| { |
| "best_metric": 30.297225891677677, |
| "best_model_checkpoint": "./whisper-small-lt/checkpoint-2000", |
| "epoch": 5.0275, |
| "eval_steps": 1000, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0125, |
| "grad_norm": 1.7294858694076538, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 0.0291, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.025, |
| "grad_norm": 1.1127374172210693, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.0178, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0375, |
| "grad_norm": 1.248637318611145, |
| "learning_rate": 1.5e-06, |
| "loss": 0.0202, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.05, |
| "grad_norm": 0.8879645466804504, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.0166, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0625, |
| "grad_norm": 1.0460960865020752, |
| "learning_rate": 2.5e-06, |
| "loss": 0.0148, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.075, |
| "grad_norm": 0.7859419584274292, |
| "learning_rate": 3e-06, |
| "loss": 0.0138, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.0875, |
| "grad_norm": 0.6411359906196594, |
| "learning_rate": 3.5e-06, |
| "loss": 0.0124, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 1.4224746227264404, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0157, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1125, |
| "grad_norm": 1.8457200527191162, |
| "learning_rate": 4.5e-06, |
| "loss": 0.0283, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.125, |
| "grad_norm": 2.3054425716400146, |
| "learning_rate": 5e-06, |
| "loss": 0.0244, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.1375, |
| "grad_norm": 2.961075782775879, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.0226, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 1.1010462045669556, |
| "learning_rate": 6e-06, |
| "loss": 0.0158, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.1625, |
| "grad_norm": 1.5947000980377197, |
| "learning_rate": 6.5000000000000004e-06, |
| "loss": 0.0185, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.175, |
| "grad_norm": 2.136035203933716, |
| "learning_rate": 7e-06, |
| "loss": 0.0182, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.1875, |
| "grad_norm": 1.8465747833251953, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.0149, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.0055, |
| "grad_norm": 2.093752384185791, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.0277, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.018, |
| "grad_norm": 1.3066338300704956, |
| "learning_rate": 8.5e-06, |
| "loss": 0.0236, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.0305, |
| "grad_norm": 2.310856819152832, |
| "learning_rate": 9e-06, |
| "loss": 0.023, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.043, |
| "grad_norm": 1.4942700862884521, |
| "learning_rate": 9.5e-06, |
| "loss": 0.022, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.0555, |
| "grad_norm": 1.1907243728637695, |
| "learning_rate": 1e-05, |
| "loss": 0.0183, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.068, |
| "grad_norm": 1.8676977157592773, |
| "learning_rate": 9.833333333333333e-06, |
| "loss": 0.0183, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.0805, |
| "grad_norm": 0.9104222059249878, |
| "learning_rate": 9.666666666666667e-06, |
| "loss": 0.016, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.093, |
| "grad_norm": 1.465457558631897, |
| "learning_rate": 9.5e-06, |
| "loss": 0.0151, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.1055, |
| "grad_norm": 1.5364313125610352, |
| "learning_rate": 9.333333333333334e-06, |
| "loss": 0.0205, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.1179999999999999, |
| "grad_norm": 1.29054594039917, |
| "learning_rate": 9.166666666666666e-06, |
| "loss": 0.0198, |
| "step": 625 |
| }, |
| { |
| "epoch": 1.1305, |
| "grad_norm": 2.222632884979248, |
| "learning_rate": 9e-06, |
| "loss": 0.0167, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.143, |
| "grad_norm": 1.1213107109069824, |
| "learning_rate": 8.833333333333334e-06, |
| "loss": 0.015, |
| "step": 675 |
| }, |
| { |
| "epoch": 1.1555, |
| "grad_norm": 3.053809642791748, |
| "learning_rate": 8.666666666666668e-06, |
| "loss": 0.0123, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.168, |
| "grad_norm": 3.0312676429748535, |
| "learning_rate": 8.5e-06, |
| "loss": 0.0135, |
| "step": 725 |
| }, |
| { |
| "epoch": 1.1804999999999999, |
| "grad_norm": 1.2940341234207153, |
| "learning_rate": 8.333333333333334e-06, |
| "loss": 0.0152, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.193, |
| "grad_norm": 1.9949597120285034, |
| "learning_rate": 8.166666666666668e-06, |
| "loss": 0.015, |
| "step": 775 |
| }, |
| { |
| "epoch": 2.011, |
| "grad_norm": 1.2895445823669434, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.0251, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.0235, |
| "grad_norm": 1.7078819274902344, |
| "learning_rate": 7.833333333333333e-06, |
| "loss": 0.0159, |
| "step": 825 |
| }, |
| { |
| "epoch": 2.036, |
| "grad_norm": 0.7963767647743225, |
| "learning_rate": 7.666666666666667e-06, |
| "loss": 0.0158, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.0485, |
| "grad_norm": 1.2390975952148438, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.0141, |
| "step": 875 |
| }, |
| { |
| "epoch": 2.061, |
| "grad_norm": 1.4780830144882202, |
| "learning_rate": 7.333333333333333e-06, |
| "loss": 0.0112, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.0735, |
| "grad_norm": 0.7993568778038025, |
| "learning_rate": 7.166666666666667e-06, |
| "loss": 0.0118, |
| "step": 925 |
| }, |
| { |
| "epoch": 2.086, |
| "grad_norm": 1.1336815357208252, |
| "learning_rate": 7e-06, |
| "loss": 0.0089, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.0985, |
| "grad_norm": 1.7068537473678589, |
| "learning_rate": 6.833333333333334e-06, |
| "loss": 0.0107, |
| "step": 975 |
| }, |
| { |
| "epoch": 2.111, |
| "grad_norm": 1.4282974004745483, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.0117, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.111, |
| "eval_loss": 0.15551722049713135, |
| "eval_runtime": 621.1845, |
| "eval_samples_per_second": 1.025, |
| "eval_steps_per_second": 0.129, |
| "eval_wer": 33.69881109643329, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.1235, |
| "grad_norm": 2.979623317718506, |
| "learning_rate": 6.5000000000000004e-06, |
| "loss": 0.0111, |
| "step": 1025 |
| }, |
| { |
| "epoch": 2.136, |
| "grad_norm": 2.2827956676483154, |
| "learning_rate": 6.333333333333333e-06, |
| "loss": 0.0137, |
| "step": 1050 |
| }, |
| { |
| "epoch": 2.1485, |
| "grad_norm": 1.0386461019515991, |
| "learning_rate": 6.166666666666667e-06, |
| "loss": 0.0102, |
| "step": 1075 |
| }, |
| { |
| "epoch": 2.161, |
| "grad_norm": 1.0650137662887573, |
| "learning_rate": 6e-06, |
| "loss": 0.0104, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.1734999999999998, |
| "grad_norm": 1.1739250421524048, |
| "learning_rate": 5.833333333333334e-06, |
| "loss": 0.0115, |
| "step": 1125 |
| }, |
| { |
| "epoch": 2.186, |
| "grad_norm": 1.6481997966766357, |
| "learning_rate": 5.666666666666667e-06, |
| "loss": 0.0096, |
| "step": 1150 |
| }, |
| { |
| "epoch": 3.004, |
| "grad_norm": 1.7796248197555542, |
| "learning_rate": 5.500000000000001e-06, |
| "loss": 0.0166, |
| "step": 1175 |
| }, |
| { |
| "epoch": 3.0165, |
| "grad_norm": 1.6211556196212769, |
| "learning_rate": 5.333333333333334e-06, |
| "loss": 0.0125, |
| "step": 1200 |
| }, |
| { |
| "epoch": 3.029, |
| "grad_norm": 1.1395519971847534, |
| "learning_rate": 5.1666666666666675e-06, |
| "loss": 0.008, |
| "step": 1225 |
| }, |
| { |
| "epoch": 3.0415, |
| "grad_norm": 0.41915813088417053, |
| "learning_rate": 5e-06, |
| "loss": 0.007, |
| "step": 1250 |
| }, |
| { |
| "epoch": 3.054, |
| "grad_norm": 2.371992588043213, |
| "learning_rate": 4.833333333333333e-06, |
| "loss": 0.0056, |
| "step": 1275 |
| }, |
| { |
| "epoch": 3.0665, |
| "grad_norm": 0.7025607824325562, |
| "learning_rate": 4.666666666666667e-06, |
| "loss": 0.0051, |
| "step": 1300 |
| }, |
| { |
| "epoch": 3.079, |
| "grad_norm": 0.7528577446937561, |
| "learning_rate": 4.5e-06, |
| "loss": 0.0044, |
| "step": 1325 |
| }, |
| { |
| "epoch": 3.0915, |
| "grad_norm": 0.7671001553535461, |
| "learning_rate": 4.333333333333334e-06, |
| "loss": 0.0035, |
| "step": 1350 |
| }, |
| { |
| "epoch": 3.104, |
| "grad_norm": 1.1365867853164673, |
| "learning_rate": 4.166666666666667e-06, |
| "loss": 0.0053, |
| "step": 1375 |
| }, |
| { |
| "epoch": 3.1165, |
| "grad_norm": 0.31649962067604065, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0057, |
| "step": 1400 |
| }, |
| { |
| "epoch": 3.129, |
| "grad_norm": 0.866807758808136, |
| "learning_rate": 3.833333333333334e-06, |
| "loss": 0.0059, |
| "step": 1425 |
| }, |
| { |
| "epoch": 3.1415, |
| "grad_norm": 0.9588886499404907, |
| "learning_rate": 3.6666666666666666e-06, |
| "loss": 0.0061, |
| "step": 1450 |
| }, |
| { |
| "epoch": 3.154, |
| "grad_norm": 0.5269432663917542, |
| "learning_rate": 3.5e-06, |
| "loss": 0.0042, |
| "step": 1475 |
| }, |
| { |
| "epoch": 3.1665, |
| "grad_norm": 1.0368000268936157, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.0044, |
| "step": 1500 |
| }, |
| { |
| "epoch": 3.179, |
| "grad_norm": 0.9669756889343262, |
| "learning_rate": 3.1666666666666667e-06, |
| "loss": 0.0051, |
| "step": 1525 |
| }, |
| { |
| "epoch": 3.1915, |
| "grad_norm": 1.1753712892532349, |
| "learning_rate": 3e-06, |
| "loss": 0.0037, |
| "step": 1550 |
| }, |
| { |
| "epoch": 4.0095, |
| "grad_norm": 0.7525417804718018, |
| "learning_rate": 2.8333333333333335e-06, |
| "loss": 0.0073, |
| "step": 1575 |
| }, |
| { |
| "epoch": 4.022, |
| "grad_norm": 0.36638399958610535, |
| "learning_rate": 2.666666666666667e-06, |
| "loss": 0.0048, |
| "step": 1600 |
| }, |
| { |
| "epoch": 4.0345, |
| "grad_norm": 0.5773335099220276, |
| "learning_rate": 2.5e-06, |
| "loss": 0.0031, |
| "step": 1625 |
| }, |
| { |
| "epoch": 4.047, |
| "grad_norm": 0.44142794609069824, |
| "learning_rate": 2.3333333333333336e-06, |
| "loss": 0.0022, |
| "step": 1650 |
| }, |
| { |
| "epoch": 4.0595, |
| "grad_norm": 0.3425196409225464, |
| "learning_rate": 2.166666666666667e-06, |
| "loss": 0.0019, |
| "step": 1675 |
| }, |
| { |
| "epoch": 4.072, |
| "grad_norm": 0.23644089698791504, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.0019, |
| "step": 1700 |
| }, |
| { |
| "epoch": 4.0845, |
| "grad_norm": 0.29089945554733276, |
| "learning_rate": 1.8333333333333333e-06, |
| "loss": 0.0013, |
| "step": 1725 |
| }, |
| { |
| "epoch": 4.097, |
| "grad_norm": 1.356613278388977, |
| "learning_rate": 1.6666666666666667e-06, |
| "loss": 0.0017, |
| "step": 1750 |
| }, |
| { |
| "epoch": 4.1095, |
| "grad_norm": 0.5859806537628174, |
| "learning_rate": 1.5e-06, |
| "loss": 0.0024, |
| "step": 1775 |
| }, |
| { |
| "epoch": 4.122, |
| "grad_norm": 0.4378674626350403, |
| "learning_rate": 1.3333333333333334e-06, |
| "loss": 0.0027, |
| "step": 1800 |
| }, |
| { |
| "epoch": 4.1345, |
| "grad_norm": 0.46167829632759094, |
| "learning_rate": 1.1666666666666668e-06, |
| "loss": 0.0025, |
| "step": 1825 |
| }, |
| { |
| "epoch": 4.147, |
| "grad_norm": 0.41351112723350525, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.0024, |
| "step": 1850 |
| }, |
| { |
| "epoch": 4.1595, |
| "grad_norm": 0.35589855909347534, |
| "learning_rate": 8.333333333333333e-07, |
| "loss": 0.0019, |
| "step": 1875 |
| }, |
| { |
| "epoch": 4.172, |
| "grad_norm": 1.8024345636367798, |
| "learning_rate": 6.666666666666667e-07, |
| "loss": 0.0018, |
| "step": 1900 |
| }, |
| { |
| "epoch": 4.1845, |
| "grad_norm": 0.5813783407211304, |
| "learning_rate": 5.000000000000001e-07, |
| "loss": 0.0013, |
| "step": 1925 |
| }, |
| { |
| "epoch": 5.0025, |
| "grad_norm": 0.9400327205657959, |
| "learning_rate": 3.3333333333333335e-07, |
| "loss": 0.0023, |
| "step": 1950 |
| }, |
| { |
| "epoch": 5.015, |
| "grad_norm": 0.6248894333839417, |
| "learning_rate": 1.6666666666666668e-07, |
| "loss": 0.0046, |
| "step": 1975 |
| }, |
| { |
| "epoch": 5.0275, |
| "grad_norm": 0.5471067428588867, |
| "learning_rate": 0.0, |
| "loss": 0.0022, |
| "step": 2000 |
| }, |
| { |
| "epoch": 5.0275, |
| "eval_loss": 0.1518355756998062, |
| "eval_runtime": 632.1111, |
| "eval_samples_per_second": 1.008, |
| "eval_steps_per_second": 0.127, |
| "eval_wer": 30.297225891677677, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "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": 9.2217464672256e+18, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
