| { | |
| "best_metric": 0.17137235403060913, | |
| "best_model_checkpoint": "./results_en2ar/checkpoint-5200", | |
| "epoch": 0.9872792861211316, | |
| "eval_steps": 100, | |
| "global_step": 5200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.999050692994115e-05, | |
| "loss": 9.2952, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9905069299411435e-05, | |
| "loss": 2.0203, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.981013859882286e-05, | |
| "loss": 0.4495, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.971520789823429e-05, | |
| "loss": 0.5883, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.962027719764572e-05, | |
| "loss": 0.4076, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.952534649705715e-05, | |
| "loss": 0.4073, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9430415796468585e-05, | |
| "loss": 0.237, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9335485095880004e-05, | |
| "loss": 0.3867, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.924055439529144e-05, | |
| "loss": 0.3353, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.914562369470287e-05, | |
| "loss": 0.2702, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.90506929941143e-05, | |
| "loss": 0.3428, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.3094424605369568, | |
| "eval_runtime": 58.2772, | |
| "eval_samples_per_second": 40.17, | |
| "eval_steps_per_second": 5.028, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.895576229352573e-05, | |
| "loss": 0.3244, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.8860831592937154e-05, | |
| "loss": 0.2542, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.876590089234859e-05, | |
| "loss": 0.3446, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.867097019176002e-05, | |
| "loss": 0.3159, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.857603949117145e-05, | |
| "loss": 0.381, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.848110879058287e-05, | |
| "loss": 0.347, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8386178089994304e-05, | |
| "loss": 0.3842, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8291247389405736e-05, | |
| "loss": 0.2412, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.819631668881717e-05, | |
| "loss": 0.2087, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.8101385988228595e-05, | |
| "loss": 0.2329, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.27652889490127563, | |
| "eval_runtime": 58.541, | |
| "eval_samples_per_second": 39.989, | |
| "eval_steps_per_second": 5.005, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.800645528764002e-05, | |
| "loss": 0.3388, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.7911524587051454e-05, | |
| "loss": 0.2755, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.7816593886462886e-05, | |
| "loss": 0.3393, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.772166318587432e-05, | |
| "loss": 0.2184, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.762673248528574e-05, | |
| "loss": 0.361, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.753180178469717e-05, | |
| "loss": 0.319, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7436871084108604e-05, | |
| "loss": 0.243, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7341940383520036e-05, | |
| "loss": 0.1723, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.724700968293146e-05, | |
| "loss": 0.2985, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.715207898234289e-05, | |
| "loss": 0.219, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.26980558037757874, | |
| "eval_runtime": 58.4964, | |
| "eval_samples_per_second": 40.02, | |
| "eval_steps_per_second": 5.009, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.705714828175432e-05, | |
| "loss": 0.2404, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.696221758116575e-05, | |
| "loss": 0.2999, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.686728688057718e-05, | |
| "loss": 0.1991, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.6772356179988605e-05, | |
| "loss": 0.2792, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.667742547940004e-05, | |
| "loss": 0.3693, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.658249477881147e-05, | |
| "loss": 0.184, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.64875640782229e-05, | |
| "loss": 0.301, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.639263337763433e-05, | |
| "loss": 0.3877, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.6297702677045755e-05, | |
| "loss": 0.3542, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.620277197645719e-05, | |
| "loss": 0.3478, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.260137140750885, | |
| "eval_runtime": 58.3879, | |
| "eval_samples_per_second": 40.094, | |
| "eval_steps_per_second": 5.018, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.610784127586862e-05, | |
| "loss": 0.2447, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6012910575280046e-05, | |
| "loss": 0.2646, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.591797987469147e-05, | |
| "loss": 0.2069, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5823049174102905e-05, | |
| "loss": 0.2278, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.572811847351434e-05, | |
| "loss": 0.2683, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.563318777292577e-05, | |
| "loss": 0.2214, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5538257072337196e-05, | |
| "loss": 0.2504, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.544332637174862e-05, | |
| "loss": 0.3694, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.5348395671160055e-05, | |
| "loss": 0.2084, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.525346497057149e-05, | |
| "loss": 0.2796, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 0.2488514631986618, | |
| "eval_runtime": 58.4775, | |
| "eval_samples_per_second": 40.032, | |
| "eval_steps_per_second": 5.01, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.515853426998291e-05, | |
| "loss": 0.3201, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5063603569394346e-05, | |
| "loss": 0.2574, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.496867286880577e-05, | |
| "loss": 0.3238, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.4873742168217205e-05, | |
| "loss": 0.2491, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.477881146762864e-05, | |
| "loss": 0.2018, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.468388076704006e-05, | |
| "loss": 0.2491, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.458895006645149e-05, | |
| "loss": 0.2946, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.449401936586292e-05, | |
| "loss": 0.2457, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4399088665274355e-05, | |
| "loss": 0.3586, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.430415796468578e-05, | |
| "loss": 0.3481, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.23894372582435608, | |
| "eval_runtime": 58.5146, | |
| "eval_samples_per_second": 40.007, | |
| "eval_steps_per_second": 5.007, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.420922726409721e-05, | |
| "loss": 0.3249, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.411429656350864e-05, | |
| "loss": 0.2069, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.401936586292007e-05, | |
| "loss": 0.2861, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.39244351623315e-05, | |
| "loss": 0.3132, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.382950446174293e-05, | |
| "loss": 0.3351, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3734573761154356e-05, | |
| "loss": 0.242, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.363964306056579e-05, | |
| "loss": 0.1696, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.354471235997722e-05, | |
| "loss": 0.2097, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.344978165938865e-05, | |
| "loss": 0.1941, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.335485095880008e-05, | |
| "loss": 0.288, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.23884864151477814, | |
| "eval_runtime": 58.471, | |
| "eval_samples_per_second": 40.037, | |
| "eval_steps_per_second": 5.011, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3259920258211506e-05, | |
| "loss": 0.4013, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.316498955762294e-05, | |
| "loss": 0.2957, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.3070058857034365e-05, | |
| "loss": 0.3827, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.29751281564458e-05, | |
| "loss": 0.3267, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.288019745585722e-05, | |
| "loss": 0.2165, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.2785266755268656e-05, | |
| "loss": 0.2865, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.269033605468009e-05, | |
| "loss": 0.3312, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2595405354091514e-05, | |
| "loss": 0.148, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.250047465350295e-05, | |
| "loss": 0.2366, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.240554395291437e-05, | |
| "loss": 0.2897, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.231247678399086, | |
| "eval_runtime": 58.3783, | |
| "eval_samples_per_second": 40.101, | |
| "eval_steps_per_second": 5.019, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.2310613252325806e-05, | |
| "loss": 0.336, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.221568255173723e-05, | |
| "loss": 0.1777, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.2120751851148664e-05, | |
| "loss": 0.2939, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.202582115056009e-05, | |
| "loss": 0.1607, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.193089044997152e-05, | |
| "loss": 0.2133, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.1835959749382956e-05, | |
| "loss": 0.2108, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.174102904879438e-05, | |
| "loss": 0.29, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1646098348205814e-05, | |
| "loss": 0.1991, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.155116764761724e-05, | |
| "loss": 0.1924, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.145623694702867e-05, | |
| "loss": 0.2086, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.22816401720046997, | |
| "eval_runtime": 58.4804, | |
| "eval_samples_per_second": 40.031, | |
| "eval_steps_per_second": 5.01, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.13613062464401e-05, | |
| "loss": 0.4082, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.126637554585153e-05, | |
| "loss": 0.2258, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.117144484526296e-05, | |
| "loss": 0.2124, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.107651414467439e-05, | |
| "loss": 0.2221, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.098158344408582e-05, | |
| "loss": 0.2443, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.088665274349725e-05, | |
| "loss": 0.2726, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.079172204290868e-05, | |
| "loss": 0.2459, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.069679134232011e-05, | |
| "loss": 0.3175, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.060186064173154e-05, | |
| "loss": 0.2747, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.0506929941142966e-05, | |
| "loss": 0.2623, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 0.22370626032352448, | |
| "eval_runtime": 58.4454, | |
| "eval_samples_per_second": 40.055, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.04119992405544e-05, | |
| "loss": 0.1652, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.0317068539965824e-05, | |
| "loss": 0.2484, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.022213783937726e-05, | |
| "loss": 0.3282, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.012720713878868e-05, | |
| "loss": 0.3819, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0032276438200116e-05, | |
| "loss": 0.2284, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.993734573761155e-05, | |
| "loss": 0.2976, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.9842415037022974e-05, | |
| "loss": 0.2607, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.974748433643441e-05, | |
| "loss": 0.1952, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.965255363584583e-05, | |
| "loss": 0.2174, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9557622935257265e-05, | |
| "loss": 0.2908, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.22206127643585205, | |
| "eval_runtime": 58.4493, | |
| "eval_samples_per_second": 40.052, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.946269223466869e-05, | |
| "loss": 0.3271, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9367761534080124e-05, | |
| "loss": 0.1407, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.927283083349155e-05, | |
| "loss": 0.2099, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.917790013290298e-05, | |
| "loss": 0.1994, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.9082969432314415e-05, | |
| "loss": 0.3258, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.898803873172584e-05, | |
| "loss": 0.1717, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.8893108031137274e-05, | |
| "loss": 0.2402, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.87981773305487e-05, | |
| "loss": 0.2235, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.870324662996013e-05, | |
| "loss": 0.2722, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.860831592937156e-05, | |
| "loss": 0.3279, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.21985061466693878, | |
| "eval_runtime": 58.3288, | |
| "eval_samples_per_second": 40.135, | |
| "eval_steps_per_second": 5.023, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.851338522878299e-05, | |
| "loss": 0.3217, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.841845452819442e-05, | |
| "loss": 0.2229, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.832352382760585e-05, | |
| "loss": 0.1454, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.822859312701728e-05, | |
| "loss": 0.3342, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.813366242642871e-05, | |
| "loss": 0.2445, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.803873172584014e-05, | |
| "loss": 0.2585, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.794380102525157e-05, | |
| "loss": 0.1308, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.7848870324663e-05, | |
| "loss": 0.3355, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.7753939624074425e-05, | |
| "loss": 0.2536, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.765900892348586e-05, | |
| "loss": 0.2139, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.21853680908679962, | |
| "eval_runtime": 58.4469, | |
| "eval_samples_per_second": 40.053, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7564078222897284e-05, | |
| "loss": 0.1639, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.746914752230872e-05, | |
| "loss": 0.1836, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.737421682172015e-05, | |
| "loss": 0.2165, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7279286121131575e-05, | |
| "loss": 0.3279, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7184355420543e-05, | |
| "loss": 0.2399, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.7089424719954434e-05, | |
| "loss": 0.2136, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.6994494019365867e-05, | |
| "loss": 0.2507, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.68995633187773e-05, | |
| "loss": 0.1976, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.6804632618188725e-05, | |
| "loss": 0.2714, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.670970191760015e-05, | |
| "loss": 0.3335, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.21167145669460297, | |
| "eval_runtime": 58.4442, | |
| "eval_samples_per_second": 40.055, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6614771217011584e-05, | |
| "loss": 0.1951, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6519840516423016e-05, | |
| "loss": 0.225, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.642490981583444e-05, | |
| "loss": 0.2911, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.632997911524587e-05, | |
| "loss": 0.2851, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.62350484146573e-05, | |
| "loss": 0.1638, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6140117714068734e-05, | |
| "loss": 0.3227, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.6045187013480166e-05, | |
| "loss": 0.3921, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.595025631289159e-05, | |
| "loss": 0.2796, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.585532561230302e-05, | |
| "loss": 0.2344, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.576039491171445e-05, | |
| "loss": 0.2523, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.2083868384361267, | |
| "eval_runtime": 58.4415, | |
| "eval_samples_per_second": 40.057, | |
| "eval_steps_per_second": 5.014, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.5665464211125884e-05, | |
| "loss": 0.3042, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.557053351053731e-05, | |
| "loss": 0.221, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.5475602809948735e-05, | |
| "loss": 0.1296, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.538067210936017e-05, | |
| "loss": 0.2397, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.52857414087716e-05, | |
| "loss": 0.2175, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.519081070818303e-05, | |
| "loss": 0.2222, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.509588000759446e-05, | |
| "loss": 0.2333, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.5000949307005885e-05, | |
| "loss": 0.0962, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.490601860641732e-05, | |
| "loss": 0.2326, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.481108790582875e-05, | |
| "loss": 0.1996, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.20676040649414062, | |
| "eval_runtime": 58.3991, | |
| "eval_samples_per_second": 40.086, | |
| "eval_steps_per_second": 5.017, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4716157205240176e-05, | |
| "loss": 0.2545, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.46212265046516e-05, | |
| "loss": 0.3154, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4526295804063035e-05, | |
| "loss": 0.2173, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.443136510347447e-05, | |
| "loss": 0.228, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.43364344028859e-05, | |
| "loss": 0.1942, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.424150370229732e-05, | |
| "loss": 0.1846, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.414657300170875e-05, | |
| "loss": 0.1876, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.4051642301120185e-05, | |
| "loss": 0.2501, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.395671160053162e-05, | |
| "loss": 0.3002, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.3861780899943043e-05, | |
| "loss": 0.2272, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.20572568476200104, | |
| "eval_runtime": 58.3352, | |
| "eval_samples_per_second": 40.13, | |
| "eval_steps_per_second": 5.023, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.376685019935447e-05, | |
| "loss": 0.197, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.36719194987659e-05, | |
| "loss": 0.2047, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.3576988798177335e-05, | |
| "loss": 0.2821, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.348205809758877e-05, | |
| "loss": 0.2521, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.3387127397000187e-05, | |
| "loss": 0.2899, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.329219669641162e-05, | |
| "loss": 0.3044, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.319726599582305e-05, | |
| "loss": 0.1524, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.3102335295234485e-05, | |
| "loss": 0.2236, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.300740459464591e-05, | |
| "loss": 0.3355, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.2912473894057336e-05, | |
| "loss": 0.2483, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.20285062491893768, | |
| "eval_runtime": 58.4497, | |
| "eval_samples_per_second": 40.052, | |
| "eval_steps_per_second": 5.013, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.281754319346877e-05, | |
| "loss": 0.1557, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.27226124928802e-05, | |
| "loss": 0.3256, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.2627681792291634e-05, | |
| "loss": 0.1996, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.2532751091703054e-05, | |
| "loss": 0.2646, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.2437820391114486e-05, | |
| "loss": 0.299, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.234288969052592e-05, | |
| "loss": 0.298, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.224795898993735e-05, | |
| "loss": 0.2281, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.215302828934878e-05, | |
| "loss": 0.1323, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.2058097588760203e-05, | |
| "loss": 0.2415, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.1963166888171636e-05, | |
| "loss": 0.2174, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.20354433357715607, | |
| "eval_runtime": 58.4014, | |
| "eval_samples_per_second": 40.085, | |
| "eval_steps_per_second": 5.017, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.186823618758307e-05, | |
| "loss": 0.152, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.1773305486994495e-05, | |
| "loss": 0.1671, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.167837478640592e-05, | |
| "loss": 0.1866, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.158344408581735e-05, | |
| "loss": 0.1769, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.1488513385228786e-05, | |
| "loss": 0.2413, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.139358268464022e-05, | |
| "loss": 0.2458, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.129865198405164e-05, | |
| "loss": 0.1918, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.120372128346307e-05, | |
| "loss": 0.244, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.11087905828745e-05, | |
| "loss": 0.2254, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1013859882285936e-05, | |
| "loss": 0.2934, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.19765831530094147, | |
| "eval_runtime": 58.4337, | |
| "eval_samples_per_second": 40.062, | |
| "eval_steps_per_second": 5.014, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.091892918169736e-05, | |
| "loss": 0.1601, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.082399848110879e-05, | |
| "loss": 0.1778, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.072906778052022e-05, | |
| "loss": 0.1302, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.063413707993165e-05, | |
| "loss": 0.1359, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.0539206379343086e-05, | |
| "loss": 0.2351, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.0444275678754508e-05, | |
| "loss": 0.0917, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.0349344978165938e-05, | |
| "loss": 0.1658, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.025441427757737e-05, | |
| "loss": 0.1769, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.01594835769888e-05, | |
| "loss": 0.2233, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.0064552876400232e-05, | |
| "loss": 0.178, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.200357124209404, | |
| "eval_runtime": 58.4498, | |
| "eval_samples_per_second": 40.051, | |
| "eval_steps_per_second": 5.013, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.9969622175811658e-05, | |
| "loss": 0.2113, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.9874691475223087e-05, | |
| "loss": 0.1336, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.977976077463452e-05, | |
| "loss": 0.2023, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.968483007404595e-05, | |
| "loss": 0.1174, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9589899373457375e-05, | |
| "loss": 0.2178, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9494968672868805e-05, | |
| "loss": 0.1917, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9400037972280237e-05, | |
| "loss": 0.1737, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9305107271691667e-05, | |
| "loss": 0.2051, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.92101765711031e-05, | |
| "loss": 0.1652, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9115245870514525e-05, | |
| "loss": 0.0923, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.19968745112419128, | |
| "eval_runtime": 58.499, | |
| "eval_samples_per_second": 40.018, | |
| "eval_steps_per_second": 5.009, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9020315169925954e-05, | |
| "loss": 0.1799, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.8925384469337384e-05, | |
| "loss": 0.1597, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.8830453768748816e-05, | |
| "loss": 0.3413, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8735523068160242e-05, | |
| "loss": 0.1615, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.864059236757167e-05, | |
| "loss": 0.2355, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8545661666983104e-05, | |
| "loss": 0.1218, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8450730966394534e-05, | |
| "loss": 0.2614, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8355800265805966e-05, | |
| "loss": 0.1555, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.826086956521739e-05, | |
| "loss": 0.1589, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.816593886462882e-05, | |
| "loss": 0.2157, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.196543350815773, | |
| "eval_runtime": 58.4466, | |
| "eval_samples_per_second": 40.054, | |
| "eval_steps_per_second": 5.013, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.807100816404025e-05, | |
| "loss": 0.2694, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.7976077463451683e-05, | |
| "loss": 0.1692, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.7881146762863113e-05, | |
| "loss": 0.2634, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.778621606227454e-05, | |
| "loss": 0.2017, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.769128536168597e-05, | |
| "loss": 0.2822, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.75963546610974e-05, | |
| "loss": 0.1717, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7501423960508833e-05, | |
| "loss": 0.217, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7406493259920256e-05, | |
| "loss": 0.2446, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.731156255933169e-05, | |
| "loss": 0.0997, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7216631858743118e-05, | |
| "loss": 0.1756, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.19417181611061096, | |
| "eval_runtime": 58.5165, | |
| "eval_samples_per_second": 40.006, | |
| "eval_steps_per_second": 5.007, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.712170115815455e-05, | |
| "loss": 0.284, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.702677045756598e-05, | |
| "loss": 0.2041, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.6931839756977406e-05, | |
| "loss": 0.1631, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.683690905638884e-05, | |
| "loss": 0.2154, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6741978355800268e-05, | |
| "loss": 0.2117, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.66470476552117e-05, | |
| "loss": 0.1765, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6552116954623123e-05, | |
| "loss": 0.2031, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6457186254034556e-05, | |
| "loss": 0.1512, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6362255553445985e-05, | |
| "loss": 0.2909, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6267324852857418e-05, | |
| "loss": 0.1469, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.19603069126605988, | |
| "eval_runtime": 58.4148, | |
| "eval_samples_per_second": 40.075, | |
| "eval_steps_per_second": 5.016, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6172394152268847e-05, | |
| "loss": 0.1734, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6077463451680273e-05, | |
| "loss": 0.313, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.5982532751091705e-05, | |
| "loss": 0.1663, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.5887602050503135e-05, | |
| "loss": 0.3132, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.5792671349914564e-05, | |
| "loss": 0.2293, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.569774064932599e-05, | |
| "loss": 0.186, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5602809948737423e-05, | |
| "loss": 0.2088, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5507879248148852e-05, | |
| "loss": 0.1345, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5412948547560285e-05, | |
| "loss": 0.2065, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5318017846971714e-05, | |
| "loss": 0.258, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 0.19143950939178467, | |
| "eval_runtime": 58.5228, | |
| "eval_samples_per_second": 40.001, | |
| "eval_steps_per_second": 5.007, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.522308714638314e-05, | |
| "loss": 0.1787, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.512815644579457e-05, | |
| "loss": 0.1638, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5033225745206002e-05, | |
| "loss": 0.1707, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.493829504461743e-05, | |
| "loss": 0.1747, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.484336434402886e-05, | |
| "loss": 0.2062, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.474843364344029e-05, | |
| "loss": 0.2059, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.465350294285172e-05, | |
| "loss": 0.2113, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.455857224226315e-05, | |
| "loss": 0.2218, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4463641541674578e-05, | |
| "loss": 0.1355, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.436871084108601e-05, | |
| "loss": 0.2385, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.18914321064949036, | |
| "eval_runtime": 58.3785, | |
| "eval_samples_per_second": 40.1, | |
| "eval_steps_per_second": 5.019, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4273780140497436e-05, | |
| "loss": 0.1727, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.417884943990887e-05, | |
| "loss": 0.1262, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4083918739320295e-05, | |
| "loss": 0.2272, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.3988988038731727e-05, | |
| "loss": 0.1757, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.3894057338143157e-05, | |
| "loss": 0.2295, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.3799126637554586e-05, | |
| "loss": 0.2275, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.370419593696602e-05, | |
| "loss": 0.231, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3609265236377445e-05, | |
| "loss": 0.1622, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3514334535788877e-05, | |
| "loss": 0.2007, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3419403835200303e-05, | |
| "loss": 0.2505, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.1877710372209549, | |
| "eval_runtime": 58.4546, | |
| "eval_samples_per_second": 40.048, | |
| "eval_steps_per_second": 5.012, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3324473134611736e-05, | |
| "loss": 0.2512, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.3229542434023162e-05, | |
| "loss": 0.1914, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.3134611733434594e-05, | |
| "loss": 0.22, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.3039681032846024e-05, | |
| "loss": 0.1865, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.2944750332257453e-05, | |
| "loss": 0.1343, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.2849819631668882e-05, | |
| "loss": 0.1456, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.275488893108031e-05, | |
| "loss": 0.1365, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2659958230491744e-05, | |
| "loss": 0.2423, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.256502752990317e-05, | |
| "loss": 0.1526, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2470096829314603e-05, | |
| "loss": 0.2539, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.18716147541999817, | |
| "eval_runtime": 58.4521, | |
| "eval_samples_per_second": 40.05, | |
| "eval_steps_per_second": 5.013, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.237516612872603e-05, | |
| "loss": 0.1349, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.228023542813746e-05, | |
| "loss": 0.1244, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.2185304727548887e-05, | |
| "loss": 0.1925, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.209037402696032e-05, | |
| "loss": 0.182, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.199544332637175e-05, | |
| "loss": 0.2175, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.190051262578318e-05, | |
| "loss": 0.2785, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.180558192519461e-05, | |
| "loss": 0.2238, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1710651224606037e-05, | |
| "loss": 0.2064, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.161572052401747e-05, | |
| "loss": 0.216, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1520789823428896e-05, | |
| "loss": 0.2044, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.1867467164993286, | |
| "eval_runtime": 58.4213, | |
| "eval_samples_per_second": 40.071, | |
| "eval_steps_per_second": 5.015, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.142585912284033e-05, | |
| "loss": 0.1543, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1330928422251758e-05, | |
| "loss": 0.1908, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1235997721663187e-05, | |
| "loss": 0.2032, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1141067021074616e-05, | |
| "loss": 0.2523, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1046136320486046e-05, | |
| "loss": 0.338, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.0951205619897475e-05, | |
| "loss": 0.1203, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.0856274919308904e-05, | |
| "loss": 0.2273, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.0761344218720337e-05, | |
| "loss": 0.2939, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0666413518131763e-05, | |
| "loss": 0.2844, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0571482817543196e-05, | |
| "loss": 0.1955, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.18449129164218903, | |
| "eval_runtime": 58.3906, | |
| "eval_samples_per_second": 40.092, | |
| "eval_steps_per_second": 5.018, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0476552116954625e-05, | |
| "loss": 0.1577, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0381621416366054e-05, | |
| "loss": 0.1706, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0286690715777483e-05, | |
| "loss": 0.1748, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.0191760015188913e-05, | |
| "loss": 0.2236, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.0096829314600342e-05, | |
| "loss": 0.2346, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.000189861401177e-05, | |
| "loss": 0.284, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.99069679134232e-05, | |
| "loss": 0.2868, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.981203721283463e-05, | |
| "loss": 0.2196, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9717106512246063e-05, | |
| "loss": 0.1372, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9622175811657492e-05, | |
| "loss": 0.1619, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.18382784724235535, | |
| "eval_runtime": 58.4804, | |
| "eval_samples_per_second": 40.031, | |
| "eval_steps_per_second": 5.01, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.952724511106892e-05, | |
| "loss": 0.1281, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.943231441048035e-05, | |
| "loss": 0.1864, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.933738370989178e-05, | |
| "loss": 0.2146, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.924245300930321e-05, | |
| "loss": 0.245, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.914752230871464e-05, | |
| "loss": 0.1107, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9052591608126068e-05, | |
| "loss": 0.1602, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8957660907537497e-05, | |
| "loss": 0.2293, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.886273020694893e-05, | |
| "loss": 0.1431, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.876779950636036e-05, | |
| "loss": 0.1759, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8672868805771788e-05, | |
| "loss": 0.1977, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.18313062191009521, | |
| "eval_runtime": 58.2108, | |
| "eval_samples_per_second": 40.216, | |
| "eval_steps_per_second": 5.033, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8577938105183218e-05, | |
| "loss": 0.1802, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8483007404594647e-05, | |
| "loss": 0.2396, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8388076704006076e-05, | |
| "loss": 0.1982, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8293146003417505e-05, | |
| "loss": 0.1658, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8198215302828935e-05, | |
| "loss": 0.2003, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8103284602240364e-05, | |
| "loss": 0.2009, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8008353901651793e-05, | |
| "loss": 0.1288, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.7913423201063226e-05, | |
| "loss": 0.2254, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.7818492500474655e-05, | |
| "loss": 0.2588, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7723561799886085e-05, | |
| "loss": 0.1509, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.18137221038341522, | |
| "eval_runtime": 58.5173, | |
| "eval_samples_per_second": 40.005, | |
| "eval_steps_per_second": 5.007, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7628631099297514e-05, | |
| "loss": 0.2978, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7533700398708943e-05, | |
| "loss": 0.1508, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7438769698120372e-05, | |
| "loss": 0.2011, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7343838997531802e-05, | |
| "loss": 0.1574, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.7248908296943234e-05, | |
| "loss": 0.1486, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.715397759635466e-05, | |
| "loss": 0.1581, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.7059046895766093e-05, | |
| "loss": 0.3014, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.6964116195177522e-05, | |
| "loss": 0.2699, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.686918549458895e-05, | |
| "loss": 0.1748, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.677425479400038e-05, | |
| "loss": 0.2453, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.18177372217178345, | |
| "eval_runtime": 58.3665, | |
| "eval_samples_per_second": 40.109, | |
| "eval_steps_per_second": 5.02, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.667932409341181e-05, | |
| "loss": 0.1506, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.658439339282324e-05, | |
| "loss": 0.169, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.648946269223467e-05, | |
| "loss": 0.177, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.63945319916461e-05, | |
| "loss": 0.2706, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6299601291057527e-05, | |
| "loss": 0.2052, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.620467059046896e-05, | |
| "loss": 0.2956, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.6109739889880386e-05, | |
| "loss": 0.1348, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.601480918929182e-05, | |
| "loss": 0.2255, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.5919878488703248e-05, | |
| "loss": 0.1527, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.5824947788114677e-05, | |
| "loss": 0.1772, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.1805400401353836, | |
| "eval_runtime": 58.3241, | |
| "eval_samples_per_second": 40.138, | |
| "eval_steps_per_second": 5.024, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5730017087526107e-05, | |
| "loss": 0.2948, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5635086386937536e-05, | |
| "loss": 0.1911, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.554015568634897e-05, | |
| "loss": 0.1564, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5445224985760394e-05, | |
| "loss": 0.1219, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5350294285171827e-05, | |
| "loss": 0.1635, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.5255363584583255e-05, | |
| "loss": 0.1318, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5160432883994686e-05, | |
| "loss": 0.1294, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5065502183406113e-05, | |
| "loss": 0.1627, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.4970571482817544e-05, | |
| "loss": 0.1727, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.4875640782228972e-05, | |
| "loss": 0.1618, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.17953605949878693, | |
| "eval_runtime": 58.4568, | |
| "eval_samples_per_second": 40.047, | |
| "eval_steps_per_second": 5.012, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.4780710081640403e-05, | |
| "loss": 0.2285, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4685779381051834e-05, | |
| "loss": 0.2551, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4590848680463261e-05, | |
| "loss": 0.1614, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4495917979874692e-05, | |
| "loss": 0.1668, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4400987279286122e-05, | |
| "loss": 0.1845, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4306056578697553e-05, | |
| "loss": 0.1944, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.421112587810898e-05, | |
| "loss": 0.1395, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.4116195177520411e-05, | |
| "loss": 0.218, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.4021264476931839e-05, | |
| "loss": 0.1906, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.392633377634327e-05, | |
| "loss": 0.2207, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.17874407768249512, | |
| "eval_runtime": 58.3852, | |
| "eval_samples_per_second": 40.096, | |
| "eval_steps_per_second": 5.018, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3831403075754701e-05, | |
| "loss": 0.1741, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3736472375166129e-05, | |
| "loss": 0.1913, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.364154167457756e-05, | |
| "loss": 0.215, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3546610973988987e-05, | |
| "loss": 0.2837, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3451680273400418e-05, | |
| "loss": 0.2142, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3356749572811847e-05, | |
| "loss": 0.1603, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3261818872223278e-05, | |
| "loss": 0.1684, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.316688817163471e-05, | |
| "loss": 0.3142, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.3071957471046137e-05, | |
| "loss": 0.1799, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.2977026770457568e-05, | |
| "loss": 0.2678, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.17639276385307312, | |
| "eval_runtime": 58.4337, | |
| "eval_samples_per_second": 40.062, | |
| "eval_steps_per_second": 5.014, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.2882096069868996e-05, | |
| "loss": 0.2038, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.2787165369280427e-05, | |
| "loss": 0.2256, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2692234668691854e-05, | |
| "loss": 0.1223, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2597303968103285e-05, | |
| "loss": 0.2096, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2502373267514714e-05, | |
| "loss": 0.2944, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2407442566926145e-05, | |
| "loss": 0.1925, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2312511866337575e-05, | |
| "loss": 0.186, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2217581165749004e-05, | |
| "loss": 0.1997, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2122650465160433e-05, | |
| "loss": 0.2256, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2027719764571863e-05, | |
| "loss": 0.2631, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.17684458196163177, | |
| "eval_runtime": 58.4335, | |
| "eval_samples_per_second": 40.063, | |
| "eval_steps_per_second": 5.014, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.1932789063983294e-05, | |
| "loss": 0.1079, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.1837858363394723e-05, | |
| "loss": 0.2022, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1742927662806152e-05, | |
| "loss": 0.1546, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1647996962217581e-05, | |
| "loss": 0.2763, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.155306626162901e-05, | |
| "loss": 0.2312, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.145813556104044e-05, | |
| "loss": 0.1166, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1363204860451871e-05, | |
| "loss": 0.1367, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.12682741598633e-05, | |
| "loss": 0.1772, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.117334345927473e-05, | |
| "loss": 0.1582, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.107841275868616e-05, | |
| "loss": 0.1752, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.17702791094779968, | |
| "eval_runtime": 58.4032, | |
| "eval_samples_per_second": 40.083, | |
| "eval_steps_per_second": 5.017, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.098348205809759e-05, | |
| "loss": 0.1964, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.088855135750902e-05, | |
| "loss": 0.152, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.0793620656920449e-05, | |
| "loss": 0.1868, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0698689956331878e-05, | |
| "loss": 0.2053, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0603759255743307e-05, | |
| "loss": 0.2861, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0508828555154736e-05, | |
| "loss": 0.1649, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0413897854566167e-05, | |
| "loss": 0.1928, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0318967153977597e-05, | |
| "loss": 0.3268, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0224036453389028e-05, | |
| "loss": 0.2028, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0129105752800457e-05, | |
| "loss": 0.1363, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.17664198577404022, | |
| "eval_runtime": 58.4373, | |
| "eval_samples_per_second": 40.06, | |
| "eval_steps_per_second": 5.014, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0034175052211886e-05, | |
| "loss": 0.1729, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.939244351623316e-06, | |
| "loss": 0.1749, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.844313651034745e-06, | |
| "loss": 0.213, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.749382950446174e-06, | |
| "loss": 0.2011, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.654452249857603e-06, | |
| "loss": 0.2514, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.559521549269033e-06, | |
| "loss": 0.208, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.464590848680464e-06, | |
| "loss": 0.2008, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.369660148091893e-06, | |
| "loss": 0.1669, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.274729447503324e-06, | |
| "loss": 0.2574, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.179798746914753e-06, | |
| "loss": 0.1677, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.17548422515392303, | |
| "eval_runtime": 58.2554, | |
| "eval_samples_per_second": 40.185, | |
| "eval_steps_per_second": 5.03, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 9.084868046326183e-06, | |
| "loss": 0.2055, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.989937345737612e-06, | |
| "loss": 0.2344, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.895006645149041e-06, | |
| "loss": 0.1855, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.80007594456047e-06, | |
| "loss": 0.264, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.7051452439719e-06, | |
| "loss": 0.1931, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.61021454338333e-06, | |
| "loss": 0.1721, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.51528384279476e-06, | |
| "loss": 0.1217, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.42035314220619e-06, | |
| "loss": 0.1433, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.32542244161762e-06, | |
| "loss": 0.147, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.23049174102905e-06, | |
| "loss": 0.2486, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.17436346411705017, | |
| "eval_runtime": 58.3751, | |
| "eval_samples_per_second": 40.103, | |
| "eval_steps_per_second": 5.019, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.135561040440479e-06, | |
| "loss": 0.1932, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.040630339851908e-06, | |
| "loss": 0.1938, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.945699639263338e-06, | |
| "loss": 0.161, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.850768938674769e-06, | |
| "loss": 0.3298, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.755838238086198e-06, | |
| "loss": 0.1625, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.660907537497627e-06, | |
| "loss": 0.2666, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.565976836909057e-06, | |
| "loss": 0.183, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.4710461363204865e-06, | |
| "loss": 0.1222, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.376115435731916e-06, | |
| "loss": 0.2511, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.281184735143345e-06, | |
| "loss": 0.1793, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.17454643547534943, | |
| "eval_runtime": 58.4194, | |
| "eval_samples_per_second": 40.072, | |
| "eval_steps_per_second": 5.015, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.186254034554775e-06, | |
| "loss": 0.2343, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 7.0913233339662046e-06, | |
| "loss": 0.2605, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.9963926333776356e-06, | |
| "loss": 0.2308, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.901461932789065e-06, | |
| "loss": 0.2096, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.806531232200494e-06, | |
| "loss": 0.1517, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.7116005316119234e-06, | |
| "loss": 0.15, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.616669831023354e-06, | |
| "loss": 0.1687, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.521739130434783e-06, | |
| "loss": 0.1835, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.426808429846212e-06, | |
| "loss": 0.1475, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.3318777292576415e-06, | |
| "loss": 0.1875, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.17363451421260834, | |
| "eval_runtime": 58.3279, | |
| "eval_samples_per_second": 40.135, | |
| "eval_steps_per_second": 5.023, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.236947028669072e-06, | |
| "loss": 0.202, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.142016328080502e-06, | |
| "loss": 0.2219, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.047085627491931e-06, | |
| "loss": 0.1998, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.952154926903361e-06, | |
| "loss": 0.2013, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.8572242263147905e-06, | |
| "loss": 0.1644, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.76229352572622e-06, | |
| "loss": 0.1696, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.66736282513765e-06, | |
| "loss": 0.1925, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.57243212454908e-06, | |
| "loss": 0.1828, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.477501423960509e-06, | |
| "loss": 0.232, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.382570723371939e-06, | |
| "loss": 0.1045, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 0.1733243316411972, | |
| "eval_runtime": 58.4606, | |
| "eval_samples_per_second": 40.044, | |
| "eval_steps_per_second": 5.012, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.287640022783368e-06, | |
| "loss": 0.1167, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.192709322194798e-06, | |
| "loss": 0.2227, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.097778621606228e-06, | |
| "loss": 0.1359, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.0028479210176575e-06, | |
| "loss": 0.1982, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.907917220429087e-06, | |
| "loss": 0.138, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.812986519840516e-06, | |
| "loss": 0.1427, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.718055819251946e-06, | |
| "loss": 0.1676, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.623125118663376e-06, | |
| "loss": 0.1023, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.528194418074806e-06, | |
| "loss": 0.2042, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.433263717486235e-06, | |
| "loss": 0.2182, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.17259711027145386, | |
| "eval_runtime": 58.4026, | |
| "eval_samples_per_second": 40.084, | |
| "eval_steps_per_second": 5.017, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.338333016897665e-06, | |
| "loss": 0.1344, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.2434023163090944e-06, | |
| "loss": 0.2458, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.1484716157205246e-06, | |
| "loss": 0.2166, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.053540915131954e-06, | |
| "loss": 0.2117, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.958610214543384e-06, | |
| "loss": 0.1784, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.863679513954813e-06, | |
| "loss": 0.1336, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.768748813366243e-06, | |
| "loss": 0.2307, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.6738181127776723e-06, | |
| "loss": 0.174, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.5788874121891016e-06, | |
| "loss": 0.2324, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.483956711600532e-06, | |
| "loss": 0.1661, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.17190437018871307, | |
| "eval_runtime": 58.4266, | |
| "eval_samples_per_second": 40.067, | |
| "eval_steps_per_second": 5.015, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.3890260110119615e-06, | |
| "loss": 0.1649, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.294095310423391e-06, | |
| "loss": 0.2308, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.1991646098348205e-06, | |
| "loss": 0.1403, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.10423390924625e-06, | |
| "loss": 0.1748, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.0093032086576803e-06, | |
| "loss": 0.2285, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.9143725080691096e-06, | |
| "loss": 0.1798, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.8194418074805394e-06, | |
| "loss": 0.1421, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.724511106891969e-06, | |
| "loss": 0.3226, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.629580406303399e-06, | |
| "loss": 0.1795, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.534649705714828e-06, | |
| "loss": 0.1219, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.17184509336948395, | |
| "eval_runtime": 58.247, | |
| "eval_samples_per_second": 40.191, | |
| "eval_steps_per_second": 5.03, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.439719005126258e-06, | |
| "loss": 0.1187, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.3447883045376875e-06, | |
| "loss": 0.2332, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.2498576039491172e-06, | |
| "loss": 0.2408, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.154926903360547e-06, | |
| "loss": 0.1693, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 2.0599962027719763e-06, | |
| "loss": 0.2376, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.9650655021834064e-06, | |
| "loss": 0.2142, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.8701348015948357e-06, | |
| "loss": 0.0916, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.7752041010062656e-06, | |
| "loss": 0.1838, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.6802734004176951e-06, | |
| "loss": 0.2352, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.5853426998291248e-06, | |
| "loss": 0.2286, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 0.17164459824562073, | |
| "eval_runtime": 58.2956, | |
| "eval_samples_per_second": 40.157, | |
| "eval_steps_per_second": 5.026, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.4904119992405544e-06, | |
| "loss": 0.2136, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.395481298651984e-06, | |
| "loss": 0.1367, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.3005505980634138e-06, | |
| "loss": 0.1116, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.2056198974748435e-06, | |
| "loss": 0.1649, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.110689196886273e-06, | |
| "loss": 0.1865, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0157584962977027e-06, | |
| "loss": 0.2308, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 9.208277957091325e-07, | |
| "loss": 0.1919, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.258970951205621e-07, | |
| "loss": 0.1813, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.309663945319917e-07, | |
| "loss": 0.1814, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 6.360356939434213e-07, | |
| "loss": 0.1964, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 0.17137235403060913, | |
| "eval_runtime": 58.4148, | |
| "eval_samples_per_second": 40.075, | |
| "eval_steps_per_second": 5.016, | |
| "step": 5200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5267, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 1454239855411200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |