| { | |
| "best_metric": 0.8478260869565217, | |
| "best_model_checkpoint": "beit-base-patch16-224-ve-U13-b-80\\checkpoint-188", | |
| "epoch": 73.84615384615384, | |
| "eval_steps": 500, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.3187189102172852, | |
| "eval_runtime": 0.8006, | |
| "eval_samples_per_second": 57.455, | |
| "eval_steps_per_second": 2.498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.6193, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.3087053298950195, | |
| "eval_runtime": 0.8503, | |
| "eval_samples_per_second": 54.096, | |
| "eval_steps_per_second": 2.352, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.293927550315857, | |
| "eval_runtime": 0.7719, | |
| "eval_samples_per_second": 59.591, | |
| "eval_steps_per_second": 2.591, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.6044, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2801765203475952, | |
| "eval_runtime": 0.7782, | |
| "eval_samples_per_second": 59.11, | |
| "eval_steps_per_second": 2.57, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.5061, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2867043018341064, | |
| "eval_runtime": 0.7859, | |
| "eval_samples_per_second": 58.535, | |
| "eval_steps_per_second": 2.545, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2812776565551758, | |
| "eval_runtime": 0.8418, | |
| "eval_samples_per_second": 54.646, | |
| "eval_steps_per_second": 2.376, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.3879, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.45652173913043476, | |
| "eval_loss": 1.2511413097381592, | |
| "eval_runtime": 0.8169, | |
| "eval_samples_per_second": 56.314, | |
| "eval_steps_per_second": 2.448, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 1.3007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.12944495677948, | |
| "eval_runtime": 0.7692, | |
| "eval_samples_per_second": 59.803, | |
| "eval_steps_per_second": 2.6, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.0096081495285034, | |
| "eval_runtime": 0.8226, | |
| "eval_samples_per_second": 55.922, | |
| "eval_steps_per_second": 2.431, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.1213, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 0.9308165907859802, | |
| "eval_runtime": 0.7964, | |
| "eval_samples_per_second": 57.76, | |
| "eval_steps_per_second": 2.511, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.9968, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 0.9280174374580383, | |
| "eval_runtime": 0.8014, | |
| "eval_samples_per_second": 57.397, | |
| "eval_steps_per_second": 2.496, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.8033515810966492, | |
| "eval_runtime": 0.8132, | |
| "eval_samples_per_second": 56.567, | |
| "eval_steps_per_second": 2.459, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 3.703703703703704e-05, | |
| "loss": 0.8771, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.7791343331336975, | |
| "eval_runtime": 0.815, | |
| "eval_samples_per_second": 56.443, | |
| "eval_steps_per_second": 2.454, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 3.6111111111111116e-05, | |
| "loss": 0.7383, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8005303740501404, | |
| "eval_runtime": 0.8319, | |
| "eval_samples_per_second": 55.297, | |
| "eval_steps_per_second": 2.404, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7408289909362793, | |
| "eval_runtime": 0.8044, | |
| "eval_samples_per_second": 57.183, | |
| "eval_steps_per_second": 2.486, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.6658, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.9304527044296265, | |
| "eval_runtime": 0.8264, | |
| "eval_samples_per_second": 55.661, | |
| "eval_steps_per_second": 2.42, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.5879, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7136292457580566, | |
| "eval_runtime": 0.8173, | |
| "eval_samples_per_second": 56.28, | |
| "eval_steps_per_second": 2.447, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7106310725212097, | |
| "eval_runtime": 0.8057, | |
| "eval_samples_per_second": 57.096, | |
| "eval_steps_per_second": 2.482, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4609, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.6998218894004822, | |
| "eval_runtime": 0.9084, | |
| "eval_samples_per_second": 50.637, | |
| "eval_steps_per_second": 2.202, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.2407407407407415e-05, | |
| "loss": 0.4123, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7930821180343628, | |
| "eval_runtime": 0.8165, | |
| "eval_samples_per_second": 56.336, | |
| "eval_steps_per_second": 2.449, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9417108297348022, | |
| "eval_runtime": 0.8063, | |
| "eval_samples_per_second": 57.053, | |
| "eval_steps_per_second": 2.481, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.148148148148149e-05, | |
| "loss": 0.3552, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7867944836616516, | |
| "eval_runtime": 0.8323, | |
| "eval_samples_per_second": 55.269, | |
| "eval_steps_per_second": 2.403, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.907270610332489, | |
| "eval_runtime": 0.9203, | |
| "eval_samples_per_second": 49.986, | |
| "eval_steps_per_second": 2.173, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.0555555555555554e-05, | |
| "loss": 0.2896, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8542404770851135, | |
| "eval_runtime": 0.7865, | |
| "eval_samples_per_second": 58.49, | |
| "eval_steps_per_second": 2.543, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.2316, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7158516645431519, | |
| "eval_runtime": 0.8612, | |
| "eval_samples_per_second": 53.412, | |
| "eval_steps_per_second": 2.322, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.7218698263168335, | |
| "eval_runtime": 0.8157, | |
| "eval_samples_per_second": 56.392, | |
| "eval_steps_per_second": 2.452, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.2339, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7070921063423157, | |
| "eval_runtime": 0.8041, | |
| "eval_samples_per_second": 57.206, | |
| "eval_steps_per_second": 2.487, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2055, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0110474824905396, | |
| "eval_runtime": 0.8167, | |
| "eval_samples_per_second": 56.325, | |
| "eval_steps_per_second": 2.449, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6396859884262085, | |
| "eval_runtime": 0.785, | |
| "eval_samples_per_second": 58.6, | |
| "eval_steps_per_second": 2.548, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 2.6851851851851852e-05, | |
| "loss": 0.1995, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6921820640563965, | |
| "eval_runtime": 0.8031, | |
| "eval_samples_per_second": 57.276, | |
| "eval_steps_per_second": 2.49, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 2.5925925925925928e-05, | |
| "loss": 0.169, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.6171072125434875, | |
| "eval_runtime": 0.8032, | |
| "eval_samples_per_second": 57.267, | |
| "eval_steps_per_second": 2.49, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.663216769695282, | |
| "eval_runtime": 0.7746, | |
| "eval_samples_per_second": 59.389, | |
| "eval_steps_per_second": 2.582, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1586, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6475113034248352, | |
| "eval_runtime": 0.8032, | |
| "eval_samples_per_second": 57.273, | |
| "eval_steps_per_second": 2.49, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 2.4074074074074077e-05, | |
| "loss": 0.1439, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8331847786903381, | |
| "eval_runtime": 0.8433, | |
| "eval_samples_per_second": 54.547, | |
| "eval_steps_per_second": 2.372, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.6816123723983765, | |
| "eval_runtime": 0.7895, | |
| "eval_samples_per_second": 58.264, | |
| "eval_steps_per_second": 2.533, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.1698, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8065864443778992, | |
| "eval_runtime": 0.7867, | |
| "eval_samples_per_second": 58.473, | |
| "eval_steps_per_second": 2.542, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.2222222222222227e-05, | |
| "loss": 0.1362, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7150391936302185, | |
| "eval_runtime": 0.8081, | |
| "eval_samples_per_second": 56.927, | |
| "eval_steps_per_second": 2.475, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7192500829696655, | |
| "eval_runtime": 0.8027, | |
| "eval_samples_per_second": 57.307, | |
| "eval_steps_per_second": 2.492, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.12962962962963e-05, | |
| "loss": 0.1344, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8180671334266663, | |
| "eval_runtime": 0.7916, | |
| "eval_samples_per_second": 58.109, | |
| "eval_steps_per_second": 2.526, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.0370370370370372e-05, | |
| "loss": 0.1317, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.6546934247016907, | |
| "eval_runtime": 0.7874, | |
| "eval_samples_per_second": 58.418, | |
| "eval_steps_per_second": 2.54, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8459427952766418, | |
| "eval_runtime": 0.8103, | |
| "eval_samples_per_second": 56.767, | |
| "eval_steps_per_second": 2.468, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.123, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7700240015983582, | |
| "eval_runtime": 0.7727, | |
| "eval_samples_per_second": 59.532, | |
| "eval_steps_per_second": 2.588, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9337859749794006, | |
| "eval_runtime": 0.7941, | |
| "eval_samples_per_second": 57.926, | |
| "eval_steps_per_second": 2.519, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 1.851851851851852e-05, | |
| "loss": 0.102, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8535920977592468, | |
| "eval_runtime": 0.7804, | |
| "eval_samples_per_second": 58.944, | |
| "eval_steps_per_second": 2.563, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.1015, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.9725267291069031, | |
| "eval_runtime": 0.8151, | |
| "eval_samples_per_second": 56.432, | |
| "eval_steps_per_second": 2.454, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.886543333530426, | |
| "eval_runtime": 0.8146, | |
| "eval_samples_per_second": 56.47, | |
| "eval_steps_per_second": 2.455, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1313, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.8946501016616821, | |
| "eval_runtime": 0.8015, | |
| "eval_samples_per_second": 57.395, | |
| "eval_steps_per_second": 2.495, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.5740740740740744e-05, | |
| "loss": 0.1312, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8235049843788147, | |
| "eval_runtime": 0.8012, | |
| "eval_samples_per_second": 57.416, | |
| "eval_steps_per_second": 2.496, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7325660586357117, | |
| "eval_runtime": 0.7855, | |
| "eval_samples_per_second": 58.562, | |
| "eval_steps_per_second": 2.546, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.1168, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.8654406070709229, | |
| "eval_runtime": 0.8065, | |
| "eval_samples_per_second": 57.034, | |
| "eval_steps_per_second": 2.48, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.09, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7645005583763123, | |
| "eval_runtime": 0.7927, | |
| "eval_samples_per_second": 58.03, | |
| "eval_steps_per_second": 2.523, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.7632436156272888, | |
| "eval_runtime": 0.7906, | |
| "eval_samples_per_second": 58.181, | |
| "eval_steps_per_second": 2.53, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.2962962962962964e-05, | |
| "loss": 0.0872, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.7496499419212341, | |
| "eval_runtime": 0.814, | |
| "eval_samples_per_second": 56.509, | |
| "eval_steps_per_second": 2.457, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.2037037037037039e-05, | |
| "loss": 0.0813, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8845884799957275, | |
| "eval_runtime": 0.8027, | |
| "eval_samples_per_second": 57.304, | |
| "eval_steps_per_second": 2.491, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9214064478874207, | |
| "eval_runtime": 0.8344, | |
| "eval_samples_per_second": 55.126, | |
| "eval_steps_per_second": 2.397, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.0955, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.9284290671348572, | |
| "eval_runtime": 0.7964, | |
| "eval_samples_per_second": 57.758, | |
| "eval_steps_per_second": 2.511, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.0185185185185186e-05, | |
| "loss": 0.1031, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.8855016827583313, | |
| "eval_runtime": 0.8017, | |
| "eval_samples_per_second": 57.377, | |
| "eval_steps_per_second": 2.495, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.861878514289856, | |
| "eval_runtime": 0.7874, | |
| "eval_samples_per_second": 58.417, | |
| "eval_steps_per_second": 2.54, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.0962, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.8186527490615845, | |
| "eval_runtime": 0.806, | |
| "eval_samples_per_second": 57.069, | |
| "eval_steps_per_second": 2.481, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0891, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.7430442571640015, | |
| "eval_runtime": 0.7839, | |
| "eval_samples_per_second": 58.681, | |
| "eval_steps_per_second": 2.551, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_loss": 0.7530257105827332, | |
| "eval_runtime": 0.7978, | |
| "eval_samples_per_second": 57.655, | |
| "eval_steps_per_second": 2.507, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0679, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7789714932441711, | |
| "eval_runtime": 0.7865, | |
| "eval_samples_per_second": 58.486, | |
| "eval_steps_per_second": 2.543, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.7904501557350159, | |
| "eval_runtime": 0.7916, | |
| "eval_samples_per_second": 58.11, | |
| "eval_steps_per_second": 2.527, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 6.481481481481482e-06, | |
| "loss": 0.0805, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_loss": 0.8285916447639465, | |
| "eval_runtime": 0.7851, | |
| "eval_samples_per_second": 58.592, | |
| "eval_steps_per_second": 2.547, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.0619, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8371415138244629, | |
| "eval_runtime": 0.7843, | |
| "eval_samples_per_second": 58.649, | |
| "eval_steps_per_second": 2.55, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8654527068138123, | |
| "eval_runtime": 0.7995, | |
| "eval_samples_per_second": 57.539, | |
| "eval_steps_per_second": 2.502, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 4.62962962962963e-06, | |
| "loss": 0.0778, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.8896797299385071, | |
| "eval_runtime": 0.7866, | |
| "eval_samples_per_second": 58.483, | |
| "eval_steps_per_second": 2.543, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.0712, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9384985566139221, | |
| "eval_runtime": 0.798, | |
| "eval_samples_per_second": 57.647, | |
| "eval_steps_per_second": 2.506, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9610966444015503, | |
| "eval_runtime": 0.7968, | |
| "eval_samples_per_second": 57.729, | |
| "eval_steps_per_second": 2.51, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 0.0659, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9596511721611023, | |
| "eval_runtime": 0.7833, | |
| "eval_samples_per_second": 58.724, | |
| "eval_steps_per_second": 2.553, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0602, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.963528037071228, | |
| "eval_runtime": 0.7784, | |
| "eval_samples_per_second": 59.095, | |
| "eval_steps_per_second": 2.569, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9732967019081116, | |
| "eval_runtime": 0.7919, | |
| "eval_samples_per_second": 58.085, | |
| "eval_steps_per_second": 2.525, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.0641, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9753540754318237, | |
| "eval_runtime": 0.7911, | |
| "eval_samples_per_second": 58.148, | |
| "eval_steps_per_second": 2.528, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.0653, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.8043478260869565, | |
| "eval_loss": 0.9753237366676331, | |
| "eval_runtime": 0.7931, | |
| "eval_samples_per_second": 58.004, | |
| "eval_steps_per_second": 2.522, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 4.685648449140449e+18, | |
| "train_loss": 0.3708515681326389, | |
| "train_runtime": 1053.7167, | |
| "train_samples_per_second": 62.18, | |
| "train_steps_per_second": 0.456 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 4.685648449140449e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |