| { | |
| "best_metric": 0.7419354838709677, | |
| "best_model_checkpoint": "videomae-base-finetuned-subset-check10/checkpoint-896", | |
| "epoch": 19.041441441441442, | |
| "eval_steps": 500, | |
| "global_step": 1110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.00900900900901e-07, | |
| "loss": 1.6695, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.801801801801802e-06, | |
| "loss": 1.6945, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.702702702702703e-06, | |
| "loss": 1.6484, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3.603603603603604e-06, | |
| "loss": 1.6661, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 1.6348, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.511520737327189, | |
| "eval_loss": 1.544296383857727, | |
| "eval_runtime": 169.659, | |
| "eval_samples_per_second": 1.279, | |
| "eval_steps_per_second": 0.165, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 1.5964, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.3063063063063065e-06, | |
| "loss": 1.6218, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.207207207207208e-06, | |
| "loss": 1.6405, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 8.108108108108109e-06, | |
| "loss": 1.6203, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 1.6147, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.90990990990991e-06, | |
| "loss": 1.6015, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_accuracy": 0.4792626728110599, | |
| "eval_loss": 1.529832124710083, | |
| "eval_runtime": 163.2712, | |
| "eval_samples_per_second": 1.329, | |
| "eval_steps_per_second": 0.171, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.90990990990991e-06, | |
| "loss": 1.5899, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.80980980980981e-06, | |
| "loss": 1.6095, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.70970970970971e-06, | |
| "loss": 1.613, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.60960960960961e-06, | |
| "loss": 1.5829, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.50950950950951e-06, | |
| "loss": 1.5683, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_accuracy": 0.3271889400921659, | |
| "eval_loss": 1.5288971662521362, | |
| "eval_runtime": 162.8221, | |
| "eval_samples_per_second": 1.333, | |
| "eval_steps_per_second": 0.172, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.40940940940941e-06, | |
| "loss": 1.5958, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.30930930930931e-06, | |
| "loss": 1.5487, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.20920920920921e-06, | |
| "loss": 1.5407, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 9.10910910910911e-06, | |
| "loss": 1.5352, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.00900900900901e-06, | |
| "loss": 1.4537, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 8.90890890890891e-06, | |
| "loss": 1.512, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_accuracy": 0.631336405529954, | |
| "eval_loss": 1.302922248840332, | |
| "eval_runtime": 162.9796, | |
| "eval_samples_per_second": 1.331, | |
| "eval_steps_per_second": 0.172, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.80880880880881e-06, | |
| "loss": 1.4831, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 8.70870870870871e-06, | |
| "loss": 1.3654, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 8.60860860860861e-06, | |
| "loss": 1.3439, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 8.50850850850851e-06, | |
| "loss": 1.2985, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 8.408408408408409e-06, | |
| "loss": 1.2316, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 8.308308308308309e-06, | |
| "loss": 1.2309, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_accuracy": 0.5207373271889401, | |
| "eval_loss": 1.21807861328125, | |
| "eval_runtime": 162.5548, | |
| "eval_samples_per_second": 1.335, | |
| "eval_steps_per_second": 0.172, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 8.208208208208209e-06, | |
| "loss": 1.3147, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 8.108108108108109e-06, | |
| "loss": 1.2977, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 8.00800800800801e-06, | |
| "loss": 1.2603, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 7.90790790790791e-06, | |
| "loss": 1.1538, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 7.807807807807808e-06, | |
| "loss": 1.1949, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "eval_accuracy": 0.6589861751152074, | |
| "eval_loss": 1.0441014766693115, | |
| "eval_runtime": 161.7405, | |
| "eval_samples_per_second": 1.342, | |
| "eval_steps_per_second": 0.173, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.707707707707708e-06, | |
| "loss": 1.2623, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 7.607607607607608e-06, | |
| "loss": 1.1608, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 6.02, | |
| "learning_rate": 7.507507507507507e-06, | |
| "loss": 1.1801, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 1.0873, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 7.307307307307308e-06, | |
| "loss": 1.0739, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 7.207207207207208e-06, | |
| "loss": 1.0987, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "eval_accuracy": 0.6129032258064516, | |
| "eval_loss": 1.004054307937622, | |
| "eval_runtime": 161.9536, | |
| "eval_samples_per_second": 1.34, | |
| "eval_steps_per_second": 0.173, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 7.107107107107107e-06, | |
| "loss": 1.142, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 7.007007007007007e-06, | |
| "loss": 1.0111, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 6.906906906906907e-06, | |
| "loss": 1.0603, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 6.8068068068068075e-06, | |
| "loss": 1.185, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 6.706706706706707e-06, | |
| "loss": 1.148, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "eval_accuracy": 0.6175115207373272, | |
| "eval_loss": 1.0258899927139282, | |
| "eval_runtime": 163.4987, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.171, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.606606606606607e-06, | |
| "loss": 1.1361, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 6.506506506506507e-06, | |
| "loss": 0.9612, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 6.406406406406407e-06, | |
| "loss": 1.0823, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 6.3063063063063065e-06, | |
| "loss": 1.21, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.04, | |
| "learning_rate": 6.206206206206207e-06, | |
| "loss": 0.9171, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 6.106106106106107e-06, | |
| "loss": 0.9958, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "eval_accuracy": 0.6728110599078341, | |
| "eval_loss": 0.9507986307144165, | |
| "eval_runtime": 161.9408, | |
| "eval_samples_per_second": 1.34, | |
| "eval_steps_per_second": 0.173, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 6.006006006006007e-06, | |
| "loss": 0.9985, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "learning_rate": 5.905905905905906e-06, | |
| "loss": 1.1594, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 5.805805805805806e-06, | |
| "loss": 1.0034, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 5.7057057057057065e-06, | |
| "loss": 0.9761, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 5.605605605605607e-06, | |
| "loss": 0.8942, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.505505505505506e-06, | |
| "loss": 1.0856, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "eval_accuracy": 0.5944700460829493, | |
| "eval_loss": 1.0041232109069824, | |
| "eval_runtime": 162.8782, | |
| "eval_samples_per_second": 1.332, | |
| "eval_steps_per_second": 0.172, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 0.972, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 10.02, | |
| "learning_rate": 5.305305305305306e-06, | |
| "loss": 1.0112, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "learning_rate": 5.205205205205206e-06, | |
| "loss": 0.9801, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 5.105105105105106e-06, | |
| "loss": 0.8615, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "learning_rate": 5.005005005005006e-06, | |
| "loss": 0.8809, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.05, | |
| "eval_accuracy": 0.6359447004608295, | |
| "eval_loss": 0.9638356566429138, | |
| "eval_runtime": 161.5478, | |
| "eval_samples_per_second": 1.343, | |
| "eval_steps_per_second": 0.173, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.904904904904905e-06, | |
| "loss": 0.8911, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 4.804804804804805e-06, | |
| "loss": 0.8545, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 11.02, | |
| "learning_rate": 4.704704704704705e-06, | |
| "loss": 0.8887, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "learning_rate": 4.604604604604605e-06, | |
| "loss": 0.8687, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 4.504504504504505e-06, | |
| "loss": 0.8959, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "learning_rate": 4.404404404404405e-06, | |
| "loss": 0.9185, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 11.05, | |
| "eval_accuracy": 0.6820276497695853, | |
| "eval_loss": 0.9248147010803223, | |
| "eval_runtime": 161.5706, | |
| "eval_samples_per_second": 1.343, | |
| "eval_steps_per_second": 0.173, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 4.304304304304305e-06, | |
| "loss": 0.9707, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "learning_rate": 4.204204204204204e-06, | |
| "loss": 0.7837, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 4.1041041041041045e-06, | |
| "loss": 0.9325, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 12.03, | |
| "learning_rate": 4.004004004004005e-06, | |
| "loss": 0.8425, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 12.04, | |
| "learning_rate": 3.903903903903904e-06, | |
| "loss": 0.9136, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "eval_accuracy": 0.6728110599078341, | |
| "eval_loss": 1.0136313438415527, | |
| "eval_runtime": 162.7529, | |
| "eval_samples_per_second": 1.333, | |
| "eval_steps_per_second": 0.172, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.803803803803804e-06, | |
| "loss": 0.9652, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.8421, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "learning_rate": 3.603603603603604e-06, | |
| "loss": 0.9862, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 13.03, | |
| "learning_rate": 3.5035035035035036e-06, | |
| "loss": 0.9638, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "learning_rate": 3.4034034034034037e-06, | |
| "loss": 0.8826, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 3.3033033033033035e-06, | |
| "loss": 0.8537, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "eval_accuracy": 0.7188940092165899, | |
| "eval_loss": 0.8515194058418274, | |
| "eval_runtime": 164.1283, | |
| "eval_samples_per_second": 1.322, | |
| "eval_steps_per_second": 0.171, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.2032032032032036e-06, | |
| "loss": 0.9158, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "learning_rate": 3.1031031031031033e-06, | |
| "loss": 0.8456, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 3.0030030030030034e-06, | |
| "loss": 0.8235, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 2.902902902902903e-06, | |
| "loss": 0.7452, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "learning_rate": 2.8028028028028033e-06, | |
| "loss": 0.8251, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "learning_rate": 2.702702702702703e-06, | |
| "loss": 0.7921, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 14.05, | |
| "eval_accuracy": 0.7004608294930875, | |
| "eval_loss": 0.8222436308860779, | |
| "eval_runtime": 161.8478, | |
| "eval_samples_per_second": 1.341, | |
| "eval_steps_per_second": 0.173, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "learning_rate": 2.602602602602603e-06, | |
| "loss": 0.9356, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "learning_rate": 2.502502502502503e-06, | |
| "loss": 0.8556, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 2.4024024024024026e-06, | |
| "loss": 0.7946, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.3023023023023023e-06, | |
| "loss": 0.7411, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "learning_rate": 2.2022022022022024e-06, | |
| "loss": 0.7313, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 15.05, | |
| "eval_accuracy": 0.7419354838709677, | |
| "eval_loss": 0.7512253522872925, | |
| "eval_runtime": 161.7824, | |
| "eval_samples_per_second": 1.341, | |
| "eval_steps_per_second": 0.173, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.102102102102102e-06, | |
| "loss": 0.8169, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "learning_rate": 2.0020020020020023e-06, | |
| "loss": 0.7236, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "learning_rate": 1.901901901901902e-06, | |
| "loss": 0.8335, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 16.03, | |
| "learning_rate": 1.801801801801802e-06, | |
| "loss": 0.8666, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 1.7017017017017019e-06, | |
| "loss": 0.8429, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "learning_rate": 1.6016016016016018e-06, | |
| "loss": 0.5998, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 16.05, | |
| "eval_accuracy": 0.6129032258064516, | |
| "eval_loss": 0.9409515857696533, | |
| "eval_runtime": 161.5869, | |
| "eval_samples_per_second": 1.343, | |
| "eval_steps_per_second": 0.173, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "learning_rate": 1.5015015015015017e-06, | |
| "loss": 0.8206, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "learning_rate": 1.4014014014014016e-06, | |
| "loss": 0.7474, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 1.3013013013013016e-06, | |
| "loss": 0.7778, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 17.03, | |
| "learning_rate": 1.2012012012012013e-06, | |
| "loss": 0.7003, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 1.1011011011011012e-06, | |
| "loss": 0.8093, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "eval_accuracy": 0.7050691244239631, | |
| "eval_loss": 0.8144727349281311, | |
| "eval_runtime": 161.5502, | |
| "eval_samples_per_second": 1.343, | |
| "eval_steps_per_second": 0.173, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.0010010010010011e-06, | |
| "loss": 0.8227, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 9.00900900900901e-07, | |
| "loss": 0.8949, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "learning_rate": 8.008008008008009e-07, | |
| "loss": 0.6573, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 7.007007007007008e-07, | |
| "loss": 0.8836, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "learning_rate": 6.006006006006006e-07, | |
| "loss": 0.7605, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "learning_rate": 5.005005005005006e-07, | |
| "loss": 0.604, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 18.05, | |
| "eval_accuracy": 0.6820276497695853, | |
| "eval_loss": 0.9013708233833313, | |
| "eval_runtime": 162.7504, | |
| "eval_samples_per_second": 1.333, | |
| "eval_steps_per_second": 0.172, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 4.0040040040040045e-07, | |
| "loss": 0.7955, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 3.003003003003003e-07, | |
| "loss": 0.9212, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 2.0020020020020022e-07, | |
| "loss": 0.9198, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 19.03, | |
| "learning_rate": 1.0010010010010011e-07, | |
| "loss": 0.5744, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 0.0, | |
| "loss": 0.7066, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "eval_accuracy": 0.6682027649769585, | |
| "eval_loss": 0.893532931804657, | |
| "eval_runtime": 167.9329, | |
| "eval_samples_per_second": 1.292, | |
| "eval_steps_per_second": 0.167, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "step": 1110, | |
| "total_flos": 1.1041673732998595e+19, | |
| "train_loss": 1.0829452497465117, | |
| "train_runtime": 11433.1912, | |
| "train_samples_per_second": 0.777, | |
| "train_steps_per_second": 0.097 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.6926783919334412, | |
| "eval_runtime": 164.6443, | |
| "eval_samples_per_second": 1.312, | |
| "eval_steps_per_second": 0.164, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "eval_accuracy": 0.6666666666666666, | |
| "eval_loss": 0.6926783919334412, | |
| "eval_runtime": 163.2396, | |
| "eval_samples_per_second": 1.323, | |
| "eval_steps_per_second": 0.165, | |
| "step": 1110 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1110, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 1.1041673732998595e+19, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |