| { | |
| "best_global_step": 41000, | |
| "best_metric": 0.359779867002981, | |
| "best_model_checkpoint": "/home/cluster-dgxa100/slp01/bagas-fine-tune-whisper/whisper-tiny-javanese-openslr-v6/checkpoint-41000", | |
| "epoch": 159.7456, | |
| "eval_steps": 1000, | |
| "global_step": 50000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 25.32911491394043, | |
| "learning_rate": 7.88e-07, | |
| "loss": 3.6275, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2784, | |
| "grad_norm": 20.188899993896484, | |
| "learning_rate": 1.588e-06, | |
| "loss": 2.0941, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.9184, | |
| "grad_norm": 20.781444549560547, | |
| "learning_rate": 2.3880000000000003e-06, | |
| "loss": 1.6316, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.5568, | |
| "grad_norm": 18.28050994873047, | |
| "learning_rate": 3.188e-06, | |
| "loss": 1.3303, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.1952, | |
| "grad_norm": 19.185575485229492, | |
| "learning_rate": 3.988000000000001e-06, | |
| "loss": 1.1166, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.1952, | |
| "eval_loss": 1.0200245380401611, | |
| "eval_runtime": 143.6337, | |
| "eval_samples_per_second": 4.351, | |
| "eval_steps_per_second": 1.093, | |
| "eval_wer": 0.6975464343040587, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.8352, | |
| "grad_norm": 16.41274070739746, | |
| "learning_rate": 4.7880000000000006e-06, | |
| "loss": 0.9805, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 4.4736, | |
| "grad_norm": 14.031892776489258, | |
| "learning_rate": 5.588e-06, | |
| "loss": 0.8521, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 5.112, | |
| "grad_norm": 14.105754852294922, | |
| "learning_rate": 6.3880000000000005e-06, | |
| "loss": 0.7633, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 5.752, | |
| "grad_norm": 13.716428756713867, | |
| "learning_rate": 7.1880000000000005e-06, | |
| "loss": 0.6676, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 6.3904, | |
| "grad_norm": 12.681669235229492, | |
| "learning_rate": 7.988e-06, | |
| "loss": 0.5644, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 6.3904, | |
| "eval_loss": 0.7341693043708801, | |
| "eval_runtime": 113.3954, | |
| "eval_samples_per_second": 5.512, | |
| "eval_steps_per_second": 1.385, | |
| "eval_wer": 0.5897729878468241, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0288, | |
| "grad_norm": 12.7446928024292, | |
| "learning_rate": 8.788000000000001e-06, | |
| "loss": 0.5326, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 7.6688, | |
| "grad_norm": 12.206501007080078, | |
| "learning_rate": 9.588e-06, | |
| "loss": 0.4346, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 8.3072, | |
| "grad_norm": 9.13988208770752, | |
| "learning_rate": 1.0388e-05, | |
| "loss": 0.3967, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 8.9472, | |
| "grad_norm": 12.071162223815918, | |
| "learning_rate": 1.1188e-05, | |
| "loss": 0.3532, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 9.5856, | |
| "grad_norm": 8.742654800415039, | |
| "learning_rate": 1.1988000000000001e-05, | |
| "loss": 0.2837, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 9.5856, | |
| "eval_loss": 0.666342556476593, | |
| "eval_runtime": 133.4076, | |
| "eval_samples_per_second": 4.685, | |
| "eval_steps_per_second": 1.177, | |
| "eval_wer": 0.5700527401972024, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.224, | |
| "grad_norm": 10.311443328857422, | |
| "learning_rate": 1.2788e-05, | |
| "loss": 0.2601, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 10.864, | |
| "grad_norm": 10.367297172546387, | |
| "learning_rate": 1.3588000000000001e-05, | |
| "loss": 0.227, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 11.5024, | |
| "grad_norm": 10.210521697998047, | |
| "learning_rate": 1.4388000000000002e-05, | |
| "loss": 0.1883, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 12.1408, | |
| "grad_norm": 9.120365142822266, | |
| "learning_rate": 1.5188000000000001e-05, | |
| "loss": 0.1716, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 12.7808, | |
| "grad_norm": 8.728864669799805, | |
| "learning_rate": 1.5988e-05, | |
| "loss": 0.1451, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 12.7808, | |
| "eval_loss": 0.669156551361084, | |
| "eval_runtime": 111.1099, | |
| "eval_samples_per_second": 5.625, | |
| "eval_steps_per_second": 1.413, | |
| "eval_wer": 0.615684476037606, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.4192, | |
| "grad_norm": 8.055611610412598, | |
| "learning_rate": 1.6788000000000003e-05, | |
| "loss": 0.1277, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 14.0576, | |
| "grad_norm": 10.252028465270996, | |
| "learning_rate": 1.7588e-05, | |
| "loss": 0.1231, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 14.6976, | |
| "grad_norm": 8.062397956848145, | |
| "learning_rate": 1.8388e-05, | |
| "loss": 0.1015, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 15.336, | |
| "grad_norm": 5.604861736297607, | |
| "learning_rate": 1.9188000000000003e-05, | |
| "loss": 0.0966, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 15.975999999999999, | |
| "grad_norm": 5.753713130950928, | |
| "learning_rate": 1.9988000000000002e-05, | |
| "loss": 0.0949, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 15.975999999999999, | |
| "eval_loss": 0.6928630471229553, | |
| "eval_runtime": 104.9987, | |
| "eval_samples_per_second": 5.952, | |
| "eval_steps_per_second": 1.495, | |
| "eval_wer": 0.6140793396010089, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 16.6144, | |
| "grad_norm": 7.435614109039307, | |
| "learning_rate": 1.991288888888889e-05, | |
| "loss": 0.0763, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 17.2528, | |
| "grad_norm": 5.643408298492432, | |
| "learning_rate": 1.9824000000000002e-05, | |
| "loss": 0.0767, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 17.8928, | |
| "grad_norm": 6.685403823852539, | |
| "learning_rate": 1.9735111111111112e-05, | |
| "loss": 0.0695, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 18.5312, | |
| "grad_norm": 5.571532249450684, | |
| "learning_rate": 1.9646222222222223e-05, | |
| "loss": 0.0649, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 19.1696, | |
| "grad_norm": 5.548845291137695, | |
| "learning_rate": 1.9557333333333333e-05, | |
| "loss": 0.0621, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 19.1696, | |
| "eval_loss": 0.7081567049026489, | |
| "eval_runtime": 106.1316, | |
| "eval_samples_per_second": 5.889, | |
| "eval_steps_per_second": 1.479, | |
| "eval_wer": 0.4790185737216235, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 19.8096, | |
| "grad_norm": 5.352997779846191, | |
| "learning_rate": 1.9468444444444444e-05, | |
| "loss": 0.0578, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 20.448, | |
| "grad_norm": 4.763257026672363, | |
| "learning_rate": 1.9379555555555558e-05, | |
| "loss": 0.0521, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 21.0864, | |
| "grad_norm": 2.98003888130188, | |
| "learning_rate": 1.9290666666666668e-05, | |
| "loss": 0.0527, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 21.7264, | |
| "grad_norm": 12.276226043701172, | |
| "learning_rate": 1.920177777777778e-05, | |
| "loss": 0.0456, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 22.3648, | |
| "grad_norm": 4.935642719268799, | |
| "learning_rate": 1.911288888888889e-05, | |
| "loss": 0.0466, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 22.3648, | |
| "eval_loss": 0.7455945611000061, | |
| "eval_runtime": 105.1482, | |
| "eval_samples_per_second": 5.944, | |
| "eval_steps_per_second": 1.493, | |
| "eval_wer": 0.4469158449896813, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 23.0032, | |
| "grad_norm": 4.248728275299072, | |
| "learning_rate": 1.9024000000000003e-05, | |
| "loss": 0.0449, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 23.6432, | |
| "grad_norm": 6.321920394897461, | |
| "learning_rate": 1.8935111111111113e-05, | |
| "loss": 0.0388, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 24.2816, | |
| "grad_norm": 4.33453893661499, | |
| "learning_rate": 1.8846222222222224e-05, | |
| "loss": 0.0412, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 24.9216, | |
| "grad_norm": 8.20227336883545, | |
| "learning_rate": 1.8757333333333334e-05, | |
| "loss": 0.0386, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "grad_norm": 4.103025913238525, | |
| "learning_rate": 1.8668444444444448e-05, | |
| "loss": 0.0338, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "eval_loss": 0.760087251663208, | |
| "eval_runtime": 103.2404, | |
| "eval_samples_per_second": 6.054, | |
| "eval_steps_per_second": 1.521, | |
| "eval_wer": 0.43659711075441415, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 26.1984, | |
| "grad_norm": 3.744155168533325, | |
| "learning_rate": 1.858e-05, | |
| "loss": 0.0356, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 26.8384, | |
| "grad_norm": 3.403186082839966, | |
| "learning_rate": 1.8491111111111112e-05, | |
| "loss": 0.0334, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 27.4768, | |
| "grad_norm": 4.127572536468506, | |
| "learning_rate": 1.8402222222222223e-05, | |
| "loss": 0.0327, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 28.1152, | |
| "grad_norm": 4.966237545013428, | |
| "learning_rate": 1.8313333333333333e-05, | |
| "loss": 0.0309, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 28.7552, | |
| "grad_norm": 6.874843120574951, | |
| "learning_rate": 1.8224444444444447e-05, | |
| "loss": 0.0288, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 28.7552, | |
| "eval_loss": 0.7782142758369446, | |
| "eval_runtime": 101.996, | |
| "eval_samples_per_second": 6.128, | |
| "eval_steps_per_second": 1.539, | |
| "eval_wer": 0.3893602384774134, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 29.3936, | |
| "grad_norm": 2.1933653354644775, | |
| "learning_rate": 1.8135555555555557e-05, | |
| "loss": 0.0275, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 30.032, | |
| "grad_norm": 2.639747381210327, | |
| "learning_rate": 1.8046666666666668e-05, | |
| "loss": 0.027, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 30.672, | |
| "grad_norm": 2.232715368270874, | |
| "learning_rate": 1.7957777777777778e-05, | |
| "loss": 0.0248, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 31.3104, | |
| "grad_norm": 1.4926921129226685, | |
| "learning_rate": 1.7868888888888892e-05, | |
| "loss": 0.0266, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 31.9504, | |
| "grad_norm": 2.4175844192504883, | |
| "learning_rate": 1.7780000000000003e-05, | |
| "loss": 0.0232, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 31.9504, | |
| "eval_loss": 0.79770827293396, | |
| "eval_runtime": 104.7759, | |
| "eval_samples_per_second": 5.965, | |
| "eval_steps_per_second": 1.498, | |
| "eval_wer": 0.41068562256363217, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 32.5888, | |
| "grad_norm": 1.8864479064941406, | |
| "learning_rate": 1.7691111111111113e-05, | |
| "loss": 0.0218, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 33.2272, | |
| "grad_norm": 8.317153930664062, | |
| "learning_rate": 1.7602222222222223e-05, | |
| "loss": 0.0239, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 33.8672, | |
| "grad_norm": 4.491159439086914, | |
| "learning_rate": 1.7513333333333334e-05, | |
| "loss": 0.023, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 34.5056, | |
| "grad_norm": 2.753185272216797, | |
| "learning_rate": 1.7424444444444444e-05, | |
| "loss": 0.0202, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 35.144, | |
| "grad_norm": 2.579869270324707, | |
| "learning_rate": 1.7335555555555558e-05, | |
| "loss": 0.0212, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 35.144, | |
| "eval_loss": 0.797561764717102, | |
| "eval_runtime": 106.2768, | |
| "eval_samples_per_second": 5.881, | |
| "eval_steps_per_second": 1.477, | |
| "eval_wer": 0.41435450584728273, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 35.784, | |
| "grad_norm": 2.2582919597625732, | |
| "learning_rate": 1.724666666666667e-05, | |
| "loss": 0.0193, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 36.4224, | |
| "grad_norm": 2.982079029083252, | |
| "learning_rate": 1.715777777777778e-05, | |
| "loss": 0.0207, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 37.0608, | |
| "grad_norm": 3.09155011177063, | |
| "learning_rate": 1.706888888888889e-05, | |
| "loss": 0.0176, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 37.7008, | |
| "grad_norm": 3.805440902709961, | |
| "learning_rate": 1.6980444444444447e-05, | |
| "loss": 0.0177, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 38.3392, | |
| "grad_norm": 2.447655439376831, | |
| "learning_rate": 1.6891555555555557e-05, | |
| "loss": 0.0178, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 38.3392, | |
| "eval_loss": 0.8184047341346741, | |
| "eval_runtime": 140.2428, | |
| "eval_samples_per_second": 4.457, | |
| "eval_steps_per_second": 1.119, | |
| "eval_wer": 0.4010548039440495, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 38.9792, | |
| "grad_norm": 6.444581031799316, | |
| "learning_rate": 1.6802666666666668e-05, | |
| "loss": 0.018, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 39.6176, | |
| "grad_norm": 1.9832179546356201, | |
| "learning_rate": 1.671377777777778e-05, | |
| "loss": 0.0185, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 40.256, | |
| "grad_norm": 1.374569058418274, | |
| "learning_rate": 1.6624888888888892e-05, | |
| "loss": 0.0159, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 40.896, | |
| "grad_norm": 4.2071309089660645, | |
| "learning_rate": 1.6536000000000002e-05, | |
| "loss": 0.0138, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 41.5344, | |
| "grad_norm": 2.3069539070129395, | |
| "learning_rate": 1.6447111111111113e-05, | |
| "loss": 0.0132, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 41.5344, | |
| "eval_loss": 0.8310635089874268, | |
| "eval_runtime": 138.029, | |
| "eval_samples_per_second": 4.528, | |
| "eval_steps_per_second": 1.137, | |
| "eval_wer": 0.3762898417794084, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 42.1728, | |
| "grad_norm": 1.6480227708816528, | |
| "learning_rate": 1.6358222222222223e-05, | |
| "loss": 0.016, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 42.8128, | |
| "grad_norm": 4.483267784118652, | |
| "learning_rate": 1.6269333333333334e-05, | |
| "loss": 0.0145, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 43.4512, | |
| "grad_norm": 1.1435110569000244, | |
| "learning_rate": 1.6180444444444444e-05, | |
| "loss": 0.0129, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 44.0896, | |
| "grad_norm": 0.6056487560272217, | |
| "learning_rate": 1.6091555555555555e-05, | |
| "loss": 0.015, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 44.7296, | |
| "grad_norm": 7.710687160491943, | |
| "learning_rate": 1.600266666666667e-05, | |
| "loss": 0.0145, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 44.7296, | |
| "eval_loss": 0.8473762273788452, | |
| "eval_runtime": 109.9727, | |
| "eval_samples_per_second": 5.683, | |
| "eval_steps_per_second": 1.428, | |
| "eval_wer": 0.3790415042421463, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 45.368, | |
| "grad_norm": 0.3126671314239502, | |
| "learning_rate": 1.591377777777778e-05, | |
| "loss": 0.0151, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 46.0064, | |
| "grad_norm": 1.5604488849639893, | |
| "learning_rate": 1.582488888888889e-05, | |
| "loss": 0.0126, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 46.6464, | |
| "grad_norm": 1.0523457527160645, | |
| "learning_rate": 1.5736000000000003e-05, | |
| "loss": 0.0124, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 47.2848, | |
| "grad_norm": 2.6398849487304688, | |
| "learning_rate": 1.5647111111111114e-05, | |
| "loss": 0.013, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 47.9248, | |
| "grad_norm": 1.1916667222976685, | |
| "learning_rate": 1.5558222222222224e-05, | |
| "loss": 0.0117, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 47.9248, | |
| "eval_loss": 0.8624815940856934, | |
| "eval_runtime": 105.5676, | |
| "eval_samples_per_second": 5.92, | |
| "eval_steps_per_second": 1.487, | |
| "eval_wer": 0.4155010318734235, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 48.5632, | |
| "grad_norm": 1.593981146812439, | |
| "learning_rate": 1.5469333333333335e-05, | |
| "loss": 0.0115, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 49.2016, | |
| "grad_norm": 2.9825565814971924, | |
| "learning_rate": 1.538044444444445e-05, | |
| "loss": 0.0111, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 49.8416, | |
| "grad_norm": 1.278347134590149, | |
| "learning_rate": 1.529155555555556e-05, | |
| "loss": 0.0109, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 50.48, | |
| "grad_norm": 1.986265778541565, | |
| "learning_rate": 1.5202666666666668e-05, | |
| "loss": 0.0115, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 51.1184, | |
| "grad_norm": 0.23057551681995392, | |
| "learning_rate": 1.5114222222222223e-05, | |
| "loss": 0.0101, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 51.1184, | |
| "eval_loss": 0.8906803727149963, | |
| "eval_runtime": 106.8162, | |
| "eval_samples_per_second": 5.851, | |
| "eval_steps_per_second": 1.47, | |
| "eval_wer": 0.3758312313689521, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 51.7584, | |
| "grad_norm": 2.8394742012023926, | |
| "learning_rate": 1.5025333333333333e-05, | |
| "loss": 0.01, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 52.3968, | |
| "grad_norm": 3.907292366027832, | |
| "learning_rate": 1.4936444444444447e-05, | |
| "loss": 0.0101, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 53.0352, | |
| "grad_norm": 0.3342689871788025, | |
| "learning_rate": 1.4847555555555558e-05, | |
| "loss": 0.0106, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 53.6752, | |
| "grad_norm": 14.257401466369629, | |
| "learning_rate": 1.4758666666666668e-05, | |
| "loss": 0.0096, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 54.3136, | |
| "grad_norm": 4.482171535491943, | |
| "learning_rate": 1.4669777777777779e-05, | |
| "loss": 0.0091, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 54.3136, | |
| "eval_loss": 0.8973252773284912, | |
| "eval_runtime": 107.1216, | |
| "eval_samples_per_second": 5.834, | |
| "eval_steps_per_second": 1.466, | |
| "eval_wer": 0.3999082779179087, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 54.9536, | |
| "grad_norm": 0.3064260184764862, | |
| "learning_rate": 1.458088888888889e-05, | |
| "loss": 0.0089, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 55.592, | |
| "grad_norm": 3.7441632747650146, | |
| "learning_rate": 1.4492000000000001e-05, | |
| "loss": 0.01, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 56.2304, | |
| "grad_norm": 2.9929962158203125, | |
| "learning_rate": 1.4403111111111112e-05, | |
| "loss": 0.0099, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 56.8704, | |
| "grad_norm": 3.1295619010925293, | |
| "learning_rate": 1.4314222222222222e-05, | |
| "loss": 0.0083, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 57.5088, | |
| "grad_norm": 3.032670736312866, | |
| "learning_rate": 1.4225777777777779e-05, | |
| "loss": 0.0087, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 57.5088, | |
| "eval_loss": 0.9277347922325134, | |
| "eval_runtime": 108.6583, | |
| "eval_samples_per_second": 5.752, | |
| "eval_steps_per_second": 1.445, | |
| "eval_wer": 0.4182526943361614, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 58.1472, | |
| "grad_norm": 0.5450573563575745, | |
| "learning_rate": 1.4137333333333334e-05, | |
| "loss": 0.0081, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 58.7872, | |
| "grad_norm": 3.2385668754577637, | |
| "learning_rate": 1.4048444444444445e-05, | |
| "loss": 0.008, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 59.4256, | |
| "grad_norm": 2.490182638168335, | |
| "learning_rate": 1.3959555555555557e-05, | |
| "loss": 0.0074, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 60.064, | |
| "grad_norm": 2.916256904602051, | |
| "learning_rate": 1.3870666666666667e-05, | |
| "loss": 0.009, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 60.704, | |
| "grad_norm": 0.9266663789749146, | |
| "learning_rate": 1.3781777777777778e-05, | |
| "loss": 0.0068, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 60.704, | |
| "eval_loss": 0.9448923468589783, | |
| "eval_runtime": 110.101, | |
| "eval_samples_per_second": 5.677, | |
| "eval_steps_per_second": 1.426, | |
| "eval_wer": 0.43889016280669574, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 61.3424, | |
| "grad_norm": 0.37736016511917114, | |
| "learning_rate": 1.3692888888888892e-05, | |
| "loss": 0.0079, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 61.9824, | |
| "grad_norm": 2.7307522296905518, | |
| "learning_rate": 1.3604000000000002e-05, | |
| "loss": 0.008, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 62.6208, | |
| "grad_norm": 0.1229301169514656, | |
| "learning_rate": 1.3515111111111113e-05, | |
| "loss": 0.0065, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 63.2592, | |
| "grad_norm": 0.7501879930496216, | |
| "learning_rate": 1.3426222222222223e-05, | |
| "loss": 0.0074, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 63.8992, | |
| "grad_norm": 0.5861854553222656, | |
| "learning_rate": 1.3337333333333335e-05, | |
| "loss": 0.0073, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 63.8992, | |
| "eval_loss": 0.9372482895851135, | |
| "eval_runtime": 139.4248, | |
| "eval_samples_per_second": 4.483, | |
| "eval_steps_per_second": 1.126, | |
| "eval_wer": 0.3833983031414813, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 64.5376, | |
| "grad_norm": 1.7161897420883179, | |
| "learning_rate": 1.3248444444444446e-05, | |
| "loss": 0.0072, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 65.176, | |
| "grad_norm": 1.3181058168411255, | |
| "learning_rate": 1.3159555555555556e-05, | |
| "loss": 0.0064, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 65.816, | |
| "grad_norm": 0.576824426651001, | |
| "learning_rate": 1.3070666666666667e-05, | |
| "loss": 0.0073, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 66.4544, | |
| "grad_norm": 1.2488709688186646, | |
| "learning_rate": 1.298177777777778e-05, | |
| "loss": 0.0067, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 67.0928, | |
| "grad_norm": 0.8621447682380676, | |
| "learning_rate": 1.2892888888888891e-05, | |
| "loss": 0.0066, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 67.0928, | |
| "eval_loss": 0.9511934518814087, | |
| "eval_runtime": 138.3581, | |
| "eval_samples_per_second": 4.517, | |
| "eval_steps_per_second": 1.135, | |
| "eval_wer": 0.4038064664067874, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 67.7328, | |
| "grad_norm": 2.959468364715576, | |
| "learning_rate": 1.2804000000000001e-05, | |
| "loss": 0.0063, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 68.3712, | |
| "grad_norm": 4.359962463378906, | |
| "learning_rate": 1.2715111111111112e-05, | |
| "loss": 0.0069, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 69.0096, | |
| "grad_norm": 0.8827808499336243, | |
| "learning_rate": 1.2626222222222224e-05, | |
| "loss": 0.0067, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 69.6496, | |
| "grad_norm": 4.478594779968262, | |
| "learning_rate": 1.2537333333333334e-05, | |
| "loss": 0.0063, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 70.288, | |
| "grad_norm": 0.3562716245651245, | |
| "learning_rate": 1.2448444444444445e-05, | |
| "loss": 0.0056, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 70.288, | |
| "eval_loss": 0.9799156188964844, | |
| "eval_runtime": 108.661, | |
| "eval_samples_per_second": 5.752, | |
| "eval_steps_per_second": 1.445, | |
| "eval_wer": 0.4063288236642972, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 70.928, | |
| "grad_norm": 0.21852029860019684, | |
| "learning_rate": 1.2359555555555555e-05, | |
| "loss": 0.0058, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 71.5664, | |
| "grad_norm": 0.7513341307640076, | |
| "learning_rate": 1.227111111111111e-05, | |
| "loss": 0.0051, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 72.2048, | |
| "grad_norm": 1.729013204574585, | |
| "learning_rate": 1.2182222222222225e-05, | |
| "loss": 0.0048, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 72.8448, | |
| "grad_norm": 0.363949179649353, | |
| "learning_rate": 1.2093333333333335e-05, | |
| "loss": 0.0043, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 73.4832, | |
| "grad_norm": 0.09823896735906601, | |
| "learning_rate": 1.2004444444444445e-05, | |
| "loss": 0.0049, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 73.4832, | |
| "eval_loss": 0.9892968535423279, | |
| "eval_runtime": 127.4129, | |
| "eval_samples_per_second": 4.905, | |
| "eval_steps_per_second": 1.232, | |
| "eval_wer": 0.3845448291676221, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 74.1216, | |
| "grad_norm": 0.18766258656978607, | |
| "learning_rate": 1.1915555555555556e-05, | |
| "loss": 0.0061, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 74.7616, | |
| "grad_norm": 2.374441623687744, | |
| "learning_rate": 1.1827111111111111e-05, | |
| "loss": 0.0049, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 75.4, | |
| "grad_norm": 1.901435136795044, | |
| "learning_rate": 1.1738222222222223e-05, | |
| "loss": 0.0042, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 76.0384, | |
| "grad_norm": 1.8781205415725708, | |
| "learning_rate": 1.1649333333333336e-05, | |
| "loss": 0.0066, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 76.6784, | |
| "grad_norm": 4.333975791931152, | |
| "learning_rate": 1.1560444444444446e-05, | |
| "loss": 0.0046, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 76.6784, | |
| "eval_loss": 0.9896656274795532, | |
| "eval_runtime": 128.2479, | |
| "eval_samples_per_second": 4.873, | |
| "eval_steps_per_second": 1.224, | |
| "eval_wer": 0.38087594588397156, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 77.3168, | |
| "grad_norm": 1.9272364377975464, | |
| "learning_rate": 1.1471555555555556e-05, | |
| "loss": 0.0035, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 77.9568, | |
| "grad_norm": 0.6323594450950623, | |
| "learning_rate": 1.1382666666666669e-05, | |
| "loss": 0.0051, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 78.5952, | |
| "grad_norm": 1.1000163555145264, | |
| "learning_rate": 1.1293777777777779e-05, | |
| "loss": 0.0038, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 79.2336, | |
| "grad_norm": 0.48444664478302, | |
| "learning_rate": 1.120488888888889e-05, | |
| "loss": 0.0045, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 79.8736, | |
| "grad_norm": 0.6538843512535095, | |
| "learning_rate": 1.1116e-05, | |
| "loss": 0.0044, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 79.8736, | |
| "eval_loss": 0.9970444440841675, | |
| "eval_runtime": 131.0293, | |
| "eval_samples_per_second": 4.77, | |
| "eval_steps_per_second": 1.198, | |
| "eval_wer": 0.37491401054803947, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 80.512, | |
| "grad_norm": 3.5870893001556396, | |
| "learning_rate": 1.1027111111111112e-05, | |
| "loss": 0.0045, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 81.1504, | |
| "grad_norm": 0.1785198152065277, | |
| "learning_rate": 1.0938222222222223e-05, | |
| "loss": 0.0035, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 81.7904, | |
| "grad_norm": 0.870185375213623, | |
| "learning_rate": 1.0849333333333335e-05, | |
| "loss": 0.0039, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 82.4288, | |
| "grad_norm": 0.21784505248069763, | |
| "learning_rate": 1.0760444444444445e-05, | |
| "loss": 0.0041, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 83.0672, | |
| "grad_norm": 3.4108142852783203, | |
| "learning_rate": 1.0671555555555557e-05, | |
| "loss": 0.0039, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 83.0672, | |
| "eval_loss": 1.011253833770752, | |
| "eval_runtime": 125.5354, | |
| "eval_samples_per_second": 4.979, | |
| "eval_steps_per_second": 1.251, | |
| "eval_wer": 0.37606053657418026, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 83.7072, | |
| "grad_norm": 0.04159156233072281, | |
| "learning_rate": 1.0582666666666668e-05, | |
| "loss": 0.0031, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 84.3456, | |
| "grad_norm": 0.20573270320892334, | |
| "learning_rate": 1.0493777777777778e-05, | |
| "loss": 0.0043, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 84.9856, | |
| "grad_norm": 2.9891881942749023, | |
| "learning_rate": 1.0404888888888889e-05, | |
| "loss": 0.0041, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 85.624, | |
| "grad_norm": 2.5772018432617188, | |
| "learning_rate": 1.0316e-05, | |
| "loss": 0.0039, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 86.2624, | |
| "grad_norm": 0.12921689450740814, | |
| "learning_rate": 1.0227111111111111e-05, | |
| "loss": 0.0035, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 86.2624, | |
| "eval_loss": 1.0148670673370361, | |
| "eval_runtime": 126.4781, | |
| "eval_samples_per_second": 4.942, | |
| "eval_steps_per_second": 1.241, | |
| "eval_wer": 0.38316899793625314, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 86.9024, | |
| "grad_norm": 1.1538918018341064, | |
| "learning_rate": 1.0138222222222223e-05, | |
| "loss": 0.0041, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 87.5408, | |
| "grad_norm": 3.53802490234375, | |
| "learning_rate": 1.0049333333333334e-05, | |
| "loss": 0.0037, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 88.1792, | |
| "grad_norm": 0.03811612352728844, | |
| "learning_rate": 9.960444444444444e-06, | |
| "loss": 0.0035, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 88.8192, | |
| "grad_norm": 0.8571044206619263, | |
| "learning_rate": 9.871555555555557e-06, | |
| "loss": 0.0027, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 89.4576, | |
| "grad_norm": 1.1792042255401611, | |
| "learning_rate": 9.782666666666667e-06, | |
| "loss": 0.003, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 89.4576, | |
| "eval_loss": 1.0032455921173096, | |
| "eval_runtime": 152.9287, | |
| "eval_samples_per_second": 4.087, | |
| "eval_steps_per_second": 1.027, | |
| "eval_wer": 0.38592066039899103, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 90.096, | |
| "grad_norm": 0.32366737723350525, | |
| "learning_rate": 9.693777777777779e-06, | |
| "loss": 0.0034, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 90.736, | |
| "grad_norm": 0.4921131134033203, | |
| "learning_rate": 9.60488888888889e-06, | |
| "loss": 0.0035, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 91.3744, | |
| "grad_norm": 3.0860531330108643, | |
| "learning_rate": 9.516e-06, | |
| "loss": 0.0031, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 92.0128, | |
| "grad_norm": 3.8854892253875732, | |
| "learning_rate": 9.427111111111112e-06, | |
| "loss": 0.0034, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 92.6528, | |
| "grad_norm": 0.3374783396720886, | |
| "learning_rate": 9.338222222222223e-06, | |
| "loss": 0.0025, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 92.6528, | |
| "eval_loss": 1.0094186067581177, | |
| "eval_runtime": 135.2467, | |
| "eval_samples_per_second": 4.621, | |
| "eval_steps_per_second": 1.161, | |
| "eval_wer": 0.3856913551937629, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 93.2912, | |
| "grad_norm": 0.9511881470680237, | |
| "learning_rate": 9.249333333333335e-06, | |
| "loss": 0.0023, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 93.9312, | |
| "grad_norm": 0.5302645564079285, | |
| "learning_rate": 9.160888888888888e-06, | |
| "loss": 0.0025, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 94.5696, | |
| "grad_norm": 0.22430481016635895, | |
| "learning_rate": 9.072444444444445e-06, | |
| "loss": 0.003, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 95.208, | |
| "grad_norm": 0.18836861848831177, | |
| "learning_rate": 8.983555555555556e-06, | |
| "loss": 0.0025, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 95.848, | |
| "grad_norm": 0.5240734815597534, | |
| "learning_rate": 8.894666666666666e-06, | |
| "loss": 0.0034, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 95.848, | |
| "eval_loss": 1.02016282081604, | |
| "eval_runtime": 122.5101, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 1.282, | |
| "eval_wer": 0.3733088741114423, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 96.4864, | |
| "grad_norm": 0.10021472722291946, | |
| "learning_rate": 8.805777777777778e-06, | |
| "loss": 0.0029, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 97.1248, | |
| "grad_norm": 0.07506231218576431, | |
| "learning_rate": 8.716888888888889e-06, | |
| "loss": 0.0028, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 97.7648, | |
| "grad_norm": 0.6782508492469788, | |
| "learning_rate": 8.628000000000001e-06, | |
| "loss": 0.0031, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 98.4032, | |
| "grad_norm": 0.1539822518825531, | |
| "learning_rate": 8.539111111111112e-06, | |
| "loss": 0.0032, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 99.0416, | |
| "grad_norm": 0.3094239830970764, | |
| "learning_rate": 8.450222222222224e-06, | |
| "loss": 0.0027, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 99.0416, | |
| "eval_loss": 1.011278510093689, | |
| "eval_runtime": 106.3459, | |
| "eval_samples_per_second": 5.877, | |
| "eval_steps_per_second": 1.476, | |
| "eval_wer": 0.36551249713368494, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 99.6816, | |
| "grad_norm": 0.32241737842559814, | |
| "learning_rate": 8.361333333333334e-06, | |
| "loss": 0.0025, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 100.32, | |
| "grad_norm": 0.7617099285125732, | |
| "learning_rate": 8.272444444444445e-06, | |
| "loss": 0.0024, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 100.96, | |
| "grad_norm": 0.16760019958019257, | |
| "learning_rate": 8.183555555555555e-06, | |
| "loss": 0.0022, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 101.5984, | |
| "grad_norm": 0.05670633167028427, | |
| "learning_rate": 8.095111111111112e-06, | |
| "loss": 0.0029, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 102.2368, | |
| "grad_norm": 1.7071377038955688, | |
| "learning_rate": 8.006222222222223e-06, | |
| "loss": 0.0023, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 102.2368, | |
| "eval_loss": 1.0178241729736328, | |
| "eval_runtime": 104.5181, | |
| "eval_samples_per_second": 5.98, | |
| "eval_steps_per_second": 1.502, | |
| "eval_wer": 0.3767484521898647, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 102.8768, | |
| "grad_norm": 0.09089858084917068, | |
| "learning_rate": 7.917333333333333e-06, | |
| "loss": 0.0021, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 103.5152, | |
| "grad_norm": 0.31245774030685425, | |
| "learning_rate": 7.828444444444445e-06, | |
| "loss": 0.0027, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 104.1536, | |
| "grad_norm": 0.11016162484884262, | |
| "learning_rate": 7.739555555555556e-06, | |
| "loss": 0.0024, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 104.7936, | |
| "grad_norm": 1.1260924339294434, | |
| "learning_rate": 7.650666666666668e-06, | |
| "loss": 0.002, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 105.432, | |
| "grad_norm": 0.3586418330669403, | |
| "learning_rate": 7.561777777777778e-06, | |
| "loss": 0.002, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 105.432, | |
| "eval_loss": 1.0109715461730957, | |
| "eval_runtime": 110.8526, | |
| "eval_samples_per_second": 5.638, | |
| "eval_steps_per_second": 1.416, | |
| "eval_wer": 0.36711763357028204, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 106.0704, | |
| "grad_norm": 0.06334754824638367, | |
| "learning_rate": 7.4728888888888895e-06, | |
| "loss": 0.0021, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 106.7104, | |
| "grad_norm": 0.018475733697414398, | |
| "learning_rate": 7.384e-06, | |
| "loss": 0.002, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 107.3488, | |
| "grad_norm": 0.0939849466085434, | |
| "learning_rate": 7.295111111111112e-06, | |
| "loss": 0.0018, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 107.9888, | |
| "grad_norm": 0.6405438780784607, | |
| "learning_rate": 7.206222222222223e-06, | |
| "loss": 0.0025, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 108.6272, | |
| "grad_norm": 2.7534918785095215, | |
| "learning_rate": 7.117333333333334e-06, | |
| "loss": 0.002, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 108.6272, | |
| "eval_loss": 1.0300931930541992, | |
| "eval_runtime": 115.653, | |
| "eval_samples_per_second": 5.404, | |
| "eval_steps_per_second": 1.358, | |
| "eval_wer": 0.3733088741114423, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 109.2656, | |
| "grad_norm": 0.15731623768806458, | |
| "learning_rate": 7.028444444444445e-06, | |
| "loss": 0.0018, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 109.9056, | |
| "grad_norm": 1.9066952466964722, | |
| "learning_rate": 6.9395555555555565e-06, | |
| "loss": 0.0025, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 110.544, | |
| "grad_norm": 0.7084272503852844, | |
| "learning_rate": 6.850666666666668e-06, | |
| "loss": 0.002, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 111.1824, | |
| "grad_norm": 0.11165124177932739, | |
| "learning_rate": 6.761777777777778e-06, | |
| "loss": 0.0017, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 111.8224, | |
| "grad_norm": 0.16031847894191742, | |
| "learning_rate": 6.6733333333333335e-06, | |
| "loss": 0.0018, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 111.8224, | |
| "eval_loss": 1.047860026359558, | |
| "eval_runtime": 128.5964, | |
| "eval_samples_per_second": 4.86, | |
| "eval_steps_per_second": 1.221, | |
| "eval_wer": 0.3850034395780784, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 112.4608, | |
| "grad_norm": 0.2045450359582901, | |
| "learning_rate": 6.584444444444446e-06, | |
| "loss": 0.0023, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 113.0992, | |
| "grad_norm": 0.3708573281764984, | |
| "learning_rate": 6.495555555555556e-06, | |
| "loss": 0.002, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 113.7392, | |
| "grad_norm": 0.015015633776783943, | |
| "learning_rate": 6.4066666666666674e-06, | |
| "loss": 0.002, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 114.3776, | |
| "grad_norm": 0.04302428662776947, | |
| "learning_rate": 6.317777777777778e-06, | |
| "loss": 0.002, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 115.016, | |
| "grad_norm": 0.14831684529781342, | |
| "learning_rate": 6.22888888888889e-06, | |
| "loss": 0.002, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 115.016, | |
| "eval_loss": 1.0215903520584106, | |
| "eval_runtime": 125.0936, | |
| "eval_samples_per_second": 4.996, | |
| "eval_steps_per_second": 1.255, | |
| "eval_wer": 0.36253152946571887, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 115.656, | |
| "grad_norm": 0.06726387143135071, | |
| "learning_rate": 6.1400000000000005e-06, | |
| "loss": 0.0017, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 116.2944, | |
| "grad_norm": 0.059277065098285675, | |
| "learning_rate": 6.051111111111112e-06, | |
| "loss": 0.0016, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 116.9344, | |
| "grad_norm": 1.2333521842956543, | |
| "learning_rate": 5.962222222222222e-06, | |
| "loss": 0.0015, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 117.5728, | |
| "grad_norm": 0.1064881980419159, | |
| "learning_rate": 5.873333333333334e-06, | |
| "loss": 0.0013, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 118.2112, | |
| "grad_norm": 0.025924814864993095, | |
| "learning_rate": 5.784444444444445e-06, | |
| "loss": 0.002, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 118.2112, | |
| "eval_loss": 1.040561556816101, | |
| "eval_runtime": 127.336, | |
| "eval_samples_per_second": 4.908, | |
| "eval_steps_per_second": 1.233, | |
| "eval_wer": 0.36872277000687914, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 118.8512, | |
| "grad_norm": 0.05642084404826164, | |
| "learning_rate": 5.695555555555556e-06, | |
| "loss": 0.0017, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 119.4896, | |
| "grad_norm": 0.045298777520656586, | |
| "learning_rate": 5.606666666666667e-06, | |
| "loss": 0.0013, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 120.128, | |
| "grad_norm": 0.4968818724155426, | |
| "learning_rate": 5.517777777777779e-06, | |
| "loss": 0.0018, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 120.768, | |
| "grad_norm": 0.10297541320323944, | |
| "learning_rate": 5.428888888888889e-06, | |
| "loss": 0.0013, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 121.4064, | |
| "grad_norm": 0.022102700546383858, | |
| "learning_rate": 5.3400000000000005e-06, | |
| "loss": 0.0011, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 121.4064, | |
| "eval_loss": 1.0520411729812622, | |
| "eval_runtime": 132.307, | |
| "eval_samples_per_second": 4.724, | |
| "eval_steps_per_second": 1.187, | |
| "eval_wer": 0.41297867461591375, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 122.0448, | |
| "grad_norm": 0.13088802993297577, | |
| "learning_rate": 5.251555555555557e-06, | |
| "loss": 0.0018, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 122.6848, | |
| "grad_norm": 0.1453741490840912, | |
| "learning_rate": 5.162666666666667e-06, | |
| "loss": 0.0016, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 123.3232, | |
| "grad_norm": 0.0916297510266304, | |
| "learning_rate": 5.0737777777777785e-06, | |
| "loss": 0.0014, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 123.9632, | |
| "grad_norm": 3.053272008895874, | |
| "learning_rate": 4.984888888888889e-06, | |
| "loss": 0.0014, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 124.6016, | |
| "grad_norm": 0.06683260202407837, | |
| "learning_rate": 4.896e-06, | |
| "loss": 0.0014, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 124.6016, | |
| "eval_loss": 1.0563929080963135, | |
| "eval_runtime": 129.9946, | |
| "eval_samples_per_second": 4.808, | |
| "eval_steps_per_second": 1.208, | |
| "eval_wer": 0.36620041274936943, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 125.24, | |
| "grad_norm": 0.12738560140132904, | |
| "learning_rate": 4.8071111111111115e-06, | |
| "loss": 0.001, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 125.88, | |
| "grad_norm": 0.2464442402124405, | |
| "learning_rate": 4.718222222222222e-06, | |
| "loss": 0.0016, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 126.5184, | |
| "grad_norm": 0.026401793584227562, | |
| "learning_rate": 4.629333333333333e-06, | |
| "loss": 0.0015, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 127.1568, | |
| "grad_norm": 0.2598608732223511, | |
| "learning_rate": 4.540444444444445e-06, | |
| "loss": 0.0017, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 127.7968, | |
| "grad_norm": 0.11029820889234543, | |
| "learning_rate": 4.451555555555556e-06, | |
| "loss": 0.0009, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 127.7968, | |
| "eval_loss": 1.0525336265563965, | |
| "eval_runtime": 130.5048, | |
| "eval_samples_per_second": 4.789, | |
| "eval_steps_per_second": 1.203, | |
| "eval_wer": 0.37881219903691815, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 128.4352, | |
| "grad_norm": 0.03331665322184563, | |
| "learning_rate": 4.362666666666667e-06, | |
| "loss": 0.001, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 129.0736, | |
| "grad_norm": 0.12977726757526398, | |
| "learning_rate": 4.2737777777777785e-06, | |
| "loss": 0.0015, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 129.7136, | |
| "grad_norm": 0.031082535162568092, | |
| "learning_rate": 4.18488888888889e-06, | |
| "loss": 0.0011, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 130.352, | |
| "grad_norm": 2.1375820636749268, | |
| "learning_rate": 4.096e-06, | |
| "loss": 0.001, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 130.992, | |
| "grad_norm": 1.0629844665527344, | |
| "learning_rate": 4.0071111111111116e-06, | |
| "loss": 0.0009, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 130.992, | |
| "eval_loss": 1.0391464233398438, | |
| "eval_runtime": 131.1426, | |
| "eval_samples_per_second": 4.766, | |
| "eval_steps_per_second": 1.197, | |
| "eval_wer": 0.359779867002981, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 131.6304, | |
| "grad_norm": 0.0641772672533989, | |
| "learning_rate": 3.918222222222223e-06, | |
| "loss": 0.0012, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 132.2688, | |
| "grad_norm": 0.018780462443828583, | |
| "learning_rate": 3.829333333333334e-06, | |
| "loss": 0.0012, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 132.9088, | |
| "grad_norm": 0.021932663396000862, | |
| "learning_rate": 3.7408888888888895e-06, | |
| "loss": 0.0013, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 133.5472, | |
| "grad_norm": 0.40411534905433655, | |
| "learning_rate": 3.6520000000000004e-06, | |
| "loss": 0.0013, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 134.1856, | |
| "grad_norm": 2.085688352584839, | |
| "learning_rate": 3.5631111111111117e-06, | |
| "loss": 0.0011, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 134.1856, | |
| "eval_loss": 1.04826819896698, | |
| "eval_runtime": 125.1858, | |
| "eval_samples_per_second": 4.993, | |
| "eval_steps_per_second": 1.254, | |
| "eval_wer": 0.3762898417794084, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 134.8256, | |
| "grad_norm": 0.1101042777299881, | |
| "learning_rate": 3.4742222222222225e-06, | |
| "loss": 0.001, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 135.464, | |
| "grad_norm": 0.5308594107627869, | |
| "learning_rate": 3.385333333333334e-06, | |
| "loss": 0.0012, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 136.1024, | |
| "grad_norm": 0.10180327296257019, | |
| "learning_rate": 3.2964444444444447e-06, | |
| "loss": 0.001, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 136.7424, | |
| "grad_norm": 0.029545770958065987, | |
| "learning_rate": 3.207555555555556e-06, | |
| "loss": 0.0009, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 137.3808, | |
| "grad_norm": 0.022081894800066948, | |
| "learning_rate": 3.118666666666667e-06, | |
| "loss": 0.001, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 137.3808, | |
| "eval_loss": 1.0376399755477905, | |
| "eval_runtime": 129.9317, | |
| "eval_samples_per_second": 4.81, | |
| "eval_steps_per_second": 1.208, | |
| "eval_wer": 0.4168768631047925, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 138.0192, | |
| "grad_norm": 0.7658660411834717, | |
| "learning_rate": 3.029777777777778e-06, | |
| "loss": 0.0011, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 138.6592, | |
| "grad_norm": 0.027192605659365654, | |
| "learning_rate": 2.940888888888889e-06, | |
| "loss": 0.0011, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 139.2976, | |
| "grad_norm": 0.03390691056847572, | |
| "learning_rate": 2.8520000000000004e-06, | |
| "loss": 0.001, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 139.9376, | |
| "grad_norm": 0.08181264251470566, | |
| "learning_rate": 2.7631111111111113e-06, | |
| "loss": 0.0011, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 140.576, | |
| "grad_norm": 0.3259316086769104, | |
| "learning_rate": 2.6742222222222226e-06, | |
| "loss": 0.0008, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 140.576, | |
| "eval_loss": 1.0424144268035889, | |
| "eval_runtime": 104.1123, | |
| "eval_samples_per_second": 6.003, | |
| "eval_steps_per_second": 1.508, | |
| "eval_wer": 0.36321944508140336, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 141.2144, | |
| "grad_norm": 0.02337617427110672, | |
| "learning_rate": 2.5853333333333335e-06, | |
| "loss": 0.0005, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 141.8544, | |
| "grad_norm": 0.01961325667798519, | |
| "learning_rate": 2.4964444444444448e-06, | |
| "loss": 0.001, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 142.4928, | |
| "grad_norm": 0.0774613469839096, | |
| "learning_rate": 2.4075555555555556e-06, | |
| "loss": 0.0008, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 143.1312, | |
| "grad_norm": 0.4658966660499573, | |
| "learning_rate": 2.318666666666667e-06, | |
| "loss": 0.0007, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 143.7712, | |
| "grad_norm": 0.39419323205947876, | |
| "learning_rate": 2.229777777777778e-06, | |
| "loss": 0.0007, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 143.7712, | |
| "eval_loss": 1.0494757890701294, | |
| "eval_runtime": 104.6831, | |
| "eval_samples_per_second": 5.97, | |
| "eval_steps_per_second": 1.5, | |
| "eval_wer": 0.4159596422838798, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 144.4096, | |
| "grad_norm": 1.093592882156372, | |
| "learning_rate": 2.140888888888889e-06, | |
| "loss": 0.0008, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 145.048, | |
| "grad_norm": 0.011096829548478127, | |
| "learning_rate": 2.052e-06, | |
| "loss": 0.0008, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 145.688, | |
| "grad_norm": 0.18569226562976837, | |
| "learning_rate": 1.9631111111111113e-06, | |
| "loss": 0.0009, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 146.3264, | |
| "grad_norm": 0.17811138927936554, | |
| "learning_rate": 1.8742222222222222e-06, | |
| "loss": 0.0008, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 146.9664, | |
| "grad_norm": 0.01262740883976221, | |
| "learning_rate": 1.7853333333333333e-06, | |
| "loss": 0.0009, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 146.9664, | |
| "eval_loss": 1.054679274559021, | |
| "eval_runtime": 104.7175, | |
| "eval_samples_per_second": 5.968, | |
| "eval_steps_per_second": 1.499, | |
| "eval_wer": 0.36872277000687914, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 147.6048, | |
| "grad_norm": 7.735331058502197, | |
| "learning_rate": 1.6964444444444444e-06, | |
| "loss": 0.0008, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 148.2432, | |
| "grad_norm": 0.2187137007713318, | |
| "learning_rate": 1.608e-06, | |
| "loss": 0.0009, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 148.8832, | |
| "grad_norm": 0.15815149247646332, | |
| "learning_rate": 1.5191111111111112e-06, | |
| "loss": 0.0008, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 149.5216, | |
| "grad_norm": 0.3170558214187622, | |
| "learning_rate": 1.430666666666667e-06, | |
| "loss": 0.0005, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 150.16, | |
| "grad_norm": 0.09482572972774506, | |
| "learning_rate": 1.341777777777778e-06, | |
| "loss": 0.0005, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 150.16, | |
| "eval_loss": 1.058286428451538, | |
| "eval_runtime": 103.6331, | |
| "eval_samples_per_second": 6.031, | |
| "eval_steps_per_second": 1.515, | |
| "eval_wer": 0.3689520752121073, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 150.8, | |
| "grad_norm": 0.012617244385182858, | |
| "learning_rate": 1.2528888888888891e-06, | |
| "loss": 0.0006, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 151.4384, | |
| "grad_norm": 0.032891806215047836, | |
| "learning_rate": 1.1640000000000002e-06, | |
| "loss": 0.0009, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 152.0768, | |
| "grad_norm": 1.6969341039657593, | |
| "learning_rate": 1.0751111111111113e-06, | |
| "loss": 0.0006, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 152.7168, | |
| "grad_norm": 0.2790795862674713, | |
| "learning_rate": 9.862222222222224e-07, | |
| "loss": 0.0006, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 153.3552, | |
| "grad_norm": 0.33090606331825256, | |
| "learning_rate": 8.973333333333334e-07, | |
| "loss": 0.0007, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 153.3552, | |
| "eval_loss": 1.0462735891342163, | |
| "eval_runtime": 105.9059, | |
| "eval_samples_per_second": 5.901, | |
| "eval_steps_per_second": 1.482, | |
| "eval_wer": 0.4122907590002293, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 153.9952, | |
| "grad_norm": 0.005133169237524271, | |
| "learning_rate": 8.084444444444445e-07, | |
| "loss": 0.0008, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 154.6336, | |
| "grad_norm": 0.020690323784947395, | |
| "learning_rate": 7.195555555555556e-07, | |
| "loss": 0.001, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 155.272, | |
| "grad_norm": 2.341998338699341, | |
| "learning_rate": 6.306666666666666e-07, | |
| "loss": 0.0007, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 155.912, | |
| "grad_norm": 0.0469956174492836, | |
| "learning_rate": 5.417777777777778e-07, | |
| "loss": 0.0006, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 156.5504, | |
| "grad_norm": 0.006763980723917484, | |
| "learning_rate": 4.528888888888889e-07, | |
| "loss": 0.0007, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 156.5504, | |
| "eval_loss": 1.0463974475860596, | |
| "eval_runtime": 104.646, | |
| "eval_samples_per_second": 5.973, | |
| "eval_steps_per_second": 1.5, | |
| "eval_wer": 0.3600091722082091, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 157.1888, | |
| "grad_norm": 0.01508264522999525, | |
| "learning_rate": 3.6400000000000003e-07, | |
| "loss": 0.0008, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 157.8288, | |
| "grad_norm": 0.008547438308596611, | |
| "learning_rate": 2.751111111111111e-07, | |
| "loss": 0.0013, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 158.4672, | |
| "grad_norm": 0.03822452574968338, | |
| "learning_rate": 1.8622222222222221e-07, | |
| "loss": 0.0005, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 159.1056, | |
| "grad_norm": 0.07067080587148666, | |
| "learning_rate": 9.733333333333334e-08, | |
| "loss": 0.0006, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 159.7456, | |
| "grad_norm": 0.007019846700131893, | |
| "learning_rate": 8.444444444444445e-09, | |
| "loss": 0.0005, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 159.7456, | |
| "eval_loss": 1.0454859733581543, | |
| "eval_runtime": 104.5679, | |
| "eval_samples_per_second": 5.977, | |
| "eval_steps_per_second": 1.501, | |
| "eval_wer": 0.3609263930291218, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 159.7456, | |
| "step": 50000, | |
| "total_flos": 1.966379287412736e+19, | |
| "train_loss": 0.0770821487186849, | |
| "train_runtime": 117170.0508, | |
| "train_samples_per_second": 6.828, | |
| "train_steps_per_second": 0.427 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 50000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 161, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.966379287412736e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |