| { | |
| "best_metric": 0.0005516423261724412, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.007326141504423158, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014652283008846317, | |
| "grad_norm": 67.87615203857422, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014652283008846317, | |
| "eval_loss": 7.334836959838867, | |
| "eval_runtime": 2438.9079, | |
| "eval_samples_per_second": 18.852, | |
| "eval_steps_per_second": 2.357, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00029304566017692633, | |
| "grad_norm": 67.87747955322266, | |
| "learning_rate": 0.0001, | |
| "loss": 7.3346, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004395684902653895, | |
| "grad_norm": 18.16913414001465, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.2513, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005860913203538527, | |
| "grad_norm": 10.074419021606445, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007326141504423158, | |
| "grad_norm": 4.317474842071533, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2698, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000879136980530779, | |
| "grad_norm": 1.243073582649231, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0253, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001025659810619242, | |
| "grad_norm": 0.8550915122032166, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.0034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011721826407077053, | |
| "grad_norm": 0.01695163920521736, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0003, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013187054707961684, | |
| "grad_norm": 0.009161525405943394, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0001, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014652283008846315, | |
| "grad_norm": 0.004700306337326765, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016117511309730948, | |
| "grad_norm": 0.002197882393375039, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001758273961061558, | |
| "grad_norm": 0.002685612766072154, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.001904796791150021, | |
| "grad_norm": 0.00469649164006114, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002051319621238484, | |
| "grad_norm": 0.007126097567379475, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021978424513269474, | |
| "grad_norm": 0.004539829678833485, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023443652814154107, | |
| "grad_norm": 0.0024929079227149487, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0024908881115038735, | |
| "grad_norm": 0.001898004557006061, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002637410941592337, | |
| "grad_norm": 0.0017185908509418368, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0027839337716808, | |
| "grad_norm": 0.0014609902864322066, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002930456601769263, | |
| "grad_norm": 0.0010621019173413515, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0030769794318577263, | |
| "grad_norm": 0.0007855401490814984, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0032235022619461896, | |
| "grad_norm": 0.000533660757355392, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0033700250920346525, | |
| "grad_norm": 0.00034762825816869736, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003516547922123116, | |
| "grad_norm": 0.0002546625619288534, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003663070752211579, | |
| "grad_norm": 0.00020840756769757718, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003663070752211579, | |
| "eval_loss": 0.0005516423261724412, | |
| "eval_runtime": 2436.6617, | |
| "eval_samples_per_second": 18.869, | |
| "eval_steps_per_second": 2.359, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.003809593582300042, | |
| "grad_norm": 0.00015822373097762465, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.003956116412388505, | |
| "grad_norm": 0.00013516444596461952, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004102639242476968, | |
| "grad_norm": 0.00011721820919774473, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004249162072565432, | |
| "grad_norm": 0.00010643725545378402, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004395684902653895, | |
| "grad_norm": 0.00010524487879592925, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004542207732742358, | |
| "grad_norm": 9.345701255369931e-05, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.004688730562830821, | |
| "grad_norm": 9.012578084366396e-05, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004835253392919284, | |
| "grad_norm": 8.863666880642995e-05, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004981776223007747, | |
| "grad_norm": 8.313306170748547e-05, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.005128299053096211, | |
| "grad_norm": 8.131038339342922e-05, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005274821883184674, | |
| "grad_norm": 7.79785550548695e-05, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0054213447132731366, | |
| "grad_norm": 7.947424455778673e-05, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0055678675433616, | |
| "grad_norm": 8.158644777722657e-05, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.005714390373450063, | |
| "grad_norm": 7.519957580370829e-05, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.005860913203538526, | |
| "grad_norm": 7.528267451561987e-05, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00600743603362699, | |
| "grad_norm": 8.020062523428351e-05, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.006153958863715453, | |
| "grad_norm": 7.912742148619145e-05, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0063004816938039155, | |
| "grad_norm": 7.51012412365526e-05, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006447004523892379, | |
| "grad_norm": 7.722243026364595e-05, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006593527353980842, | |
| "grad_norm": 7.798113074386492e-05, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006740050184069305, | |
| "grad_norm": 7.62744530220516e-05, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006886573014157769, | |
| "grad_norm": 7.456322782672942e-05, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007033095844246232, | |
| "grad_norm": 7.672930951230228e-05, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0071796186743346944, | |
| "grad_norm": 7.462252688128501e-05, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007326141504423158, | |
| "grad_norm": 7.582093530800194e-05, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007326141504423158, | |
| "eval_loss": 0.0005818467470817268, | |
| "eval_runtime": 2448.467, | |
| "eval_samples_per_second": 18.778, | |
| "eval_steps_per_second": 2.348, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |