| { | |
| "best_metric": 2.332979202270508, | |
| "best_model_checkpoint": "ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-rbma13-2_7k/checkpoint-40", | |
| "epoch": 100.0, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 68.1357650756836, | |
| "eval_runtime": 0.3976, | |
| "eval_samples_per_second": 5.03, | |
| "eval_steps_per_second": 2.515, | |
| "eval_wer": 1.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 68.1357650756836, | |
| "eval_runtime": 0.4117, | |
| "eval_samples_per_second": 4.858, | |
| "eval_steps_per_second": 2.429, | |
| "eval_wer": 1.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 68.1357650756836, | |
| "eval_runtime": 0.4341, | |
| "eval_samples_per_second": 4.607, | |
| "eval_steps_per_second": 2.304, | |
| "eval_wer": 1.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 68.02447509765625, | |
| "eval_runtime": 0.4095, | |
| "eval_samples_per_second": 4.884, | |
| "eval_steps_per_second": 2.442, | |
| "eval_wer": 1.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 67.78739166259766, | |
| "eval_runtime": 0.4118, | |
| "eval_samples_per_second": 4.857, | |
| "eval_steps_per_second": 2.428, | |
| "eval_wer": 1.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 67.45346069335938, | |
| "eval_runtime": 0.4145, | |
| "eval_samples_per_second": 4.825, | |
| "eval_steps_per_second": 2.413, | |
| "eval_wer": 1.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 67.01423645019531, | |
| "eval_runtime": 0.4121, | |
| "eval_samples_per_second": 4.853, | |
| "eval_steps_per_second": 2.427, | |
| "eval_wer": 1.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 67.01423645019531, | |
| "eval_runtime": 0.4095, | |
| "eval_samples_per_second": 4.884, | |
| "eval_steps_per_second": 2.442, | |
| "eval_wer": 1.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 66.4334716796875, | |
| "eval_runtime": 0.4143, | |
| "eval_samples_per_second": 4.828, | |
| "eval_steps_per_second": 2.414, | |
| "eval_wer": 1.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7e-05, | |
| "loss": 38.4011, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 65.70997619628906, | |
| "eval_runtime": 0.4061, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 2.463, | |
| "eval_wer": 1.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 64.820556640625, | |
| "eval_runtime": 0.4105, | |
| "eval_samples_per_second": 4.872, | |
| "eval_steps_per_second": 2.436, | |
| "eval_wer": 1.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 63.82392120361328, | |
| "eval_runtime": 0.4177, | |
| "eval_samples_per_second": 4.788, | |
| "eval_steps_per_second": 2.394, | |
| "eval_wer": 1.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 62.648887634277344, | |
| "eval_runtime": 0.41, | |
| "eval_samples_per_second": 4.878, | |
| "eval_steps_per_second": 2.439, | |
| "eval_wer": 1.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 61.307098388671875, | |
| "eval_runtime": 0.4232, | |
| "eval_samples_per_second": 4.726, | |
| "eval_steps_per_second": 2.363, | |
| "eval_wer": 1.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 59.74273681640625, | |
| "eval_runtime": 0.4053, | |
| "eval_samples_per_second": 4.934, | |
| "eval_steps_per_second": 2.467, | |
| "eval_wer": 1.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 58.02557373046875, | |
| "eval_runtime": 0.4173, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 2.397, | |
| "eval_wer": 0.98, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 56.03272247314453, | |
| "eval_runtime": 0.4178, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 2.394, | |
| "eval_wer": 1.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 53.77244567871094, | |
| "eval_runtime": 0.4131, | |
| "eval_samples_per_second": 4.841, | |
| "eval_steps_per_second": 2.421, | |
| "eval_wer": 1.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 51.255592346191406, | |
| "eval_runtime": 0.4212, | |
| "eval_samples_per_second": 4.748, | |
| "eval_steps_per_second": 2.374, | |
| "eval_wer": 1.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.00016999999999999999, | |
| "loss": 33.2554, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 48.49556350708008, | |
| "eval_runtime": 0.4219, | |
| "eval_samples_per_second": 4.741, | |
| "eval_steps_per_second": 2.37, | |
| "eval_wer": 1.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 45.40376281738281, | |
| "eval_runtime": 0.4164, | |
| "eval_samples_per_second": 4.803, | |
| "eval_steps_per_second": 2.401, | |
| "eval_wer": 1.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 41.99801254272461, | |
| "eval_runtime": 0.4115, | |
| "eval_samples_per_second": 4.86, | |
| "eval_steps_per_second": 2.43, | |
| "eval_wer": 1.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 41.99801254272461, | |
| "eval_runtime": 0.4148, | |
| "eval_samples_per_second": 4.822, | |
| "eval_steps_per_second": 2.411, | |
| "eval_wer": 1.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 38.22810745239258, | |
| "eval_runtime": 0.4152, | |
| "eval_samples_per_second": 4.817, | |
| "eval_steps_per_second": 2.409, | |
| "eval_wer": 1.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 34.15771484375, | |
| "eval_runtime": 0.4229, | |
| "eval_samples_per_second": 4.73, | |
| "eval_steps_per_second": 2.365, | |
| "eval_wer": 1.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 29.798538208007812, | |
| "eval_runtime": 0.4129, | |
| "eval_samples_per_second": 4.843, | |
| "eval_steps_per_second": 2.422, | |
| "eval_wer": 1.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 25.11461067199707, | |
| "eval_runtime": 0.441, | |
| "eval_samples_per_second": 4.535, | |
| "eval_steps_per_second": 2.268, | |
| "eval_wer": 1.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 20.228670120239258, | |
| "eval_runtime": 0.4246, | |
| "eval_samples_per_second": 4.71, | |
| "eval_steps_per_second": 2.355, | |
| "eval_wer": 1.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 15.340555191040039, | |
| "eval_runtime": 0.4159, | |
| "eval_samples_per_second": 4.809, | |
| "eval_steps_per_second": 2.405, | |
| "eval_wer": 1.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.00026, | |
| "loss": 15.1206, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 10.769251823425293, | |
| "eval_runtime": 0.4274, | |
| "eval_samples_per_second": 4.68, | |
| "eval_steps_per_second": 2.34, | |
| "eval_wer": 1.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_loss": 6.8997721672058105, | |
| "eval_runtime": 0.4239, | |
| "eval_samples_per_second": 4.718, | |
| "eval_steps_per_second": 2.359, | |
| "eval_wer": 1.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_loss": 4.590747356414795, | |
| "eval_runtime": 0.423, | |
| "eval_samples_per_second": 4.728, | |
| "eval_steps_per_second": 2.364, | |
| "eval_wer": 1.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_loss": 3.359570026397705, | |
| "eval_runtime": 0.4292, | |
| "eval_samples_per_second": 4.66, | |
| "eval_steps_per_second": 2.33, | |
| "eval_wer": 1.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_loss": 2.7710704803466797, | |
| "eval_runtime": 0.4158, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 2.405, | |
| "eval_wer": 1.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_loss": 2.5961642265319824, | |
| "eval_runtime": 0.4262, | |
| "eval_samples_per_second": 4.692, | |
| "eval_steps_per_second": 2.346, | |
| "eval_wer": 1.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_loss": 2.900197982788086, | |
| "eval_runtime": 0.4192, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 2.386, | |
| "eval_wer": 1.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_loss": 3.0060811042785645, | |
| "eval_runtime": 0.4182, | |
| "eval_samples_per_second": 4.783, | |
| "eval_steps_per_second": 2.391, | |
| "eval_wer": 1.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_loss": 2.817464828491211, | |
| "eval_runtime": 0.4241, | |
| "eval_samples_per_second": 4.716, | |
| "eval_steps_per_second": 2.358, | |
| "eval_wer": 1.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_loss": 2.4512133598327637, | |
| "eval_runtime": 0.4212, | |
| "eval_samples_per_second": 4.748, | |
| "eval_steps_per_second": 2.374, | |
| "eval_wer": 1.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 0.00027428571428571427, | |
| "loss": 2.4298, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_loss": 2.332979202270508, | |
| "eval_runtime": 0.4231, | |
| "eval_samples_per_second": 4.727, | |
| "eval_steps_per_second": 2.363, | |
| "eval_wer": 1.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_loss": 2.3766188621520996, | |
| "eval_runtime": 0.4235, | |
| "eval_samples_per_second": 4.723, | |
| "eval_steps_per_second": 2.361, | |
| "eval_wer": 1.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_loss": 2.5625646114349365, | |
| "eval_runtime": 0.4219, | |
| "eval_samples_per_second": 4.741, | |
| "eval_steps_per_second": 2.37, | |
| "eval_wer": 1.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_loss": 2.9632387161254883, | |
| "eval_runtime": 0.4235, | |
| "eval_samples_per_second": 4.722, | |
| "eval_steps_per_second": 2.361, | |
| "eval_wer": 1.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_loss": 3.279555082321167, | |
| "eval_runtime": 0.4175, | |
| "eval_samples_per_second": 4.79, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 1.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_loss": 3.4015283584594727, | |
| "eval_runtime": 0.4178, | |
| "eval_samples_per_second": 4.787, | |
| "eval_steps_per_second": 2.393, | |
| "eval_wer": 1.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_loss": 3.2808432579040527, | |
| "eval_runtime": 0.4209, | |
| "eval_samples_per_second": 4.752, | |
| "eval_steps_per_second": 2.376, | |
| "eval_wer": 1.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_loss": 3.2373273372650146, | |
| "eval_runtime": 0.4225, | |
| "eval_samples_per_second": 4.734, | |
| "eval_steps_per_second": 2.367, | |
| "eval_wer": 1.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_loss": 3.2461540699005127, | |
| "eval_runtime": 0.4121, | |
| "eval_samples_per_second": 4.853, | |
| "eval_steps_per_second": 2.427, | |
| "eval_wer": 1.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_loss": 3.6168460845947266, | |
| "eval_runtime": 0.436, | |
| "eval_samples_per_second": 4.587, | |
| "eval_steps_per_second": 2.293, | |
| "eval_wer": 1.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.00023142857142857142, | |
| "loss": 1.6143, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_loss": 3.6624670028686523, | |
| "eval_runtime": 0.4363, | |
| "eval_samples_per_second": 4.584, | |
| "eval_steps_per_second": 2.292, | |
| "eval_wer": 1.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_loss": 3.759349822998047, | |
| "eval_runtime": 0.4284, | |
| "eval_samples_per_second": 4.668, | |
| "eval_steps_per_second": 2.334, | |
| "eval_wer": 1.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_loss": 3.9326891899108887, | |
| "eval_runtime": 0.4199, | |
| "eval_samples_per_second": 4.763, | |
| "eval_steps_per_second": 2.382, | |
| "eval_wer": 1.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_loss": 3.718548536300659, | |
| "eval_runtime": 0.4129, | |
| "eval_samples_per_second": 4.843, | |
| "eval_steps_per_second": 2.422, | |
| "eval_wer": 1.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_loss": 3.90997052192688, | |
| "eval_runtime": 0.4206, | |
| "eval_samples_per_second": 4.755, | |
| "eval_steps_per_second": 2.377, | |
| "eval_wer": 1.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_loss": 4.312277317047119, | |
| "eval_runtime": 0.4164, | |
| "eval_samples_per_second": 4.803, | |
| "eval_steps_per_second": 2.401, | |
| "eval_wer": 1.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_loss": 4.2904229164123535, | |
| "eval_runtime": 0.4192, | |
| "eval_samples_per_second": 4.771, | |
| "eval_steps_per_second": 2.386, | |
| "eval_wer": 1.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_loss": 3.951892852783203, | |
| "eval_runtime": 0.4198, | |
| "eval_samples_per_second": 4.765, | |
| "eval_steps_per_second": 2.382, | |
| "eval_wer": 1.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_loss": 3.45182728767395, | |
| "eval_runtime": 0.4295, | |
| "eval_samples_per_second": 4.657, | |
| "eval_steps_per_second": 2.328, | |
| "eval_wer": 1.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_loss": 3.0196707248687744, | |
| "eval_runtime": 0.4211, | |
| "eval_samples_per_second": 4.75, | |
| "eval_steps_per_second": 2.375, | |
| "eval_wer": 1.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 0.00018857142857142854, | |
| "loss": 1.4054, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_loss": 2.886315107345581, | |
| "eval_runtime": 0.4413, | |
| "eval_samples_per_second": 4.533, | |
| "eval_steps_per_second": 2.266, | |
| "eval_wer": 1.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 2.97536563873291, | |
| "eval_runtime": 0.4417, | |
| "eval_samples_per_second": 4.528, | |
| "eval_steps_per_second": 2.264, | |
| "eval_wer": 1.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 3.299807548522949, | |
| "eval_runtime": 0.426, | |
| "eval_samples_per_second": 4.695, | |
| "eval_steps_per_second": 2.347, | |
| "eval_wer": 1.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 3.871462821960449, | |
| "eval_runtime": 0.4236, | |
| "eval_samples_per_second": 4.721, | |
| "eval_steps_per_second": 2.36, | |
| "eval_wer": 1.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 4.189750671386719, | |
| "eval_runtime": 0.4223, | |
| "eval_samples_per_second": 4.736, | |
| "eval_steps_per_second": 2.368, | |
| "eval_wer": 1.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 4.18125057220459, | |
| "eval_runtime": 0.4138, | |
| "eval_samples_per_second": 4.833, | |
| "eval_steps_per_second": 2.417, | |
| "eval_wer": 1.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 3.9024930000305176, | |
| "eval_runtime": 0.4391, | |
| "eval_samples_per_second": 4.555, | |
| "eval_steps_per_second": 2.277, | |
| "eval_wer": 1.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 3.4319417476654053, | |
| "eval_runtime": 0.4273, | |
| "eval_samples_per_second": 4.681, | |
| "eval_steps_per_second": 2.34, | |
| "eval_wer": 1.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 3.275496482849121, | |
| "eval_runtime": 0.4173, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 2.396, | |
| "eval_wer": 1.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 3.334933042526245, | |
| "eval_runtime": 0.4221, | |
| "eval_samples_per_second": 4.738, | |
| "eval_steps_per_second": 2.369, | |
| "eval_wer": 1.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 0.0001457142857142857, | |
| "loss": 1.3121, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 3.548488140106201, | |
| "eval_runtime": 0.4291, | |
| "eval_samples_per_second": 4.661, | |
| "eval_steps_per_second": 2.331, | |
| "eval_wer": 1.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 3.9019012451171875, | |
| "eval_runtime": 0.4171, | |
| "eval_samples_per_second": 4.795, | |
| "eval_steps_per_second": 2.398, | |
| "eval_wer": 1.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 4.081923961639404, | |
| "eval_runtime": 0.4176, | |
| "eval_samples_per_second": 4.789, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 1.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 3.9955055713653564, | |
| "eval_runtime": 0.4176, | |
| "eval_samples_per_second": 4.789, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 1.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 3.70878529548645, | |
| "eval_runtime": 0.423, | |
| "eval_samples_per_second": 4.729, | |
| "eval_steps_per_second": 2.364, | |
| "eval_wer": 1.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 3.295703887939453, | |
| "eval_runtime": 0.4128, | |
| "eval_samples_per_second": 4.846, | |
| "eval_steps_per_second": 2.423, | |
| "eval_wer": 1.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 3.114126682281494, | |
| "eval_runtime": 0.4146, | |
| "eval_samples_per_second": 4.824, | |
| "eval_steps_per_second": 2.412, | |
| "eval_wer": 1.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 3.085181713104248, | |
| "eval_runtime": 0.4266, | |
| "eval_samples_per_second": 4.688, | |
| "eval_steps_per_second": 2.344, | |
| "eval_wer": 1.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 3.187084436416626, | |
| "eval_runtime": 0.4233, | |
| "eval_samples_per_second": 4.725, | |
| "eval_steps_per_second": 2.362, | |
| "eval_wer": 1.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 3.4126548767089844, | |
| "eval_runtime": 0.406, | |
| "eval_samples_per_second": 4.926, | |
| "eval_steps_per_second": 2.463, | |
| "eval_wer": 1.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 0.00010285714285714284, | |
| "loss": 1.2576, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 3.6913061141967773, | |
| "eval_runtime": 0.4088, | |
| "eval_samples_per_second": 4.892, | |
| "eval_steps_per_second": 2.446, | |
| "eval_wer": 1.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 3.8285651206970215, | |
| "eval_runtime": 0.4079, | |
| "eval_samples_per_second": 4.904, | |
| "eval_steps_per_second": 2.452, | |
| "eval_wer": 1.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 3.815654993057251, | |
| "eval_runtime": 0.4087, | |
| "eval_samples_per_second": 4.894, | |
| "eval_steps_per_second": 2.447, | |
| "eval_wer": 1.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 3.6813836097717285, | |
| "eval_runtime": 0.4035, | |
| "eval_samples_per_second": 4.957, | |
| "eval_steps_per_second": 2.478, | |
| "eval_wer": 1.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 3.44958758354187, | |
| "eval_runtime": 0.4079, | |
| "eval_samples_per_second": 4.903, | |
| "eval_steps_per_second": 2.452, | |
| "eval_wer": 1.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 3.284428119659424, | |
| "eval_runtime": 0.4066, | |
| "eval_samples_per_second": 4.919, | |
| "eval_steps_per_second": 2.46, | |
| "eval_wer": 1.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 3.2253918647766113, | |
| "eval_runtime": 0.405, | |
| "eval_samples_per_second": 4.938, | |
| "eval_steps_per_second": 2.469, | |
| "eval_wer": 1.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 3.268294334411621, | |
| "eval_runtime": 0.4089, | |
| "eval_samples_per_second": 4.892, | |
| "eval_steps_per_second": 2.446, | |
| "eval_wer": 1.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 3.3791449069976807, | |
| "eval_runtime": 0.4084, | |
| "eval_samples_per_second": 4.897, | |
| "eval_steps_per_second": 2.449, | |
| "eval_wer": 1.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 3.550123453140259, | |
| "eval_runtime": 0.4056, | |
| "eval_samples_per_second": 4.931, | |
| "eval_steps_per_second": 2.466, | |
| "eval_wer": 1.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.2373, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 3.662168025970459, | |
| "eval_runtime": 0.4176, | |
| "eval_samples_per_second": 4.789, | |
| "eval_steps_per_second": 2.395, | |
| "eval_wer": 1.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_loss": 3.7207443714141846, | |
| "eval_runtime": 0.4173, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 2.396, | |
| "eval_wer": 1.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_loss": 3.6961331367492676, | |
| "eval_runtime": 0.4129, | |
| "eval_samples_per_second": 4.844, | |
| "eval_steps_per_second": 2.422, | |
| "eval_wer": 1.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_loss": 3.6098761558532715, | |
| "eval_runtime": 0.4061, | |
| "eval_samples_per_second": 4.925, | |
| "eval_steps_per_second": 2.463, | |
| "eval_wer": 1.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_loss": 3.533604860305786, | |
| "eval_runtime": 0.4224, | |
| "eval_samples_per_second": 4.735, | |
| "eval_steps_per_second": 2.368, | |
| "eval_wer": 1.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_loss": 3.4341912269592285, | |
| "eval_runtime": 0.4255, | |
| "eval_samples_per_second": 4.701, | |
| "eval_steps_per_second": 2.35, | |
| "eval_wer": 1.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_loss": 3.316969871520996, | |
| "eval_runtime": 0.4089, | |
| "eval_samples_per_second": 4.891, | |
| "eval_steps_per_second": 2.445, | |
| "eval_wer": 1.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_loss": 3.2624034881591797, | |
| "eval_runtime": 0.4046, | |
| "eval_samples_per_second": 4.943, | |
| "eval_steps_per_second": 2.471, | |
| "eval_wer": 1.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_loss": 3.2437386512756348, | |
| "eval_runtime": 0.4006, | |
| "eval_samples_per_second": 4.993, | |
| "eval_steps_per_second": 2.497, | |
| "eval_wer": 1.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_loss": 3.259126663208008, | |
| "eval_runtime": 0.4066, | |
| "eval_samples_per_second": 4.919, | |
| "eval_steps_per_second": 2.46, | |
| "eval_wer": 1.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 1.1952, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_loss": 3.292677402496338, | |
| "eval_runtime": 0.4167, | |
| "eval_samples_per_second": 4.799, | |
| "eval_steps_per_second": 2.4, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "step": 100, | |
| "total_flos": 2.094330789153408e+17, | |
| "train_loss": 9.722876396179199, | |
| "train_runtime": 860.4357, | |
| "train_samples_per_second": 1.86, | |
| "train_steps_per_second": 0.116 | |
| } | |
| ], | |
| "max_steps": 100, | |
| "num_train_epochs": 100, | |
| "total_flos": 2.094330789153408e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |