| { | |
| "best_metric": 0.4569474458694458, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008854846921833838, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017709693843667677, | |
| "grad_norm": 117.74211883544922, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017709693843667677, | |
| "eval_loss": 1.7598378658294678, | |
| "eval_runtime": 1565.1778, | |
| "eval_samples_per_second": 24.305, | |
| "eval_steps_per_second": 3.039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035419387687335354, | |
| "grad_norm": 144.3221435546875, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8027, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005312908153100303, | |
| "grad_norm": 134.8468017578125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.2757, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007083877537467071, | |
| "grad_norm": 84.56224822998047, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1062, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008854846921833839, | |
| "grad_norm": 52.89167022705078, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010625816306200607, | |
| "grad_norm": 92.34407806396484, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9017, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0012396785690567374, | |
| "grad_norm": 46.530521392822266, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8768, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0014167755074934142, | |
| "grad_norm": 33.14015579223633, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7773, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001593872445930091, | |
| "grad_norm": 34.68248748779297, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7603, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017709693843667679, | |
| "grad_norm": 31.410905838012695, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019480663228034446, | |
| "grad_norm": 30.384151458740234, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7125, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0021251632612401213, | |
| "grad_norm": 43.795509338378906, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7481, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002302260199676798, | |
| "grad_norm": 48.145652770996094, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7942, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002479357138113475, | |
| "grad_norm": 43.399681091308594, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6538, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0026564540765501516, | |
| "grad_norm": 35.737213134765625, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6559, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0028335510149868283, | |
| "grad_norm": 29.4437198638916, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5808, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003010647953423505, | |
| "grad_norm": 25.55437660217285, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003187744891860182, | |
| "grad_norm": 22.801061630249023, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5435, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0033648418302968585, | |
| "grad_norm": 23.629531860351562, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5911, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0035419387687335357, | |
| "grad_norm": 24.318557739257812, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5332, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037190357071702125, | |
| "grad_norm": 22.01402473449707, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5355, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003896132645606889, | |
| "grad_norm": 26.791213989257812, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5295, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0040732295840435655, | |
| "grad_norm": 28.695446014404297, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6232, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004250326522480243, | |
| "grad_norm": 30.2479248046875, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.617, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004427423460916919, | |
| "grad_norm": 32.574432373046875, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5934, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004427423460916919, | |
| "eval_loss": 0.555499255657196, | |
| "eval_runtime": 1566.0928, | |
| "eval_samples_per_second": 24.29, | |
| "eval_steps_per_second": 3.037, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004604520399353596, | |
| "grad_norm": 37.32914352416992, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6278, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004781617337790273, | |
| "grad_norm": 30.841808319091797, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.526, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00495871427622695, | |
| "grad_norm": 26.814208984375, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5521, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005135811214663627, | |
| "grad_norm": 22.27334976196289, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5206, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005312908153100303, | |
| "grad_norm": 18.109580993652344, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.4236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00549000509153698, | |
| "grad_norm": 21.037906646728516, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4845, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005667102029973657, | |
| "grad_norm": 21.314884185791016, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4973, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005844198968410334, | |
| "grad_norm": 23.060914993286133, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.503, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00602129590684701, | |
| "grad_norm": 21.678466796875, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.006198392845283687, | |
| "grad_norm": 22.18929672241211, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4831, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006375489783720364, | |
| "grad_norm": 21.511735916137695, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4702, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006552586722157041, | |
| "grad_norm": 27.066511154174805, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5608, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006729683660593717, | |
| "grad_norm": 22.099491119384766, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5373, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006906780599030394, | |
| "grad_norm": 21.110164642333984, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.51, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.007083877537467071, | |
| "grad_norm": 18.117944717407227, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4379, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007260974475903748, | |
| "grad_norm": 17.371549606323242, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4025, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007438071414340425, | |
| "grad_norm": 18.518346786499023, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4477, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007615168352777101, | |
| "grad_norm": 19.548995971679688, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4838, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007792265291213778, | |
| "grad_norm": 20.07686424255371, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5081, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007969362229650456, | |
| "grad_norm": 20.308269500732422, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4412, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008146459168087131, | |
| "grad_norm": 20.340423583984375, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4678, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008323556106523808, | |
| "grad_norm": 20.577301025390625, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4283, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008500653044960485, | |
| "grad_norm": 22.188573837280273, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.471, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008677749983397163, | |
| "grad_norm": 24.928325653076172, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5276, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008854846921833838, | |
| "grad_norm": 27.5335636138916, | |
| "learning_rate": 0.0, | |
| "loss": 0.4987, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008854846921833838, | |
| "eval_loss": 0.4569474458694458, | |
| "eval_runtime": 1567.1076, | |
| "eval_samples_per_second": 24.275, | |
| "eval_steps_per_second": 3.035, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |