| { | |
| "best_metric": 2.1415767669677734, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013470054385344581, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002694010877068916, | |
| "grad_norm": 0.40946441888809204, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002694010877068916, | |
| "eval_loss": 2.357184886932373, | |
| "eval_runtime": 287.8117, | |
| "eval_samples_per_second": 86.887, | |
| "eval_steps_per_second": 10.861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005388021754137832, | |
| "grad_norm": 0.4856288433074951, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9696, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008082032631206748, | |
| "grad_norm": 0.4114547371864319, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.0578, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0010776043508275665, | |
| "grad_norm": 0.26117223501205444, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1568, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013470054385344582, | |
| "grad_norm": 0.21311452984809875, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.2005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016164065262413497, | |
| "grad_norm": 0.23245510458946228, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2305, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018858076139482414, | |
| "grad_norm": 0.25996315479278564, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.3206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002155208701655133, | |
| "grad_norm": 0.2768327593803406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3271, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0024246097893620244, | |
| "grad_norm": 0.2988227903842926, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.4038, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026940108770689163, | |
| "grad_norm": 0.2970982491970062, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3869, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002963411964775808, | |
| "grad_norm": 0.32313239574432373, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.4894, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0032328130524826994, | |
| "grad_norm": 0.4109671711921692, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.4265, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003502214140189591, | |
| "grad_norm": 0.39615362882614136, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.7993, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003771615227896483, | |
| "grad_norm": 0.3981967568397522, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8405, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004041016315603374, | |
| "grad_norm": 0.36522895097732544, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9493, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004310417403310266, | |
| "grad_norm": 0.2553641200065613, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0117, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004579818491017158, | |
| "grad_norm": 0.2109195739030838, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.1104, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004849219578724049, | |
| "grad_norm": 0.19856570661067963, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.1572, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005118620666430941, | |
| "grad_norm": 0.21353407204151154, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1831, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005388021754137833, | |
| "grad_norm": 0.21216340363025665, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2599, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005657422841844724, | |
| "grad_norm": 0.2223528027534485, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2288, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005926823929551616, | |
| "grad_norm": 0.22507056593894958, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.3356, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006196225017258507, | |
| "grad_norm": 0.24927861988544464, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3646, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006465626104965399, | |
| "grad_norm": 0.2960977554321289, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3566, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006735027192672291, | |
| "grad_norm": 0.4397338628768921, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4203, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006735027192672291, | |
| "eval_loss": 2.152416944503784, | |
| "eval_runtime": 287.8747, | |
| "eval_samples_per_second": 86.868, | |
| "eval_steps_per_second": 10.859, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007004428280379182, | |
| "grad_norm": 0.12296074628829956, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7179, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007273829368086074, | |
| "grad_norm": 0.1352420449256897, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.8508, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007543230455792966, | |
| "grad_norm": 0.14206938445568085, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9431, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007812631543499857, | |
| "grad_norm": 0.1531849354505539, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.0376, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008082032631206748, | |
| "grad_norm": 0.17265917360782623, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.1185, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00835143371891364, | |
| "grad_norm": 0.1766246110200882, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.1605, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008620834806620532, | |
| "grad_norm": 0.17309987545013428, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1793, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008890235894327423, | |
| "grad_norm": 0.20584042370319366, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.285, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009159636982034315, | |
| "grad_norm": 0.22178272902965546, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3379, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009429038069741207, | |
| "grad_norm": 0.2220696061849594, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.3039, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009698439157448098, | |
| "grad_norm": 0.25546637177467346, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.408, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00996784024515499, | |
| "grad_norm": 0.24715134501457214, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.3815, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010237241332861882, | |
| "grad_norm": 0.13599006831645966, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6916, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010506642420568773, | |
| "grad_norm": 0.13048195838928223, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.7807, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.010776043508275665, | |
| "grad_norm": 0.1338452249765396, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.8669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011045444595982556, | |
| "grad_norm": 0.13688980042934418, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.9812, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011314845683689448, | |
| "grad_norm": 0.1470724195241928, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.065, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01158424677139634, | |
| "grad_norm": 0.1516406238079071, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.1349, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011853647859103231, | |
| "grad_norm": 0.15423178672790527, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1353, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012123048946810122, | |
| "grad_norm": 0.16444306075572968, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.27, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012392450034517014, | |
| "grad_norm": 0.17130832374095917, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.2999, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012661851122223906, | |
| "grad_norm": 0.1853959560394287, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.3348, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.012931252209930797, | |
| "grad_norm": 0.20296545326709747, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.4142, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013200653297637688, | |
| "grad_norm": 0.23544824123382568, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.4167, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013470054385344581, | |
| "grad_norm": 0.3853051960468292, | |
| "learning_rate": 0.0, | |
| "loss": 2.3263, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013470054385344581, | |
| "eval_loss": 2.1415767669677734, | |
| "eval_runtime": 287.9217, | |
| "eval_samples_per_second": 86.853, | |
| "eval_steps_per_second": 10.857, | |
| "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": 1.0598674582837658e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |