| { | |
| "best_metric": 0.23947130143642426, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3722126929674099, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0274442538593482, | |
| "grad_norm": 20.02713394165039, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0274442538593482, | |
| "eval_loss": 10.55981731414795, | |
| "eval_runtime": 7.4955, | |
| "eval_samples_per_second": 32.82, | |
| "eval_steps_per_second": 4.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0548885077186964, | |
| "grad_norm": 21.01955795288086, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4168, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0823327615780446, | |
| "grad_norm": 22.81420135498047, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.4869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1097770154373928, | |
| "grad_norm": 14.403693199157715, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.3918, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.137221269296741, | |
| "grad_norm": 26.064863204956055, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.3884, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1646655231560892, | |
| "grad_norm": 21.41654396057129, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9462, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19210977701543738, | |
| "grad_norm": 12.151286125183105, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.5429, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2195540308747856, | |
| "grad_norm": 7.747121810913086, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7676, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2469982847341338, | |
| "grad_norm": 1.5629345178604126, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.376, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.274442538593482, | |
| "grad_norm": 8.8690767288208, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.5113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3018867924528302, | |
| "grad_norm": 8.829638481140137, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.475, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3293310463121784, | |
| "grad_norm": 6.145401477813721, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4189, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3567753001715266, | |
| "grad_norm": 11.0570068359375, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4763, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.38421955403087477, | |
| "grad_norm": 2.748438835144043, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3324, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.411663807890223, | |
| "grad_norm": 6.770146369934082, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4391080617495712, | |
| "grad_norm": 6.866976261138916, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4739, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4665523156089194, | |
| "grad_norm": 4.819671154022217, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3943, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4939965694682676, | |
| "grad_norm": 1.791094183921814, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3153, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5214408233276158, | |
| "grad_norm": 9.809853553771973, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4615, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.548885077186964, | |
| "grad_norm": 11.302535057067871, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5353, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5763293310463122, | |
| "grad_norm": 10.900662422180176, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5425, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6037735849056604, | |
| "grad_norm": 5.77044677734375, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3849, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6312178387650086, | |
| "grad_norm": 1.3968511819839478, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3059, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6586620926243568, | |
| "grad_norm": 3.511702299118042, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3027, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6861063464837049, | |
| "grad_norm": 3.883240222930908, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3339, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6861063464837049, | |
| "eval_loss": 0.3096383512020111, | |
| "eval_runtime": 7.4776, | |
| "eval_samples_per_second": 32.898, | |
| "eval_steps_per_second": 4.146, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7135506003430532, | |
| "grad_norm": 1.412707805633545, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2791, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7409948542024014, | |
| "grad_norm": 3.2293643951416016, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3073, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7684391080617495, | |
| "grad_norm": 2.6210861206054688, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2711, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7958833619210978, | |
| "grad_norm": 1.1996179819107056, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.284, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.823327615780446, | |
| "grad_norm": 1.061237096786499, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2495, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8507718696397941, | |
| "grad_norm": 3.171156644821167, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2924, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8782161234991424, | |
| "grad_norm": 3.558387279510498, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2806, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9056603773584906, | |
| "grad_norm": 2.23264217376709, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2428, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.9331046312178388, | |
| "grad_norm": 0.7858607172966003, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2808, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9605488850771869, | |
| "grad_norm": 1.0410429239273071, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2407, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9879931389365352, | |
| "grad_norm": 0.9726614952087402, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2454, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.0154373927958833, | |
| "grad_norm": 4.215343952178955, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4031, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0428816466552315, | |
| "grad_norm": 3.6619632244110107, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2747, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0703259005145798, | |
| "grad_norm": 3.1446211338043213, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.097770154373928, | |
| "grad_norm": 4.393820762634277, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2587, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1252144082332762, | |
| "grad_norm": 1.2491259574890137, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2152, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1526586620926245, | |
| "grad_norm": 4.064204692840576, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2517, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.1801029159519725, | |
| "grad_norm": 1.7868139743804932, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2029, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.2075471698113207, | |
| "grad_norm": 2.360548734664917, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2119, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.234991423670669, | |
| "grad_norm": 2.1075613498687744, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1995, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2624356775300172, | |
| "grad_norm": 2.620868682861328, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2165, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2898799313893654, | |
| "grad_norm": 1.3369566202163696, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1972, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.3173241852487134, | |
| "grad_norm": 0.9853492379188538, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2016, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.3447684391080617, | |
| "grad_norm": 1.5131672620773315, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2154, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3722126929674099, | |
| "grad_norm": 2.93576717376709, | |
| "learning_rate": 0.0, | |
| "loss": 0.2323, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3722126929674099, | |
| "eval_loss": 0.23947130143642426, | |
| "eval_runtime": 7.4903, | |
| "eval_samples_per_second": 32.843, | |
| "eval_steps_per_second": 4.139, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |