743362832, | |
| "grad_norm": 0.35112181305885315, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.3985, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "grad_norm": 0.3286685049533844, | |
| "learning_rate": 0.0, | |
| "loss": 1.3658, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7699115044247788, | |
| "eval_loss": 1.3707951307296753, | |
| "eval_runtime": 2.2194, | |
| "eval_samples_per_second": 85.61, | |
| "eval_steps_per_second": 10.814, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |