| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 10880, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.37, |
| "eval_loss": 0.9124094247817993, |
| "eval_runtime": 151.7243, |
| "eval_samples_per_second": 17.044, |
| "eval_steps_per_second": 2.135, |
| "eval_wer": 0.7336481700118064, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0002982, |
| "loss": 3.904, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.74, |
| "eval_loss": 0.4753111004829407, |
| "eval_runtime": 151.0266, |
| "eval_samples_per_second": 17.123, |
| "eval_steps_per_second": 2.145, |
| "eval_wer": 0.5022038567493113, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.000285635838150289, |
| "loss": 0.4384, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.1, |
| "eval_loss": 0.3940904438495636, |
| "eval_runtime": 151.5781, |
| "eval_samples_per_second": 17.061, |
| "eval_steps_per_second": 2.138, |
| "eval_wer": 0.3730814639905549, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00027118497109826587, |
| "loss": 0.2985, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.47, |
| "eval_loss": 0.40066808462142944, |
| "eval_runtime": 151.8065, |
| "eval_samples_per_second": 17.035, |
| "eval_steps_per_second": 2.134, |
| "eval_wer": 0.3829988193624557, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.00025673410404624276, |
| "loss": 0.2719, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.84, |
| "eval_loss": 0.35764721035957336, |
| "eval_runtime": 151.6256, |
| "eval_samples_per_second": 17.055, |
| "eval_steps_per_second": 2.137, |
| "eval_wer": 0.3597009051554506, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.21, |
| "eval_loss": 0.3570806384086609, |
| "eval_runtime": 151.5024, |
| "eval_samples_per_second": 17.069, |
| "eval_steps_per_second": 2.139, |
| "eval_wer": 0.32857142857142857, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 0.00024228323699421964, |
| "loss": 0.2158, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.57, |
| "eval_loss": 0.3464970290660858, |
| "eval_runtime": 151.87, |
| "eval_samples_per_second": 17.028, |
| "eval_steps_per_second": 2.133, |
| "eval_wer": 0.3197560015741834, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 0.00022783236994219653, |
| "loss": 0.2054, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.94, |
| "eval_loss": 0.3161996603012085, |
| "eval_runtime": 151.7631, |
| "eval_samples_per_second": 17.04, |
| "eval_steps_per_second": 2.135, |
| "eval_wer": 0.29818968909878, |
| "step": 3200 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 0.00021338150289017341, |
| "loss": 0.1783, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.31, |
| "eval_loss": 0.32945507764816284, |
| "eval_runtime": 151.3693, |
| "eval_samples_per_second": 17.084, |
| "eval_steps_per_second": 2.14, |
| "eval_wer": 0.3089334907516726, |
| "step": 3600 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 0.0001989306358381503, |
| "loss": 0.1495, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.68, |
| "eval_loss": 0.32478460669517517, |
| "eval_runtime": 151.7198, |
| "eval_samples_per_second": 17.045, |
| "eval_steps_per_second": 2.136, |
| "eval_wer": 0.3033844942935852, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.04, |
| "eval_loss": 0.31009042263031006, |
| "eval_runtime": 152.1775, |
| "eval_samples_per_second": 16.993, |
| "eval_steps_per_second": 2.129, |
| "eval_wer": 0.30275482093663914, |
| "step": 4400 |
| }, |
| { |
| "epoch": 4.14, |
| "learning_rate": 0.00018447976878612713, |
| "loss": 0.1397, |
| "step": 4500 |
| }, |
| { |
| "epoch": 4.41, |
| "eval_loss": 0.3587653338909149, |
| "eval_runtime": 154.3439, |
| "eval_samples_per_second": 16.755, |
| "eval_steps_per_second": 2.099, |
| "eval_wer": 0.3005509641873278, |
| "step": 4800 |
| }, |
| { |
| "epoch": 4.6, |
| "learning_rate": 0.00017002890173410402, |
| "loss": 0.123, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.78, |
| "eval_loss": 0.34509825706481934, |
| "eval_runtime": 151.8759, |
| "eval_samples_per_second": 17.027, |
| "eval_steps_per_second": 2.133, |
| "eval_wer": 0.30405352223534043, |
| "step": 5200 |
| }, |
| { |
| "epoch": 5.06, |
| "learning_rate": 0.0001555780346820809, |
| "loss": 0.115, |
| "step": 5500 |
| }, |
| { |
| "epoch": 5.15, |
| "eval_loss": 0.33334314823150635, |
| "eval_runtime": 152.7065, |
| "eval_samples_per_second": 16.934, |
| "eval_steps_per_second": 2.122, |
| "eval_wer": 0.2921290830381739, |
| "step": 5600 |
| }, |
| { |
| "epoch": 5.51, |
| "learning_rate": 0.0001411271676300578, |
| "loss": 0.0947, |
| "step": 6000 |
| }, |
| { |
| "epoch": 5.51, |
| "eval_loss": 0.3331167697906494, |
| "eval_runtime": 153.2633, |
| "eval_samples_per_second": 16.873, |
| "eval_steps_per_second": 2.114, |
| "eval_wer": 0.285792994883904, |
| "step": 6000 |
| }, |
| { |
| "epoch": 5.88, |
| "eval_loss": 0.35364603996276855, |
| "eval_runtime": 152.0713, |
| "eval_samples_per_second": 17.005, |
| "eval_steps_per_second": 2.131, |
| "eval_wer": 0.2950019677292405, |
| "step": 6400 |
| }, |
| { |
| "epoch": 5.97, |
| "learning_rate": 0.00012667630057803468, |
| "loss": 0.0952, |
| "step": 6500 |
| }, |
| { |
| "epoch": 6.25, |
| "eval_loss": 0.334403395652771, |
| "eval_runtime": 153.3648, |
| "eval_samples_per_second": 16.862, |
| "eval_steps_per_second": 2.113, |
| "eval_wer": 0.2785911058638331, |
| "step": 6800 |
| }, |
| { |
| "epoch": 6.43, |
| "learning_rate": 0.00011222543352601155, |
| "loss": 0.0778, |
| "step": 7000 |
| }, |
| { |
| "epoch": 6.62, |
| "eval_loss": 0.3363187313079834, |
| "eval_runtime": 153.0496, |
| "eval_samples_per_second": 16.896, |
| "eval_steps_per_second": 2.117, |
| "eval_wer": 0.2698543880362062, |
| "step": 7200 |
| }, |
| { |
| "epoch": 6.89, |
| "learning_rate": 9.777456647398842e-05, |
| "loss": 0.0744, |
| "step": 7500 |
| }, |
| { |
| "epoch": 6.99, |
| "eval_loss": 0.3245686888694763, |
| "eval_runtime": 151.5563, |
| "eval_samples_per_second": 17.063, |
| "eval_steps_per_second": 2.138, |
| "eval_wer": 0.2655253837072019, |
| "step": 7600 |
| }, |
| { |
| "epoch": 7.35, |
| "learning_rate": 8.33236994219653e-05, |
| "loss": 0.0648, |
| "step": 8000 |
| }, |
| { |
| "epoch": 7.35, |
| "eval_loss": 0.33904263377189636, |
| "eval_runtime": 152.0758, |
| "eval_samples_per_second": 17.005, |
| "eval_steps_per_second": 2.131, |
| "eval_wer": 0.2626918536009445, |
| "step": 8000 |
| }, |
| { |
| "epoch": 7.72, |
| "eval_loss": 0.3405352532863617, |
| "eval_runtime": 151.6808, |
| "eval_samples_per_second": 17.049, |
| "eval_steps_per_second": 2.136, |
| "eval_wer": 0.26300669027941753, |
| "step": 8400 |
| }, |
| { |
| "epoch": 7.81, |
| "learning_rate": 6.887283236994219e-05, |
| "loss": 0.0591, |
| "step": 8500 |
| }, |
| { |
| "epoch": 8.09, |
| "eval_loss": 0.3366956114768982, |
| "eval_runtime": 152.0044, |
| "eval_samples_per_second": 17.013, |
| "eval_steps_per_second": 2.132, |
| "eval_wer": 0.25340417158598977, |
| "step": 8800 |
| }, |
| { |
| "epoch": 8.27, |
| "learning_rate": 5.445086705202312e-05, |
| "loss": 0.0527, |
| "step": 9000 |
| }, |
| { |
| "epoch": 8.46, |
| "eval_loss": 0.3448215126991272, |
| "eval_runtime": 151.6214, |
| "eval_samples_per_second": 17.056, |
| "eval_steps_per_second": 2.137, |
| "eval_wer": 0.2509248327430146, |
| "step": 9200 |
| }, |
| { |
| "epoch": 8.73, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": 0.0461, |
| "step": 9500 |
| }, |
| { |
| "epoch": 8.82, |
| "eval_loss": 0.3378887474536896, |
| "eval_runtime": 151.4481, |
| "eval_samples_per_second": 17.075, |
| "eval_steps_per_second": 2.139, |
| "eval_wer": 0.24254230617866981, |
| "step": 9600 |
| }, |
| { |
| "epoch": 9.19, |
| "learning_rate": 2.554913294797688e-05, |
| "loss": 0.0408, |
| "step": 10000 |
| }, |
| { |
| "epoch": 9.19, |
| "eval_loss": 0.34909504652023315, |
| "eval_runtime": 151.2414, |
| "eval_samples_per_second": 17.098, |
| "eval_steps_per_second": 2.142, |
| "eval_wer": 0.24092876820149547, |
| "step": 10000 |
| }, |
| { |
| "epoch": 9.56, |
| "eval_loss": 0.3456341028213501, |
| "eval_runtime": 151.2228, |
| "eval_samples_per_second": 17.101, |
| "eval_steps_per_second": 2.143, |
| "eval_wer": 0.23774104683195593, |
| "step": 10400 |
| }, |
| { |
| "epoch": 9.65, |
| "learning_rate": 1.1098265895953756e-05, |
| "loss": 0.0393, |
| "step": 10500 |
| }, |
| { |
| "epoch": 9.93, |
| "eval_loss": 0.34881335496902466, |
| "eval_runtime": 151.3922, |
| "eval_samples_per_second": 17.081, |
| "eval_steps_per_second": 2.14, |
| "eval_wer": 0.23695395513577333, |
| "step": 10800 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 10880, |
| "total_flos": 1.3810821820032008e+19, |
| "train_loss": 0.30854525013881573, |
| "train_runtime": 13756.3958, |
| "train_samples_per_second": 6.326, |
| "train_steps_per_second": 0.791 |
| } |
| ], |
| "max_steps": 10880, |
| "num_train_epochs": 10, |
| "total_flos": 1.3810821820032008e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
