| { | |
| "best_metric": 1.3449122905731201, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 1.1450094161958568, | |
| "eval_steps": 25, | |
| "global_step": 133, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008609093354856066, | |
| "grad_norm": 0.6988075971603394, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008609093354856066, | |
| "eval_loss": 3.2656900882720947, | |
| "eval_runtime": 1.2466, | |
| "eval_samples_per_second": 40.11, | |
| "eval_steps_per_second": 10.429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017218186709712133, | |
| "grad_norm": 0.7088323831558228, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0087, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0258272800645682, | |
| "grad_norm": 1.009822130203247, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4702, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034436373419424265, | |
| "grad_norm": 0.9133837819099426, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5742, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04304546677428033, | |
| "grad_norm": 1.0774202346801758, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4651, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0516545601291364, | |
| "grad_norm": 1.940169095993042, | |
| "learning_rate": 9.99864468413292e-05, | |
| "loss": 2.7402, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.060263653483992465, | |
| "grad_norm": 2.5114591121673584, | |
| "learning_rate": 9.994579552923277e-05, | |
| "loss": 2.36, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06887274683884853, | |
| "grad_norm": 2.1416642665863037, | |
| "learning_rate": 9.987807055054106e-05, | |
| "loss": 2.1412, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0774818401937046, | |
| "grad_norm": 2.493290424346924, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 2.134, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08609093354856066, | |
| "grad_norm": 2.5377631187438965, | |
| "learning_rate": 9.966157905694196e-05, | |
| "loss": 2.2798, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09470002690341674, | |
| "grad_norm": 5.070113658905029, | |
| "learning_rate": 9.951294294841516e-05, | |
| "loss": 2.0949, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1033091202582728, | |
| "grad_norm": 8.32091999053955, | |
| "learning_rate": 9.933749390750235e-05, | |
| "loss": 2.669, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11191821361312887, | |
| "grad_norm": 10.361486434936523, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.7766, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12052730696798493, | |
| "grad_norm": 5.311871528625488, | |
| "learning_rate": 9.890659585173379e-05, | |
| "loss": 1.494, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.129136400322841, | |
| "grad_norm": 4.676233291625977, | |
| "learning_rate": 9.865140639375449e-05, | |
| "loss": 1.5863, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13774549367769706, | |
| "grad_norm": 3.6029069423675537, | |
| "learning_rate": 9.83699229607948e-05, | |
| "loss": 1.7019, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14635458703255314, | |
| "grad_norm": 1.6760152578353882, | |
| "learning_rate": 9.80623151079494e-05, | |
| "loss": 1.6638, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1549636803874092, | |
| "grad_norm": 1.4253727197647095, | |
| "learning_rate": 9.772876812668666e-05, | |
| "loss": 1.7801, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16357277374226525, | |
| "grad_norm": 1.3295799493789673, | |
| "learning_rate": 9.736948293323593e-05, | |
| "loss": 1.7038, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17218186709712133, | |
| "grad_norm": 0.7724640965461731, | |
| "learning_rate": 9.698467594756325e-05, | |
| "loss": 1.7746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1807909604519774, | |
| "grad_norm": 0.8214246034622192, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5971, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18940005380683347, | |
| "grad_norm": 1.1587809324264526, | |
| "learning_rate": 9.613943900665889e-05, | |
| "loss": 1.7559, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19800914716168955, | |
| "grad_norm": 1.8553802967071533, | |
| "learning_rate": 9.567951819055496e-05, | |
| "loss": 1.7612, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2066182405165456, | |
| "grad_norm": 2.004556655883789, | |
| "learning_rate": 9.519509355379818e-05, | |
| "loss": 1.5969, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21522733387140167, | |
| "grad_norm": 5.224137783050537, | |
| "learning_rate": 9.468645689567598e-05, | |
| "loss": 2.0711, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21522733387140167, | |
| "eval_loss": 1.508137822151184, | |
| "eval_runtime": 1.2723, | |
| "eval_samples_per_second": 39.3, | |
| "eval_steps_per_second": 10.218, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22383642722625774, | |
| "grad_norm": 1.341894268989563, | |
| "learning_rate": 9.415391459989203e-05, | |
| "loss": 1.2867, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2324455205811138, | |
| "grad_norm": 2.224653720855713, | |
| "learning_rate": 9.359778745001225e-05, | |
| "loss": 1.2927, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24105461393596986, | |
| "grad_norm": 1.4196522235870361, | |
| "learning_rate": 9.301841043623682e-05, | |
| "loss": 1.3711, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24966370729082593, | |
| "grad_norm": 1.2161178588867188, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.4576, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.258272800645682, | |
| "grad_norm": 0.8192944526672363, | |
| "learning_rate": 9.179131659182127e-05, | |
| "loss": 1.6426, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2668818940005381, | |
| "grad_norm": 0.6419580578804016, | |
| "learning_rate": 9.114433891662902e-05, | |
| "loss": 1.7142, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2754909873553941, | |
| "grad_norm": 0.41701650619506836, | |
| "learning_rate": 9.047558924319729e-05, | |
| "loss": 1.6853, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2841000807102502, | |
| "grad_norm": 0.4797891080379486, | |
| "learning_rate": 8.978547040132317e-05, | |
| "loss": 1.6622, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29270917406510627, | |
| "grad_norm": 0.737724781036377, | |
| "learning_rate": 8.907439809279181e-05, | |
| "loss": 1.6734, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3013182674199623, | |
| "grad_norm": 1.0522786378860474, | |
| "learning_rate": 8.834280064097317e-05, | |
| "loss": 1.6301, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3099273607748184, | |
| "grad_norm": 1.4976811408996582, | |
| "learning_rate": 8.759111873281603e-05, | |
| "loss": 1.6521, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.31853645412967446, | |
| "grad_norm": 3.2661497592926025, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.5304, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3271455474845305, | |
| "grad_norm": 2.8426661491394043, | |
| "learning_rate": 8.602932451316802e-05, | |
| "loss": 1.437, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3357546408393866, | |
| "grad_norm": 0.49562180042266846, | |
| "learning_rate": 8.522015296811584e-05, | |
| "loss": 1.2391, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.34436373419424265, | |
| "grad_norm": 0.5359828472137451, | |
| "learning_rate": 8.439277793291995e-05, | |
| "loss": 1.2585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35297282754909876, | |
| "grad_norm": 0.8592618107795715, | |
| "learning_rate": 8.354769778736406e-05, | |
| "loss": 1.3682, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3615819209039548, | |
| "grad_norm": 0.8251994848251343, | |
| "learning_rate": 8.268542157612821e-05, | |
| "loss": 1.548, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37019101425881085, | |
| "grad_norm": 0.9783174991607666, | |
| "learning_rate": 8.180646870215952e-05, | |
| "loss": 1.7041, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37880010761366695, | |
| "grad_norm": 0.894888699054718, | |
| "learning_rate": 8.091136861380305e-05, | |
| "loss": 1.8391, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.387409200968523, | |
| "grad_norm": 0.5933730006217957, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.6974, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3960182943233791, | |
| "grad_norm": 0.7440256476402283, | |
| "learning_rate": 7.907489289491939e-05, | |
| "loss": 1.6231, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.40462738767823514, | |
| "grad_norm": 0.7255629897117615, | |
| "learning_rate": 7.813462348869497e-05, | |
| "loss": 1.6172, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4132364810330912, | |
| "grad_norm": 1.1230436563491821, | |
| "learning_rate": 7.71804186503403e-05, | |
| "loss": 1.5745, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4218455743879473, | |
| "grad_norm": 1.6526938676834106, | |
| "learning_rate": 7.62128531571699e-05, | |
| "loss": 1.2586, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.43045466774280333, | |
| "grad_norm": 5.730405330657959, | |
| "learning_rate": 7.523250983445731e-05, | |
| "loss": 1.7199, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43045466774280333, | |
| "eval_loss": 1.389930248260498, | |
| "eval_runtime": 1.2729, | |
| "eval_samples_per_second": 39.28, | |
| "eval_steps_per_second": 10.213, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4390637610976594, | |
| "grad_norm": 0.4678877890110016, | |
| "learning_rate": 7.42399792043627e-05, | |
| "loss": 1.2294, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4476728544525155, | |
| "grad_norm": 0.5002795457839966, | |
| "learning_rate": 7.323585913022454e-05, | |
| "loss": 1.2342, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4562819478073715, | |
| "grad_norm": 0.3534197509288788, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2975, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4648910411622276, | |
| "grad_norm": 0.6102612018585205, | |
| "learning_rate": 7.119527664407447e-05, | |
| "loss": 1.4773, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47350013451708367, | |
| "grad_norm": 0.5064122080802917, | |
| "learning_rate": 7.01600434026499e-05, | |
| "loss": 1.5257, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4821092278719397, | |
| "grad_norm": 0.6477398872375488, | |
| "learning_rate": 6.911567831795013e-05, | |
| "loss": 1.7135, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4907183212267958, | |
| "grad_norm": 1.0539360046386719, | |
| "learning_rate": 6.80628104764508e-05, | |
| "loss": 1.8241, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.49932741458165186, | |
| "grad_norm": 0.7702855467796326, | |
| "learning_rate": 6.700207408637044e-05, | |
| "loss": 1.7362, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 0.6455403566360474, | |
| "learning_rate": 6.593410809564689e-05, | |
| "loss": 1.5381, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.516545601291364, | |
| "grad_norm": 0.6673574447631836, | |
| "learning_rate": 6.485955580705913e-05, | |
| "loss": 1.4796, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5251546946462201, | |
| "grad_norm": 0.8242542743682861, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6654, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5337637880010762, | |
| "grad_norm": 1.4092378616333008, | |
| "learning_rate": 6.269328499421356e-05, | |
| "loss": 1.2351, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 2.419718027114868, | |
| "learning_rate": 6.160287135049127e-05, | |
| "loss": 1.4315, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5509819747107882, | |
| "grad_norm": 0.38671913743019104, | |
| "learning_rate": 6.050848038396473e-05, | |
| "loss": 1.2274, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5595910680656443, | |
| "grad_norm": 0.5623155832290649, | |
| "learning_rate": 5.941077131483025e-05, | |
| "loss": 1.3062, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5682001614205004, | |
| "grad_norm": 0.6458035111427307, | |
| "learning_rate": 5.831040536198504e-05, | |
| "loss": 1.4318, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5768092547753565, | |
| "grad_norm": 0.6504884958267212, | |
| "learning_rate": 5.720804534473382e-05, | |
| "loss": 1.3897, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5854183481302125, | |
| "grad_norm": 0.4223068356513977, | |
| "learning_rate": 5.610435528353106e-05, | |
| "loss": 1.5331, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5940274414850686, | |
| "grad_norm": 0.5046920776367188, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.6225, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6026365348399246, | |
| "grad_norm": 0.41651174426078796, | |
| "learning_rate": 5.389564471646895e-05, | |
| "loss": 1.7376, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6112456281947808, | |
| "grad_norm": 0.32924169301986694, | |
| "learning_rate": 5.27919546552662e-05, | |
| "loss": 1.5401, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6198547215496368, | |
| "grad_norm": 0.4280257821083069, | |
| "learning_rate": 5.168959463801497e-05, | |
| "loss": 1.5662, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6284638149044929, | |
| "grad_norm": 0.6656383275985718, | |
| "learning_rate": 5.058922868516978e-05, | |
| "loss": 1.4713, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6370729082593489, | |
| "grad_norm": 0.8646160960197449, | |
| "learning_rate": 4.9491519616035276e-05, | |
| "loss": 1.2566, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.645682001614205, | |
| "grad_norm": 2.5206289291381836, | |
| "learning_rate": 4.839712864950873e-05, | |
| "loss": 1.7236, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.645682001614205, | |
| "eval_loss": 1.349289894104004, | |
| "eval_runtime": 1.2727, | |
| "eval_samples_per_second": 39.288, | |
| "eval_steps_per_second": 10.215, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.654291094969061, | |
| "grad_norm": 0.4360639750957489, | |
| "learning_rate": 4.730671500578645e-05, | |
| "loss": 1.1383, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6629001883239172, | |
| "grad_norm": 0.8731722235679626, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.4032, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6715092816787732, | |
| "grad_norm": 0.7142120003700256, | |
| "learning_rate": 4.5140444192940864e-05, | |
| "loss": 1.1904, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6801183750336293, | |
| "grad_norm": 0.594018280506134, | |
| "learning_rate": 4.406589190435313e-05, | |
| "loss": 1.3872, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6887274683884853, | |
| "grad_norm": 0.6022002696990967, | |
| "learning_rate": 4.2997925913629577e-05, | |
| "loss": 1.5956, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6973365617433414, | |
| "grad_norm": 0.5471949577331543, | |
| "learning_rate": 4.19371895235492e-05, | |
| "loss": 1.6525, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7059456550981975, | |
| "grad_norm": 0.3283829391002655, | |
| "learning_rate": 4.0884321682049884e-05, | |
| "loss": 1.772, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7145547484530536, | |
| "grad_norm": 0.34206530451774597, | |
| "learning_rate": 3.98399565973501e-05, | |
| "loss": 1.6938, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7231638418079096, | |
| "grad_norm": 0.35002151131629944, | |
| "learning_rate": 3.880472335592553e-05, | |
| "loss": 1.418, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7317729351627656, | |
| "grad_norm": 0.7404176592826843, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.5774, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7403820285176217, | |
| "grad_norm": 0.8380143046379089, | |
| "learning_rate": 3.676414086977546e-05, | |
| "loss": 1.3188, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7489911218724778, | |
| "grad_norm": 2.1834990978240967, | |
| "learning_rate": 3.576002079563732e-05, | |
| "loss": 1.4621, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7576002152273339, | |
| "grad_norm": 2.3319005966186523, | |
| "learning_rate": 3.4767490165542704e-05, | |
| "loss": 1.5594, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7662093085821899, | |
| "grad_norm": 0.3592979311943054, | |
| "learning_rate": 3.378714684283011e-05, | |
| "loss": 1.1, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.774818401937046, | |
| "grad_norm": 0.49761757254600525, | |
| "learning_rate": 3.281958134965972e-05, | |
| "loss": 1.3531, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.783427495291902, | |
| "grad_norm": 0.3277381658554077, | |
| "learning_rate": 3.186537651130503e-05, | |
| "loss": 1.3467, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7920365886467582, | |
| "grad_norm": 0.3256728947162628, | |
| "learning_rate": 3.0925107105080636e-05, | |
| "loss": 1.5374, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8006456820016142, | |
| "grad_norm": 0.35263001918792725, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5367, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8092547753564703, | |
| "grad_norm": 0.3698779344558716, | |
| "learning_rate": 2.9088631386196964e-05, | |
| "loss": 1.7344, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.8178638687113263, | |
| "grad_norm": 0.445311576128006, | |
| "learning_rate": 2.8193531297840503e-05, | |
| "loss": 1.7141, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8264729620661824, | |
| "grad_norm": 0.4353031814098358, | |
| "learning_rate": 2.73145784238718e-05, | |
| "loss": 1.5168, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8350820554210385, | |
| "grad_norm": 0.6268022060394287, | |
| "learning_rate": 2.645230221263596e-05, | |
| "loss": 1.4016, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8436911487758946, | |
| "grad_norm": 0.5284622311592102, | |
| "learning_rate": 2.560722206708006e-05, | |
| "loss": 1.5741, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8523002421307506, | |
| "grad_norm": 0.7828362584114075, | |
| "learning_rate": 2.4779847031884175e-05, | |
| "loss": 1.243, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8609093354856067, | |
| "grad_norm": 3.621532678604126, | |
| "learning_rate": 2.397067548683199e-05, | |
| "loss": 1.5976, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8609093354856067, | |
| "eval_loss": 1.3449122905731201, | |
| "eval_runtime": 1.2724, | |
| "eval_samples_per_second": 39.295, | |
| "eval_steps_per_second": 10.217, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8695184288404627, | |
| "grad_norm": 0.3012229800224304, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.176, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8781275221953188, | |
| "grad_norm": 0.4754287004470825, | |
| "learning_rate": 2.2408881267183997e-05, | |
| "loss": 1.1958, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.8867366155501749, | |
| "grad_norm": 0.43265655636787415, | |
| "learning_rate": 2.165719935902685e-05, | |
| "loss": 1.3262, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.895345708905031, | |
| "grad_norm": 0.5260616540908813, | |
| "learning_rate": 2.09256019072082e-05, | |
| "loss": 1.3721, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.903954802259887, | |
| "grad_norm": 0.5602609515190125, | |
| "learning_rate": 2.0214529598676836e-05, | |
| "loss": 1.401, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.912563895614743, | |
| "grad_norm": 0.29336562752723694, | |
| "learning_rate": 1.952441075680272e-05, | |
| "loss": 1.6924, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9211729889695991, | |
| "grad_norm": 0.9488304853439331, | |
| "learning_rate": 1.8855661083370986e-05, | |
| "loss": 1.8012, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9297820823244553, | |
| "grad_norm": 0.3932758867740631, | |
| "learning_rate": 1.820868340817874e-05, | |
| "loss": 1.6428, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9383911756793113, | |
| "grad_norm": 0.3379191756248474, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3678, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9470002690341673, | |
| "grad_norm": 0.5376018285751343, | |
| "learning_rate": 1.698158956376318e-05, | |
| "loss": 1.6057, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9556093623890234, | |
| "grad_norm": 0.6705049872398376, | |
| "learning_rate": 1.6402212549987762e-05, | |
| "loss": 1.5497, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9642184557438794, | |
| "grad_norm": 1.5708343982696533, | |
| "learning_rate": 1.584608540010799e-05, | |
| "loss": 1.4589, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9728275490987356, | |
| "grad_norm": 2.8929443359375, | |
| "learning_rate": 1.531354310432403e-05, | |
| "loss": 1.5784, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9814366424535916, | |
| "grad_norm": 0.3657113313674927, | |
| "learning_rate": 1.4804906446201816e-05, | |
| "loss": 1.3912, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9900457358084477, | |
| "grad_norm": 0.3794941306114197, | |
| "learning_rate": 1.4320481809445051e-05, | |
| "loss": 1.5847, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9986548291633037, | |
| "grad_norm": 0.7362991571426392, | |
| "learning_rate": 1.386056099334112e-05, | |
| "loss": 1.399, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0072639225181599, | |
| "grad_norm": 0.8029009103775024, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2215, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.0158730158730158, | |
| "grad_norm": 0.5080808997154236, | |
| "learning_rate": 1.3015324052436753e-05, | |
| "loss": 1.2015, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.024482109227872, | |
| "grad_norm": 0.44496291875839233, | |
| "learning_rate": 1.2630517066764069e-05, | |
| "loss": 1.2138, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.033091202582728, | |
| "grad_norm": 0.4348479211330414, | |
| "learning_rate": 1.227123187331335e-05, | |
| "loss": 1.2767, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.041700295937584, | |
| "grad_norm": 0.37992164492607117, | |
| "learning_rate": 1.1937684892050604e-05, | |
| "loss": 1.5242, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.0503093892924402, | |
| "grad_norm": 0.32971861958503723, | |
| "learning_rate": 1.1630077039205209e-05, | |
| "loss": 1.5498, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.0589184826472962, | |
| "grad_norm": 0.5224172472953796, | |
| "learning_rate": 1.1348593606245522e-05, | |
| "loss": 1.6984, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.0675275760021523, | |
| "grad_norm": 0.43070971965789795, | |
| "learning_rate": 1.109340414826622e-05, | |
| "loss": 1.5932, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.0761366693570082, | |
| "grad_norm": 0.4774491786956787, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4308, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0761366693570082, | |
| "eval_loss": 1.3410676717758179, | |
| "eval_runtime": 1.2741, | |
| "eval_samples_per_second": 39.242, | |
| "eval_steps_per_second": 10.203, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0847457627118644, | |
| "grad_norm": 0.5184400677680969, | |
| "learning_rate": 1.0662506092497646e-05, | |
| "loss": 1.4641, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.0933548560667206, | |
| "grad_norm": 0.5525245666503906, | |
| "learning_rate": 1.0487057051584856e-05, | |
| "loss": 1.5545, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.1019639494215765, | |
| "grad_norm": 1.609927773475647, | |
| "learning_rate": 1.0338420943058053e-05, | |
| "loss": 1.3439, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.1105730427764327, | |
| "grad_norm": 2.2938551902770996, | |
| "learning_rate": 1.0216687299751144e-05, | |
| "loss": 1.4817, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.1191821361312886, | |
| "grad_norm": 0.45292142033576965, | |
| "learning_rate": 1.0121929449458941e-05, | |
| "loss": 1.1242, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1277912294861447, | |
| "grad_norm": 0.4423352777957916, | |
| "learning_rate": 1.0054204470767243e-05, | |
| "loss": 1.1672, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.136400322841001, | |
| "grad_norm": 0.33851832151412964, | |
| "learning_rate": 1.0013553158670811e-05, | |
| "loss": 1.2433, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.1450094161958568, | |
| "grad_norm": 0.3434777855873108, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4094, | |
| "step": 133 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 133, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "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": 2.8256510115053568e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |