| { | |
| "best_metric": 1.011842966079712, | |
| "best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v3/checkpoint-198", | |
| "epoch": 99.69565217391305, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 65.68504333496094, | |
| "eval_runtime": 2.5882, | |
| "eval_samples_per_second": 6.568, | |
| "eval_steps_per_second": 1.159, | |
| "eval_wer": 0.9201430274135876, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 65.31504821777344, | |
| "eval_runtime": 2.8243, | |
| "eval_samples_per_second": 6.019, | |
| "eval_steps_per_second": 1.062, | |
| "eval_wer": 0.9165673420738975, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "eval_loss": 63.401397705078125, | |
| "eval_runtime": 2.7045, | |
| "eval_samples_per_second": 6.286, | |
| "eval_steps_per_second": 1.109, | |
| "eval_wer": 0.8986889153754469, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 61.84690856933594, | |
| "eval_runtime": 2.7848, | |
| "eval_samples_per_second": 6.105, | |
| "eval_steps_per_second": 1.077, | |
| "eval_wer": 0.8700834326579261, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 20.497, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "eval_loss": 57.46735382080078, | |
| "eval_runtime": 2.7178, | |
| "eval_samples_per_second": 6.255, | |
| "eval_steps_per_second": 1.104, | |
| "eval_wer": 0.8557806912991657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "eval_loss": 51.37147903442383, | |
| "eval_runtime": 2.7102, | |
| "eval_samples_per_second": 6.273, | |
| "eval_steps_per_second": 1.107, | |
| "eval_wer": 0.9356376638855781, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_loss": 43.46580123901367, | |
| "eval_runtime": 2.6418, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 1.136, | |
| "eval_wer": 0.9868891537544696, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "eval_loss": 33.7960319519043, | |
| "eval_runtime": 2.6634, | |
| "eval_samples_per_second": 6.383, | |
| "eval_steps_per_second": 1.126, | |
| "eval_wer": 1.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "eval_loss": 22.868000030517578, | |
| "eval_runtime": 2.6558, | |
| "eval_samples_per_second": 6.401, | |
| "eval_steps_per_second": 1.13, | |
| "eval_wer": 1.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 13.2039, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "eval_loss": 12.010748863220215, | |
| "eval_runtime": 2.6219, | |
| "eval_samples_per_second": 6.484, | |
| "eval_steps_per_second": 1.144, | |
| "eval_wer": 1.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "eval_loss": 4.675407886505127, | |
| "eval_runtime": 2.566, | |
| "eval_samples_per_second": 6.625, | |
| "eval_steps_per_second": 1.169, | |
| "eval_wer": 1.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "eval_loss": 2.5355348587036133, | |
| "eval_runtime": 2.5403, | |
| "eval_samples_per_second": 6.692, | |
| "eval_steps_per_second": 1.181, | |
| "eval_wer": 1.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "eval_loss": 2.2340898513793945, | |
| "eval_runtime": 2.5381, | |
| "eval_samples_per_second": 6.698, | |
| "eval_steps_per_second": 1.182, | |
| "eval_wer": 1.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "eval_loss": 2.8692574501037598, | |
| "eval_runtime": 2.5952, | |
| "eval_samples_per_second": 6.55, | |
| "eval_steps_per_second": 1.156, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 0.0002883333333333333, | |
| "loss": 3.0397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "eval_loss": 3.508324384689331, | |
| "eval_runtime": 2.5954, | |
| "eval_samples_per_second": 6.55, | |
| "eval_steps_per_second": 1.156, | |
| "eval_wer": 1.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "eval_loss": 3.1664485931396484, | |
| "eval_runtime": 2.587, | |
| "eval_samples_per_second": 6.571, | |
| "eval_steps_per_second": 1.16, | |
| "eval_wer": 1.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "eval_loss": 2.6171875, | |
| "eval_runtime": 2.5928, | |
| "eval_samples_per_second": 6.557, | |
| "eval_steps_per_second": 1.157, | |
| "eval_wer": 1.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "eval_loss": 2.2690131664276123, | |
| "eval_runtime": 2.5759, | |
| "eval_samples_per_second": 6.6, | |
| "eval_steps_per_second": 1.165, | |
| "eval_wer": 1.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "eval_loss": 2.380885124206543, | |
| "eval_runtime": 2.5845, | |
| "eval_samples_per_second": 6.578, | |
| "eval_steps_per_second": 1.161, | |
| "eval_wer": 1.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 0.00027166666666666664, | |
| "loss": 2.133, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "eval_loss": 2.2537014484405518, | |
| "eval_runtime": 2.5569, | |
| "eval_samples_per_second": 6.649, | |
| "eval_steps_per_second": 1.173, | |
| "eval_wer": 1.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 20.7, | |
| "eval_loss": 1.9851531982421875, | |
| "eval_runtime": 2.532, | |
| "eval_samples_per_second": 6.714, | |
| "eval_steps_per_second": 1.185, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 21.7, | |
| "eval_loss": 2.072378396987915, | |
| "eval_runtime": 2.6203, | |
| "eval_samples_per_second": 6.488, | |
| "eval_steps_per_second": 1.145, | |
| "eval_wer": 1.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 22.7, | |
| "eval_loss": 2.00761342048645, | |
| "eval_runtime": 2.532, | |
| "eval_samples_per_second": 6.714, | |
| "eval_steps_per_second": 1.185, | |
| "eval_wer": 1.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 23.7, | |
| "eval_loss": 1.94607675075531, | |
| "eval_runtime": 2.5261, | |
| "eval_samples_per_second": 6.73, | |
| "eval_steps_per_second": 1.188, | |
| "eval_wer": 1.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "learning_rate": 0.00025499999999999996, | |
| "loss": 1.8964, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 24.7, | |
| "eval_loss": 2.0850636959075928, | |
| "eval_runtime": 2.5842, | |
| "eval_samples_per_second": 6.578, | |
| "eval_steps_per_second": 1.161, | |
| "eval_wer": 1.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 25.7, | |
| "eval_loss": 2.0501198768615723, | |
| "eval_runtime": 2.5619, | |
| "eval_samples_per_second": 6.636, | |
| "eval_steps_per_second": 1.171, | |
| "eval_wer": 1.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "eval_loss": 1.8149293661117554, | |
| "eval_runtime": 2.5646, | |
| "eval_samples_per_second": 6.629, | |
| "eval_steps_per_second": 1.17, | |
| "eval_wer": 1.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 27.7, | |
| "eval_loss": 1.8059440851211548, | |
| "eval_runtime": 2.5604, | |
| "eval_samples_per_second": 6.64, | |
| "eval_steps_per_second": 1.172, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 28.7, | |
| "eval_loss": 1.9727060794830322, | |
| "eval_runtime": 2.5065, | |
| "eval_samples_per_second": 6.782, | |
| "eval_steps_per_second": 1.197, | |
| "eval_wer": 1.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 29.7, | |
| "learning_rate": 0.0002383333333333333, | |
| "loss": 1.8599, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 29.7, | |
| "eval_loss": 1.7996188402175903, | |
| "eval_runtime": 2.5606, | |
| "eval_samples_per_second": 6.639, | |
| "eval_steps_per_second": 1.172, | |
| "eval_wer": 1.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 30.7, | |
| "eval_loss": 1.64518141746521, | |
| "eval_runtime": 2.5395, | |
| "eval_samples_per_second": 6.694, | |
| "eval_steps_per_second": 1.181, | |
| "eval_wer": 1.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 31.7, | |
| "eval_loss": 1.8070778846740723, | |
| "eval_runtime": 2.5418, | |
| "eval_samples_per_second": 6.688, | |
| "eval_steps_per_second": 1.18, | |
| "eval_wer": 1.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 32.7, | |
| "eval_loss": 1.7773442268371582, | |
| "eval_runtime": 2.5825, | |
| "eval_samples_per_second": 6.583, | |
| "eval_steps_per_second": 1.162, | |
| "eval_wer": 1.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 33.7, | |
| "eval_loss": 1.6233692169189453, | |
| "eval_runtime": 2.5954, | |
| "eval_samples_per_second": 6.55, | |
| "eval_steps_per_second": 1.156, | |
| "eval_wer": 1.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 34.7, | |
| "learning_rate": 0.00022166666666666667, | |
| "loss": 1.7166, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 34.7, | |
| "eval_loss": 1.6564326286315918, | |
| "eval_runtime": 2.5596, | |
| "eval_samples_per_second": 6.642, | |
| "eval_steps_per_second": 1.172, | |
| "eval_wer": 1.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 35.7, | |
| "eval_loss": 1.6549872159957886, | |
| "eval_runtime": 2.5502, | |
| "eval_samples_per_second": 6.666, | |
| "eval_steps_per_second": 1.176, | |
| "eval_wer": 1.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 36.7, | |
| "eval_loss": 1.565232753753662, | |
| "eval_runtime": 2.5958, | |
| "eval_samples_per_second": 6.549, | |
| "eval_steps_per_second": 1.156, | |
| "eval_wer": 1.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "eval_loss": 1.5213314294815063, | |
| "eval_runtime": 2.6219, | |
| "eval_samples_per_second": 6.484, | |
| "eval_steps_per_second": 1.144, | |
| "eval_wer": 0.9952324195470799, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 38.7, | |
| "eval_loss": 1.47950279712677, | |
| "eval_runtime": 2.6468, | |
| "eval_samples_per_second": 6.423, | |
| "eval_steps_per_second": 1.133, | |
| "eval_wer": 0.9856972586412396, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 39.7, | |
| "learning_rate": 0.000205, | |
| "loss": 1.4764, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 39.7, | |
| "eval_loss": 1.4402477741241455, | |
| "eval_runtime": 2.6428, | |
| "eval_samples_per_second": 6.433, | |
| "eval_steps_per_second": 1.135, | |
| "eval_wer": 0.9868891537544696, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 40.7, | |
| "eval_loss": 1.4424933195114136, | |
| "eval_runtime": 2.631, | |
| "eval_samples_per_second": 6.461, | |
| "eval_steps_per_second": 1.14, | |
| "eval_wer": 0.9415971394517283, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 41.7, | |
| "eval_loss": 1.4473284482955933, | |
| "eval_runtime": 2.6449, | |
| "eval_samples_per_second": 6.427, | |
| "eval_steps_per_second": 1.134, | |
| "eval_wer": 0.8462455303933254, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 42.7, | |
| "eval_loss": 1.3785685300827026, | |
| "eval_runtime": 2.6492, | |
| "eval_samples_per_second": 6.417, | |
| "eval_steps_per_second": 1.132, | |
| "eval_wer": 0.899880810488677, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 43.7, | |
| "eval_loss": 1.460979700088501, | |
| "eval_runtime": 2.6782, | |
| "eval_samples_per_second": 6.348, | |
| "eval_steps_per_second": 1.12, | |
| "eval_wer": 0.8486293206197855, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 44.7, | |
| "learning_rate": 0.00018833333333333332, | |
| "loss": 1.3782, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 44.7, | |
| "eval_loss": 1.6983370780944824, | |
| "eval_runtime": 2.6416, | |
| "eval_samples_per_second": 6.436, | |
| "eval_steps_per_second": 1.136, | |
| "eval_wer": 0.8498212157330155, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 45.7, | |
| "eval_loss": 1.5572391748428345, | |
| "eval_runtime": 2.6072, | |
| "eval_samples_per_second": 6.52, | |
| "eval_steps_per_second": 1.151, | |
| "eval_wer": 0.9129916567342073, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 46.7, | |
| "eval_loss": 1.6036518812179565, | |
| "eval_runtime": 2.6041, | |
| "eval_samples_per_second": 6.528, | |
| "eval_steps_per_second": 1.152, | |
| "eval_wer": 0.8128724672228844, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 47.7, | |
| "eval_loss": 1.6874778270721436, | |
| "eval_runtime": 2.5174, | |
| "eval_samples_per_second": 6.753, | |
| "eval_steps_per_second": 1.192, | |
| "eval_wer": 0.7151370679380215, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 48.7, | |
| "eval_loss": 1.6261805295944214, | |
| "eval_runtime": 2.5248, | |
| "eval_samples_per_second": 6.733, | |
| "eval_steps_per_second": 1.188, | |
| "eval_wer": 0.7783075089392133, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 49.7, | |
| "learning_rate": 0.00017166666666666665, | |
| "loss": 1.3406, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 49.7, | |
| "eval_loss": 1.6008760929107666, | |
| "eval_runtime": 2.5052, | |
| "eval_samples_per_second": 6.786, | |
| "eval_steps_per_second": 1.197, | |
| "eval_wer": 0.7306317044100119, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 50.7, | |
| "eval_loss": 1.5744612216949463, | |
| "eval_runtime": 2.5272, | |
| "eval_samples_per_second": 6.727, | |
| "eval_steps_per_second": 1.187, | |
| "eval_wer": 0.6758045292014303, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 51.7, | |
| "eval_loss": 1.5347764492034912, | |
| "eval_runtime": 2.562, | |
| "eval_samples_per_second": 6.636, | |
| "eval_steps_per_second": 1.171, | |
| "eval_wer": 0.6805721096543504, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 52.7, | |
| "eval_loss": 1.5455317497253418, | |
| "eval_runtime": 2.5351, | |
| "eval_samples_per_second": 6.706, | |
| "eval_steps_per_second": 1.183, | |
| "eval_wer": 0.6591179976162098, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 53.7, | |
| "eval_loss": 1.4915562868118286, | |
| "eval_runtime": 2.5349, | |
| "eval_samples_per_second": 6.706, | |
| "eval_steps_per_second": 1.183, | |
| "eval_wer": 0.6293206197854588, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 54.7, | |
| "learning_rate": 0.000155, | |
| "loss": 1.1939, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 54.7, | |
| "eval_loss": 1.399192214012146, | |
| "eval_runtime": 2.5718, | |
| "eval_samples_per_second": 6.61, | |
| "eval_steps_per_second": 1.166, | |
| "eval_wer": 0.6317044100119189, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 55.7, | |
| "eval_loss": 1.3632481098175049, | |
| "eval_runtime": 2.531, | |
| "eval_samples_per_second": 6.717, | |
| "eval_steps_per_second": 1.185, | |
| "eval_wer": 0.6078665077473182, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 56.7, | |
| "eval_loss": 1.297105073928833, | |
| "eval_runtime": 2.5234, | |
| "eval_samples_per_second": 6.737, | |
| "eval_steps_per_second": 1.189, | |
| "eval_wer": 0.6126340882002383, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 57.7, | |
| "eval_loss": 1.2397348880767822, | |
| "eval_runtime": 2.589, | |
| "eval_samples_per_second": 6.566, | |
| "eval_steps_per_second": 1.159, | |
| "eval_wer": 0.6257449344457687, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 58.7, | |
| "eval_loss": 1.2213208675384521, | |
| "eval_runtime": 2.5427, | |
| "eval_samples_per_second": 6.686, | |
| "eval_steps_per_second": 1.18, | |
| "eval_wer": 0.6114421930870083, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 59.7, | |
| "learning_rate": 0.00013833333333333333, | |
| "loss": 1.2298, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 59.7, | |
| "eval_loss": 1.270306944847107, | |
| "eval_runtime": 2.5565, | |
| "eval_samples_per_second": 6.65, | |
| "eval_steps_per_second": 1.173, | |
| "eval_wer": 0.600715137067938, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 60.7, | |
| "eval_loss": 1.328464388847351, | |
| "eval_runtime": 2.5828, | |
| "eval_samples_per_second": 6.582, | |
| "eval_steps_per_second": 1.162, | |
| "eval_wer": 0.5935637663885578, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 61.7, | |
| "eval_loss": 1.4112215042114258, | |
| "eval_runtime": 2.5426, | |
| "eval_samples_per_second": 6.686, | |
| "eval_steps_per_second": 1.18, | |
| "eval_wer": 0.599523241954708, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 62.7, | |
| "eval_loss": 1.4663811922073364, | |
| "eval_runtime": 2.5264, | |
| "eval_samples_per_second": 6.729, | |
| "eval_steps_per_second": 1.187, | |
| "eval_wer": 0.599523241954708, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 63.7, | |
| "eval_loss": 1.5034104585647583, | |
| "eval_runtime": 2.5056, | |
| "eval_samples_per_second": 6.785, | |
| "eval_steps_per_second": 1.197, | |
| "eval_wer": 0.6042908224076281, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 64.7, | |
| "learning_rate": 0.00012166666666666665, | |
| "loss": 1.1321, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 64.7, | |
| "eval_loss": 1.4717862606048584, | |
| "eval_runtime": 2.5441, | |
| "eval_samples_per_second": 6.682, | |
| "eval_steps_per_second": 1.179, | |
| "eval_wer": 0.6126340882002383, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 65.7, | |
| "eval_loss": 1.4656554460525513, | |
| "eval_runtime": 2.5454, | |
| "eval_samples_per_second": 6.679, | |
| "eval_steps_per_second": 1.179, | |
| "eval_wer": 0.6293206197854588, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 66.7, | |
| "eval_loss": 1.4940413236618042, | |
| "eval_runtime": 2.5574, | |
| "eval_samples_per_second": 6.647, | |
| "eval_steps_per_second": 1.173, | |
| "eval_wer": 0.600715137067938, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 67.7, | |
| "eval_loss": 1.5150542259216309, | |
| "eval_runtime": 2.5242, | |
| "eval_samples_per_second": 6.735, | |
| "eval_steps_per_second": 1.189, | |
| "eval_wer": 0.5899880810488677, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 68.7, | |
| "eval_loss": 1.4332056045532227, | |
| "eval_runtime": 2.5934, | |
| "eval_samples_per_second": 6.555, | |
| "eval_steps_per_second": 1.157, | |
| "eval_wer": 0.601907032181168, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 69.7, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 1.068, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 69.7, | |
| "eval_loss": 1.317719578742981, | |
| "eval_runtime": 2.5535, | |
| "eval_samples_per_second": 6.658, | |
| "eval_steps_per_second": 1.175, | |
| "eval_wer": 0.6138259833134684, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 70.7, | |
| "eval_loss": 1.2635740041732788, | |
| "eval_runtime": 2.5266, | |
| "eval_samples_per_second": 6.728, | |
| "eval_steps_per_second": 1.187, | |
| "eval_wer": 0.6138259833134684, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 71.7, | |
| "eval_loss": 1.2209337949752808, | |
| "eval_runtime": 2.5438, | |
| "eval_samples_per_second": 6.683, | |
| "eval_steps_per_second": 1.179, | |
| "eval_wer": 0.600715137067938, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 72.7, | |
| "eval_loss": 1.1463706493377686, | |
| "eval_runtime": 2.5299, | |
| "eval_samples_per_second": 6.72, | |
| "eval_steps_per_second": 1.186, | |
| "eval_wer": 0.601907032181168, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 73.7, | |
| "eval_loss": 1.0894441604614258, | |
| "eval_runtime": 2.5089, | |
| "eval_samples_per_second": 6.776, | |
| "eval_steps_per_second": 1.196, | |
| "eval_wer": 0.6245530393325387, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 74.7, | |
| "learning_rate": 8.833333333333333e-05, | |
| "loss": 1.0462, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 74.7, | |
| "eval_loss": 1.0838207006454468, | |
| "eval_runtime": 2.5093, | |
| "eval_samples_per_second": 6.775, | |
| "eval_steps_per_second": 1.196, | |
| "eval_wer": 0.6245530393325387, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 75.7, | |
| "eval_loss": 1.0775409936904907, | |
| "eval_runtime": 2.5517, | |
| "eval_samples_per_second": 6.662, | |
| "eval_steps_per_second": 1.176, | |
| "eval_wer": 0.6221692491060786, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 76.7, | |
| "eval_loss": 1.0624889135360718, | |
| "eval_runtime": 2.5824, | |
| "eval_samples_per_second": 6.583, | |
| "eval_steps_per_second": 1.162, | |
| "eval_wer": 0.6114421930870083, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 77.7, | |
| "eval_loss": 1.052101492881775, | |
| "eval_runtime": 2.5652, | |
| "eval_samples_per_second": 6.627, | |
| "eval_steps_per_second": 1.17, | |
| "eval_wer": 0.6042908224076281, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 78.7, | |
| "eval_loss": 1.045043706893921, | |
| "eval_runtime": 2.5323, | |
| "eval_samples_per_second": 6.713, | |
| "eval_steps_per_second": 1.185, | |
| "eval_wer": 0.599523241954708, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 79.7, | |
| "learning_rate": 7.166666666666667e-05, | |
| "loss": 1.0199, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 79.7, | |
| "eval_loss": 1.0607061386108398, | |
| "eval_runtime": 2.5995, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 1.154, | |
| "eval_wer": 0.5947556615017878, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 80.7, | |
| "eval_loss": 1.0569047927856445, | |
| "eval_runtime": 2.5398, | |
| "eval_samples_per_second": 6.694, | |
| "eval_steps_per_second": 1.181, | |
| "eval_wer": 0.5923718712753278, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 81.7, | |
| "eval_loss": 1.0500773191452026, | |
| "eval_runtime": 2.5189, | |
| "eval_samples_per_second": 6.749, | |
| "eval_steps_per_second": 1.191, | |
| "eval_wer": 0.5911799761620977, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 82.7, | |
| "eval_loss": 1.051140546798706, | |
| "eval_runtime": 2.5362, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.183, | |
| "eval_wer": 0.5887961859356377, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 83.7, | |
| "eval_loss": 1.0690089464187622, | |
| "eval_runtime": 2.5428, | |
| "eval_samples_per_second": 6.686, | |
| "eval_steps_per_second": 1.18, | |
| "eval_wer": 0.5828367103694875, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 84.7, | |
| "learning_rate": 5.499999999999999e-05, | |
| "loss": 0.9651, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 84.7, | |
| "eval_loss": 1.0684703588485718, | |
| "eval_runtime": 2.5471, | |
| "eval_samples_per_second": 6.674, | |
| "eval_steps_per_second": 1.178, | |
| "eval_wer": 0.5804529201430274, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 85.7, | |
| "eval_loss": 1.0487909317016602, | |
| "eval_runtime": 2.4883, | |
| "eval_samples_per_second": 6.832, | |
| "eval_steps_per_second": 1.206, | |
| "eval_wer": 0.5864123957091776, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 86.7, | |
| "eval_loss": 1.031644344329834, | |
| "eval_runtime": 2.5435, | |
| "eval_samples_per_second": 6.684, | |
| "eval_steps_per_second": 1.179, | |
| "eval_wer": 0.5899880810488677, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 87.7, | |
| "eval_loss": 1.0346258878707886, | |
| "eval_runtime": 2.5551, | |
| "eval_samples_per_second": 6.653, | |
| "eval_steps_per_second": 1.174, | |
| "eval_wer": 0.5899880810488677, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 88.7, | |
| "eval_loss": 1.0490374565124512, | |
| "eval_runtime": 2.5304, | |
| "eval_samples_per_second": 6.718, | |
| "eval_steps_per_second": 1.186, | |
| "eval_wer": 0.5828367103694875, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 89.7, | |
| "learning_rate": 3.833333333333333e-05, | |
| "loss": 0.9867, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 89.7, | |
| "eval_loss": 1.046677827835083, | |
| "eval_runtime": 2.5362, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.183, | |
| "eval_wer": 0.5828367103694875, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 90.7, | |
| "eval_loss": 1.0315073728561401, | |
| "eval_runtime": 2.5361, | |
| "eval_samples_per_second": 6.703, | |
| "eval_steps_per_second": 1.183, | |
| "eval_wer": 0.5887961859356377, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 91.7, | |
| "eval_loss": 1.0205892324447632, | |
| "eval_runtime": 2.5305, | |
| "eval_samples_per_second": 6.718, | |
| "eval_steps_per_second": 1.186, | |
| "eval_wer": 0.5911799761620977, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 92.7, | |
| "eval_loss": 1.0165022611618042, | |
| "eval_runtime": 2.5148, | |
| "eval_samples_per_second": 6.76, | |
| "eval_steps_per_second": 1.193, | |
| "eval_wer": 0.5923718712753278, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 93.7, | |
| "eval_loss": 1.0147016048431396, | |
| "eval_runtime": 2.5058, | |
| "eval_samples_per_second": 6.784, | |
| "eval_steps_per_second": 1.197, | |
| "eval_wer": 0.5899880810488677, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 94.7, | |
| "learning_rate": 2.1666666666666664e-05, | |
| "loss": 0.9332, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 94.7, | |
| "eval_loss": 1.0174245834350586, | |
| "eval_runtime": 2.538, | |
| "eval_samples_per_second": 6.698, | |
| "eval_steps_per_second": 1.182, | |
| "eval_wer": 0.5876042908224076, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 95.7, | |
| "eval_loss": 1.0195481777191162, | |
| "eval_runtime": 2.5587, | |
| "eval_samples_per_second": 6.644, | |
| "eval_steps_per_second": 1.172, | |
| "eval_wer": 0.5852205005959475, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 96.7, | |
| "eval_loss": 1.0195115804672241, | |
| "eval_runtime": 2.5251, | |
| "eval_samples_per_second": 6.732, | |
| "eval_steps_per_second": 1.188, | |
| "eval_wer": 0.5840286054827175, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 97.7, | |
| "eval_loss": 1.015172004699707, | |
| "eval_runtime": 2.5398, | |
| "eval_samples_per_second": 6.694, | |
| "eval_steps_per_second": 1.181, | |
| "eval_wer": 0.5840286054827175, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 98.7, | |
| "eval_loss": 1.011842966079712, | |
| "eval_runtime": 2.6053, | |
| "eval_samples_per_second": 6.525, | |
| "eval_steps_per_second": 1.151, | |
| "eval_wer": 0.5852205005959475, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 99.7, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 0.9299, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 99.7, | |
| "eval_loss": 1.0128355026245117, | |
| "eval_runtime": 2.5227, | |
| "eval_samples_per_second": 6.739, | |
| "eval_steps_per_second": 1.189, | |
| "eval_wer": 0.5852205005959475, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 99.7, | |
| "step": 200, | |
| "total_flos": 1.8368228141544445e+18, | |
| "train_loss": 2.952321643829346, | |
| "train_runtime": 3905.0975, | |
| "train_samples_per_second": 4.584, | |
| "train_steps_per_second": 0.051 | |
| } | |
| ], | |
| "max_steps": 200, | |
| "num_train_epochs": 100, | |
| "total_flos": 1.8368228141544445e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |