| { | |
| "best_metric": 1.5961111783981323, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.16725904244198203, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00334518084883964, | |
| "grad_norm": 2.2231602668762207, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00334518084883964, | |
| "eval_loss": 4.248070240020752, | |
| "eval_runtime": 104.3854, | |
| "eval_samples_per_second": 19.294, | |
| "eval_steps_per_second": 2.414, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00669036169767928, | |
| "grad_norm": 2.6496012210845947, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1778, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010035542546518922, | |
| "grad_norm": 2.398160457611084, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.2355, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01338072339535856, | |
| "grad_norm": 1.6712936162948608, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9431, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.016725904244198203, | |
| "grad_norm": 1.6603524684906006, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.8639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020071085093037844, | |
| "grad_norm": 1.9895721673965454, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.7555, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.023416265941877484, | |
| "grad_norm": 1.6873689889907837, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.6076, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02676144679071712, | |
| "grad_norm": 1.3678803443908691, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.536, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.030106627639556762, | |
| "grad_norm": 1.443657398223877, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.371, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.033451808488396406, | |
| "grad_norm": 1.534454107284546, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03679698933723605, | |
| "grad_norm": 1.7034695148468018, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2205, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04014217018607569, | |
| "grad_norm": 2.4645097255706787, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.4059, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04348735103491533, | |
| "grad_norm": 2.0418405532836914, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0751, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04683253188375497, | |
| "grad_norm": 2.194927215576172, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0398, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05017771273259461, | |
| "grad_norm": 1.8354201316833496, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9412, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05352289358143424, | |
| "grad_norm": 1.319340705871582, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0067, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.056868074430273884, | |
| "grad_norm": 1.5245641469955444, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8729, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.060213255279113524, | |
| "grad_norm": 1.598117470741272, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0434, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06355843612795317, | |
| "grad_norm": 1.3242369890213013, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.9568, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06690361697679281, | |
| "grad_norm": 1.2119096517562866, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07024879782563245, | |
| "grad_norm": 1.2839982509613037, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8604, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0735939786744721, | |
| "grad_norm": 1.4792462587356567, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.7927, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07693915952331173, | |
| "grad_norm": 1.5949089527130127, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8756, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08028434037215137, | |
| "grad_norm": 2.0640158653259277, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8811, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08362952122099102, | |
| "grad_norm": 2.864583730697632, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.1161, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08362952122099102, | |
| "eval_loss": 1.759958028793335, | |
| "eval_runtime": 104.4433, | |
| "eval_samples_per_second": 19.283, | |
| "eval_steps_per_second": 2.413, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08697470206983066, | |
| "grad_norm": 1.0084614753723145, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6066, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0903198829186703, | |
| "grad_norm": 1.0460926294326782, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.6602, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09366506376750994, | |
| "grad_norm": 1.0078924894332886, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6295, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09701024461634958, | |
| "grad_norm": 1.0543190240859985, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6352, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10035542546518922, | |
| "grad_norm": 1.0644540786743164, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6549, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10370060631402885, | |
| "grad_norm": 1.1043634414672852, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7471, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10704578716286849, | |
| "grad_norm": 1.1335960626602173, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7029, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11039096801170813, | |
| "grad_norm": 1.2425991296768188, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.7174, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11373614886054777, | |
| "grad_norm": 1.2737070322036743, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.718, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11708132970938741, | |
| "grad_norm": 1.4903675317764282, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.6766, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12042651055822705, | |
| "grad_norm": 1.6684659719467163, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.6386, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12377169140706669, | |
| "grad_norm": 2.2402453422546387, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.8643, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12711687225590634, | |
| "grad_norm": 1.0088212490081787, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5225, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13046205310474598, | |
| "grad_norm": 0.778500497341156, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.46, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.13380723395358562, | |
| "grad_norm": 0.8704653382301331, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5428, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13715241480242527, | |
| "grad_norm": 0.9207085371017456, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.6426, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1404975956512649, | |
| "grad_norm": 0.9859210848808289, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6149, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14384277650010455, | |
| "grad_norm": 1.0169706344604492, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.5638, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1471879573489442, | |
| "grad_norm": 1.1154978275299072, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6267, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15053313819778383, | |
| "grad_norm": 1.179999589920044, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6497, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15387831904662347, | |
| "grad_norm": 1.3208422660827637, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5948, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1572234998954631, | |
| "grad_norm": 1.452532410621643, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6376, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16056868074430275, | |
| "grad_norm": 1.700157880783081, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.7256, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1639138615931424, | |
| "grad_norm": 2.0633585453033447, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7677, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16725904244198203, | |
| "grad_norm": 3.042532205581665, | |
| "learning_rate": 0.0, | |
| "loss": 2.0048, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16725904244198203, | |
| "eval_loss": 1.5961111783981323, | |
| "eval_runtime": 104.3423, | |
| "eval_samples_per_second": 19.302, | |
| "eval_steps_per_second": 2.415, | |
| "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": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |