| { | |
| "best_metric": 0.6692019104957581, | |
| "best_model_checkpoint": "./croupier-creature-classifier/checkpoint-2000", | |
| "epoch": 50.0, | |
| "global_step": 4550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.9934065934065934e-05, | |
| "loss": 1.3796, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.9868131868131868e-05, | |
| "loss": 1.3597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.9802197802197805e-05, | |
| "loss": 1.3427, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.973626373626374e-05, | |
| "loss": 1.3331, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.9670329670329673e-05, | |
| "loss": 1.275, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 2.9604395604395606e-05, | |
| "loss": 1.2765, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.953846153846154e-05, | |
| "loss": 1.2306, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.947252747252747e-05, | |
| "loss": 1.2621, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.9406593406593407e-05, | |
| "loss": 1.1997, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 2.934065934065934e-05, | |
| "loss": 1.1159, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.611764705882353, | |
| "eval_loss": 1.1144014596939087, | |
| "eval_runtime": 1.5221, | |
| "eval_samples_per_second": 111.687, | |
| "eval_steps_per_second": 14.454, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 2.9274725274725275e-05, | |
| "loss": 1.0839, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.920879120879121e-05, | |
| "loss": 1.0689, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9142857142857142e-05, | |
| "loss": 0.9898, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.907692307692308e-05, | |
| "loss": 0.9495, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.9010989010989013e-05, | |
| "loss": 0.9943, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.8945054945054947e-05, | |
| "loss": 0.98, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.887912087912088e-05, | |
| "loss": 0.9986, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.8813186813186814e-05, | |
| "loss": 0.9522, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.8747252747252748e-05, | |
| "loss": 0.8533, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 2.8681318681318685e-05, | |
| "loss": 0.8183, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_accuracy": 0.6882352941176471, | |
| "eval_loss": 0.9109101891517639, | |
| "eval_runtime": 1.6142, | |
| "eval_samples_per_second": 105.317, | |
| "eval_steps_per_second": 13.629, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 2.861538461538462e-05, | |
| "loss": 0.7843, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.854945054945055e-05, | |
| "loss": 0.8093, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 2.8483516483516482e-05, | |
| "loss": 0.8541, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 2.8417582417582416e-05, | |
| "loss": 0.7405, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.8351648351648353e-05, | |
| "loss": 0.7858, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.8285714285714287e-05, | |
| "loss": 0.7966, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.821978021978022e-05, | |
| "loss": 0.695, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 2.8153846153846154e-05, | |
| "loss": 0.6649, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 2.8087912087912088e-05, | |
| "loss": 0.605, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 2.802197802197802e-05, | |
| "loss": 0.6829, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "eval_accuracy": 0.7235294117647059, | |
| "eval_loss": 0.7676671743392944, | |
| "eval_runtime": 1.6247, | |
| "eval_samples_per_second": 104.633, | |
| "eval_steps_per_second": 13.541, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.795604395604396e-05, | |
| "loss": 0.5722, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 2.7890109890109892e-05, | |
| "loss": 0.654, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 2.7824175824175826e-05, | |
| "loss": 0.7001, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 2.775824175824176e-05, | |
| "loss": 0.5804, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 2.7692307692307694e-05, | |
| "loss": 0.6638, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 2.7626373626373624e-05, | |
| "loss": 0.6668, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 2.756043956043956e-05, | |
| "loss": 0.5599, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 2.7494505494505495e-05, | |
| "loss": 0.5317, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 2.7428571428571428e-05, | |
| "loss": 0.5403, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 2.7362637362637362e-05, | |
| "loss": 0.5575, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "eval_accuracy": 0.6764705882352942, | |
| "eval_loss": 0.7670463919639587, | |
| "eval_runtime": 1.6237, | |
| "eval_samples_per_second": 104.698, | |
| "eval_steps_per_second": 13.549, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 2.7296703296703296e-05, | |
| "loss": 0.5018, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.7230769230769233e-05, | |
| "loss": 0.5715, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 2.7164835164835166e-05, | |
| "loss": 0.4884, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 2.7105494505494504e-05, | |
| "loss": 0.5533, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 2.703956043956044e-05, | |
| "loss": 0.5183, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 2.6973626373626375e-05, | |
| "loss": 0.4451, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.690769230769231e-05, | |
| "loss": 0.4605, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.6841758241758243e-05, | |
| "loss": 0.4289, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 2.6775824175824176e-05, | |
| "loss": 0.4433, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 2.670989010989011e-05, | |
| "loss": 0.4644, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "eval_accuracy": 0.6647058823529411, | |
| "eval_loss": 0.8459996581077576, | |
| "eval_runtime": 1.6386, | |
| "eval_samples_per_second": 103.747, | |
| "eval_steps_per_second": 13.426, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 2.6643956043956047e-05, | |
| "loss": 0.4732, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 2.657802197802198e-05, | |
| "loss": 0.4939, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 2.651208791208791e-05, | |
| "loss": 0.4209, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.6446153846153845e-05, | |
| "loss": 0.3783, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 2.638021978021978e-05, | |
| "loss": 0.4665, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 2.6314285714285715e-05, | |
| "loss": 0.2572, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.26, | |
| "learning_rate": 2.624835164835165e-05, | |
| "loss": 0.3752, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.37, | |
| "learning_rate": 2.6182417582417583e-05, | |
| "loss": 0.2943, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 2.6116483516483517e-05, | |
| "loss": 0.3949, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 2.605054945054945e-05, | |
| "loss": 0.3096, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.7081632614135742, | |
| "eval_runtime": 1.6198, | |
| "eval_samples_per_second": 104.953, | |
| "eval_steps_per_second": 13.582, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 2.5984615384615384e-05, | |
| "loss": 0.4314, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 2.591868131868132e-05, | |
| "loss": 0.3389, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 2.5852747252747255e-05, | |
| "loss": 0.399, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 2.578681318681319e-05, | |
| "loss": 0.3425, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 2.5720879120879122e-05, | |
| "loss": 0.3395, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 2.5654945054945056e-05, | |
| "loss": 0.3558, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 2.558901098901099e-05, | |
| "loss": 0.3773, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 2.5523076923076923e-05, | |
| "loss": 0.3493, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 2.5457142857142857e-05, | |
| "loss": 0.402, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 2.539120879120879e-05, | |
| "loss": 0.305, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.693938136100769, | |
| "eval_runtime": 1.7847, | |
| "eval_samples_per_second": 95.254, | |
| "eval_steps_per_second": 12.327, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 2.5325274725274724e-05, | |
| "loss": 0.3702, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 2.5259340659340658e-05, | |
| "loss": 0.374, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 2.5193406593406595e-05, | |
| "loss": 0.3374, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 2.512747252747253e-05, | |
| "loss": 0.2479, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 2.5061538461538462e-05, | |
| "loss": 0.3161, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 2.4995604395604396e-05, | |
| "loss": 0.3229, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 2.492967032967033e-05, | |
| "loss": 0.2871, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 2.4863736263736267e-05, | |
| "loss": 0.3116, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.68, | |
| "learning_rate": 2.47978021978022e-05, | |
| "loss": 0.3632, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "learning_rate": 2.4731868131868134e-05, | |
| "loss": 0.3349, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.79, | |
| "eval_accuracy": 0.7235294117647059, | |
| "eval_loss": 0.7285170555114746, | |
| "eval_runtime": 1.7358, | |
| "eval_samples_per_second": 97.94, | |
| "eval_steps_per_second": 12.675, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 2.4665934065934068e-05, | |
| "loss": 0.3465, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 2.4599999999999998e-05, | |
| "loss": 0.2579, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 2.4534065934065932e-05, | |
| "loss": 0.324, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 2.446813186813187e-05, | |
| "loss": 0.3192, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 2.4402197802197803e-05, | |
| "loss": 0.2076, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 2.4336263736263736e-05, | |
| "loss": 0.2456, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.56, | |
| "learning_rate": 2.427032967032967e-05, | |
| "loss": 0.3255, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 2.4204395604395604e-05, | |
| "loss": 0.3601, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 2.413846153846154e-05, | |
| "loss": 0.1986, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 2.4072527472527475e-05, | |
| "loss": 0.36, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "eval_accuracy": 0.7294117647058823, | |
| "eval_loss": 0.7664376497268677, | |
| "eval_runtime": 1.6387, | |
| "eval_samples_per_second": 103.742, | |
| "eval_steps_per_second": 13.425, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.4006593406593408e-05, | |
| "loss": 0.259, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 2.3940659340659342e-05, | |
| "loss": 0.2984, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 2.3874725274725276e-05, | |
| "loss": 0.2073, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 2.380879120879121e-05, | |
| "loss": 0.3265, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.44, | |
| "learning_rate": 2.3742857142857146e-05, | |
| "loss": 0.3372, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.55, | |
| "learning_rate": 2.3676923076923077e-05, | |
| "loss": 0.3518, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.66, | |
| "learning_rate": 2.361098901098901e-05, | |
| "loss": 0.2707, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 2.3545054945054944e-05, | |
| "loss": 0.2529, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 2.3479120879120878e-05, | |
| "loss": 0.258, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 2.341978021978022e-05, | |
| "loss": 0.3184, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.6806656718254089, | |
| "eval_runtime": 1.6209, | |
| "eval_samples_per_second": 104.882, | |
| "eval_steps_per_second": 13.573, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 2.3353846153846153e-05, | |
| "loss": 0.2439, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "learning_rate": 2.3287912087912087e-05, | |
| "loss": 0.1827, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 11.32, | |
| "learning_rate": 2.3221978021978024e-05, | |
| "loss": 0.2845, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 2.3156043956043957e-05, | |
| "loss": 0.2503, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 2.309010989010989e-05, | |
| "loss": 0.2009, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 2.3024175824175825e-05, | |
| "loss": 0.2486, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 2.295824175824176e-05, | |
| "loss": 0.1877, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 2.2892307692307692e-05, | |
| "loss": 0.3497, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 2.282637362637363e-05, | |
| "loss": 0.2559, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 2.2760439560439563e-05, | |
| "loss": 0.2815, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "eval_accuracy": 0.7352941176470589, | |
| "eval_loss": 0.7407693266868591, | |
| "eval_runtime": 1.6974, | |
| "eval_samples_per_second": 100.156, | |
| "eval_steps_per_second": 12.961, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 2.2694505494505497e-05, | |
| "loss": 0.2352, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 2.262857142857143e-05, | |
| "loss": 0.2422, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 2.256263736263736e-05, | |
| "loss": 0.2287, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 12.53, | |
| "learning_rate": 2.2496703296703298e-05, | |
| "loss": 0.282, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 2.243076923076923e-05, | |
| "loss": 0.2579, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 2.2364835164835165e-05, | |
| "loss": 0.2907, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "learning_rate": 2.22989010989011e-05, | |
| "loss": 0.3221, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 2.2232967032967032e-05, | |
| "loss": 0.2657, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 13.08, | |
| "learning_rate": 2.2167032967032966e-05, | |
| "loss": 0.2456, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "learning_rate": 2.2101098901098903e-05, | |
| "loss": 0.1745, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.19, | |
| "eval_accuracy": 0.7294117647058823, | |
| "eval_loss": 0.7527948617935181, | |
| "eval_runtime": 1.6243, | |
| "eval_samples_per_second": 104.661, | |
| "eval_steps_per_second": 13.544, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 2.2035164835164837e-05, | |
| "loss": 0.202, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 13.41, | |
| "learning_rate": 2.196923076923077e-05, | |
| "loss": 0.1601, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 13.52, | |
| "learning_rate": 2.1903296703296704e-05, | |
| "loss": 0.1467, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 13.63, | |
| "learning_rate": 2.1837362637362638e-05, | |
| "loss": 0.287, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 13.74, | |
| "learning_rate": 2.177142857142857e-05, | |
| "loss": 0.2805, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 2.170549450549451e-05, | |
| "loss": 0.2405, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 2.163956043956044e-05, | |
| "loss": 0.3035, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 14.07, | |
| "learning_rate": 2.1573626373626373e-05, | |
| "loss": 0.2273, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 2.1507692307692306e-05, | |
| "loss": 0.1933, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 2.144175824175824e-05, | |
| "loss": 0.1894, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.7634099721908569, | |
| "eval_runtime": 1.6355, | |
| "eval_samples_per_second": 103.947, | |
| "eval_steps_per_second": 13.452, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.1375824175824177e-05, | |
| "loss": 0.1862, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 14.51, | |
| "learning_rate": 2.130989010989011e-05, | |
| "loss": 0.258, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 14.62, | |
| "learning_rate": 2.1243956043956045e-05, | |
| "loss": 0.231, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 2.1178021978021978e-05, | |
| "loss": 0.2558, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 14.84, | |
| "learning_rate": 2.1112087912087912e-05, | |
| "loss": 0.1848, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 14.95, | |
| "learning_rate": 2.1046153846153846e-05, | |
| "loss": 0.2495, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 2.0980219780219783e-05, | |
| "loss": 0.2079, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 2.0914285714285716e-05, | |
| "loss": 0.1803, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 15.27, | |
| "learning_rate": 2.084835164835165e-05, | |
| "loss": 0.2434, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 2.0782417582417584e-05, | |
| "loss": 0.1641, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.7208631634712219, | |
| "eval_runtime": 1.7468, | |
| "eval_samples_per_second": 97.323, | |
| "eval_steps_per_second": 12.595, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.49, | |
| "learning_rate": 2.0716483516483514e-05, | |
| "loss": 0.2347, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 2.065054945054945e-05, | |
| "loss": 0.1929, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 15.71, | |
| "learning_rate": 2.0584615384615385e-05, | |
| "loss": 0.1588, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 2.051868131868132e-05, | |
| "loss": 0.2216, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 15.93, | |
| "learning_rate": 2.0452747252747252e-05, | |
| "loss": 0.1755, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 2.0386813186813186e-05, | |
| "loss": 0.2623, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 16.15, | |
| "learning_rate": 2.032087912087912e-05, | |
| "loss": 0.2498, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 16.26, | |
| "learning_rate": 2.0254945054945057e-05, | |
| "loss": 0.2103, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 16.37, | |
| "learning_rate": 2.018901098901099e-05, | |
| "loss": 0.1713, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.0123076923076924e-05, | |
| "loss": 0.1932, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "eval_accuracy": 0.7, | |
| "eval_loss": 0.9090902805328369, | |
| "eval_runtime": 1.6369, | |
| "eval_samples_per_second": 103.854, | |
| "eval_steps_per_second": 13.44, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 2.0057142857142858e-05, | |
| "loss": 0.256, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 1.999120879120879e-05, | |
| "loss": 0.1954, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 16.81, | |
| "learning_rate": 1.992527472527473e-05, | |
| "loss": 0.2644, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 1.9859340659340662e-05, | |
| "loss": 0.2049, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 1.9793406593406596e-05, | |
| "loss": 0.1822, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 1.9727472527472526e-05, | |
| "loss": 0.1925, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 1.966153846153846e-05, | |
| "loss": 0.2075, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 17.36, | |
| "learning_rate": 1.9595604395604394e-05, | |
| "loss": 0.2604, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 17.47, | |
| "learning_rate": 1.952967032967033e-05, | |
| "loss": 0.1662, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "learning_rate": 1.9463736263736264e-05, | |
| "loss": 0.1609, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.58, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.7208409309387207, | |
| "eval_runtime": 1.6376, | |
| "eval_samples_per_second": 103.809, | |
| "eval_steps_per_second": 13.434, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 17.69, | |
| "learning_rate": 1.9397802197802198e-05, | |
| "loss": 0.1817, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 1.9331868131868132e-05, | |
| "loss": 0.2423, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 1.9265934065934065e-05, | |
| "loss": 0.1722, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.1544, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 18.13, | |
| "learning_rate": 1.9134065934065936e-05, | |
| "loss": 0.1976, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 1.906813186813187e-05, | |
| "loss": 0.2191, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 18.35, | |
| "learning_rate": 1.9002197802197804e-05, | |
| "loss": 0.1458, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 1.8936263736263737e-05, | |
| "loss": 0.2027, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 18.57, | |
| "learning_rate": 1.887032967032967e-05, | |
| "loss": 0.1637, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 18.68, | |
| "learning_rate": 1.8804395604395605e-05, | |
| "loss": 0.132, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.68, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.8486713171005249, | |
| "eval_runtime": 1.6357, | |
| "eval_samples_per_second": 103.93, | |
| "eval_steps_per_second": 13.45, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 18.79, | |
| "learning_rate": 1.873846153846154e-05, | |
| "loss": 0.1319, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 1.8672527472527472e-05, | |
| "loss": 0.2005, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 1.8606593406593406e-05, | |
| "loss": 0.2234, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 19.12, | |
| "learning_rate": 1.854065934065934e-05, | |
| "loss": 0.188, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 19.23, | |
| "learning_rate": 1.8474725274725277e-05, | |
| "loss": 0.1322, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 1.840879120879121e-05, | |
| "loss": 0.2137, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 19.45, | |
| "learning_rate": 1.8342857142857144e-05, | |
| "loss": 0.2314, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 1.8276923076923078e-05, | |
| "loss": 0.1987, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 1.821098901098901e-05, | |
| "loss": 0.1955, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "learning_rate": 1.8145054945054945e-05, | |
| "loss": 0.1903, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 19.78, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.7911531329154968, | |
| "eval_runtime": 1.6371, | |
| "eval_samples_per_second": 103.842, | |
| "eval_steps_per_second": 13.438, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 19.89, | |
| "learning_rate": 1.8079120879120882e-05, | |
| "loss": 0.1333, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.8013186813186816e-05, | |
| "loss": 0.2119, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 20.11, | |
| "learning_rate": 1.794725274725275e-05, | |
| "loss": 0.1784, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 20.22, | |
| "learning_rate": 1.788131868131868e-05, | |
| "loss": 0.1821, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 1.7815384615384613e-05, | |
| "loss": 0.2508, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 1.7749450549450547e-05, | |
| "loss": 0.1599, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 20.55, | |
| "learning_rate": 1.7683516483516484e-05, | |
| "loss": 0.133, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 1.7617582417582418e-05, | |
| "loss": 0.1344, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 20.77, | |
| "learning_rate": 1.755164835164835e-05, | |
| "loss": 0.163, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 20.88, | |
| "learning_rate": 1.7485714285714285e-05, | |
| "loss": 0.121, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 20.88, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.6734881401062012, | |
| "eval_runtime": 1.6331, | |
| "eval_samples_per_second": 104.095, | |
| "eval_steps_per_second": 13.471, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "learning_rate": 1.741978021978022e-05, | |
| "loss": 0.1984, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 21.1, | |
| "learning_rate": 1.7353846153846156e-05, | |
| "loss": 0.15, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 21.21, | |
| "learning_rate": 1.728791208791209e-05, | |
| "loss": 0.11, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 1.7221978021978023e-05, | |
| "loss": 0.1753, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 21.43, | |
| "learning_rate": 1.7156043956043957e-05, | |
| "loss": 0.1535, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 1.709010989010989e-05, | |
| "loss": 0.1269, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 21.65, | |
| "learning_rate": 1.7024175824175825e-05, | |
| "loss": 0.1711, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.6958241758241758e-05, | |
| "loss": 0.1871, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 1.6892307692307692e-05, | |
| "loss": 0.1544, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "learning_rate": 1.6826373626373626e-05, | |
| "loss": 0.1903, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.7823529411764706, | |
| "eval_loss": 0.6692019104957581, | |
| "eval_runtime": 1.6545, | |
| "eval_samples_per_second": 102.753, | |
| "eval_steps_per_second": 13.297, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 22.09, | |
| "learning_rate": 1.676043956043956e-05, | |
| "loss": 0.1258, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 22.2, | |
| "learning_rate": 1.6694505494505493e-05, | |
| "loss": 0.1057, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 22.31, | |
| "learning_rate": 1.662857142857143e-05, | |
| "loss": 0.0954, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 22.42, | |
| "learning_rate": 1.6562637362637364e-05, | |
| "loss": 0.2413, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 22.53, | |
| "learning_rate": 1.6496703296703297e-05, | |
| "loss": 0.1073, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 22.64, | |
| "learning_rate": 1.643076923076923e-05, | |
| "loss": 0.2491, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "learning_rate": 1.6364835164835165e-05, | |
| "loss": 0.1972, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 1.62989010989011e-05, | |
| "loss": 0.1852, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "learning_rate": 1.6232967032967036e-05, | |
| "loss": 0.135, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 1.616703296703297e-05, | |
| "loss": 0.176, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "eval_accuracy": 0.7176470588235294, | |
| "eval_loss": 0.8350964784622192, | |
| "eval_runtime": 1.6244, | |
| "eval_samples_per_second": 104.652, | |
| "eval_steps_per_second": 13.543, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 23.19, | |
| "learning_rate": 1.6101098901098903e-05, | |
| "loss": 0.1485, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 23.3, | |
| "learning_rate": 1.6035164835164837e-05, | |
| "loss": 0.1436, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 23.41, | |
| "learning_rate": 1.5969230769230767e-05, | |
| "loss": 0.1783, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 1.5903296703296704e-05, | |
| "loss": 0.1655, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 23.63, | |
| "learning_rate": 1.5837362637362638e-05, | |
| "loss": 0.1274, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 23.74, | |
| "learning_rate": 1.577142857142857e-05, | |
| "loss": 0.1261, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 23.85, | |
| "learning_rate": 1.5705494505494505e-05, | |
| "loss": 0.2141, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 23.96, | |
| "learning_rate": 1.563956043956044e-05, | |
| "loss": 0.2215, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 24.07, | |
| "learning_rate": 1.5573626373626373e-05, | |
| "loss": 0.2243, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "learning_rate": 1.550769230769231e-05, | |
| "loss": 0.1186, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 24.18, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.7317846417427063, | |
| "eval_runtime": 1.63, | |
| "eval_samples_per_second": 104.295, | |
| "eval_steps_per_second": 13.497, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 24.29, | |
| "learning_rate": 1.5441758241758243e-05, | |
| "loss": 0.2046, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 24.4, | |
| "learning_rate": 1.5375824175824177e-05, | |
| "loss": 0.1992, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 24.51, | |
| "learning_rate": 1.530989010989011e-05, | |
| "loss": 0.1289, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 1.5243956043956046e-05, | |
| "loss": 0.1033, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 24.73, | |
| "learning_rate": 1.517802197802198e-05, | |
| "loss": 0.2098, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 24.84, | |
| "learning_rate": 1.5112087912087913e-05, | |
| "loss": 0.0928, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 24.95, | |
| "learning_rate": 1.5046153846153845e-05, | |
| "loss": 0.1469, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 25.05, | |
| "learning_rate": 1.498021978021978e-05, | |
| "loss": 0.0645, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 25.16, | |
| "learning_rate": 1.4914285714285715e-05, | |
| "loss": 0.1786, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "learning_rate": 1.4848351648351648e-05, | |
| "loss": 0.1424, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 25.27, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.7859658598899841, | |
| "eval_runtime": 1.6259, | |
| "eval_samples_per_second": 104.556, | |
| "eval_steps_per_second": 13.531, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 25.38, | |
| "learning_rate": 1.4782417582417582e-05, | |
| "loss": 0.0742, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 25.49, | |
| "learning_rate": 1.4716483516483517e-05, | |
| "loss": 0.1224, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.4650549450549451e-05, | |
| "loss": 0.1334, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 1.4584615384615385e-05, | |
| "loss": 0.1924, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 25.82, | |
| "learning_rate": 1.451868131868132e-05, | |
| "loss": 0.1386, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 25.93, | |
| "learning_rate": 1.4452747252747254e-05, | |
| "loss": 0.1982, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 26.04, | |
| "learning_rate": 1.4386813186813186e-05, | |
| "loss": 0.1341, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 1.4320879120879121e-05, | |
| "loss": 0.1664, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 26.26, | |
| "learning_rate": 1.4254945054945055e-05, | |
| "loss": 0.0903, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "learning_rate": 1.4189010989010989e-05, | |
| "loss": 0.144, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 26.37, | |
| "eval_accuracy": 0.788235294117647, | |
| "eval_loss": 0.7021328806877136, | |
| "eval_runtime": 1.618, | |
| "eval_samples_per_second": 105.065, | |
| "eval_steps_per_second": 13.597, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 26.48, | |
| "learning_rate": 1.4123076923076924e-05, | |
| "loss": 0.1747, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 26.59, | |
| "learning_rate": 1.4057142857142858e-05, | |
| "loss": 0.1655, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 1.3991208791208793e-05, | |
| "loss": 0.1003, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 26.81, | |
| "learning_rate": 1.3925274725274727e-05, | |
| "loss": 0.142, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "learning_rate": 1.3859340659340659e-05, | |
| "loss": 0.089, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 27.03, | |
| "learning_rate": 1.3793406593406594e-05, | |
| "loss": 0.2091, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 27.14, | |
| "learning_rate": 1.3727472527472528e-05, | |
| "loss": 0.1794, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 27.25, | |
| "learning_rate": 1.3661538461538461e-05, | |
| "loss": 0.133, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 1.3595604395604397e-05, | |
| "loss": 0.1039, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 27.47, | |
| "learning_rate": 1.352967032967033e-05, | |
| "loss": 0.1088, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 27.47, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.8109354972839355, | |
| "eval_runtime": 1.7131, | |
| "eval_samples_per_second": 99.233, | |
| "eval_steps_per_second": 12.842, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 27.58, | |
| "learning_rate": 1.3463736263736264e-05, | |
| "loss": 0.1443, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 1.3397802197802198e-05, | |
| "loss": 0.1106, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 27.8, | |
| "learning_rate": 1.3331868131868132e-05, | |
| "loss": 0.0908, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 27.91, | |
| "learning_rate": 1.3265934065934065e-05, | |
| "loss": 0.1268, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 28.02, | |
| "learning_rate": 1.32e-05, | |
| "loss": 0.194, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 28.13, | |
| "learning_rate": 1.3134065934065934e-05, | |
| "loss": 0.1085, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 28.24, | |
| "learning_rate": 1.306813186813187e-05, | |
| "loss": 0.0856, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 28.35, | |
| "learning_rate": 1.3002197802197803e-05, | |
| "loss": 0.1157, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 28.46, | |
| "learning_rate": 1.2936263736263735e-05, | |
| "loss": 0.0941, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 1.287032967032967e-05, | |
| "loss": 0.1019, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.8157252669334412, | |
| "eval_runtime": 1.6087, | |
| "eval_samples_per_second": 105.676, | |
| "eval_steps_per_second": 13.676, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 28.68, | |
| "learning_rate": 1.2804395604395605e-05, | |
| "loss": 0.1466, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 28.79, | |
| "learning_rate": 1.2738461538461538e-05, | |
| "loss": 0.0661, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "learning_rate": 1.2672527472527474e-05, | |
| "loss": 0.2147, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "learning_rate": 1.2606593406593407e-05, | |
| "loss": 0.2561, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.2540659340659341e-05, | |
| "loss": 0.1408, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 1.2474725274725275e-05, | |
| "loss": 0.0896, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "learning_rate": 1.2408791208791208e-05, | |
| "loss": 0.1356, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 29.45, | |
| "learning_rate": 1.2342857142857144e-05, | |
| "loss": 0.0914, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 29.56, | |
| "learning_rate": 1.2276923076923077e-05, | |
| "loss": 0.1355, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "learning_rate": 1.2210989010989011e-05, | |
| "loss": 0.0947, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.8027762174606323, | |
| "eval_runtime": 1.6188, | |
| "eval_samples_per_second": 105.014, | |
| "eval_steps_per_second": 13.59, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "learning_rate": 1.2145054945054947e-05, | |
| "loss": 0.0745, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 29.89, | |
| "learning_rate": 1.207912087912088e-05, | |
| "loss": 0.172, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 1.2013186813186812e-05, | |
| "loss": 0.1363, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 30.11, | |
| "learning_rate": 1.1947252747252748e-05, | |
| "loss": 0.1109, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 1.1881318681318681e-05, | |
| "loss": 0.0705, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 30.33, | |
| "learning_rate": 1.1815384615384615e-05, | |
| "loss": 0.1153, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 30.44, | |
| "learning_rate": 1.174945054945055e-05, | |
| "loss": 0.0552, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 30.55, | |
| "learning_rate": 1.1683516483516484e-05, | |
| "loss": 0.1828, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 30.66, | |
| "learning_rate": 1.1617582417582418e-05, | |
| "loss": 0.1159, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 1.1551648351648351e-05, | |
| "loss": 0.1715, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.8344667553901672, | |
| "eval_runtime": 1.6594, | |
| "eval_samples_per_second": 102.448, | |
| "eval_steps_per_second": 13.258, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 30.88, | |
| "learning_rate": 1.1485714285714285e-05, | |
| "loss": 0.2173, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 1.141978021978022e-05, | |
| "loss": 0.0776, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 31.1, | |
| "learning_rate": 1.1353846153846154e-05, | |
| "loss": 0.0849, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 31.21, | |
| "learning_rate": 1.1287912087912088e-05, | |
| "loss": 0.1367, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 31.32, | |
| "learning_rate": 1.1221978021978023e-05, | |
| "loss": 0.1146, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 1.1156043956043957e-05, | |
| "loss": 0.2185, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 31.54, | |
| "learning_rate": 1.1090109890109889e-05, | |
| "loss": 0.1426, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 31.65, | |
| "learning_rate": 1.1024175824175824e-05, | |
| "loss": 0.1934, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 31.76, | |
| "learning_rate": 1.0958241758241758e-05, | |
| "loss": 0.1535, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 31.87, | |
| "learning_rate": 1.0892307692307692e-05, | |
| "loss": 0.1046, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 31.87, | |
| "eval_accuracy": 0.7411764705882353, | |
| "eval_loss": 0.8577510118484497, | |
| "eval_runtime": 1.6297, | |
| "eval_samples_per_second": 104.313, | |
| "eval_steps_per_second": 13.499, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 31.98, | |
| "learning_rate": 1.0826373626373627e-05, | |
| "loss": 0.1664, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 32.09, | |
| "learning_rate": 1.076043956043956e-05, | |
| "loss": 0.1792, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 32.2, | |
| "learning_rate": 1.0694505494505496e-05, | |
| "loss": 0.1166, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 1.0628571428571428e-05, | |
| "loss": 0.078, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 32.42, | |
| "learning_rate": 1.0562637362637362e-05, | |
| "loss": 0.0868, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 32.53, | |
| "learning_rate": 1.0496703296703297e-05, | |
| "loss": 0.0976, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 32.64, | |
| "learning_rate": 1.0430769230769231e-05, | |
| "loss": 0.2388, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 32.75, | |
| "learning_rate": 1.0364835164835165e-05, | |
| "loss": 0.1135, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 1.02989010989011e-05, | |
| "loss": 0.1377, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 32.97, | |
| "learning_rate": 1.0232967032967034e-05, | |
| "loss": 0.1367, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 32.97, | |
| "eval_accuracy": 0.788235294117647, | |
| "eval_loss": 0.7669554948806763, | |
| "eval_runtime": 1.6159, | |
| "eval_samples_per_second": 105.202, | |
| "eval_steps_per_second": 13.614, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 33.08, | |
| "learning_rate": 1.0167032967032966e-05, | |
| "loss": 0.1076, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 33.19, | |
| "learning_rate": 1.0101098901098901e-05, | |
| "loss": 0.1596, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 33.3, | |
| "learning_rate": 1.0035164835164835e-05, | |
| "loss": 0.1152, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 33.41, | |
| "learning_rate": 9.96923076923077e-06, | |
| "loss": 0.1093, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 33.52, | |
| "learning_rate": 9.903296703296704e-06, | |
| "loss": 0.1465, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 33.63, | |
| "learning_rate": 9.843956043956044e-06, | |
| "loss": 0.1281, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 33.74, | |
| "learning_rate": 9.778021978021979e-06, | |
| "loss": 0.0871, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 9.712087912087913e-06, | |
| "loss": 0.0713, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 33.96, | |
| "learning_rate": 9.646153846153846e-06, | |
| "loss": 0.0605, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 34.07, | |
| "learning_rate": 9.580219780219782e-06, | |
| "loss": 0.1339, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 34.07, | |
| "eval_accuracy": 0.7647058823529411, | |
| "eval_loss": 0.776252269744873, | |
| "eval_runtime": 1.6196, | |
| "eval_samples_per_second": 104.967, | |
| "eval_steps_per_second": 13.584, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 34.18, | |
| "learning_rate": 9.514285714285714e-06, | |
| "loss": 0.1543, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 9.448351648351647e-06, | |
| "loss": 0.0526, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 34.4, | |
| "learning_rate": 9.382417582417583e-06, | |
| "loss": 0.1342, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 34.51, | |
| "learning_rate": 9.316483516483516e-06, | |
| "loss": 0.0849, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 34.62, | |
| "learning_rate": 9.25054945054945e-06, | |
| "loss": 0.0898, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 34.73, | |
| "learning_rate": 9.184615384615386e-06, | |
| "loss": 0.1102, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 34.84, | |
| "learning_rate": 9.11868131868132e-06, | |
| "loss": 0.1245, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 34.95, | |
| "learning_rate": 9.052747252747255e-06, | |
| "loss": 0.1517, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 35.05, | |
| "learning_rate": 8.986813186813187e-06, | |
| "loss": 0.15, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 35.16, | |
| "learning_rate": 8.92087912087912e-06, | |
| "loss": 0.1194, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 35.16, | |
| "eval_accuracy": 0.7705882352941177, | |
| "eval_loss": 0.7726542949676514, | |
| "eval_runtime": 1.6435, | |
| "eval_samples_per_second": 103.438, | |
| "eval_steps_per_second": 13.386, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 35.27, | |
| "learning_rate": 8.854945054945056e-06, | |
| "loss": 0.0909, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 8.78901098901099e-06, | |
| "loss": 0.0842, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 35.49, | |
| "learning_rate": 8.723076923076923e-06, | |
| "loss": 0.1693, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 35.6, | |
| "learning_rate": 8.657142857142858e-06, | |
| "loss": 0.1059, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 35.71, | |
| "learning_rate": 8.591208791208792e-06, | |
| "loss": 0.1426, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 35.82, | |
| "learning_rate": 8.525274725274724e-06, | |
| "loss": 0.1127, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 35.93, | |
| "learning_rate": 8.45934065934066e-06, | |
| "loss": 0.0513, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 36.04, | |
| "learning_rate": 8.393406593406593e-06, | |
| "loss": 0.1005, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 36.15, | |
| "learning_rate": 8.327472527472527e-06, | |
| "loss": 0.0906, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 36.26, | |
| "learning_rate": 8.261538461538462e-06, | |
| "loss": 0.151, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 36.26, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.8271679878234863, | |
| "eval_runtime": 1.8428, | |
| "eval_samples_per_second": 92.249, | |
| "eval_steps_per_second": 11.938, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 36.37, | |
| "learning_rate": 8.195604395604396e-06, | |
| "loss": 0.0569, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 36.48, | |
| "learning_rate": 8.129670329670331e-06, | |
| "loss": 0.1806, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 36.59, | |
| "learning_rate": 8.063736263736263e-06, | |
| "loss": 0.1399, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 36.7, | |
| "learning_rate": 7.997802197802197e-06, | |
| "loss": 0.1186, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 36.81, | |
| "learning_rate": 7.931868131868132e-06, | |
| "loss": 0.0971, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 7.865934065934066e-06, | |
| "loss": 0.1759, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 37.03, | |
| "learning_rate": 7.8e-06, | |
| "loss": 0.0609, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 37.14, | |
| "learning_rate": 7.734065934065935e-06, | |
| "loss": 0.101, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 37.25, | |
| "learning_rate": 7.668131868131869e-06, | |
| "loss": 0.0826, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "learning_rate": 7.602197802197802e-06, | |
| "loss": 0.0646, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 37.36, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 0.7721197009086609, | |
| "eval_runtime": 1.6753, | |
| "eval_samples_per_second": 101.472, | |
| "eval_steps_per_second": 13.132, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 37.47, | |
| "learning_rate": 7.536263736263736e-06, | |
| "loss": 0.1707, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 37.58, | |
| "learning_rate": 7.47032967032967e-06, | |
| "loss": 0.114, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 37.69, | |
| "learning_rate": 7.4043956043956046e-06, | |
| "loss": 0.1188, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 37.8, | |
| "learning_rate": 7.338461538461539e-06, | |
| "loss": 0.1788, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 37.91, | |
| "learning_rate": 7.272527472527472e-06, | |
| "loss": 0.1241, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 38.02, | |
| "learning_rate": 7.2065934065934065e-06, | |
| "loss": 0.1308, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 38.13, | |
| "learning_rate": 7.140659340659341e-06, | |
| "loss": 0.1154, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 38.24, | |
| "learning_rate": 7.0747252747252756e-06, | |
| "loss": 0.1787, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 38.35, | |
| "learning_rate": 7.008791208791208e-06, | |
| "loss": 0.1262, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 6.942857142857143e-06, | |
| "loss": 0.0801, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.8170506358146667, | |
| "eval_runtime": 1.6607, | |
| "eval_samples_per_second": 102.365, | |
| "eval_steps_per_second": 13.247, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 38.57, | |
| "learning_rate": 6.8769230769230775e-06, | |
| "loss": 0.098, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 38.68, | |
| "learning_rate": 6.810989010989011e-06, | |
| "loss": 0.1109, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 38.79, | |
| "learning_rate": 6.745054945054945e-06, | |
| "loss": 0.1078, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 38.9, | |
| "learning_rate": 6.679120879120879e-06, | |
| "loss": 0.0767, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "learning_rate": 6.613186813186814e-06, | |
| "loss": 0.0886, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 39.12, | |
| "learning_rate": 6.547252747252747e-06, | |
| "loss": 0.0631, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 39.23, | |
| "learning_rate": 6.481318681318681e-06, | |
| "loss": 0.0737, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "learning_rate": 6.415384615384616e-06, | |
| "loss": 0.1207, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 39.45, | |
| "learning_rate": 6.3494505494505496e-06, | |
| "loss": 0.0831, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 39.56, | |
| "learning_rate": 6.283516483516483e-06, | |
| "loss": 0.1038, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 39.56, | |
| "eval_accuracy": 0.7058823529411765, | |
| "eval_loss": 0.9464375376701355, | |
| "eval_runtime": 1.6231, | |
| "eval_samples_per_second": 104.738, | |
| "eval_steps_per_second": 13.554, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 39.67, | |
| "learning_rate": 6.217582417582418e-06, | |
| "loss": 0.1151, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 39.78, | |
| "learning_rate": 6.151648351648352e-06, | |
| "loss": 0.113, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 39.89, | |
| "learning_rate": 6.085714285714285e-06, | |
| "loss": 0.1226, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 6.01978021978022e-06, | |
| "loss": 0.0645, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 40.11, | |
| "learning_rate": 5.953846153846154e-06, | |
| "loss": 0.1398, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 40.22, | |
| "learning_rate": 5.887912087912089e-06, | |
| "loss": 0.0801, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 40.33, | |
| "learning_rate": 5.821978021978022e-06, | |
| "loss": 0.0787, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 40.44, | |
| "learning_rate": 5.756043956043956e-06, | |
| "loss": 0.1388, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 40.55, | |
| "learning_rate": 5.690109890109891e-06, | |
| "loss": 0.0356, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 40.66, | |
| "learning_rate": 5.624175824175824e-06, | |
| "loss": 0.16, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 40.66, | |
| "eval_accuracy": 0.7705882352941177, | |
| "eval_loss": 0.8004665374755859, | |
| "eval_runtime": 1.6262, | |
| "eval_samples_per_second": 104.537, | |
| "eval_steps_per_second": 13.528, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 40.77, | |
| "learning_rate": 5.558241758241758e-06, | |
| "loss": 0.1363, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 40.88, | |
| "learning_rate": 5.492307692307693e-06, | |
| "loss": 0.0803, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "learning_rate": 5.426373626373627e-06, | |
| "loss": 0.077, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 41.1, | |
| "learning_rate": 5.36043956043956e-06, | |
| "loss": 0.0912, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 41.21, | |
| "learning_rate": 5.2945054945054946e-06, | |
| "loss": 0.1425, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 41.32, | |
| "learning_rate": 5.228571428571429e-06, | |
| "loss": 0.0815, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 41.43, | |
| "learning_rate": 5.162637362637363e-06, | |
| "loss": 0.0987, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 5.0967032967032965e-06, | |
| "loss": 0.0457, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 41.65, | |
| "learning_rate": 5.030769230769231e-06, | |
| "loss": 0.1181, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "learning_rate": 4.9648351648351656e-06, | |
| "loss": 0.1151, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 41.76, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.8784206509590149, | |
| "eval_runtime": 1.6555, | |
| "eval_samples_per_second": 102.688, | |
| "eval_steps_per_second": 13.289, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 41.87, | |
| "learning_rate": 4.898901098901098e-06, | |
| "loss": 0.1219, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 41.98, | |
| "learning_rate": 4.832967032967033e-06, | |
| "loss": 0.0719, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 42.09, | |
| "learning_rate": 4.7670329670329675e-06, | |
| "loss": 0.0647, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 42.2, | |
| "learning_rate": 4.701098901098901e-06, | |
| "loss": 0.1066, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 42.31, | |
| "learning_rate": 4.635164835164835e-06, | |
| "loss": 0.052, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 42.42, | |
| "learning_rate": 4.569230769230769e-06, | |
| "loss": 0.0658, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 42.53, | |
| "learning_rate": 4.503296703296704e-06, | |
| "loss": 0.0851, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 4.437362637362637e-06, | |
| "loss": 0.071, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 42.75, | |
| "learning_rate": 4.371428571428571e-06, | |
| "loss": 0.0922, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "learning_rate": 4.305494505494506e-06, | |
| "loss": 0.1159, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 42.86, | |
| "eval_accuracy": 0.7470588235294118, | |
| "eval_loss": 0.85979163646698, | |
| "eval_runtime": 1.6327, | |
| "eval_samples_per_second": 104.124, | |
| "eval_steps_per_second": 13.475, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 42.97, | |
| "learning_rate": 4.2395604395604396e-06, | |
| "loss": 0.1347, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 4.173626373626373e-06, | |
| "loss": 0.0455, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 43.19, | |
| "learning_rate": 4.107692307692308e-06, | |
| "loss": 0.054, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 43.3, | |
| "learning_rate": 4.041758241758242e-06, | |
| "loss": 0.1078, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 43.41, | |
| "learning_rate": 3.975824175824176e-06, | |
| "loss": 0.0738, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 43.52, | |
| "learning_rate": 3.90989010989011e-06, | |
| "loss": 0.0672, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 43.63, | |
| "learning_rate": 3.843956043956044e-06, | |
| "loss": 0.0476, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 43.74, | |
| "learning_rate": 3.7780219780219784e-06, | |
| "loss": 0.1283, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 43.85, | |
| "learning_rate": 3.712087912087912e-06, | |
| "loss": 0.1116, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 43.96, | |
| "learning_rate": 3.646153846153846e-06, | |
| "loss": 0.0575, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 43.96, | |
| "eval_accuracy": 0.7529411764705882, | |
| "eval_loss": 0.8543334007263184, | |
| "eval_runtime": 1.6405, | |
| "eval_samples_per_second": 103.629, | |
| "eval_steps_per_second": 13.411, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 44.07, | |
| "learning_rate": 3.5802197802197803e-06, | |
| "loss": 0.079, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 44.18, | |
| "learning_rate": 3.5142857142857144e-06, | |
| "loss": 0.0763, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 44.29, | |
| "learning_rate": 3.4483516483516485e-06, | |
| "loss": 0.0445, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 44.4, | |
| "learning_rate": 3.3824175824175826e-06, | |
| "loss": 0.0939, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 44.51, | |
| "learning_rate": 3.3164835164835163e-06, | |
| "loss": 0.1475, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 3.250549450549451e-06, | |
| "loss": 0.1596, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 44.73, | |
| "learning_rate": 3.1846153846153846e-06, | |
| "loss": 0.1322, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 44.84, | |
| "learning_rate": 3.1186813186813187e-06, | |
| "loss": 0.1158, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 44.95, | |
| "learning_rate": 3.0527472527472528e-06, | |
| "loss": 0.075, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 45.05, | |
| "learning_rate": 2.986813186813187e-06, | |
| "loss": 0.164, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 45.05, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.8658636808395386, | |
| "eval_runtime": 1.518, | |
| "eval_samples_per_second": 111.989, | |
| "eval_steps_per_second": 14.493, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 45.16, | |
| "learning_rate": 2.920879120879121e-06, | |
| "loss": 0.0847, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 45.27, | |
| "learning_rate": 2.854945054945055e-06, | |
| "loss": 0.1098, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 45.38, | |
| "learning_rate": 2.7890109890109892e-06, | |
| "loss": 0.1282, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 45.49, | |
| "learning_rate": 2.723076923076923e-06, | |
| "loss": 0.0736, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 45.6, | |
| "learning_rate": 2.657142857142857e-06, | |
| "loss": 0.1344, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 45.71, | |
| "learning_rate": 2.591208791208791e-06, | |
| "loss": 0.1191, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 45.82, | |
| "learning_rate": 2.5252747252747253e-06, | |
| "loss": 0.0721, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 45.93, | |
| "learning_rate": 2.4593406593406594e-06, | |
| "loss": 0.0371, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 46.04, | |
| "learning_rate": 2.3934065934065935e-06, | |
| "loss": 0.0407, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 2.3274725274725276e-06, | |
| "loss": 0.1319, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "eval_accuracy": 0.7411764705882353, | |
| "eval_loss": 0.885351300239563, | |
| "eval_runtime": 1.4998, | |
| "eval_samples_per_second": 113.347, | |
| "eval_steps_per_second": 14.668, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 46.26, | |
| "learning_rate": 2.2615384615384617e-06, | |
| "loss": 0.1159, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 46.37, | |
| "learning_rate": 2.195604395604396e-06, | |
| "loss": 0.0659, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 46.48, | |
| "learning_rate": 2.1296703296703296e-06, | |
| "loss": 0.0948, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 46.59, | |
| "learning_rate": 2.0637362637362637e-06, | |
| "loss": 0.0886, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 46.7, | |
| "learning_rate": 1.9978021978021978e-06, | |
| "loss": 0.0889, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 46.81, | |
| "learning_rate": 1.931868131868132e-06, | |
| "loss": 0.0339, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "learning_rate": 1.8659340659340658e-06, | |
| "loss": 0.0697, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 47.03, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.0777, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 47.14, | |
| "learning_rate": 1.734065934065934e-06, | |
| "loss": 0.0546, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 47.25, | |
| "learning_rate": 1.6681318681318681e-06, | |
| "loss": 0.0489, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 47.25, | |
| "eval_accuracy": 0.7588235294117647, | |
| "eval_loss": 0.7507675886154175, | |
| "eval_runtime": 1.5139, | |
| "eval_samples_per_second": 112.29, | |
| "eval_steps_per_second": 14.532, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 47.36, | |
| "learning_rate": 1.6021978021978023e-06, | |
| "loss": 0.087, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 47.47, | |
| "learning_rate": 1.5362637362637364e-06, | |
| "loss": 0.0452, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 47.58, | |
| "learning_rate": 1.4703296703296705e-06, | |
| "loss": 0.0508, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.4043956043956046e-06, | |
| "loss": 0.0812, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 47.8, | |
| "learning_rate": 1.3384615384615383e-06, | |
| "loss": 0.0721, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 47.91, | |
| "learning_rate": 1.2725274725274724e-06, | |
| "loss": 0.0835, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 48.02, | |
| "learning_rate": 1.2065934065934065e-06, | |
| "loss": 0.1077, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 48.13, | |
| "learning_rate": 1.1406593406593406e-06, | |
| "loss": 0.0636, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 48.24, | |
| "learning_rate": 1.0747252747252748e-06, | |
| "loss": 0.1026, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 48.35, | |
| "learning_rate": 1.0087912087912089e-06, | |
| "loss": 0.0678, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 48.35, | |
| "eval_accuracy": 0.7352941176470589, | |
| "eval_loss": 0.8784447312355042, | |
| "eval_runtime": 1.5075, | |
| "eval_samples_per_second": 112.768, | |
| "eval_steps_per_second": 14.594, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 48.46, | |
| "learning_rate": 9.42857142857143e-07, | |
| "loss": 0.072, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 48.57, | |
| "learning_rate": 8.769230769230769e-07, | |
| "loss": 0.0526, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 48.68, | |
| "learning_rate": 8.10989010989011e-07, | |
| "loss": 0.0802, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 48.79, | |
| "learning_rate": 7.450549450549451e-07, | |
| "loss": 0.046, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 48.9, | |
| "learning_rate": 6.791208791208791e-07, | |
| "loss": 0.0656, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "learning_rate": 6.131868131868131e-07, | |
| "loss": 0.139, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 49.12, | |
| "learning_rate": 5.472527472527473e-07, | |
| "loss": 0.0576, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 4.813186813186814e-07, | |
| "loss": 0.0686, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 49.34, | |
| "learning_rate": 4.153846153846154e-07, | |
| "loss": 0.0658, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 49.45, | |
| "learning_rate": 3.4945054945054945e-07, | |
| "loss": 0.0832, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 49.45, | |
| "eval_accuracy": 0.7764705882352941, | |
| "eval_loss": 0.7247602343559265, | |
| "eval_runtime": 1.5084, | |
| "eval_samples_per_second": 112.699, | |
| "eval_steps_per_second": 14.585, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 49.56, | |
| "learning_rate": 2.835164835164835e-07, | |
| "loss": 0.0692, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 49.67, | |
| "learning_rate": 2.175824175824176e-07, | |
| "loss": 0.1135, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 49.78, | |
| "learning_rate": 1.5164835164835167e-07, | |
| "loss": 0.1512, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 49.89, | |
| "learning_rate": 8.571428571428572e-08, | |
| "loss": 0.1339, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 1.9780219780219782e-08, | |
| "loss": 0.1045, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 4550, | |
| "total_flos": 5.622144623740109e+18, | |
| "train_loss": 0.2358846340533141, | |
| "train_runtime": 1979.1189, | |
| "train_samples_per_second": 36.658, | |
| "train_steps_per_second": 2.299 | |
| } | |
| ], | |
| "max_steps": 4550, | |
| "num_train_epochs": 50, | |
| "total_flos": 5.622144623740109e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |