| { | |
| "best_metric": 0.782608695652174, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-ve-U13-b-80c\\checkpoint-104", | |
| "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": 0.10869565217391304, | |
| "eval_loss": 1.633338451385498, | |
| "eval_runtime": 0.7424, | |
| "eval_samples_per_second": 61.963, | |
| "eval_steps_per_second": 2.694, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 1.4981, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.6224730014801025, | |
| "eval_runtime": 0.751, | |
| "eval_samples_per_second": 61.25, | |
| "eval_steps_per_second": 2.663, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.5920681953430176, | |
| "eval_runtime": 0.7722, | |
| "eval_samples_per_second": 59.567, | |
| "eval_steps_per_second": 2.59, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.4704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.500125527381897, | |
| "eval_runtime": 0.8168, | |
| "eval_samples_per_second": 56.317, | |
| "eval_steps_per_second": 2.449, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.4116, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "eval_accuracy": 0.10869565217391304, | |
| "eval_loss": 1.407835602760315, | |
| "eval_runtime": 0.8821, | |
| "eval_samples_per_second": 52.146, | |
| "eval_steps_per_second": 2.267, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.34782608695652173, | |
| "eval_loss": 1.2960187196731567, | |
| "eval_runtime": 0.7623, | |
| "eval_samples_per_second": 60.342, | |
| "eval_steps_per_second": 2.624, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.3094, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "eval_accuracy": 0.30434782608695654, | |
| "eval_loss": 1.2926034927368164, | |
| "eval_runtime": 0.7971, | |
| "eval_samples_per_second": 57.711, | |
| "eval_steps_per_second": 2.509, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 1.2014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5434782608695652, | |
| "eval_loss": 1.153234601020813, | |
| "eval_runtime": 0.8469, | |
| "eval_samples_per_second": 54.315, | |
| "eval_steps_per_second": 2.362, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.1059072017669678, | |
| "eval_runtime": 0.7764, | |
| "eval_samples_per_second": 59.244, | |
| "eval_steps_per_second": 2.576, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.0577, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.9509550929069519, | |
| "eval_runtime": 0.7342, | |
| "eval_samples_per_second": 62.653, | |
| "eval_steps_per_second": 2.724, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 10.77, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.9185, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 10.92, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 0.969477117061615, | |
| "eval_runtime": 0.7665, | |
| "eval_samples_per_second": 60.016, | |
| "eval_steps_per_second": 2.609, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.8791983127593994, | |
| "eval_runtime": 0.7872, | |
| "eval_samples_per_second": 58.433, | |
| "eval_steps_per_second": 2.541, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 3.703703703703704e-05, | |
| "loss": 0.8369, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 12.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8616169691085815, | |
| "eval_runtime": 0.7649, | |
| "eval_samples_per_second": 60.136, | |
| "eval_steps_per_second": 2.615, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 13.85, | |
| "learning_rate": 3.6111111111111116e-05, | |
| "loss": 0.7406, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7815921902656555, | |
| "eval_runtime": 0.7689, | |
| "eval_samples_per_second": 59.823, | |
| "eval_steps_per_second": 2.601, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 14.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7638239860534668, | |
| "eval_runtime": 0.7551, | |
| "eval_samples_per_second": 60.92, | |
| "eval_steps_per_second": 2.649, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.6929, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.782608695652174, | |
| "eval_loss": 0.7710235714912415, | |
| "eval_runtime": 0.7696, | |
| "eval_samples_per_second": 59.772, | |
| "eval_steps_per_second": 2.599, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.6192, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 16.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.747129499912262, | |
| "eval_runtime": 0.7383, | |
| "eval_samples_per_second": 62.304, | |
| "eval_steps_per_second": 2.709, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.7264894247055054, | |
| "eval_runtime": 0.7721, | |
| "eval_samples_per_second": 59.579, | |
| "eval_steps_per_second": 2.59, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 18.46, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5936, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 18.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7841283679008484, | |
| "eval_runtime": 0.7506, | |
| "eval_samples_per_second": 61.284, | |
| "eval_steps_per_second": 2.665, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.2407407407407415e-05, | |
| "loss": 0.5125, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.932004451751709, | |
| "eval_runtime": 0.7626, | |
| "eval_samples_per_second": 60.318, | |
| "eval_steps_per_second": 2.623, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 20.92, | |
| "eval_accuracy": 0.7608695652173914, | |
| "eval_loss": 0.7512046694755554, | |
| "eval_runtime": 0.7618, | |
| "eval_samples_per_second": 60.38, | |
| "eval_steps_per_second": 2.625, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 21.54, | |
| "learning_rate": 3.148148148148149e-05, | |
| "loss": 0.4905, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7466354966163635, | |
| "eval_runtime": 0.753, | |
| "eval_samples_per_second": 61.091, | |
| "eval_steps_per_second": 2.656, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 22.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8029746413230896, | |
| "eval_runtime": 0.7501, | |
| "eval_samples_per_second": 61.326, | |
| "eval_steps_per_second": 2.666, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 3.0555555555555554e-05, | |
| "loss": 0.4315, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.7391304347826086, | |
| "eval_loss": 0.8183513283729553, | |
| "eval_runtime": 0.7352, | |
| "eval_samples_per_second": 62.571, | |
| "eval_steps_per_second": 2.72, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 24.62, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.4272, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 24.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8196337223052979, | |
| "eval_runtime": 0.7249, | |
| "eval_samples_per_second": 63.457, | |
| "eval_steps_per_second": 2.759, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.8711686134338379, | |
| "eval_runtime": 0.7691, | |
| "eval_samples_per_second": 59.813, | |
| "eval_steps_per_second": 2.601, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 26.15, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.4261, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 26.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.7834368348121643, | |
| "eval_runtime": 0.7329, | |
| "eval_samples_per_second": 62.761, | |
| "eval_steps_per_second": 2.729, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 27.69, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4217, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8393808603286743, | |
| "eval_runtime": 0.7675, | |
| "eval_samples_per_second": 59.933, | |
| "eval_steps_per_second": 2.606, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 28.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9940950274467468, | |
| "eval_runtime": 0.7496, | |
| "eval_samples_per_second": 61.366, | |
| "eval_steps_per_second": 2.668, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 29.23, | |
| "learning_rate": 2.6851851851851852e-05, | |
| "loss": 0.3502, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.89089435338974, | |
| "eval_runtime": 0.7831, | |
| "eval_samples_per_second": 58.743, | |
| "eval_steps_per_second": 2.554, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 30.77, | |
| "learning_rate": 2.5925925925925928e-05, | |
| "loss": 0.368, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 30.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.9994531869888306, | |
| "eval_runtime": 0.7327, | |
| "eval_samples_per_second": 62.783, | |
| "eval_steps_per_second": 2.73, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9417786002159119, | |
| "eval_runtime": 0.7664, | |
| "eval_samples_per_second": 60.024, | |
| "eval_steps_per_second": 2.61, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 32.31, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3473, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 32.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8594914078712463, | |
| "eval_runtime": 0.7833, | |
| "eval_samples_per_second": 58.729, | |
| "eval_steps_per_second": 2.553, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 33.85, | |
| "learning_rate": 2.4074074074074077e-05, | |
| "loss": 0.3079, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9562082886695862, | |
| "eval_runtime": 0.7393, | |
| "eval_samples_per_second": 62.224, | |
| "eval_steps_per_second": 2.705, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 34.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8992215991020203, | |
| "eval_runtime": 0.7796, | |
| "eval_samples_per_second": 59.002, | |
| "eval_steps_per_second": 2.565, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 35.38, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.3226, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.990846574306488, | |
| "eval_runtime": 0.9061, | |
| "eval_samples_per_second": 50.765, | |
| "eval_steps_per_second": 2.207, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "learning_rate": 2.2222222222222227e-05, | |
| "loss": 0.2603, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 36.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9469108581542969, | |
| "eval_runtime": 0.805, | |
| "eval_samples_per_second": 57.141, | |
| "eval_steps_per_second": 2.484, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9941902160644531, | |
| "eval_runtime": 0.7764, | |
| "eval_samples_per_second": 59.244, | |
| "eval_steps_per_second": 2.576, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 38.46, | |
| "learning_rate": 2.12962962962963e-05, | |
| "loss": 0.3028, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 38.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0084490776062012, | |
| "eval_runtime": 0.7378, | |
| "eval_samples_per_second": 62.345, | |
| "eval_steps_per_second": 2.711, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.0370370370370372e-05, | |
| "loss": 0.2576, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9907578825950623, | |
| "eval_runtime": 0.7579, | |
| "eval_samples_per_second": 60.697, | |
| "eval_steps_per_second": 2.639, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 40.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.066124439239502, | |
| "eval_runtime": 0.7676, | |
| "eval_samples_per_second": 59.926, | |
| "eval_steps_per_second": 2.605, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 41.54, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.2713, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 1.1347342729568481, | |
| "eval_runtime": 0.7202, | |
| "eval_samples_per_second": 63.874, | |
| "eval_steps_per_second": 2.777, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 42.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1053770780563354, | |
| "eval_runtime": 0.7694, | |
| "eval_samples_per_second": 59.788, | |
| "eval_steps_per_second": 2.599, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 43.08, | |
| "learning_rate": 1.851851851851852e-05, | |
| "loss": 0.2578, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.108882188796997, | |
| "eval_runtime": 0.7355, | |
| "eval_samples_per_second": 62.545, | |
| "eval_steps_per_second": 2.719, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 44.62, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.2367, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 44.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1452158689498901, | |
| "eval_runtime": 0.7582, | |
| "eval_samples_per_second": 60.67, | |
| "eval_steps_per_second": 2.638, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0272438526153564, | |
| "eval_runtime": 0.787, | |
| "eval_samples_per_second": 58.447, | |
| "eval_steps_per_second": 2.541, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 46.15, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.2301, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 46.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1042827367782593, | |
| "eval_runtime": 0.7272, | |
| "eval_samples_per_second": 63.255, | |
| "eval_steps_per_second": 2.75, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 47.69, | |
| "learning_rate": 1.5740740740740744e-05, | |
| "loss": 0.2191, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0814892053604126, | |
| "eval_runtime": 0.7527, | |
| "eval_samples_per_second": 61.115, | |
| "eval_steps_per_second": 2.657, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 48.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9933874607086182, | |
| "eval_runtime": 0.7492, | |
| "eval_samples_per_second": 61.399, | |
| "eval_steps_per_second": 2.67, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 49.23, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.2635, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0865848064422607, | |
| "eval_runtime": 0.7354, | |
| "eval_samples_per_second": 62.552, | |
| "eval_steps_per_second": 2.72, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 50.77, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.1874, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 50.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.0507148504257202, | |
| "eval_runtime": 0.7781, | |
| "eval_samples_per_second": 59.121, | |
| "eval_steps_per_second": 2.57, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1001808643341064, | |
| "eval_runtime": 0.7352, | |
| "eval_samples_per_second": 62.566, | |
| "eval_steps_per_second": 2.72, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 52.31, | |
| "learning_rate": 1.2962962962962964e-05, | |
| "loss": 0.2057, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 52.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.0400489568710327, | |
| "eval_runtime": 0.7423, | |
| "eval_samples_per_second": 61.968, | |
| "eval_steps_per_second": 2.694, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 53.85, | |
| "learning_rate": 1.2037037037037039e-05, | |
| "loss": 0.1808, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1092016696929932, | |
| "eval_runtime": 0.8037, | |
| "eval_samples_per_second": 57.236, | |
| "eval_steps_per_second": 2.489, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 54.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1550217866897583, | |
| "eval_runtime": 0.765, | |
| "eval_samples_per_second": 60.131, | |
| "eval_steps_per_second": 2.614, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 55.38, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.2107, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0578877925872803, | |
| "eval_runtime": 0.7693, | |
| "eval_samples_per_second": 59.792, | |
| "eval_steps_per_second": 2.6, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "learning_rate": 1.0185185185185186e-05, | |
| "loss": 0.2149, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 56.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.0935583114624023, | |
| "eval_runtime": 0.7825, | |
| "eval_samples_per_second": 58.788, | |
| "eval_steps_per_second": 2.556, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.169234275817871, | |
| "eval_runtime": 0.7848, | |
| "eval_samples_per_second": 58.615, | |
| "eval_steps_per_second": 2.548, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 58.46, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.1865, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 58.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1356713771820068, | |
| "eval_runtime": 0.7494, | |
| "eval_samples_per_second": 61.383, | |
| "eval_steps_per_second": 2.669, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.1832, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1549310684204102, | |
| "eval_runtime": 0.7627, | |
| "eval_samples_per_second": 60.315, | |
| "eval_steps_per_second": 2.622, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 60.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1631118059158325, | |
| "eval_runtime": 0.75, | |
| "eval_samples_per_second": 61.332, | |
| "eval_steps_per_second": 2.667, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 61.54, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.1732, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1312264204025269, | |
| "eval_runtime": 0.7694, | |
| "eval_samples_per_second": 59.786, | |
| "eval_steps_per_second": 2.599, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 62.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1210438013076782, | |
| "eval_runtime": 0.7676, | |
| "eval_samples_per_second": 59.927, | |
| "eval_steps_per_second": 2.606, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 63.08, | |
| "learning_rate": 6.481481481481482e-06, | |
| "loss": 0.1856, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1835136413574219, | |
| "eval_runtime": 0.7669, | |
| "eval_samples_per_second": 59.984, | |
| "eval_steps_per_second": 2.608, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 64.62, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.1503, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 64.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.1892285346984863, | |
| "eval_runtime": 0.7668, | |
| "eval_samples_per_second": 59.986, | |
| "eval_steps_per_second": 2.608, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1865118741989136, | |
| "eval_runtime": 0.7524, | |
| "eval_samples_per_second": 61.139, | |
| "eval_steps_per_second": 2.658, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 66.15, | |
| "learning_rate": 4.62962962962963e-06, | |
| "loss": 0.1713, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 66.92, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1607787609100342, | |
| "eval_runtime": 0.7246, | |
| "eval_samples_per_second": 63.484, | |
| "eval_steps_per_second": 2.76, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 67.69, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.1804, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 1.1698514223098755, | |
| "eval_runtime": 0.7533, | |
| "eval_samples_per_second": 61.069, | |
| "eval_steps_per_second": 2.655, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 68.92, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 1.169384479522705, | |
| "eval_runtime": 0.7972, | |
| "eval_samples_per_second": 57.7, | |
| "eval_steps_per_second": 2.509, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 69.23, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 0.1761, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1743987798690796, | |
| "eval_runtime": 0.7692, | |
| "eval_samples_per_second": 59.804, | |
| "eval_steps_per_second": 2.6, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 70.77, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.1619, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 70.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1782755851745605, | |
| "eval_runtime": 0.7663, | |
| "eval_samples_per_second": 60.026, | |
| "eval_steps_per_second": 2.61, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1796863079071045, | |
| "eval_runtime": 0.7855, | |
| "eval_samples_per_second": 58.564, | |
| "eval_steps_per_second": 2.546, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 72.31, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.1649, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 72.92, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1788305044174194, | |
| "eval_runtime": 0.7277, | |
| "eval_samples_per_second": 63.21, | |
| "eval_steps_per_second": 2.748, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "learning_rate": 0.0, | |
| "loss": 0.1843, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 1.1780040264129639, | |
| "eval_runtime": 0.7798, | |
| "eval_samples_per_second": 58.986, | |
| "eval_steps_per_second": 2.565, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 73.85, | |
| "step": 480, | |
| "total_flos": 1.9681438145406566e+18, | |
| "train_loss": 0.45775609463453293, | |
| "train_runtime": 806.7419, | |
| "train_samples_per_second": 81.216, | |
| "train_steps_per_second": 0.595 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 1.9681438145406566e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |