|
{ |
|
"best_metric": 1.328393816947937, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.45454545454545453, |
|
"eval_steps": 25, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.00909090909090909, |
|
"grad_norm": 0.43840864300727844, |
|
"learning_rate": 5e-05, |
|
"loss": 1.6435, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00909090909090909, |
|
"eval_loss": 2.161210298538208, |
|
"eval_runtime": 27.8988, |
|
"eval_samples_per_second": 26.56, |
|
"eval_steps_per_second": 3.333, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01818181818181818, |
|
"grad_norm": 0.5271226763725281, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6374, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.02727272727272727, |
|
"grad_norm": 0.5705170631408691, |
|
"learning_rate": 9.989294616193017e-05, |
|
"loss": 1.7139, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.03636363636363636, |
|
"grad_norm": 0.6076046824455261, |
|
"learning_rate": 9.957224306869053e-05, |
|
"loss": 1.8229, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.045454545454545456, |
|
"grad_norm": 0.46959155797958374, |
|
"learning_rate": 9.903926402016153e-05, |
|
"loss": 1.6404, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.05454545454545454, |
|
"grad_norm": 0.6464632749557495, |
|
"learning_rate": 9.829629131445342e-05, |
|
"loss": 1.7171, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.06363636363636363, |
|
"grad_norm": 0.6275486946105957, |
|
"learning_rate": 9.73465064747553e-05, |
|
"loss": 1.6393, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.07272727272727272, |
|
"grad_norm": 0.5121647715568542, |
|
"learning_rate": 9.619397662556435e-05, |
|
"loss": 1.6314, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.08181818181818182, |
|
"grad_norm": 0.6559847593307495, |
|
"learning_rate": 9.484363707663442e-05, |
|
"loss": 1.574, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.09090909090909091, |
|
"grad_norm": 0.7980840802192688, |
|
"learning_rate": 9.330127018922194e-05, |
|
"loss": 1.4944, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"grad_norm": 0.8259976506233215, |
|
"learning_rate": 9.157348061512727e-05, |
|
"loss": 1.4888, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.10909090909090909, |
|
"grad_norm": 1.0967543125152588, |
|
"learning_rate": 8.966766701456177e-05, |
|
"loss": 1.4157, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.11818181818181818, |
|
"grad_norm": 1.396427869796753, |
|
"learning_rate": 8.759199037394887e-05, |
|
"loss": 1.4676, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.12727272727272726, |
|
"grad_norm": 1.0643088817596436, |
|
"learning_rate": 8.535533905932738e-05, |
|
"loss": 1.4466, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.13636363636363635, |
|
"grad_norm": 0.7951937913894653, |
|
"learning_rate": 8.296729075500344e-05, |
|
"loss": 1.5571, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.14545454545454545, |
|
"grad_norm": 0.6135804057121277, |
|
"learning_rate": 8.043807145043604e-05, |
|
"loss": 1.4813, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.15454545454545454, |
|
"grad_norm": 0.47333285212516785, |
|
"learning_rate": 7.777851165098012e-05, |
|
"loss": 1.4708, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.16363636363636364, |
|
"grad_norm": 0.45460066199302673, |
|
"learning_rate": 7.500000000000001e-05, |
|
"loss": 1.5531, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.17272727272727273, |
|
"grad_norm": 0.48867130279541016, |
|
"learning_rate": 7.211443451095007e-05, |
|
"loss": 1.5439, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.18181818181818182, |
|
"grad_norm": 0.5177707672119141, |
|
"learning_rate": 6.91341716182545e-05, |
|
"loss": 1.5002, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.19090909090909092, |
|
"grad_norm": 0.5035902857780457, |
|
"learning_rate": 6.607197326515808e-05, |
|
"loss": 1.4441, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"grad_norm": 0.5819491744041443, |
|
"learning_rate": 6.294095225512603e-05, |
|
"loss": 1.3929, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.20909090909090908, |
|
"grad_norm": 0.670968234539032, |
|
"learning_rate": 5.9754516100806423e-05, |
|
"loss": 1.4114, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.21818181818181817, |
|
"grad_norm": 0.9142773747444153, |
|
"learning_rate": 5.6526309611002594e-05, |
|
"loss": 1.3526, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.22727272727272727, |
|
"grad_norm": 1.6704258918762207, |
|
"learning_rate": 5.327015646150716e-05, |
|
"loss": 1.532, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.22727272727272727, |
|
"eval_loss": 1.3843603134155273, |
|
"eval_runtime": 23.7716, |
|
"eval_samples_per_second": 31.172, |
|
"eval_steps_per_second": 3.912, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.23636363636363636, |
|
"grad_norm": 0.36956995725631714, |
|
"learning_rate": 5e-05, |
|
"loss": 1.5298, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.24545454545454545, |
|
"grad_norm": 0.49253299832344055, |
|
"learning_rate": 4.6729843538492847e-05, |
|
"loss": 1.4411, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.2545454545454545, |
|
"grad_norm": 0.5202022194862366, |
|
"learning_rate": 4.347369038899744e-05, |
|
"loss": 1.3987, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.2636363636363636, |
|
"grad_norm": 0.5346823334693909, |
|
"learning_rate": 4.0245483899193595e-05, |
|
"loss": 1.4693, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.2727272727272727, |
|
"grad_norm": 0.5093651413917542, |
|
"learning_rate": 3.705904774487396e-05, |
|
"loss": 1.4682, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.2818181818181818, |
|
"grad_norm": 0.7494578957557678, |
|
"learning_rate": 3.392802673484193e-05, |
|
"loss": 1.4346, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.2909090909090909, |
|
"grad_norm": 0.41236063838005066, |
|
"learning_rate": 3.086582838174551e-05, |
|
"loss": 1.5035, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"grad_norm": 0.569702684879303, |
|
"learning_rate": 2.7885565489049946e-05, |
|
"loss": 1.3644, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.3090909090909091, |
|
"grad_norm": 0.6248189210891724, |
|
"learning_rate": 2.500000000000001e-05, |
|
"loss": 1.4663, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.3181818181818182, |
|
"grad_norm": 0.7485700845718384, |
|
"learning_rate": 2.2221488349019903e-05, |
|
"loss": 1.3821, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.32727272727272727, |
|
"grad_norm": 1.061784029006958, |
|
"learning_rate": 1.9561928549563968e-05, |
|
"loss": 1.2502, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.33636363636363636, |
|
"grad_norm": 1.3697577714920044, |
|
"learning_rate": 1.703270924499656e-05, |
|
"loss": 1.2969, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.34545454545454546, |
|
"grad_norm": 0.2654924690723419, |
|
"learning_rate": 1.4644660940672627e-05, |
|
"loss": 1.0297, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.35454545454545455, |
|
"grad_norm": 0.20454204082489014, |
|
"learning_rate": 1.2408009626051137e-05, |
|
"loss": 1.341, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.36363636363636365, |
|
"grad_norm": 0.24198082089424133, |
|
"learning_rate": 1.0332332985438248e-05, |
|
"loss": 1.3627, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.37272727272727274, |
|
"grad_norm": 0.23670072853565216, |
|
"learning_rate": 8.426519384872733e-06, |
|
"loss": 1.3985, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.38181818181818183, |
|
"grad_norm": 0.2668602466583252, |
|
"learning_rate": 6.698729810778065e-06, |
|
"loss": 1.4415, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.39090909090909093, |
|
"grad_norm": 0.2617162764072418, |
|
"learning_rate": 5.156362923365588e-06, |
|
"loss": 1.4121, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"grad_norm": 0.2912660241127014, |
|
"learning_rate": 3.8060233744356633e-06, |
|
"loss": 1.4957, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.4090909090909091, |
|
"grad_norm": 0.31733399629592896, |
|
"learning_rate": 2.653493525244721e-06, |
|
"loss": 1.3998, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.41818181818181815, |
|
"grad_norm": 0.3562355935573578, |
|
"learning_rate": 1.70370868554659e-06, |
|
"loss": 1.3615, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.42727272727272725, |
|
"grad_norm": 0.3990439474582672, |
|
"learning_rate": 9.607359798384785e-07, |
|
"loss": 1.3774, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.43636363636363634, |
|
"grad_norm": 0.4939119517803192, |
|
"learning_rate": 4.277569313094809e-07, |
|
"loss": 1.4047, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.44545454545454544, |
|
"grad_norm": 0.6996358036994934, |
|
"learning_rate": 1.0705383806982606e-07, |
|
"loss": 1.2233, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.45454545454545453, |
|
"grad_norm": 1.5292341709136963, |
|
"learning_rate": 0.0, |
|
"loss": 1.4825, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.45454545454545453, |
|
"eval_loss": 1.328393816947937, |
|
"eval_runtime": 52.3704, |
|
"eval_samples_per_second": 14.149, |
|
"eval_steps_per_second": 1.776, |
|
"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": 6.01284422028755e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|