| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.657169990503323, | |
| "global_step": 15600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 14.0657, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 6.884028911590576, | |
| "eval_runtime": 316.7633, | |
| "eval_samples_per_second": 7.217, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 1.3018771418341772, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.960000000000001e-05, | |
| "loss": 6.1255, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 3.8771634101867676, | |
| "eval_runtime": 322.5603, | |
| "eval_samples_per_second": 7.087, | |
| "eval_steps_per_second": 0.887, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.96e-05, | |
| "loss": 3.2311, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 3.20473313331604, | |
| "eval_runtime": 316.4632, | |
| "eval_samples_per_second": 7.224, | |
| "eval_steps_per_second": 0.904, | |
| "eval_wer": 0.999386220653675, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 7.960000000000001e-05, | |
| "loss": 3.1379, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 3.1962826251983643, | |
| "eval_runtime": 316.7959, | |
| "eval_samples_per_second": 7.216, | |
| "eval_steps_per_second": 0.903, | |
| "eval_wer": 0.999386220653675, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 9.960000000000001e-05, | |
| "loss": 2.7389, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.8025017976760864, | |
| "eval_runtime": 318.5421, | |
| "eval_samples_per_second": 7.176, | |
| "eval_steps_per_second": 0.898, | |
| "eval_wer": 0.7388880364175745, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.913427561837456e-05, | |
| "loss": 1.1799, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.5602023601531982, | |
| "eval_runtime": 320.0374, | |
| "eval_samples_per_second": 7.143, | |
| "eval_steps_per_second": 0.894, | |
| "eval_wer": 0.3688302388624623, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 9.825088339222615e-05, | |
| "loss": 0.5985, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "eval_loss": 0.46469706296920776, | |
| "eval_runtime": 317.0532, | |
| "eval_samples_per_second": 7.21, | |
| "eval_steps_per_second": 0.902, | |
| "eval_wer": 0.3150222495013043, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 9.736749116607774e-05, | |
| "loss": 0.4944, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "eval_loss": 0.38040226697921753, | |
| "eval_runtime": 319.5077, | |
| "eval_samples_per_second": 7.155, | |
| "eval_steps_per_second": 0.895, | |
| "eval_wer": 0.28331031660784617, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 9.648409893992934e-05, | |
| "loss": 0.4011, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 0.3565872609615326, | |
| "eval_runtime": 326.4601, | |
| "eval_samples_per_second": 7.002, | |
| "eval_steps_per_second": 0.876, | |
| "eval_wer": 0.2767121886348524, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 9.560070671378091e-05, | |
| "loss": 0.355, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 0.33882376551628113, | |
| "eval_runtime": 327.1229, | |
| "eval_samples_per_second": 6.988, | |
| "eval_steps_per_second": 0.874, | |
| "eval_wer": 0.26934683647895247, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 9.471731448763252e-05, | |
| "loss": 0.3319, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "eval_loss": 0.3453792929649353, | |
| "eval_runtime": 327.4176, | |
| "eval_samples_per_second": 6.982, | |
| "eval_steps_per_second": 0.874, | |
| "eval_wer": 0.2657153086798629, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 9.383392226148411e-05, | |
| "loss": 0.3052, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_loss": 0.3088168799877167, | |
| "eval_runtime": 328.7404, | |
| "eval_samples_per_second": 6.954, | |
| "eval_steps_per_second": 0.87, | |
| "eval_wer": 0.2609073704669838, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 9.295053003533569e-05, | |
| "loss": 0.2707, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "eval_loss": 0.3140409290790558, | |
| "eval_runtime": 329.2489, | |
| "eval_samples_per_second": 6.943, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.25297938724361924, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 9.206713780918729e-05, | |
| "loss": 0.2603, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_loss": 0.43849411606788635, | |
| "eval_runtime": 330.8014, | |
| "eval_samples_per_second": 6.91, | |
| "eval_steps_per_second": 0.865, | |
| "eval_wer": 0.2776328576543399, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 9.118374558303887e-05, | |
| "loss": 0.2559, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 0.28870412707328796, | |
| "eval_runtime": 328.263, | |
| "eval_samples_per_second": 6.964, | |
| "eval_steps_per_second": 0.871, | |
| "eval_wer": 0.24919441460794844, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 9.030035335689046e-05, | |
| "loss": 0.231, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "eval_loss": 0.2984590232372284, | |
| "eval_runtime": 329.584, | |
| "eval_samples_per_second": 6.936, | |
| "eval_steps_per_second": 0.868, | |
| "eval_wer": 0.24812030075187969, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 8.941696113074205e-05, | |
| "loss": 0.2194, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "eval_loss": 0.33247044682502747, | |
| "eval_runtime": 325.7403, | |
| "eval_samples_per_second": 7.018, | |
| "eval_steps_per_second": 0.878, | |
| "eval_wer": 0.2547184287248734, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "learning_rate": 8.853356890459364e-05, | |
| "loss": 0.2205, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.14, | |
| "eval_loss": 0.2854120135307312, | |
| "eval_runtime": 323.7366, | |
| "eval_samples_per_second": 7.061, | |
| "eval_steps_per_second": 0.883, | |
| "eval_wer": 0.2446933660682318, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 8.765017667844523e-05, | |
| "loss": 0.1904, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "eval_loss": 0.26710790395736694, | |
| "eval_runtime": 322.8659, | |
| "eval_samples_per_second": 7.08, | |
| "eval_steps_per_second": 0.886, | |
| "eval_wer": 0.24346580737558182, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 8.676678445229682e-05, | |
| "loss": 0.187, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "eval_loss": 0.2750653624534607, | |
| "eval_runtime": 323.9203, | |
| "eval_samples_per_second": 7.057, | |
| "eval_steps_per_second": 0.883, | |
| "eval_wer": 0.2428008797503964, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 8.588339222614842e-05, | |
| "loss": 0.1724, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "eval_loss": 0.2918902337551117, | |
| "eval_runtime": 340.4683, | |
| "eval_samples_per_second": 6.714, | |
| "eval_steps_per_second": 0.84, | |
| "eval_wer": 0.24049920720167767, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.1666, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 11.17, | |
| "eval_loss": 0.28774362802505493, | |
| "eval_runtime": 342.0819, | |
| "eval_samples_per_second": 6.683, | |
| "eval_steps_per_second": 0.836, | |
| "eval_wer": 0.23799294153751727, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "learning_rate": 8.412102473498234e-05, | |
| "loss": 0.1562, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "eval_loss": 0.2777426540851593, | |
| "eval_runtime": 341.5835, | |
| "eval_samples_per_second": 6.692, | |
| "eval_steps_per_second": 0.837, | |
| "eval_wer": 0.2387090174415631, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "learning_rate": 8.323763250883393e-05, | |
| "loss": 0.1489, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 12.18, | |
| "eval_loss": 0.27934086322784424, | |
| "eval_runtime": 342.4524, | |
| "eval_samples_per_second": 6.675, | |
| "eval_steps_per_second": 0.835, | |
| "eval_wer": 0.24014116924965476, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 8.235424028268552e-05, | |
| "loss": 0.1567, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "eval_loss": 0.29788124561309814, | |
| "eval_runtime": 339.8038, | |
| "eval_samples_per_second": 6.727, | |
| "eval_steps_per_second": 0.842, | |
| "eval_wer": 0.2369188276814485, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 8.147084805653711e-05, | |
| "loss": 0.1501, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "eval_loss": 0.3033454418182373, | |
| "eval_runtime": 338.8207, | |
| "eval_samples_per_second": 6.747, | |
| "eval_steps_per_second": 0.844, | |
| "eval_wer": 0.23543552759449646, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 8.058745583038869e-05, | |
| "loss": 0.1362, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "eval_loss": 0.282699853181839, | |
| "eval_runtime": 343.5056, | |
| "eval_samples_per_second": 6.655, | |
| "eval_steps_per_second": 0.833, | |
| "eval_wer": 0.23144596184338398, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 7.970406360424029e-05, | |
| "loss": 0.1391, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "eval_loss": 0.30705466866493225, | |
| "eval_runtime": 342.7503, | |
| "eval_samples_per_second": 6.67, | |
| "eval_steps_per_second": 0.834, | |
| "eval_wer": 0.2315482584011048, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 7.882067137809188e-05, | |
| "loss": 0.1299, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "eval_loss": 0.2924181818962097, | |
| "eval_runtime": 343.6951, | |
| "eval_samples_per_second": 6.651, | |
| "eval_steps_per_second": 0.832, | |
| "eval_wer": 0.23093447905477982, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 7.793727915194346e-05, | |
| "loss": 0.1187, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "eval_loss": 0.31287097930908203, | |
| "eval_runtime": 343.6023, | |
| "eval_samples_per_second": 6.653, | |
| "eval_steps_per_second": 0.832, | |
| "eval_wer": 0.2343102654595673, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "learning_rate": 7.705388692579506e-05, | |
| "loss": 0.121, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 15.74, | |
| "eval_loss": 0.3056861162185669, | |
| "eval_runtime": 343.3615, | |
| "eval_samples_per_second": 6.658, | |
| "eval_steps_per_second": 0.833, | |
| "eval_wer": 0.23139481356452354, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "learning_rate": 7.617049469964664e-05, | |
| "loss": 0.1237, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 16.24, | |
| "eval_loss": 0.33616331219673157, | |
| "eval_runtime": 348.2247, | |
| "eval_samples_per_second": 6.565, | |
| "eval_steps_per_second": 0.821, | |
| "eval_wer": 0.2368676794025881, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 7.528710247349823e-05, | |
| "loss": 0.1257, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "eval_loss": 0.30364322662353516, | |
| "eval_runtime": 354.4023, | |
| "eval_samples_per_second": 6.45, | |
| "eval_steps_per_second": 0.807, | |
| "eval_wer": 0.23067873766047772, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "learning_rate": 7.440371024734982e-05, | |
| "loss": 0.1151, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 17.26, | |
| "eval_loss": 0.3333089351654053, | |
| "eval_runtime": 353.6951, | |
| "eval_samples_per_second": 6.463, | |
| "eval_steps_per_second": 0.809, | |
| "eval_wer": 0.23103677561250063, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 17.77, | |
| "learning_rate": 7.352031802120141e-05, | |
| "loss": 0.1045, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 17.77, | |
| "eval_loss": 0.31175628304481506, | |
| "eval_runtime": 340.1327, | |
| "eval_samples_per_second": 6.721, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.23415682062298604, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "learning_rate": 7.2636925795053e-05, | |
| "loss": 0.114, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 18.27, | |
| "eval_loss": 0.2973700165748596, | |
| "eval_runtime": 331.883, | |
| "eval_samples_per_second": 6.888, | |
| "eval_steps_per_second": 0.862, | |
| "eval_wer": 0.2294000306889673, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "learning_rate": 7.17535335689046e-05, | |
| "loss": 0.1064, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 18.78, | |
| "eval_loss": 0.3128357529640198, | |
| "eval_runtime": 340.1178, | |
| "eval_samples_per_second": 6.721, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.22837706511175898, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "learning_rate": 7.087014134275619e-05, | |
| "loss": 0.1009, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 19.29, | |
| "eval_loss": 0.31967654824256897, | |
| "eval_runtime": 336.3559, | |
| "eval_samples_per_second": 6.796, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.2297069203621298, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 6.998674911660778e-05, | |
| "loss": 0.1047, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "eval_loss": 0.2982560694217682, | |
| "eval_runtime": 324.6466, | |
| "eval_samples_per_second": 7.042, | |
| "eval_steps_per_second": 0.881, | |
| "eval_wer": 0.2346171551327298, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "learning_rate": 6.910335689045937e-05, | |
| "loss": 0.0989, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 20.3, | |
| "eval_loss": 0.3321704864501953, | |
| "eval_runtime": 325.4996, | |
| "eval_samples_per_second": 7.023, | |
| "eval_steps_per_second": 0.879, | |
| "eval_wer": 0.23170170323768605, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "learning_rate": 6.821996466431095e-05, | |
| "loss": 0.0976, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "eval_loss": 0.3263297379016876, | |
| "eval_runtime": 327.1397, | |
| "eval_samples_per_second": 6.988, | |
| "eval_steps_per_second": 0.874, | |
| "eval_wer": 0.23395222750754438, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 6.733657243816255e-05, | |
| "loss": 0.0915, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "eval_loss": 0.3296717703342438, | |
| "eval_runtime": 327.0362, | |
| "eval_samples_per_second": 6.99, | |
| "eval_steps_per_second": 0.875, | |
| "eval_wer": 0.22832591683289857, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 21.83, | |
| "learning_rate": 6.645318021201413e-05, | |
| "loss": 0.0874, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 21.83, | |
| "eval_loss": 0.3275238573551178, | |
| "eval_runtime": 326.5367, | |
| "eval_samples_per_second": 7.001, | |
| "eval_steps_per_second": 0.876, | |
| "eval_wer": 0.22945117896782774, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "learning_rate": 6.557420494699646e-05, | |
| "loss": 0.0952, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 22.33, | |
| "eval_loss": 0.34165430068969727, | |
| "eval_runtime": 331.1514, | |
| "eval_samples_per_second": 6.903, | |
| "eval_steps_per_second": 0.864, | |
| "eval_wer": 0.22796787888087566, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 22.84, | |
| "learning_rate": 6.469081272084806e-05, | |
| "loss": 0.0907, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 22.84, | |
| "eval_loss": 0.32556086778640747, | |
| "eval_runtime": 330.5, | |
| "eval_samples_per_second": 6.917, | |
| "eval_steps_per_second": 0.865, | |
| "eval_wer": 0.22858165822720067, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 23.35, | |
| "learning_rate": 6.380742049469966e-05, | |
| "loss": 0.0807, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 23.35, | |
| "eval_loss": 0.3502887785434723, | |
| "eval_runtime": 336.4566, | |
| "eval_samples_per_second": 6.794, | |
| "eval_steps_per_second": 0.85, | |
| "eval_wer": 0.2290419927369444, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 23.86, | |
| "learning_rate": 6.292402826855123e-05, | |
| "loss": 0.082, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 23.86, | |
| "eval_loss": 0.344855934381485, | |
| "eval_runtime": 339.6685, | |
| "eval_samples_per_second": 6.73, | |
| "eval_steps_per_second": 0.842, | |
| "eval_wer": 0.2290419927369444, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 24.37, | |
| "learning_rate": 6.204063604240284e-05, | |
| "loss": 0.0801, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 24.37, | |
| "eval_loss": 0.36849820613861084, | |
| "eval_runtime": 338.3914, | |
| "eval_samples_per_second": 6.755, | |
| "eval_steps_per_second": 0.845, | |
| "eval_wer": 0.22801902715973607, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "learning_rate": 6.115724381625441e-05, | |
| "loss": 0.0755, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 24.87, | |
| "eval_loss": 0.3435544967651367, | |
| "eval_runtime": 337.5045, | |
| "eval_samples_per_second": 6.773, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.22893969617922358, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 6.027385159010601e-05, | |
| "loss": 0.0735, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "eval_loss": 0.3514951467514038, | |
| "eval_runtime": 337.5311, | |
| "eval_samples_per_second": 6.773, | |
| "eval_steps_per_second": 0.847, | |
| "eval_wer": 0.22766098920771316, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "learning_rate": 5.93904593639576e-05, | |
| "loss": 0.0749, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 25.89, | |
| "eval_loss": 0.3425111174583435, | |
| "eval_runtime": 341.8062, | |
| "eval_samples_per_second": 6.688, | |
| "eval_steps_per_second": 0.837, | |
| "eval_wer": 0.22893969617922358, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 5.850706713780919e-05, | |
| "loss": 0.0756, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "eval_loss": 0.34799715876579285, | |
| "eval_runtime": 327.2581, | |
| "eval_samples_per_second": 6.985, | |
| "eval_steps_per_second": 0.874, | |
| "eval_wer": 0.22658687535164443, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 26.9, | |
| "learning_rate": 5.7623674911660786e-05, | |
| "loss": 0.0745, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 26.9, | |
| "eval_loss": 0.3655582368373871, | |
| "eval_runtime": 327.7963, | |
| "eval_samples_per_second": 6.974, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.2249501304281111, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "learning_rate": 5.674028268551237e-05, | |
| "loss": 0.0739, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 27.41, | |
| "eval_loss": 0.3493630588054657, | |
| "eval_runtime": 325.9215, | |
| "eval_samples_per_second": 7.014, | |
| "eval_steps_per_second": 0.878, | |
| "eval_wer": 0.23098562733364023, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 27.92, | |
| "learning_rate": 5.585689045936396e-05, | |
| "loss": 0.0747, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 27.92, | |
| "eval_loss": 0.3572988510131836, | |
| "eval_runtime": 326.4765, | |
| "eval_samples_per_second": 7.002, | |
| "eval_steps_per_second": 0.876, | |
| "eval_wer": 0.22541046493785485, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 5.49779151943463e-05, | |
| "loss": 0.0638, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "eval_loss": 0.37718120217323303, | |
| "eval_runtime": 326.7276, | |
| "eval_samples_per_second": 6.997, | |
| "eval_steps_per_second": 0.875, | |
| "eval_wer": 0.22382486829318193, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 28.93, | |
| "learning_rate": 5.409452296819788e-05, | |
| "loss": 0.0692, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 28.93, | |
| "eval_loss": 0.3608773648738861, | |
| "eval_runtime": 327.8617, | |
| "eval_samples_per_second": 6.972, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.227763285765434, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.321113074204947e-05, | |
| "loss": 0.0628, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "eval_loss": 0.3680490553379059, | |
| "eval_runtime": 328.0778, | |
| "eval_samples_per_second": 6.968, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.2249501304281111, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "learning_rate": 5.232773851590106e-05, | |
| "loss": 0.0639, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 29.95, | |
| "eval_loss": 0.3743281364440918, | |
| "eval_runtime": 334.0745, | |
| "eval_samples_per_second": 6.843, | |
| "eval_steps_per_second": 0.856, | |
| "eval_wer": 0.22541046493785485, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 30.46, | |
| "learning_rate": 5.1444346289752655e-05, | |
| "loss": 0.067, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 30.46, | |
| "eval_loss": 0.370677649974823, | |
| "eval_runtime": 334.479, | |
| "eval_samples_per_second": 6.835, | |
| "eval_steps_per_second": 0.855, | |
| "eval_wer": 0.22397831312976318, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 30.96, | |
| "learning_rate": 5.056095406360424e-05, | |
| "loss": 0.0586, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 30.96, | |
| "eval_loss": 0.3863554298877716, | |
| "eval_runtime": 334.1121, | |
| "eval_samples_per_second": 6.842, | |
| "eval_steps_per_second": 0.856, | |
| "eval_wer": 0.22413175796634444, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "learning_rate": 4.967756183745583e-05, | |
| "loss": 0.0601, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "eval_loss": 0.3715435266494751, | |
| "eval_runtime": 337.8795, | |
| "eval_samples_per_second": 6.766, | |
| "eval_steps_per_second": 0.846, | |
| "eval_wer": 0.22633113395734233, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 31.98, | |
| "learning_rate": 4.8798586572438167e-05, | |
| "loss": 0.0607, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 31.98, | |
| "eval_loss": 0.36769574880599976, | |
| "eval_runtime": 335.2748, | |
| "eval_samples_per_second": 6.818, | |
| "eval_steps_per_second": 0.853, | |
| "eval_wer": 0.22566620633215692, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 32.49, | |
| "learning_rate": 4.791519434628976e-05, | |
| "loss": 0.0585, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 32.49, | |
| "eval_loss": 0.38456135988235474, | |
| "eval_runtime": 335.5304, | |
| "eval_samples_per_second": 6.813, | |
| "eval_steps_per_second": 0.852, | |
| "eval_wer": 0.22607539256304027, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "learning_rate": 4.703180212014134e-05, | |
| "loss": 0.0549, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "eval_loss": 0.376272976398468, | |
| "eval_runtime": 339.7138, | |
| "eval_samples_per_second": 6.729, | |
| "eval_steps_per_second": 0.842, | |
| "eval_wer": 0.22883739962150274, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 33.5, | |
| "learning_rate": 4.614840989399293e-05, | |
| "loss": 0.0566, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 33.5, | |
| "eval_loss": 0.375703901052475, | |
| "eval_runtime": 340.809, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 0.839, | |
| "eval_wer": 0.22551276149557567, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "learning_rate": 4.5265017667844524e-05, | |
| "loss": 0.0601, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "eval_loss": 0.3690040707588196, | |
| "eval_runtime": 340.0174, | |
| "eval_samples_per_second": 6.723, | |
| "eval_steps_per_second": 0.841, | |
| "eval_wer": 0.2242852028029257, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 34.52, | |
| "learning_rate": 4.4381625441696115e-05, | |
| "loss": 0.0644, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 34.52, | |
| "eval_loss": 0.38989028334617615, | |
| "eval_runtime": 330.5652, | |
| "eval_samples_per_second": 6.915, | |
| "eval_steps_per_second": 0.865, | |
| "eval_wer": 0.22801902715973607, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 35.03, | |
| "learning_rate": 4.3498233215547706e-05, | |
| "loss": 0.0534, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 35.03, | |
| "eval_loss": 0.3764423429965973, | |
| "eval_runtime": 331.0495, | |
| "eval_samples_per_second": 6.905, | |
| "eval_steps_per_second": 0.864, | |
| "eval_wer": 0.22643343051506318, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "learning_rate": 4.26148409893993e-05, | |
| "loss": 0.0533, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 35.53, | |
| "eval_loss": 0.39295488595962524, | |
| "eval_runtime": 324.4991, | |
| "eval_samples_per_second": 7.045, | |
| "eval_steps_per_second": 0.881, | |
| "eval_wer": 0.2250012787069715, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 36.04, | |
| "learning_rate": 4.173144876325089e-05, | |
| "loss": 0.0538, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 36.04, | |
| "eval_loss": 0.3971385061740875, | |
| "eval_runtime": 324.5617, | |
| "eval_samples_per_second": 7.043, | |
| "eval_steps_per_second": 0.881, | |
| "eval_wer": 0.22423405452406525, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "learning_rate": 4.084805653710247e-05, | |
| "loss": 0.0549, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 36.55, | |
| "eval_loss": 0.41013625264167786, | |
| "eval_runtime": 327.8225, | |
| "eval_samples_per_second": 6.973, | |
| "eval_steps_per_second": 0.872, | |
| "eval_wer": 0.22766098920771316, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 37.06, | |
| "learning_rate": 3.9964664310954064e-05, | |
| "loss": 0.0558, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 37.06, | |
| "eval_loss": 0.3944765031337738, | |
| "eval_runtime": 329.1988, | |
| "eval_samples_per_second": 6.944, | |
| "eval_steps_per_second": 0.869, | |
| "eval_wer": 0.22408060968748403, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 37.56, | |
| "learning_rate": 3.9081272084805655e-05, | |
| "loss": 0.0592, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 37.56, | |
| "eval_loss": 0.4027334451675415, | |
| "eval_runtime": 325.5906, | |
| "eval_samples_per_second": 7.021, | |
| "eval_steps_per_second": 0.878, | |
| "eval_wer": 0.2249501304281111, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 5.421465968586388e-05, | |
| "loss": 0.125, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "eval_loss": 0.310897558927536, | |
| "eval_runtime": 158.8811, | |
| "eval_samples_per_second": 7.282, | |
| "eval_steps_per_second": 0.913, | |
| "eval_wer": 0.1662258953168044, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "learning_rate": 5.3560209424083776e-05, | |
| "loss": 0.1162, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "eval_loss": 0.2863084673881531, | |
| "eval_runtime": 159.2387, | |
| "eval_samples_per_second": 7.266, | |
| "eval_steps_per_second": 0.911, | |
| "eval_wer": 0.16831955922865013, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 5.290575916230367e-05, | |
| "loss": 0.1021, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "eval_loss": 0.2973718047142029, | |
| "eval_runtime": 159.1999, | |
| "eval_samples_per_second": 7.268, | |
| "eval_steps_per_second": 0.911, | |
| "eval_wer": 0.16815426997245178, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 29.66, | |
| "learning_rate": 5.225130890052357e-05, | |
| "loss": 0.1019, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 29.66, | |
| "eval_loss": 0.2894442677497864, | |
| "eval_runtime": 161.3136, | |
| "eval_samples_per_second": 7.172, | |
| "eval_steps_per_second": 0.899, | |
| "eval_wer": 0.16820936639118458, | |
| "step": 15600 | |
| } | |
| ], | |
| "max_steps": 31560, | |
| "num_train_epochs": 60, | |
| "total_flos": 6.589332771620831e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |