| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.932689343335731, | |
| "global_step": 48000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.6874999999999996e-07, | |
| "loss": 0.2448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.374999999999999e-07, | |
| "loss": 0.2401, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.4062499999999999e-06, | |
| "loss": 0.241, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.8749999999999998e-06, | |
| "loss": 0.2391, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.34375e-06, | |
| "loss": 0.2395, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.8124999999999998e-06, | |
| "loss": 0.2393, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.2812499999999997e-06, | |
| "loss": 0.2307, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.7499999999999997e-06, | |
| "loss": 0.2355, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.21875e-06, | |
| "loss": 0.2422, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.6875e-06, | |
| "loss": 0.2317, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.15625e-06, | |
| "loss": 0.2429, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.6249999999999995e-06, | |
| "loss": 0.235, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.09375e-06, | |
| "loss": 0.2305, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 6.5624999999999994e-06, | |
| "loss": 0.2413, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.03125e-06, | |
| "loss": 0.2412, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.2294, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 7.968749999999999e-06, | |
| "loss": 0.2303, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 8.4375e-06, | |
| "loss": 0.2348, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 8.90625e-06, | |
| "loss": 0.2403, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.375e-06, | |
| "loss": 0.2355, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.843749999999999e-06, | |
| "loss": 0.2424, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.03125e-05, | |
| "loss": 0.24, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.0781249999999998e-05, | |
| "loss": 0.2383, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.1249999999999999e-05, | |
| "loss": 0.2377, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.1718749999999999e-05, | |
| "loss": 0.2456, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.21875e-05, | |
| "loss": 0.2433, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.265625e-05, | |
| "loss": 0.2413, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.3124999999999999e-05, | |
| "loss": 0.2357, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.3593749999999998e-05, | |
| "loss": 0.2381, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.40625e-05, | |
| "loss": 0.2362, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.4531249999999999e-05, | |
| "loss": 0.2447, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.2397, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5468749999999997e-05, | |
| "loss": 0.2447, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.5937499999999998e-05, | |
| "loss": 0.2444, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.640625e-05, | |
| "loss": 0.2363, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.6875e-05, | |
| "loss": 0.2522, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.7343749999999998e-05, | |
| "loss": 0.2493, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.78125e-05, | |
| "loss": 0.2453, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8281249999999997e-05, | |
| "loss": 0.243, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.875e-05, | |
| "loss": 0.2449, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9218749999999996e-05, | |
| "loss": 0.2568, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.9687499999999997e-05, | |
| "loss": 0.2407, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.015625e-05, | |
| "loss": 0.2357, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 0.2508, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.1093749999999998e-05, | |
| "loss": 0.244, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.1562499999999996e-05, | |
| "loss": 0.2413, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.203125e-05, | |
| "loss": 0.245, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.2477, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.296875e-05, | |
| "loss": 0.2511, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.3437499999999997e-05, | |
| "loss": 0.2423, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.3906249999999995e-05, | |
| "loss": 0.2529, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.4375e-05, | |
| "loss": 0.2423, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.4843749999999997e-05, | |
| "loss": 0.2602, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.53125e-05, | |
| "loss": 0.2578, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.5781249999999996e-05, | |
| "loss": 0.2446, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.6249999999999998e-05, | |
| "loss": 0.2473, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.671875e-05, | |
| "loss": 0.2498, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.7187499999999997e-05, | |
| "loss": 0.2634, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.7656249999999998e-05, | |
| "loss": 0.2506, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.8125e-05, | |
| "loss": 0.256, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.8593749999999997e-05, | |
| "loss": 0.239, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.9062499999999998e-05, | |
| "loss": 0.2541, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.9531249999999996e-05, | |
| "loss": 0.2583, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.2469, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.046875e-05, | |
| "loss": 0.2521, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.093749999999999e-05, | |
| "loss": 0.2511, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.140625e-05, | |
| "loss": 0.252, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.1874999999999996e-05, | |
| "loss": 0.2471, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.234375e-05, | |
| "loss": 0.2499, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.28125e-05, | |
| "loss": 0.2542, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.328124999999999e-05, | |
| "loss": 0.256, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.375e-05, | |
| "loss": 0.2563, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.4218749999999995e-05, | |
| "loss": 0.2522, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.4687499999999996e-05, | |
| "loss": 0.2588, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.515625e-05, | |
| "loss": 0.2467, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.5625e-05, | |
| "loss": 0.2696, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.609375e-05, | |
| "loss": 0.2486, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.6562499999999994e-05, | |
| "loss": 0.2517, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.7031249999999995e-05, | |
| "loss": 0.2504, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.2483, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.510062575340271, | |
| "eval_runtime": 210.5866, | |
| "eval_samples_per_second": 24.337, | |
| "eval_steps_per_second": 0.385, | |
| "eval_wer": 29.214995021394547, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.745738636363636e-05, | |
| "loss": 0.2503, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.7414772727272724e-05, | |
| "loss": 0.2533, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.737215909090909e-05, | |
| "loss": 0.2497, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.732954545454545e-05, | |
| "loss": 0.2445, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.7286931818181814e-05, | |
| "loss": 0.2421, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.724431818181818e-05, | |
| "loss": 0.2491, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.720170454545454e-05, | |
| "loss": 0.2464, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3.7159090909090905e-05, | |
| "loss": 0.2466, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.711647727272727e-05, | |
| "loss": 0.2484, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.707386363636363e-05, | |
| "loss": 0.2472, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.7031249999999995e-05, | |
| "loss": 0.2391, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3.698863636363636e-05, | |
| "loss": 0.2567, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3.694602272727272e-05, | |
| "loss": 0.2413, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 3.6903409090909086e-05, | |
| "loss": 0.2564, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3.686079545454545e-05, | |
| "loss": 0.2454, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3.681818181818181e-05, | |
| "loss": 0.2459, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3.677556818181818e-05, | |
| "loss": 0.2345, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3.673295454545454e-05, | |
| "loss": 0.2472, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 3.6690340909090904e-05, | |
| "loss": 0.2439, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 3.664772727272727e-05, | |
| "loss": 0.2432, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3.660511363636364e-05, | |
| "loss": 0.2439, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3.6562499999999994e-05, | |
| "loss": 0.2349, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.651988636363636e-05, | |
| "loss": 0.2431, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3.647727272727273e-05, | |
| "loss": 0.2448, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.6434659090909085e-05, | |
| "loss": 0.2238, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3.639204545454545e-05, | |
| "loss": 0.2324, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 3.634943181818182e-05, | |
| "loss": 0.2433, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 3.6306818181818175e-05, | |
| "loss": 0.24, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3.626420454545454e-05, | |
| "loss": 0.2361, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.622159090909091e-05, | |
| "loss": 0.2386, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 3.6178977272727266e-05, | |
| "loss": 0.2316, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.613636363636363e-05, | |
| "loss": 0.2363, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3.609375e-05, | |
| "loss": 0.2363, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.6051136363636357e-05, | |
| "loss": 0.2405, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3.600852272727272e-05, | |
| "loss": 0.232, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.596590909090909e-05, | |
| "loss": 0.2337, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.5923295454545454e-05, | |
| "loss": 0.2306, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.588068181818181e-05, | |
| "loss": 0.2261, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.583806818181818e-05, | |
| "loss": 0.2338, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.5795454545454544e-05, | |
| "loss": 0.2262, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.57528409090909e-05, | |
| "loss": 0.2246, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.571022727272727e-05, | |
| "loss": 0.2154, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.5667613636363635e-05, | |
| "loss": 0.2041, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.5625e-05, | |
| "loss": 0.1884, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.558238636363636e-05, | |
| "loss": 0.1841, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.5539772727272726e-05, | |
| "loss": 0.4209, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.549715909090909e-05, | |
| "loss": 0.4194, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.545454545454545e-05, | |
| "loss": 0.403, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.5411931818181816e-05, | |
| "loss": 0.3963, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.536931818181818e-05, | |
| "loss": 0.3775, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.532670454545454e-05, | |
| "loss": 0.3718, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.528409090909091e-05, | |
| "loss": 0.3681, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.524147727272727e-05, | |
| "loss": 0.364, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.5198863636363634e-05, | |
| "loss": 0.3699, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.515625e-05, | |
| "loss": 0.3366, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.511363636363636e-05, | |
| "loss": 0.3539, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.5071022727272724e-05, | |
| "loss": 0.3541, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.502840909090909e-05, | |
| "loss": 0.3544, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.498579545454545e-05, | |
| "loss": 0.3496, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.4943181818181815e-05, | |
| "loss": 0.3319, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.490056818181818e-05, | |
| "loss": 0.335, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.485795454545454e-05, | |
| "loss": 0.3379, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.4815340909090906e-05, | |
| "loss": 0.3369, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.477272727272727e-05, | |
| "loss": 0.3403, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.473011363636363e-05, | |
| "loss": 0.3248, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.4687499999999996e-05, | |
| "loss": 0.3337, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.464488636363636e-05, | |
| "loss": 0.3231, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.460227272727272e-05, | |
| "loss": 0.3422, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.455965909090909e-05, | |
| "loss": 0.3265, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.451704545454545e-05, | |
| "loss": 0.3259, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.4474431818181814e-05, | |
| "loss": 0.3349, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.443181818181818e-05, | |
| "loss": 0.3232, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.438920454545454e-05, | |
| "loss": 0.3204, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.4346590909090904e-05, | |
| "loss": 0.3261, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.430397727272727e-05, | |
| "loss": 0.3254, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.426136363636364e-05, | |
| "loss": 0.3144, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.4218749999999995e-05, | |
| "loss": 0.3178, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.417613636363636e-05, | |
| "loss": 0.3269, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.413352272727273e-05, | |
| "loss": 0.3243, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.4090909090909085e-05, | |
| "loss": 0.3201, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.40532994270324707, | |
| "eval_runtime": 225.1223, | |
| "eval_samples_per_second": 22.765, | |
| "eval_steps_per_second": 0.36, | |
| "eval_wer": 27.403859092010013, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.404829545454545e-05, | |
| "loss": 0.3183, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.400568181818182e-05, | |
| "loss": 0.3164, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.3963068181818176e-05, | |
| "loss": 0.3301, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.392045454545454e-05, | |
| "loss": 0.3193, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.387784090909091e-05, | |
| "loss": 0.3217, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.3835227272727267e-05, | |
| "loss": 0.3121, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.379261363636363e-05, | |
| "loss": 0.3173, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.375e-05, | |
| "loss": 0.3171, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.370738636363636e-05, | |
| "loss": 0.3144, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.366477272727272e-05, | |
| "loss": 0.324, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.362215909090909e-05, | |
| "loss": 0.3175, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.3579545454545455e-05, | |
| "loss": 0.3127, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.353693181818181e-05, | |
| "loss": 0.309, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.349431818181818e-05, | |
| "loss": 0.3062, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.3451704545454545e-05, | |
| "loss": 0.3089, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.34090909090909e-05, | |
| "loss": 0.2998, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.336647727272727e-05, | |
| "loss": 0.3129, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.3323863636363636e-05, | |
| "loss": 0.2978, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.328124999999999e-05, | |
| "loss": 0.3011, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.323863636363636e-05, | |
| "loss": 0.304, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.3196022727272726e-05, | |
| "loss": 0.3073, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.315340909090908e-05, | |
| "loss": 0.2957, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.311079545454545e-05, | |
| "loss": 0.2965, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.306818181818182e-05, | |
| "loss": 0.3015, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 3.302556818181818e-05, | |
| "loss": 0.2987, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2982954545454544e-05, | |
| "loss": 0.2952, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.294034090909091e-05, | |
| "loss": 0.3015, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.289772727272727e-05, | |
| "loss": 0.4771, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.2855113636363634e-05, | |
| "loss": 0.4538, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.28125e-05, | |
| "loss": 0.4492, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.276988636363636e-05, | |
| "loss": 0.4205, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.2727272727272725e-05, | |
| "loss": 0.4207, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.268465909090909e-05, | |
| "loss": 0.3968, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.264204545454545e-05, | |
| "loss": 0.3893, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.2599431818181816e-05, | |
| "loss": 0.3473, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.255681818181818e-05, | |
| "loss": 0.2456, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.251420454545454e-05, | |
| "loss": 0.2337, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.2471590909090906e-05, | |
| "loss": 0.2371, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.242897727272727e-05, | |
| "loss": 0.2308, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.238636363636363e-05, | |
| "loss": 0.233, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.234375e-05, | |
| "loss": 0.2293, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.230113636363636e-05, | |
| "loss": 0.2225, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.2258522727272724e-05, | |
| "loss": 0.2348, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.221590909090909e-05, | |
| "loss": 0.2199, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.217329545454545e-05, | |
| "loss": 0.2233, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.2130681818181814e-05, | |
| "loss": 0.2165, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3.208806818181818e-05, | |
| "loss": 0.2204, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.204545454545454e-05, | |
| "loss": 0.2111, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.2002840909090905e-05, | |
| "loss": 0.2233, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.196022727272727e-05, | |
| "loss": 0.213, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.191761363636364e-05, | |
| "loss": 0.2096, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.1874999999999996e-05, | |
| "loss": 0.2022, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.183238636363636e-05, | |
| "loss": 0.2056, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.178977272727273e-05, | |
| "loss": 0.2124, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.1747159090909086e-05, | |
| "loss": 0.2058, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.170454545454545e-05, | |
| "loss": 0.2119, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.166193181818182e-05, | |
| "loss": 0.2081, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.161931818181818e-05, | |
| "loss": 0.2031, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.157670454545454e-05, | |
| "loss": 0.205, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.153409090909091e-05, | |
| "loss": 0.2058, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.149147727272727e-05, | |
| "loss": 0.2062, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.144886363636363e-05, | |
| "loss": 0.1977, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.140625e-05, | |
| "loss": 0.1972, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.136363636363636e-05, | |
| "loss": 0.193, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.132102272727272e-05, | |
| "loss": 0.2014, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 3.127840909090909e-05, | |
| "loss": 0.1944, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.1235795454545455e-05, | |
| "loss": 0.202, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.119318181818181e-05, | |
| "loss": 0.1921, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.115056818181818e-05, | |
| "loss": 0.1979, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.1107954545454546e-05, | |
| "loss": 0.1931, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.10653409090909e-05, | |
| "loss": 0.204, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.102272727272727e-05, | |
| "loss": 0.1963, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.0980113636363636e-05, | |
| "loss": 0.1962, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.093749999999999e-05, | |
| "loss": 0.1906, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.089488636363636e-05, | |
| "loss": 0.1972, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3.085227272727273e-05, | |
| "loss": 0.1956, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.0809659090909084e-05, | |
| "loss": 0.1797, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.0767045454545454e-05, | |
| "loss": 0.1913, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.072443181818182e-05, | |
| "loss": 0.1846, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.068181818181818e-05, | |
| "loss": 0.1867, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 0.41450875997543335, | |
| "eval_runtime": 215.2123, | |
| "eval_samples_per_second": 23.814, | |
| "eval_steps_per_second": 0.376, | |
| "eval_wer": 24.724831131085338, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.0639204545454545e-05, | |
| "loss": 0.1838, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.059659090909091e-05, | |
| "loss": 0.1867, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.055397727272727e-05, | |
| "loss": 0.1896, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.051136363636363e-05, | |
| "loss": 0.1789, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.046875e-05, | |
| "loss": 0.1879, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.0426136363636362e-05, | |
| "loss": 0.1915, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.0383522727272722e-05, | |
| "loss": 0.1809, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.034090909090909e-05, | |
| "loss": 0.1954, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.0298295454545453e-05, | |
| "loss": 0.1842, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.0255681818181813e-05, | |
| "loss": 0.1839, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.021306818181818e-05, | |
| "loss": 0.1801, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3.0170454545454543e-05, | |
| "loss": 0.1905, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.0127840909090907e-05, | |
| "loss": 0.19, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.008522727272727e-05, | |
| "loss": 0.1825, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.0042613636363634e-05, | |
| "loss": 0.184, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.1708, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.995738636363636e-05, | |
| "loss": 0.1882, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.9914772727272724e-05, | |
| "loss": 0.178, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.987215909090909e-05, | |
| "loss": 0.1768, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.982954545454545e-05, | |
| "loss": 0.1817, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 2.9786931818181815e-05, | |
| "loss": 0.1806, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.9744318181818182e-05, | |
| "loss": 0.176, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.9701704545454542e-05, | |
| "loss": 0.1719, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.9659090909090906e-05, | |
| "loss": 0.1773, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 2.9616477272727272e-05, | |
| "loss": 0.183, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.9573863636363636e-05, | |
| "loss": 0.1768, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.9531249999999996e-05, | |
| "loss": 0.177, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.9488636363636363e-05, | |
| "loss": 0.1757, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.9446022727272727e-05, | |
| "loss": 0.1771, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9403409090909087e-05, | |
| "loss": 0.1848, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9360795454545454e-05, | |
| "loss": 0.1758, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.9318181818181817e-05, | |
| "loss": 0.1717, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.9275568181818177e-05, | |
| "loss": 0.165, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9232954545454544e-05, | |
| "loss": 0.1685, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9190340909090908e-05, | |
| "loss": 0.1723, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9147727272727268e-05, | |
| "loss": 0.1719, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9105113636363635e-05, | |
| "loss": 0.1671, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9062499999999998e-05, | |
| "loss": 0.1696, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.901988636363636e-05, | |
| "loss": 0.1634, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.8977272727272725e-05, | |
| "loss": 0.1713, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.893465909090909e-05, | |
| "loss": 0.1681, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8892045454545452e-05, | |
| "loss": 0.1638, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8849431818181816e-05, | |
| "loss": 0.163, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.880681818181818e-05, | |
| "loss": 0.1767, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.8764204545454543e-05, | |
| "loss": 0.1599, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8721590909090906e-05, | |
| "loss": 0.1675, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.867897727272727e-05, | |
| "loss": 0.1737, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8636363636363634e-05, | |
| "loss": 0.1664, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8593749999999997e-05, | |
| "loss": 0.1747, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.855113636363636e-05, | |
| "loss": 0.1685, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.8508522727272724e-05, | |
| "loss": 0.1639, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.8465909090909088e-05, | |
| "loss": 0.1628, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.842329545454545e-05, | |
| "loss": 0.1645, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.8380681818181815e-05, | |
| "loss": 0.172, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.833806818181818e-05, | |
| "loss": 0.1702, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.8295454545454542e-05, | |
| "loss": 0.1648, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.8252840909090905e-05, | |
| "loss": 0.1599, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.8210227272727272e-05, | |
| "loss": 0.169, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.8167613636363632e-05, | |
| "loss": 0.1658, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.8125e-05, | |
| "loss": 0.1546, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.8082386363636363e-05, | |
| "loss": 0.1597, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.8039772727272723e-05, | |
| "loss": 0.1672, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.799715909090909e-05, | |
| "loss": 0.1644, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.7954545454545453e-05, | |
| "loss": 0.1658, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.7911931818181813e-05, | |
| "loss": 0.1686, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.786931818181818e-05, | |
| "loss": 0.1577, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.7826704545454544e-05, | |
| "loss": 0.1651, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 2.7784090909090907e-05, | |
| "loss": 0.1671, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.774147727272727e-05, | |
| "loss": 0.1665, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.7698863636363634e-05, | |
| "loss": 0.1579, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.7656249999999998e-05, | |
| "loss": 0.1644, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.761363636363636e-05, | |
| "loss": 0.1548, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.7571022727272725e-05, | |
| "loss": 0.1605, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.752840909090909e-05, | |
| "loss": 0.1656, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.7485795454545452e-05, | |
| "loss": 0.1591, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.7443181818181816e-05, | |
| "loss": 0.1544, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.740056818181818e-05, | |
| "loss": 0.1514, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.7357954545454543e-05, | |
| "loss": 0.1399, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.7315340909090906e-05, | |
| "loss": 0.1358, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.727272727272727e-05, | |
| "loss": 0.1792, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.43016406893730164, | |
| "eval_runtime": 219.6776, | |
| "eval_samples_per_second": 23.33, | |
| "eval_steps_per_second": 0.369, | |
| "eval_wer": 27.126671869533624, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.7230113636363637e-05, | |
| "loss": 0.3324, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.7187499999999997e-05, | |
| "loss": 0.2943, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.714488636363636e-05, | |
| "loss": 0.2949, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.7102272727272727e-05, | |
| "loss": 0.2881, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.7059659090909087e-05, | |
| "loss": 0.278, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.701704545454545e-05, | |
| "loss": 0.279, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.6974431818181818e-05, | |
| "loss": 0.2686, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.6931818181818178e-05, | |
| "loss": 0.2766, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.688920454545454e-05, | |
| "loss": 0.2642, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.684659090909091e-05, | |
| "loss": 0.2528, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.680397727272727e-05, | |
| "loss": 0.2616, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.6761363636363632e-05, | |
| "loss": 0.2658, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.671875e-05, | |
| "loss": 0.2661, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.667613636363636e-05, | |
| "loss": 0.2644, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.6633522727272723e-05, | |
| "loss": 0.2478, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.659090909090909e-05, | |
| "loss": 0.2545, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.6548295454545453e-05, | |
| "loss": 0.2475, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.6505681818181813e-05, | |
| "loss": 0.2541, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.646306818181818e-05, | |
| "loss": 0.2545, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.6420454545454544e-05, | |
| "loss": 0.2523, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.6377840909090904e-05, | |
| "loss": 0.2452, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.633522727272727e-05, | |
| "loss": 0.2493, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.6292613636363634e-05, | |
| "loss": 0.2582, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.6249999999999998e-05, | |
| "loss": 0.245, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.620738636363636e-05, | |
| "loss": 0.2485, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.6164772727272725e-05, | |
| "loss": 0.2601, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.6122159090909088e-05, | |
| "loss": 0.2408, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.6079545454545452e-05, | |
| "loss": 0.2416, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.6036931818181815e-05, | |
| "loss": 0.2437, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.5994318181818182e-05, | |
| "loss": 0.2478, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.5951704545454542e-05, | |
| "loss": 0.2437, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.5909090909090906e-05, | |
| "loss": 0.2433, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.5866477272727273e-05, | |
| "loss": 0.2515, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.5823863636363633e-05, | |
| "loss": 0.252, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.5781249999999996e-05, | |
| "loss": 0.2342, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.5738636363636363e-05, | |
| "loss": 0.2507, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.5696022727272724e-05, | |
| "loss": 0.2448, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.5653409090909087e-05, | |
| "loss": 0.2504, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 2.5610795454545454e-05, | |
| "loss": 0.2472, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.5568181818181814e-05, | |
| "loss": 0.2491, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.5525568181818178e-05, | |
| "loss": 0.2373, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.5482954545454545e-05, | |
| "loss": 0.2456, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.5440340909090908e-05, | |
| "loss": 0.2426, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.5397727272727268e-05, | |
| "loss": 0.2491, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.5355113636363635e-05, | |
| "loss": 0.2459, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.53125e-05, | |
| "loss": 0.2527, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.526988636363636e-05, | |
| "loss": 0.2293, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.5227272727272726e-05, | |
| "loss": 0.2383, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.518465909090909e-05, | |
| "loss": 0.2359, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.514204545454545e-05, | |
| "loss": 0.2374, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.5099431818181816e-05, | |
| "loss": 0.2352, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.505681818181818e-05, | |
| "loss": 0.236, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.501420454545454e-05, | |
| "loss": 0.2336, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.4971590909090907e-05, | |
| "loss": 0.2292, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.492897727272727e-05, | |
| "loss": 0.2496, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 2.4886363636363637e-05, | |
| "loss": 0.228, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.4843749999999997e-05, | |
| "loss": 0.2312, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.480113636363636e-05, | |
| "loss": 0.2268, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.4758522727272728e-05, | |
| "loss": 0.2316, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.4715909090909088e-05, | |
| "loss": 0.2355, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.467329545454545e-05, | |
| "loss": 0.2298, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.463068181818182e-05, | |
| "loss": 0.2751, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.458806818181818e-05, | |
| "loss": 0.3582, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.4545454545454542e-05, | |
| "loss": 0.3436, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.450284090909091e-05, | |
| "loss": 0.3361, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.446022727272727e-05, | |
| "loss": 0.3268, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.4417613636363633e-05, | |
| "loss": 0.3229, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.4375e-05, | |
| "loss": 0.309, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.433238636363636e-05, | |
| "loss": 0.3014, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.4289772727272723e-05, | |
| "loss": 0.2187, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.424715909090909e-05, | |
| "loss": 0.1691, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.4204545454545454e-05, | |
| "loss": 0.1716, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.4161931818181814e-05, | |
| "loss": 0.1737, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.411931818181818e-05, | |
| "loss": 0.1714, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.4076704545454544e-05, | |
| "loss": 0.1719, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.4034090909090904e-05, | |
| "loss": 0.1609, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.399147727272727e-05, | |
| "loss": 0.1634, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3948863636363635e-05, | |
| "loss": 0.1731, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.3906249999999995e-05, | |
| "loss": 0.1592, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.3863636363636362e-05, | |
| "loss": 0.1684, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.35963284969329834, | |
| "eval_runtime": 215.4349, | |
| "eval_samples_per_second": 23.789, | |
| "eval_steps_per_second": 0.376, | |
| "eval_wer": 22.188433488522296, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.3821022727272725e-05, | |
| "loss": 0.156, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.3778409090909086e-05, | |
| "loss": 0.1604, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.3735795454545452e-05, | |
| "loss": 0.159, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.3693181818181816e-05, | |
| "loss": 0.1626, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.3650568181818183e-05, | |
| "loss": 0.1533, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.3607954545454543e-05, | |
| "loss": 0.153, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.3565340909090907e-05, | |
| "loss": 0.1503, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.3522727272727273e-05, | |
| "loss": 0.1559, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.3480113636363634e-05, | |
| "loss": 0.1504, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.3437499999999997e-05, | |
| "loss": 0.1556, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.3394886363636364e-05, | |
| "loss": 0.1542, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.3352272727272724e-05, | |
| "loss": 0.1508, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.3309659090909088e-05, | |
| "loss": 0.1489, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.3267045454545455e-05, | |
| "loss": 0.1586, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.3224431818181815e-05, | |
| "loss": 0.1541, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.3181818181818178e-05, | |
| "loss": 0.1528, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.3139204545454545e-05, | |
| "loss": 0.1389, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.309659090909091e-05, | |
| "loss": 0.1489, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 2.305397727272727e-05, | |
| "loss": 0.1412, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.3011363636363636e-05, | |
| "loss": 0.1481, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.296875e-05, | |
| "loss": 0.1498, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.292613636363636e-05, | |
| "loss": 0.1474, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 2.2883522727272726e-05, | |
| "loss": 0.144, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.284090909090909e-05, | |
| "loss": 0.1443, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 2.279829545454545e-05, | |
| "loss": 0.1489, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.2755681818181817e-05, | |
| "loss": 0.1565, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.271306818181818e-05, | |
| "loss": 0.1398, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.267045454545454e-05, | |
| "loss": 0.1476, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.2627840909090907e-05, | |
| "loss": 0.1419, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.258522727272727e-05, | |
| "loss": 0.1458, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 2.2542613636363638e-05, | |
| "loss": 0.1418, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.1375, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.245738636363636e-05, | |
| "loss": 0.1437, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 2.241477272727273e-05, | |
| "loss": 0.139, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.237215909090909e-05, | |
| "loss": 0.136, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.2329545454545452e-05, | |
| "loss": 0.1398, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.228693181818182e-05, | |
| "loss": 0.1367, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 2.224431818181818e-05, | |
| "loss": 0.1378, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.2201704545454543e-05, | |
| "loss": 0.1358, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 2.215909090909091e-05, | |
| "loss": 0.1421, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.211647727272727e-05, | |
| "loss": 0.1401, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.2073863636363633e-05, | |
| "loss": 0.1435, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.203125e-05, | |
| "loss": 0.1415, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.198863636363636e-05, | |
| "loss": 0.1402, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2.1946022727272724e-05, | |
| "loss": 0.1351, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 2.190340909090909e-05, | |
| "loss": 0.1398, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.1860795454545454e-05, | |
| "loss": 0.1474, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.1818181818181814e-05, | |
| "loss": 0.1424, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.177556818181818e-05, | |
| "loss": 0.1364, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.1732954545454545e-05, | |
| "loss": 0.1311, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.1690340909090905e-05, | |
| "loss": 0.1347, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 2.1647727272727272e-05, | |
| "loss": 0.1415, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.1605113636363635e-05, | |
| "loss": 0.1342, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.1562499999999996e-05, | |
| "loss": 0.1361, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.1519886363636362e-05, | |
| "loss": 0.1369, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 2.1477272727272726e-05, | |
| "loss": 0.134, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.1434659090909086e-05, | |
| "loss": 0.1351, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.1392045454545453e-05, | |
| "loss": 0.1261, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.1349431818181817e-05, | |
| "loss": 0.135, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.1306818181818183e-05, | |
| "loss": 0.1425, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.1264204545454544e-05, | |
| "loss": 0.1321, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 2.1221590909090907e-05, | |
| "loss": 0.1344, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.1178977272727274e-05, | |
| "loss": 0.1361, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 2.1136363636363634e-05, | |
| "loss": 0.1313, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.1093749999999998e-05, | |
| "loss": 0.1435, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.1051136363636365e-05, | |
| "loss": 0.1319, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.1008522727272725e-05, | |
| "loss": 0.1306, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.0965909090909088e-05, | |
| "loss": 0.127, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.0923295454545455e-05, | |
| "loss": 0.1287, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 2.0880681818181815e-05, | |
| "loss": 0.1287, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.083806818181818e-05, | |
| "loss": 0.1342, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.0795454545454546e-05, | |
| "loss": 0.1261, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 2.075284090909091e-05, | |
| "loss": 0.1268, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.071022727272727e-05, | |
| "loss": 0.1239, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 2.0667613636363636e-05, | |
| "loss": 0.1267, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 0.1276, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.058238636363636e-05, | |
| "loss": 0.1278, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.0539772727272727e-05, | |
| "loss": 0.1233, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 2.049715909090909e-05, | |
| "loss": 0.1297, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.045454545454545e-05, | |
| "loss": 0.1229, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.40952152013778687, | |
| "eval_runtime": 217.03, | |
| "eval_samples_per_second": 23.614, | |
| "eval_steps_per_second": 0.373, | |
| "eval_wer": 23.477488629941604, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.0411931818181818e-05, | |
| "loss": 0.135, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.036931818181818e-05, | |
| "loss": 0.1266, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.032670454545454e-05, | |
| "loss": 0.1295, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.0284090909090908e-05, | |
| "loss": 0.1353, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.024147727272727e-05, | |
| "loss": 0.1262, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.0198863636363635e-05, | |
| "loss": 0.1217, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.015625e-05, | |
| "loss": 0.1304, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2.0113636363636362e-05, | |
| "loss": 0.1224, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2.0071022727272726e-05, | |
| "loss": 0.1336, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 2.002840909090909e-05, | |
| "loss": 0.1284, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.9985795454545453e-05, | |
| "loss": 0.1242, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.9943181818181816e-05, | |
| "loss": 0.1261, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.990056818181818e-05, | |
| "loss": 0.1318, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.9857954545454543e-05, | |
| "loss": 0.1185, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 1.9815340909090907e-05, | |
| "loss": 0.1205, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.977272727272727e-05, | |
| "loss": 0.1249, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 1.9730113636363634e-05, | |
| "loss": 0.1259, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.9687499999999997e-05, | |
| "loss": 0.1248, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.964488636363636e-05, | |
| "loss": 0.1292, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.9602272727272724e-05, | |
| "loss": 0.1278, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.955965909090909e-05, | |
| "loss": 0.1215, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.9517045454545455e-05, | |
| "loss": 0.1295, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.9474431818181815e-05, | |
| "loss": 0.1304, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.9431818181818182e-05, | |
| "loss": 0.1205, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 1.9389204545454545e-05, | |
| "loss": 0.1258, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 1.9346590909090906e-05, | |
| "loss": 0.1256, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.9303977272727273e-05, | |
| "loss": 0.1197, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 1.9261363636363636e-05, | |
| "loss": 0.1239, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.9218749999999996e-05, | |
| "loss": 0.1253, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.9176136363636363e-05, | |
| "loss": 0.1181, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.9133522727272727e-05, | |
| "loss": 0.1199, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 1.9090909090909087e-05, | |
| "loss": 0.1131, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.9048295454545454e-05, | |
| "loss": 0.1065, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.9005681818181817e-05, | |
| "loss": 0.1051, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 1.896306818181818e-05, | |
| "loss": 0.1996, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 1.8920454545454544e-05, | |
| "loss": 0.2519, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.8877840909090908e-05, | |
| "loss": 0.2337, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.883522727272727e-05, | |
| "loss": 0.2337, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.8792613636363635e-05, | |
| "loss": 0.2312, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 1.875e-05, | |
| "loss": 0.2169, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.8707386363636362e-05, | |
| "loss": 0.2221, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.8664772727272725e-05, | |
| "loss": 0.2173, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.862215909090909e-05, | |
| "loss": 0.2247, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 1.8579545454545452e-05, | |
| "loss": 0.2024, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.8536931818181816e-05, | |
| "loss": 0.2097, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 1.849431818181818e-05, | |
| "loss": 0.216, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.8451704545454543e-05, | |
| "loss": 0.2176, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 1.8409090909090907e-05, | |
| "loss": 0.2114, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.836647727272727e-05, | |
| "loss": 0.2107, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.8323863636363634e-05, | |
| "loss": 0.2025, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.8281249999999997e-05, | |
| "loss": 0.204, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.8238636363636364e-05, | |
| "loss": 0.2067, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8196022727272724e-05, | |
| "loss": 0.2107, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.8153409090909088e-05, | |
| "loss": 0.2056, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.8110795454545455e-05, | |
| "loss": 0.2016, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.8068181818181815e-05, | |
| "loss": 0.2014, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.8025568181818178e-05, | |
| "loss": 0.2088, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.7982954545454545e-05, | |
| "loss": 0.2057, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.7940340909090905e-05, | |
| "loss": 0.2001, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 1.7897727272727272e-05, | |
| "loss": 0.2075, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.7855113636363636e-05, | |
| "loss": 0.2039, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.78125e-05, | |
| "loss": 0.1979, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.7769886363636363e-05, | |
| "loss": 0.2042, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.7727272727272726e-05, | |
| "loss": 0.1985, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.768465909090909e-05, | |
| "loss": 0.1977, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.7642045454545453e-05, | |
| "loss": 0.1997, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.7599431818181817e-05, | |
| "loss": 0.2014, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.755681818181818e-05, | |
| "loss": 0.2069, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.7514204545454544e-05, | |
| "loss": 0.2033, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.7471590909090907e-05, | |
| "loss": 0.1969, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.742897727272727e-05, | |
| "loss": 0.204, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.7386363636363635e-05, | |
| "loss": 0.2052, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 1.7343749999999998e-05, | |
| "loss": 0.2036, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.730113636363636e-05, | |
| "loss": 0.2155, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.7258522727272725e-05, | |
| "loss": 0.1889, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.721590909090909e-05, | |
| "loss": 0.2023, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 1.7173295454545452e-05, | |
| "loss": 0.2025, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.713068181818182e-05, | |
| "loss": 0.2005, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 1.708806818181818e-05, | |
| "loss": 0.2094, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.7045454545454543e-05, | |
| "loss": 0.2007, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_loss": 0.3426918685436249, | |
| "eval_runtime": 218.014, | |
| "eval_samples_per_second": 23.508, | |
| "eval_steps_per_second": 0.372, | |
| "eval_wer": 21.725557738367556, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.700284090909091e-05, | |
| "loss": 0.1989, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.696022727272727e-05, | |
| "loss": 0.1945, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.6917613636363633e-05, | |
| "loss": 0.1909, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.6875e-05, | |
| "loss": 0.2022, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.683238636363636e-05, | |
| "loss": 0.1911, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.6789772727272727e-05, | |
| "loss": 0.2002, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.674715909090909e-05, | |
| "loss": 0.1861, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.670454545454545e-05, | |
| "loss": 0.1944, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.6661931818181818e-05, | |
| "loss": 0.1894, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.661931818181818e-05, | |
| "loss": 0.2038, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.657670454545454e-05, | |
| "loss": 0.1845, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.653409090909091e-05, | |
| "loss": 0.1928, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.6491477272727272e-05, | |
| "loss": 0.189, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.6448863636363635e-05, | |
| "loss": 0.1878, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.640625e-05, | |
| "loss": 0.1909, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 1.6363636363636363e-05, | |
| "loss": 0.1908, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 1.6321022727272726e-05, | |
| "loss": 0.2691, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.627840909090909e-05, | |
| "loss": 0.2877, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.6235795454545453e-05, | |
| "loss": 0.2776, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.6193181818181817e-05, | |
| "loss": 0.2767, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.615056818181818e-05, | |
| "loss": 0.2729, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.6107954545454544e-05, | |
| "loss": 0.2592, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.6065340909090907e-05, | |
| "loss": 0.2506, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.602272727272727e-05, | |
| "loss": 0.2469, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1.5980113636363634e-05, | |
| "loss": 0.1397, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 1.5937499999999998e-05, | |
| "loss": 0.1307, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.5894886363636365e-05, | |
| "loss": 0.1381, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 1.5852272727272725e-05, | |
| "loss": 0.1346, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.580965909090909e-05, | |
| "loss": 0.1319, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.5767045454545455e-05, | |
| "loss": 0.135, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.5724431818181815e-05, | |
| "loss": 0.1236, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.568181818181818e-05, | |
| "loss": 0.1348, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.5639204545454546e-05, | |
| "loss": 0.1329, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 1.5596590909090906e-05, | |
| "loss": 0.1278, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.5553977272727273e-05, | |
| "loss": 0.1311, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.5511363636363636e-05, | |
| "loss": 0.1256, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5468749999999997e-05, | |
| "loss": 0.1164, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 1.5426136363636363e-05, | |
| "loss": 0.1319, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.5383522727272727e-05, | |
| "loss": 0.1299, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.534090909090909e-05, | |
| "loss": 0.1179, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.5298295454545454e-05, | |
| "loss": 0.1157, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.5255681818181816e-05, | |
| "loss": 0.1178, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.5213068181818181e-05, | |
| "loss": 0.1248, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.5170454545454545e-05, | |
| "loss": 0.1138, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.5127840909090906e-05, | |
| "loss": 0.1256, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.5085227272727272e-05, | |
| "loss": 0.1218, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.5042613636363635e-05, | |
| "loss": 0.1195, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.1209, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1.4957386363636362e-05, | |
| "loss": 0.1205, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 1.4914772727272726e-05, | |
| "loss": 0.1164, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.4872159090909091e-05, | |
| "loss": 0.1183, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 1.4829545454545453e-05, | |
| "loss": 0.1139, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.4786931818181818e-05, | |
| "loss": 0.1132, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.4744318181818182e-05, | |
| "loss": 0.118, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.4701704545454543e-05, | |
| "loss": 0.1113, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.4659090909090909e-05, | |
| "loss": 0.1153, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.4616477272727272e-05, | |
| "loss": 0.1123, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.4573863636363634e-05, | |
| "loss": 0.1168, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.4531249999999999e-05, | |
| "loss": 0.1094, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.4488636363636363e-05, | |
| "loss": 0.1234, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 1.4446022727272726e-05, | |
| "loss": 0.1184, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.440340909090909e-05, | |
| "loss": 0.1163, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.4360795454545453e-05, | |
| "loss": 0.1113, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.4318181818181817e-05, | |
| "loss": 0.1136, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.427556818181818e-05, | |
| "loss": 0.1182, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.4232954545454544e-05, | |
| "loss": 0.1058, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 1.4190340909090907e-05, | |
| "loss": 0.1064, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.4147727272727271e-05, | |
| "loss": 0.1136, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.4105113636363636e-05, | |
| "loss": 0.1097, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.40625e-05, | |
| "loss": 0.1028, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.4019886363636361e-05, | |
| "loss": 0.1111, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.3977272727272727e-05, | |
| "loss": 0.1096, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.393465909090909e-05, | |
| "loss": 0.105, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.3892045454545454e-05, | |
| "loss": 0.1108, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.3849431818181817e-05, | |
| "loss": 0.1112, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 1.380681818181818e-05, | |
| "loss": 0.1059, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 1.3764204545454544e-05, | |
| "loss": 0.1209, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.3721590909090908e-05, | |
| "loss": 0.1109, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.3678977272727271e-05, | |
| "loss": 0.1054, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.3636363636363635e-05, | |
| "loss": 0.1081, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_loss": 0.3724905550479889, | |
| "eval_runtime": 207.1563, | |
| "eval_samples_per_second": 24.74, | |
| "eval_steps_per_second": 0.391, | |
| "eval_wer": 20.906106192308727, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.3593749999999998e-05, | |
| "loss": 0.1118, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1.3551136363636364e-05, | |
| "loss": 0.116, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1.3508522727272725e-05, | |
| "loss": 0.1102, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.3465909090909089e-05, | |
| "loss": 0.1123, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.3423295454545454e-05, | |
| "loss": 0.0955, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.3380681818181816e-05, | |
| "loss": 0.1132, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.333806818181818e-05, | |
| "loss": 0.1072, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.3295454545454545e-05, | |
| "loss": 0.1037, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.3252840909090907e-05, | |
| "loss": 0.1102, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.3210227272727272e-05, | |
| "loss": 0.1068, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 1.3167613636363635e-05, | |
| "loss": 0.106, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.3124999999999999e-05, | |
| "loss": 0.1034, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.3082386363636362e-05, | |
| "loss": 0.1035, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.3039772727272726e-05, | |
| "loss": 0.1058, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 1.2997159090909091e-05, | |
| "loss": 0.1109, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 1.2954545454545453e-05, | |
| "loss": 0.1052, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.2911931818181816e-05, | |
| "loss": 0.1038, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.2869318181818182e-05, | |
| "loss": 0.11, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.2826704545454544e-05, | |
| "loss": 0.1043, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 1.2784090909090907e-05, | |
| "loss": 0.1163, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.2741477272727272e-05, | |
| "loss": 0.0992, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.2698863636363634e-05, | |
| "loss": 0.0988, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.265625e-05, | |
| "loss": 0.1035, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.2613636363636363e-05, | |
| "loss": 0.0993, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.2571022727272725e-05, | |
| "loss": 0.1037, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.252840909090909e-05, | |
| "loss": 0.1027, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 1.2485795454545453e-05, | |
| "loss": 0.1044, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 1.2443181818181819e-05, | |
| "loss": 0.096, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.240056818181818e-05, | |
| "loss": 0.0959, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.2357954545454544e-05, | |
| "loss": 0.1033, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.231534090909091e-05, | |
| "loss": 0.1007, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.2272727272727271e-05, | |
| "loss": 0.0973, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.2230113636363635e-05, | |
| "loss": 0.1025, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.21875e-05, | |
| "loss": 0.0982, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.2144886363636362e-05, | |
| "loss": 0.0956, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.2102272727272727e-05, | |
| "loss": 0.1087, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.205965909090909e-05, | |
| "loss": 0.0965, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 1.2017045454545452e-05, | |
| "loss": 0.1093, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.1974431818181817e-05, | |
| "loss": 0.1046, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.1931818181818181e-05, | |
| "loss": 0.0976, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.1889204545454543e-05, | |
| "loss": 0.0946, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.1846590909090908e-05, | |
| "loss": 0.1028, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.1803977272727272e-05, | |
| "loss": 0.1006, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 1.1761363636363637e-05, | |
| "loss": 0.1059, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.1718749999999999e-05, | |
| "loss": 0.1002, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.1676136363636362e-05, | |
| "loss": 0.097, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.1633522727272727e-05, | |
| "loss": 0.1017, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.1590909090909089e-05, | |
| "loss": 0.1024, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 1.1548295454545454e-05, | |
| "loss": 0.0891, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.1505681818181818e-05, | |
| "loss": 0.0927, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.146306818181818e-05, | |
| "loss": 0.1042, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.1420454545454545e-05, | |
| "loss": 0.0985, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.1377840909090908e-05, | |
| "loss": 0.1027, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.133522727272727e-05, | |
| "loss": 0.1024, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.1292613636363635e-05, | |
| "loss": 0.0966, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.1249999999999999e-05, | |
| "loss": 0.0993, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.1207386363636364e-05, | |
| "loss": 0.101, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 1.1164772727272726e-05, | |
| "loss": 0.1043, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 1.112215909090909e-05, | |
| "loss": 0.0953, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.1079545454545455e-05, | |
| "loss": 0.0987, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.1036931818181817e-05, | |
| "loss": 0.0976, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.099431818181818e-05, | |
| "loss": 0.0963, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.0951704545454545e-05, | |
| "loss": 0.0999, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.0909090909090907e-05, | |
| "loss": 0.0948, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.0866477272727272e-05, | |
| "loss": 0.0941, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.0823863636363636e-05, | |
| "loss": 0.0947, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 1.0781249999999998e-05, | |
| "loss": 0.0863, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.0738636363636363e-05, | |
| "loss": 0.0818, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.0696022727272727e-05, | |
| "loss": 0.0709, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.0653409090909092e-05, | |
| "loss": 0.2243, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.0610795454545454e-05, | |
| "loss": 0.1961, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.0568181818181817e-05, | |
| "loss": 0.1946, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.0525568181818182e-05, | |
| "loss": 0.1942, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.0482954545454544e-05, | |
| "loss": 0.1847, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.0440340909090908e-05, | |
| "loss": 0.1825, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.0397727272727273e-05, | |
| "loss": 0.1842, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 1.0355113636363635e-05, | |
| "loss": 0.1836, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.03125e-05, | |
| "loss": 0.1827, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 1.0269886363636363e-05, | |
| "loss": 0.1643, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.0227272727272725e-05, | |
| "loss": 0.178, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_loss": 0.3380821645259857, | |
| "eval_runtime": 212.4779, | |
| "eval_samples_per_second": 24.12, | |
| "eval_steps_per_second": 0.381, | |
| "eval_wer": 19.771791490621386, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.018465909090909e-05, | |
| "loss": 0.1767, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.0142045454545454e-05, | |
| "loss": 0.1841, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 1.0099431818181818e-05, | |
| "loss": 0.1775, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 1.0056818181818181e-05, | |
| "loss": 0.1698, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.0014204545454545e-05, | |
| "loss": 0.1729, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 9.971590909090908e-06, | |
| "loss": 0.1716, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 9.928977272727272e-06, | |
| "loss": 0.1724, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 9.886363636363635e-06, | |
| "loss": 0.1778, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 9.843749999999999e-06, | |
| "loss": 0.1691, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 9.801136363636362e-06, | |
| "loss": 0.1735, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 9.758522727272727e-06, | |
| "loss": 0.166, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 9.715909090909091e-06, | |
| "loss": 0.1763, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 9.673295454545453e-06, | |
| "loss": 0.1707, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 9.630681818181818e-06, | |
| "loss": 0.1713, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 9.588068181818182e-06, | |
| "loss": 0.1804, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 9.545454545454543e-06, | |
| "loss": 0.1656, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 9.502840909090909e-06, | |
| "loss": 0.1688, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 9.460227272727272e-06, | |
| "loss": 0.1697, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 9.417613636363636e-06, | |
| "loss": 0.1679, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 9.375e-06, | |
| "loss": 0.1672, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.332386363636363e-06, | |
| "loss": 0.1663, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 9.289772727272726e-06, | |
| "loss": 0.1723, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 9.24715909090909e-06, | |
| "loss": 0.1769, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 9.204545454545453e-06, | |
| "loss": 0.1678, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 9.161931818181817e-06, | |
| "loss": 0.1681, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 9.119318181818182e-06, | |
| "loss": 0.1725, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.076704545454544e-06, | |
| "loss": 0.1778, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.034090909090907e-06, | |
| "loss": 0.1726, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 8.991477272727273e-06, | |
| "loss": 0.1752, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 8.948863636363636e-06, | |
| "loss": 0.1656, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 8.90625e-06, | |
| "loss": 0.1738, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 8.863636363636363e-06, | |
| "loss": 0.1682, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 8.821022727272727e-06, | |
| "loss": 0.1682, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 8.77840909090909e-06, | |
| "loss": 0.1779, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 8.735795454545454e-06, | |
| "loss": 0.1757, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 8.693181818181817e-06, | |
| "loss": 0.1609, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 8.65056818181818e-06, | |
| "loss": 0.1631, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 8.607954545454544e-06, | |
| "loss": 0.1659, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 8.56534090909091e-06, | |
| "loss": 0.1681, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 8.522727272727271e-06, | |
| "loss": 0.1596, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 8.480113636363635e-06, | |
| "loss": 0.1693, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 8.4375e-06, | |
| "loss": 0.1637, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 8.394886363636364e-06, | |
| "loss": 0.1593, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 8.352272727272725e-06, | |
| "loss": 0.1684, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 8.30965909090909e-06, | |
| "loss": 0.1625, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 8.267045454545454e-06, | |
| "loss": 0.1644, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 8.224431818181818e-06, | |
| "loss": 0.1547, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 8.181818181818181e-06, | |
| "loss": 0.163, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 8.139204545454545e-06, | |
| "loss": 0.159, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 8.096590909090908e-06, | |
| "loss": 0.1596, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 8.053977272727272e-06, | |
| "loss": 0.1628, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 8.011363636363635e-06, | |
| "loss": 0.26, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 7.968749999999999e-06, | |
| "loss": 0.2412, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 7.926136363636362e-06, | |
| "loss": 0.2448, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 7.883522727272728e-06, | |
| "loss": 0.228, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 7.84090909090909e-06, | |
| "loss": 0.2395, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 7.798295454545453e-06, | |
| "loss": 0.2254, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.755681818181818e-06, | |
| "loss": 0.2165, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 7.713068181818182e-06, | |
| "loss": 0.1718, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.670454545454545e-06, | |
| "loss": 0.1062, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 7.627840909090908e-06, | |
| "loss": 0.1074, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.585227272727272e-06, | |
| "loss": 0.1123, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 7.542613636363636e-06, | |
| "loss": 0.1076, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.1083, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.457386363636363e-06, | |
| "loss": 0.1061, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.414772727272726e-06, | |
| "loss": 0.1045, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 7.372159090909091e-06, | |
| "loss": 0.1146, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.329545454545454e-06, | |
| "loss": 0.099, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 7.286931818181817e-06, | |
| "loss": 0.1095, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.244318181818181e-06, | |
| "loss": 0.0996, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 7.201704545454545e-06, | |
| "loss": 0.104, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 7.159090909090908e-06, | |
| "loss": 0.1022, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 7.116477272727272e-06, | |
| "loss": 0.1054, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 7.0738636363636354e-06, | |
| "loss": 0.0987, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 7.03125e-06, | |
| "loss": 0.0984, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 6.988636363636363e-06, | |
| "loss": 0.0943, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 6.946022727272727e-06, | |
| "loss": 0.0978, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 6.90340909090909e-06, | |
| "loss": 0.0965, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 6.860795454545454e-06, | |
| "loss": 0.0975, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 6.8181818181818174e-06, | |
| "loss": 0.0991, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.34442025423049927, | |
| "eval_runtime": 206.9961, | |
| "eval_samples_per_second": 24.759, | |
| "eval_steps_per_second": 0.391, | |
| "eval_wer": 19.265857531149923, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 6.775568181818182e-06, | |
| "loss": 0.1005, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 6.7329545454545445e-06, | |
| "loss": 0.0934, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.690340909090908e-06, | |
| "loss": 0.1019, | |
| "step": 40150 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 6.647727272727272e-06, | |
| "loss": 0.0965, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 6.605113636363636e-06, | |
| "loss": 0.0979, | |
| "step": 40250 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 6.5624999999999994e-06, | |
| "loss": 0.0916, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.519886363636363e-06, | |
| "loss": 0.091, | |
| "step": 40350 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.4772727272727265e-06, | |
| "loss": 0.0905, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 6.434659090909091e-06, | |
| "loss": 0.0945, | |
| "step": 40450 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 6.3920454545454535e-06, | |
| "loss": 0.0924, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 6.349431818181817e-06, | |
| "loss": 0.0975, | |
| "step": 40550 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 6.306818181818181e-06, | |
| "loss": 0.0897, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 6.264204545454545e-06, | |
| "loss": 0.093, | |
| "step": 40650 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 6.221590909090909e-06, | |
| "loss": 0.0946, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.178977272727272e-06, | |
| "loss": 0.1014, | |
| "step": 40750 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.1363636363636355e-06, | |
| "loss": 0.0927, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.09375e-06, | |
| "loss": 0.0957, | |
| "step": 40850 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.051136363636363e-06, | |
| "loss": 0.0862, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 6.008522727272726e-06, | |
| "loss": 0.0992, | |
| "step": 40950 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 5.9659090909090905e-06, | |
| "loss": 0.0913, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.923295454545454e-06, | |
| "loss": 0.0822, | |
| "step": 41050 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.880681818181818e-06, | |
| "loss": 0.0934, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 5.838068181818181e-06, | |
| "loss": 0.0874, | |
| "step": 41150 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 5.7954545454545446e-06, | |
| "loss": 0.0851, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 5.752840909090909e-06, | |
| "loss": 0.0865, | |
| "step": 41250 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 5.7102272727272725e-06, | |
| "loss": 0.0882, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 5.667613636363635e-06, | |
| "loss": 0.0894, | |
| "step": 41350 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 5.6249999999999995e-06, | |
| "loss": 0.0847, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 5.582386363636363e-06, | |
| "loss": 0.0922, | |
| "step": 41450 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 5.539772727272727e-06, | |
| "loss": 0.0914, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.49715909090909e-06, | |
| "loss": 0.0916, | |
| "step": 41550 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.454545454545454e-06, | |
| "loss": 0.0923, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 5.411931818181818e-06, | |
| "loss": 0.0908, | |
| "step": 41650 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 5.3693181818181815e-06, | |
| "loss": 0.0859, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 5.326704545454546e-06, | |
| "loss": 0.0894, | |
| "step": 41750 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 5.2840909090909086e-06, | |
| "loss": 0.0974, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 5.241477272727272e-06, | |
| "loss": 0.091, | |
| "step": 41850 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 5.1988636363636364e-06, | |
| "loss": 0.0867, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 5.15625e-06, | |
| "loss": 0.0868, | |
| "step": 41950 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 5.113636363636363e-06, | |
| "loss": 0.0836, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 5.071022727272727e-06, | |
| "loss": 0.091, | |
| "step": 42050 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 5.0284090909090905e-06, | |
| "loss": 0.087, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 4.985795454545454e-06, | |
| "loss": 0.0822, | |
| "step": 42150 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.943181818181818e-06, | |
| "loss": 0.0924, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 4.900568181818181e-06, | |
| "loss": 0.0835, | |
| "step": 42250 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.8579545454545455e-06, | |
| "loss": 0.0868, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 4.815340909090909e-06, | |
| "loss": 0.0828, | |
| "step": 42350 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 4.772727272727272e-06, | |
| "loss": 0.0877, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 4.730113636363636e-06, | |
| "loss": 0.0899, | |
| "step": 42450 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 4.6875e-06, | |
| "loss": 0.0848, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 4.644886363636363e-06, | |
| "loss": 0.0869, | |
| "step": 42550 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.602272727272727e-06, | |
| "loss": 0.0878, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 4.559659090909091e-06, | |
| "loss": 0.0853, | |
| "step": 42650 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 4.517045454545454e-06, | |
| "loss": 0.0945, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 4.474431818181818e-06, | |
| "loss": 0.0868, | |
| "step": 42750 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.431818181818182e-06, | |
| "loss": 0.0839, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 4.389204545454545e-06, | |
| "loss": 0.0805, | |
| "step": 42850 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 4.346590909090909e-06, | |
| "loss": 0.0832, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 4.303977272727272e-06, | |
| "loss": 0.083, | |
| "step": 42950 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 4.261363636363636e-06, | |
| "loss": 0.0857, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 4.21875e-06, | |
| "loss": 0.0795, | |
| "step": 43050 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 4.176136363636363e-06, | |
| "loss": 0.0846, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 4.133522727272727e-06, | |
| "loss": 0.0786, | |
| "step": 43150 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.090909090909091e-06, | |
| "loss": 0.0843, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 4.048295454545454e-06, | |
| "loss": 0.0828, | |
| "step": 43250 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 4.005681818181818e-06, | |
| "loss": 0.0771, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "learning_rate": 3.963068181818181e-06, | |
| "loss": 0.0784, | |
| "step": 43350 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 3.920454545454545e-06, | |
| "loss": 0.088, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.877840909090909e-06, | |
| "loss": 0.0757, | |
| "step": 43450 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.835227272727273e-06, | |
| "loss": 0.0853, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.792613636363636e-06, | |
| "loss": 0.0836, | |
| "step": 43550 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 3.7499999999999997e-06, | |
| "loss": 0.0834, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 3.707386363636363e-06, | |
| "loss": 0.0895, | |
| "step": 43650 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 3.664772727272727e-06, | |
| "loss": 0.0824, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.6221590909090907e-06, | |
| "loss": 0.0801, | |
| "step": 43750 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 3.579545454545454e-06, | |
| "loss": 0.082, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 3.5369318181818177e-06, | |
| "loss": 0.0826, | |
| "step": 43850 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 3.4943181818181817e-06, | |
| "loss": 0.0849, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 3.451704545454545e-06, | |
| "loss": 0.088, | |
| "step": 43950 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 3.4090909090909087e-06, | |
| "loss": 0.0778, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "eval_loss": 0.36941829323768616, | |
| "eval_runtime": 206.76, | |
| "eval_samples_per_second": 24.787, | |
| "eval_steps_per_second": 0.392, | |
| "eval_wer": 19.89154713528351, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.3664772727272722e-06, | |
| "loss": 0.0798, | |
| "step": 44050 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 3.323863636363636e-06, | |
| "loss": 0.0861, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 3.2812499999999997e-06, | |
| "loss": 0.0805, | |
| "step": 44150 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 3.2386363636363632e-06, | |
| "loss": 0.0751, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 3.1960227272727268e-06, | |
| "loss": 0.0781, | |
| "step": 44250 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 3.1534090909090907e-06, | |
| "loss": 0.0846, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 3.1107954545454547e-06, | |
| "loss": 0.0804, | |
| "step": 44350 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 3.0681818181818178e-06, | |
| "loss": 0.0851, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 3.0255681818181817e-06, | |
| "loss": 0.0856, | |
| "step": 44450 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 2.9829545454545452e-06, | |
| "loss": 0.0783, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.940340909090909e-06, | |
| "loss": 0.0823, | |
| "step": 44550 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 2.8977272727272723e-06, | |
| "loss": 0.0857, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.8551136363636362e-06, | |
| "loss": 0.0844, | |
| "step": 44650 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 2.8124999999999998e-06, | |
| "loss": 0.0789, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.7698863636363637e-06, | |
| "loss": 0.0805, | |
| "step": 44750 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 2.727272727272727e-06, | |
| "loss": 0.0801, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.6846590909090908e-06, | |
| "loss": 0.0808, | |
| "step": 44850 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 2.6420454545454543e-06, | |
| "loss": 0.0817, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.5994318181818182e-06, | |
| "loss": 0.0781, | |
| "step": 44950 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.5568181818181813e-06, | |
| "loss": 0.0776, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.5142045454545453e-06, | |
| "loss": 0.0779, | |
| "step": 45050 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.471590909090909e-06, | |
| "loss": 0.0701, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.4289772727272727e-06, | |
| "loss": 0.0686, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 2.386363636363636e-06, | |
| "loss": 0.1136, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 2.34375e-06, | |
| "loss": 0.1969, | |
| "step": 45250 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.3011363636363633e-06, | |
| "loss": 0.1696, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 2.258522727272727e-06, | |
| "loss": 0.1703, | |
| "step": 45350 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.215909090909091e-06, | |
| "loss": 0.1637, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 2.1732954545454543e-06, | |
| "loss": 0.1639, | |
| "step": 45450 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.130681818181818e-06, | |
| "loss": 0.163, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.0880681818181814e-06, | |
| "loss": 0.1568, | |
| "step": 45550 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.0454545454545453e-06, | |
| "loss": 0.167, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.002840909090909e-06, | |
| "loss": 0.1501, | |
| "step": 45650 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.9602272727272724e-06, | |
| "loss": 0.1502, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 1.9176136363636363e-06, | |
| "loss": 0.1564, | |
| "step": 45750 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.8749999999999998e-06, | |
| "loss": 0.1626, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 1.8323863636363636e-06, | |
| "loss": 0.1563, | |
| "step": 45850 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.789772727272727e-06, | |
| "loss": 0.159, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.7471590909090908e-06, | |
| "loss": 0.1513, | |
| "step": 45950 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.7045454545454544e-06, | |
| "loss": 0.1499, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.661931818181818e-06, | |
| "loss": 0.1513, | |
| "step": 46050 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.6193181818181816e-06, | |
| "loss": 0.1561, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.5767045454545454e-06, | |
| "loss": 0.1574, | |
| "step": 46150 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.5340909090909089e-06, | |
| "loss": 0.1511, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.4914772727272726e-06, | |
| "loss": 0.1524, | |
| "step": 46250 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.4488636363636361e-06, | |
| "loss": 0.1524, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 1.4062499999999999e-06, | |
| "loss": 0.1578, | |
| "step": 46350 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.3636363636363634e-06, | |
| "loss": 0.1515, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 1.3210227272727271e-06, | |
| "loss": 0.1515, | |
| "step": 46450 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.2784090909090907e-06, | |
| "loss": 0.164, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.2357954545454544e-06, | |
| "loss": 0.15, | |
| "step": 46550 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.193181818181818e-06, | |
| "loss": 0.1508, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 1.1505681818181817e-06, | |
| "loss": 0.1503, | |
| "step": 46650 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.1079545454545454e-06, | |
| "loss": 0.1525, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.065340909090909e-06, | |
| "loss": 0.1508, | |
| "step": 46750 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 1.0227272727272727e-06, | |
| "loss": 0.1532, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 9.801136363636362e-07, | |
| "loss": 0.1602, | |
| "step": 46850 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 9.374999999999999e-07, | |
| "loss": 0.156, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 8.948863636363635e-07, | |
| "loss": 0.1499, | |
| "step": 46950 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 8.522727272727272e-07, | |
| "loss": 0.1572, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 8.096590909090908e-07, | |
| "loss": 0.1528, | |
| "step": 47050 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 7.670454545454544e-07, | |
| "loss": 0.1609, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 7.244318181818181e-07, | |
| "loss": 0.1638, | |
| "step": 47150 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 6.818181818181817e-07, | |
| "loss": 0.1511, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 6.392045454545453e-07, | |
| "loss": 0.1507, | |
| "step": 47250 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 5.96590909090909e-07, | |
| "loss": 0.164, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 5.539772727272727e-07, | |
| "loss": 0.1556, | |
| "step": 47350 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 5.113636363636363e-07, | |
| "loss": 0.1564, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 4.6874999999999996e-07, | |
| "loss": 0.1571, | |
| "step": 47450 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 4.261363636363636e-07, | |
| "loss": 0.158, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.835227272727272e-07, | |
| "loss": 0.1466, | |
| "step": 47550 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.4090909090909085e-07, | |
| "loss": 0.1478, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.982954545454545e-07, | |
| "loss": 0.151, | |
| "step": 47650 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.5568181818181816e-07, | |
| "loss": 0.1539, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 2.130681818181818e-07, | |
| "loss": 0.1536, | |
| "step": 47750 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.7045454545454543e-07, | |
| "loss": 0.1432, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 1.2784090909090908e-07, | |
| "loss": 0.1504, | |
| "step": 47850 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 8.522727272727271e-08, | |
| "loss": 0.1472, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 4.2613636363636356e-08, | |
| "loss": 0.1619, | |
| "step": 47950 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 0.0, | |
| "loss": 0.1436, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "eval_loss": 0.3266472816467285, | |
| "eval_runtime": 206.9468, | |
| "eval_samples_per_second": 24.765, | |
| "eval_steps_per_second": 0.391, | |
| "eval_wer": 18.715519793320595, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "step": 48000, | |
| "total_flos": 7.562921187546759e+19, | |
| "train_loss": 0.18055239535868167, | |
| "train_runtime": 106331.79, | |
| "train_samples_per_second": 28.891, | |
| "train_steps_per_second": 0.451 | |
| } | |
| ], | |
| "max_steps": 48000, | |
| "num_train_epochs": 5, | |
| "total_flos": 7.562921187546759e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |