Upload folder using huggingface_hub
Browse files- model.pt +3 -0
- training_logs_and_testing_results.json +442 -0
model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17c3b3e6458c719031ba7ce30b223dcfa645478166b56da2700185ad69e953ab
|
| 3 |
+
size 80650026
|
training_logs_and_testing_results.json
ADDED
|
@@ -0,0 +1,442 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"epoch": 1,
|
| 4 |
+
"train_loss": 2.5585462911434083,
|
| 5 |
+
"val_loss": 2.4481061782155717,
|
| 6 |
+
"epoch_time_seconds": 79.22255253791809,
|
| 7 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 8 |
+
"line_sequence_accuracy": 0.0,
|
| 9 |
+
"line_bit_accuracy": 0.5918064923722988,
|
| 10 |
+
"line_levenshtein": 580.1304347826087,
|
| 11 |
+
"line_bleu": 0.0,
|
| 12 |
+
"line_rougeL": 0.05857836537706693,
|
| 13 |
+
"chunk_sequence_accuracy": 0.0,
|
| 14 |
+
"chunk_bit_accuracy": 0.5889557278334431,
|
| 15 |
+
"chunk_levenshtein": 315.52,
|
| 16 |
+
"chunk_bleu": 0.0,
|
| 17 |
+
"chunk_rougeL": 0.05705748108777969
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2,
|
| 21 |
+
"train_loss": 2.4357541556606925,
|
| 22 |
+
"val_loss": 2.400976743016924,
|
| 23 |
+
"epoch_time_seconds": 70.4331111907959,
|
| 24 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 25 |
+
"line_sequence_accuracy": 0.0,
|
| 26 |
+
"line_bit_accuracy": 0.6717608571368073,
|
| 27 |
+
"line_levenshtein": 494.463768115942,
|
| 28 |
+
"line_bleu": 0.0,
|
| 29 |
+
"line_rougeL": 0.09018540608419734,
|
| 30 |
+
"chunk_sequence_accuracy": 0.0,
|
| 31 |
+
"chunk_bit_accuracy": 0.6717210033966257,
|
| 32 |
+
"chunk_levenshtein": 260.43,
|
| 33 |
+
"chunk_bleu": 0.0,
|
| 34 |
+
"chunk_rougeL": 0.0865854406807637
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 3,
|
| 38 |
+
"train_loss": 2.340877313749485,
|
| 39 |
+
"val_loss": 2.1710705842290605,
|
| 40 |
+
"epoch_time_seconds": 71.3352370262146,
|
| 41 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 42 |
+
"line_sequence_accuracy": 0.0,
|
| 43 |
+
"line_bit_accuracy": 0.6838628330028451,
|
| 44 |
+
"line_levenshtein": 458.2173913043478,
|
| 45 |
+
"line_bleu": 0.0,
|
| 46 |
+
"line_rougeL": 0.12398292933931553,
|
| 47 |
+
"chunk_sequence_accuracy": 0.0,
|
| 48 |
+
"chunk_bit_accuracy": 0.6824994333635539,
|
| 49 |
+
"chunk_levenshtein": 240.48,
|
| 50 |
+
"chunk_bleu": 0.0,
|
| 51 |
+
"chunk_rougeL": 0.12460480155382525
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4,
|
| 55 |
+
"train_loss": 1.7933629420696278,
|
| 56 |
+
"val_loss": 0.7274752323116574,
|
| 57 |
+
"epoch_time_seconds": 71.25784826278687,
|
| 58 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 59 |
+
"line_sequence_accuracy": 0.0,
|
| 60 |
+
"line_bit_accuracy": 0.811141304347826,
|
| 61 |
+
"line_levenshtein": 230.30434782608697,
|
| 62 |
+
"line_bleu": 0.03209392579552222,
|
| 63 |
+
"line_rougeL": 0.2859965026884889,
|
| 64 |
+
"chunk_sequence_accuracy": 0.0,
|
| 65 |
+
"chunk_bit_accuracy": 0.8211293637427568,
|
| 66 |
+
"chunk_levenshtein": 119.96,
|
| 67 |
+
"chunk_bleu": 0.03511775731145213,
|
| 68 |
+
"chunk_rougeL": 0.27764504216795616
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5,
|
| 72 |
+
"train_loss": 0.724038249790951,
|
| 73 |
+
"val_loss": 0.34827577961342676,
|
| 74 |
+
"epoch_time_seconds": 70.74439549446106,
|
| 75 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 76 |
+
"line_sequence_accuracy": 0.0,
|
| 77 |
+
"line_bit_accuracy": 0.9511112558058775,
|
| 78 |
+
"line_levenshtein": 111.17391304347827,
|
| 79 |
+
"line_bleu": 0.1597171662962268,
|
| 80 |
+
"line_rougeL": 0.4883948915322014,
|
| 81 |
+
"chunk_sequence_accuracy": 0.0,
|
| 82 |
+
"chunk_bit_accuracy": 0.952499428865155,
|
| 83 |
+
"chunk_levenshtein": 57.77,
|
| 84 |
+
"chunk_bleu": 0.1636932754374169,
|
| 85 |
+
"chunk_rougeL": 0.46307618763549074
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 6,
|
| 89 |
+
"train_loss": 0.32591583053647627,
|
| 90 |
+
"val_loss": 0.07951089447098118,
|
| 91 |
+
"epoch_time_seconds": 71.41549181938171,
|
| 92 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 93 |
+
"line_sequence_accuracy": 1.4492753623188406,
|
| 94 |
+
"line_bit_accuracy": 0.9924679835033644,
|
| 95 |
+
"line_levenshtein": 20.043478260869566,
|
| 96 |
+
"line_bleu": 0.7044854077026654,
|
| 97 |
+
"line_rougeL": 0.868370028107672,
|
| 98 |
+
"chunk_sequence_accuracy": 3.0,
|
| 99 |
+
"chunk_bit_accuracy": 0.9923459187753471,
|
| 100 |
+
"chunk_levenshtein": 10.62,
|
| 101 |
+
"chunk_bleu": 0.7054051092056937,
|
| 102 |
+
"chunk_rougeL": 0.8501977537199353
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 7,
|
| 106 |
+
"train_loss": 0.12775223649226095,
|
| 107 |
+
"val_loss": 0.02204249074150409,
|
| 108 |
+
"epoch_time_seconds": 71.92139744758606,
|
| 109 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 110 |
+
"line_sequence_accuracy": 18.840579710144926,
|
| 111 |
+
"line_bit_accuracy": 0.9979488181285407,
|
| 112 |
+
"line_levenshtein": 5.6521739130434785,
|
| 113 |
+
"line_bleu": 0.9093660656445297,
|
| 114 |
+
"line_rougeL": 0.9674575368239117,
|
| 115 |
+
"chunk_sequence_accuracy": 23.0,
|
| 116 |
+
"chunk_bit_accuracy": 0.9980758246465801,
|
| 117 |
+
"chunk_levenshtein": 2.93,
|
| 118 |
+
"chunk_bleu": 0.9126130273405019,
|
| 119 |
+
"chunk_rougeL": 0.9568422004689281
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 8,
|
| 123 |
+
"train_loss": 0.07204781078967439,
|
| 124 |
+
"val_loss": 0.009053510896462415,
|
| 125 |
+
"epoch_time_seconds": 71.62927317619324,
|
| 126 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 127 |
+
"line_sequence_accuracy": 37.68115942028985,
|
| 128 |
+
"line_bit_accuracy": 0.9992647058823529,
|
| 129 |
+
"line_levenshtein": 2.0869565217391304,
|
| 130 |
+
"line_bleu": 0.9648654657286488,
|
| 131 |
+
"line_rougeL": 0.9878799307687587,
|
| 132 |
+
"chunk_sequence_accuracy": 44.0,
|
| 133 |
+
"chunk_bit_accuracy": 0.9992395898783344,
|
| 134 |
+
"chunk_levenshtein": 1.08,
|
| 135 |
+
"chunk_bleu": 0.9676969451766948,
|
| 136 |
+
"chunk_rougeL": 0.980427160431532
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9,
|
| 140 |
+
"train_loss": 0.05327302955479418,
|
| 141 |
+
"val_loss": 0.005204007728025317,
|
| 142 |
+
"epoch_time_seconds": 71.12352538108826,
|
| 143 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 144 |
+
"line_sequence_accuracy": 55.072463768115945,
|
| 145 |
+
"line_bit_accuracy": 0.9995875841111352,
|
| 146 |
+
"line_levenshtein": 1.2028985507246377,
|
| 147 |
+
"line_bleu": 0.9801370084189431,
|
| 148 |
+
"line_rougeL": 0.9937604979305862,
|
| 149 |
+
"chunk_sequence_accuracy": 63.0,
|
| 150 |
+
"chunk_bit_accuracy": 0.9995608899297423,
|
| 151 |
+
"chunk_levenshtein": 0.61,
|
| 152 |
+
"chunk_bleu": 0.9839256143475175,
|
| 153 |
+
"chunk_rougeL": 0.9867575096895335
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10,
|
| 157 |
+
"train_loss": 0.04448051100941066,
|
| 158 |
+
"val_loss": 0.0038089079732474473,
|
| 159 |
+
"epoch_time_seconds": 71.8369824886322,
|
| 160 |
+
"peak_gpu_memory_mb": 8283.14013671875,
|
| 161 |
+
"line_sequence_accuracy": 63.768115942028984,
|
| 162 |
+
"line_bit_accuracy": 0.9997151074451921,
|
| 163 |
+
"line_levenshtein": 0.782608695652174,
|
| 164 |
+
"line_bleu": 0.9871331413199458,
|
| 165 |
+
"line_rougeL": 0.9961635160014924,
|
| 166 |
+
"chunk_sequence_accuracy": 75.0,
|
| 167 |
+
"chunk_bit_accuracy": 0.9997072599531616,
|
| 168 |
+
"chunk_levenshtein": 0.39,
|
| 169 |
+
"chunk_bleu": 0.9897167018659223,
|
| 170 |
+
"chunk_rougeL": 0.991367233320558
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 11,
|
| 174 |
+
"train_loss": 0.03978442871210417,
|
| 175 |
+
"val_loss": 0.0031240788063899216,
|
| 176 |
+
"epoch_time_seconds": 96.81052327156067,
|
| 177 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 178 |
+
"line_sequence_accuracy": 57.971014492753625,
|
| 179 |
+
"line_bit_accuracy": 0.999725960494899,
|
| 180 |
+
"line_levenshtein": 0.7101449275362319,
|
| 181 |
+
"line_bleu": 0.9887713015998153,
|
| 182 |
+
"line_rougeL": 0.9964930415320657,
|
| 183 |
+
"chunk_sequence_accuracy": 75.0,
|
| 184 |
+
"chunk_bit_accuracy": 0.9997072599531616,
|
| 185 |
+
"chunk_levenshtein": 0.37,
|
| 186 |
+
"chunk_bleu": 0.991716650795699,
|
| 187 |
+
"chunk_rougeL": 0.9910453923911273
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 12,
|
| 191 |
+
"train_loss": 0.03723422652419427,
|
| 192 |
+
"val_loss": 0.002512387415793325,
|
| 193 |
+
"epoch_time_seconds": 96.89030194282532,
|
| 194 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 195 |
+
"line_sequence_accuracy": 73.91304347826087,
|
| 196 |
+
"line_bit_accuracy": 0.9998127848925548,
|
| 197 |
+
"line_levenshtein": 0.5217391304347826,
|
| 198 |
+
"line_bleu": 0.992169090819422,
|
| 199 |
+
"line_rougeL": 0.9977700453616232,
|
| 200 |
+
"chunk_sequence_accuracy": 84.0,
|
| 201 |
+
"chunk_bit_accuracy": 0.9998000799680128,
|
| 202 |
+
"chunk_levenshtein": 0.27,
|
| 203 |
+
"chunk_bleu": 0.994913924567763,
|
| 204 |
+
"chunk_rougeL": 0.9936419165471765
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 13,
|
| 208 |
+
"train_loss": 0.03467494431194536,
|
| 209 |
+
"val_loss": 0.0023381193875268635,
|
| 210 |
+
"epoch_time_seconds": 70.97539854049683,
|
| 211 |
+
"peak_gpu_memory_mb": 8283.14013671875,
|
| 212 |
+
"line_sequence_accuracy": 65.21739130434783,
|
| 213 |
+
"line_bit_accuracy": 0.9997422400694596,
|
| 214 |
+
"line_levenshtein": 0.6086956521739131,
|
| 215 |
+
"line_bleu": 0.9900158373645993,
|
| 216 |
+
"line_rougeL": 0.9966774252442909,
|
| 217 |
+
"chunk_sequence_accuracy": 76.0,
|
| 218 |
+
"chunk_bit_accuracy": 0.9997036899525904,
|
| 219 |
+
"chunk_levenshtein": 0.34,
|
| 220 |
+
"chunk_bleu": 0.9929375727783555,
|
| 221 |
+
"chunk_rougeL": 0.9923997351533295
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 14,
|
| 225 |
+
"train_loss": 0.03272197068055377,
|
| 226 |
+
"val_loss": 0.001847643691040243,
|
| 227 |
+
"epoch_time_seconds": 70.80777668952942,
|
| 228 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 229 |
+
"line_sequence_accuracy": 73.91304347826087,
|
| 230 |
+
"line_bit_accuracy": 0.9998236379422618,
|
| 231 |
+
"line_levenshtein": 0.463768115942029,
|
| 232 |
+
"line_bleu": 0.9926246890183639,
|
| 233 |
+
"line_rougeL": 0.997800935359255,
|
| 234 |
+
"chunk_sequence_accuracy": 81.0,
|
| 235 |
+
"chunk_bit_accuracy": 0.9997822299651568,
|
| 236 |
+
"chunk_levenshtein": 0.29,
|
| 237 |
+
"chunk_bleu": 0.9931827613424836,
|
| 238 |
+
"chunk_rougeL": 0.9920961448680449
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 15,
|
| 242 |
+
"train_loss": 0.03221050455671916,
|
| 243 |
+
"val_loss": 0.00179198597782358,
|
| 244 |
+
"epoch_time_seconds": 70.98786902427673,
|
| 245 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 246 |
+
"line_sequence_accuracy": 75.3623188405797,
|
| 247 |
+
"line_bit_accuracy": 0.9998589103538095,
|
| 248 |
+
"line_levenshtein": 0.4057971014492754,
|
| 249 |
+
"line_bleu": 0.9932789128482497,
|
| 250 |
+
"line_rougeL": 0.9979432871552043,
|
| 251 |
+
"chunk_sequence_accuracy": 84.0,
|
| 252 |
+
"chunk_bit_accuracy": 0.9998357799737247,
|
| 253 |
+
"chunk_levenshtein": 0.25,
|
| 254 |
+
"chunk_bleu": 0.9950035899718211,
|
| 255 |
+
"chunk_rougeL": 0.9933565211550301
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 16,
|
| 259 |
+
"train_loss": 0.02854390934074377,
|
| 260 |
+
"val_loss": 0.0016359371386767765,
|
| 261 |
+
"epoch_time_seconds": 71.39919400215149,
|
| 262 |
+
"peak_gpu_memory_mb": 8283.14013671875,
|
| 263 |
+
"line_sequence_accuracy": 71.01449275362319,
|
| 264 |
+
"line_bit_accuracy": 0.9998344909919687,
|
| 265 |
+
"line_levenshtein": 0.43478260869565216,
|
| 266 |
+
"line_bleu": 0.9928845154537365,
|
| 267 |
+
"line_rougeL": 0.9979206596611225,
|
| 268 |
+
"chunk_sequence_accuracy": 83.0,
|
| 269 |
+
"chunk_bit_accuracy": 0.9998143599702976,
|
| 270 |
+
"chunk_levenshtein": 0.25,
|
| 271 |
+
"chunk_bleu": 0.9943006881112142,
|
| 272 |
+
"chunk_rougeL": 0.9963587893046463
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17,
|
| 276 |
+
"train_loss": 0.016801857528545988,
|
| 277 |
+
"val_loss": 0.001743678297706148,
|
| 278 |
+
"epoch_time_seconds": 71.284494638443,
|
| 279 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 280 |
+
"line_sequence_accuracy": 73.91304347826087,
|
| 281 |
+
"line_bit_accuracy": 0.9997965053179944,
|
| 282 |
+
"line_levenshtein": 0.42028985507246375,
|
| 283 |
+
"line_bleu": 0.9930191211746919,
|
| 284 |
+
"line_rougeL": 0.9979049842043384,
|
| 285 |
+
"chunk_sequence_accuracy": 84.0,
|
| 286 |
+
"chunk_bit_accuracy": 0.999785799965728,
|
| 287 |
+
"chunk_levenshtein": 0.24,
|
| 288 |
+
"chunk_bleu": 0.9944811945714258,
|
| 289 |
+
"chunk_rougeL": 0.9928516467388262
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 18,
|
| 293 |
+
"train_loss": 0.010893825068628477,
|
| 294 |
+
"val_loss": 0.001414892906073614,
|
| 295 |
+
"epoch_time_seconds": 71.28246903419495,
|
| 296 |
+
"peak_gpu_memory_mb": 8283.14013671875,
|
| 297 |
+
"line_sequence_accuracy": 79.71014492753623,
|
| 298 |
+
"line_bit_accuracy": 0.9998968960277838,
|
| 299 |
+
"line_levenshtein": 0.3188405797101449,
|
| 300 |
+
"line_bleu": 0.9954973584635326,
|
| 301 |
+
"line_rougeL": 0.9986813947292592,
|
| 302 |
+
"chunk_sequence_accuracy": 88.0,
|
| 303 |
+
"chunk_bit_accuracy": 0.999875049980008,
|
| 304 |
+
"chunk_levenshtein": 0.2,
|
| 305 |
+
"chunk_bleu": 0.9964646988265337,
|
| 306 |
+
"chunk_rougeL": 0.9952822244880705
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 19,
|
| 310 |
+
"train_loss": 0.009642765089269215,
|
| 311 |
+
"val_loss": 0.0013836190420469002,
|
| 312 |
+
"epoch_time_seconds": 72.66708707809448,
|
| 313 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 314 |
+
"line_sequence_accuracy": 75.3623188405797,
|
| 315 |
+
"line_bit_accuracy": 0.9998860429780768,
|
| 316 |
+
"line_levenshtein": 0.34782608695652173,
|
| 317 |
+
"line_bleu": 0.9941911164421988,
|
| 318 |
+
"line_rougeL": 0.9983816138707832,
|
| 319 |
+
"chunk_sequence_accuracy": 87.0,
|
| 320 |
+
"chunk_bit_accuracy": 0.9998786199805791,
|
| 321 |
+
"chunk_levenshtein": 0.19,
|
| 322 |
+
"chunk_bleu": 0.995860436104525,
|
| 323 |
+
"chunk_rougeL": 0.9936684824338393
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 20,
|
| 327 |
+
"train_loss": 0.009064305108040571,
|
| 328 |
+
"val_loss": 0.0011867721004819032,
|
| 329 |
+
"epoch_time_seconds": 73.1685779094696,
|
| 330 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 331 |
+
"line_sequence_accuracy": 76.81159420289855,
|
| 332 |
+
"line_bit_accuracy": 0.9998616236162362,
|
| 333 |
+
"line_levenshtein": 0.36231884057971014,
|
| 334 |
+
"line_bleu": 0.9939320840266092,
|
| 335 |
+
"line_rougeL": 0.9982620978444037,
|
| 336 |
+
"chunk_sequence_accuracy": 85.0,
|
| 337 |
+
"chunk_bit_accuracy": 0.999839349974296,
|
| 338 |
+
"chunk_levenshtein": 0.22,
|
| 339 |
+
"chunk_bleu": 0.9953466141133159,
|
| 340 |
+
"chunk_rougeL": 0.9945700142632166
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 21,
|
| 344 |
+
"train_loss": 0.00835902087712634,
|
| 345 |
+
"val_loss": 0.001354207004624186,
|
| 346 |
+
"epoch_time_seconds": 71.84267210960388,
|
| 347 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 348 |
+
"line_sequence_accuracy": 84.05797101449275,
|
| 349 |
+
"line_bit_accuracy": 0.9998670501410897,
|
| 350 |
+
"line_levenshtein": 0.3188405797101449,
|
| 351 |
+
"line_bleu": 0.9960199151482736,
|
| 352 |
+
"line_rougeL": 0.9987295890876278,
|
| 353 |
+
"chunk_sequence_accuracy": 89.0,
|
| 354 |
+
"chunk_bit_accuracy": 0.9998322099731536,
|
| 355 |
+
"chunk_levenshtein": 0.21,
|
| 356 |
+
"chunk_bleu": 0.9967258397079315,
|
| 357 |
+
"chunk_rougeL": 0.9956504653094922
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 22,
|
| 361 |
+
"train_loss": 0.007978124356435797,
|
| 362 |
+
"val_loss": 0.0014450403827400546,
|
| 363 |
+
"epoch_time_seconds": 71.088463306427,
|
| 364 |
+
"peak_gpu_memory_mb": 8283.14013671875,
|
| 365 |
+
"line_sequence_accuracy": 75.3623188405797,
|
| 366 |
+
"line_bit_accuracy": 0.9998697634035164,
|
| 367 |
+
"line_levenshtein": 0.37681159420289856,
|
| 368 |
+
"line_bleu": 0.994061204231723,
|
| 369 |
+
"line_rougeL": 0.9982743285163656,
|
| 370 |
+
"chunk_sequence_accuracy": 86.0,
|
| 371 |
+
"chunk_bit_accuracy": 0.999857199977152,
|
| 372 |
+
"chunk_levenshtein": 0.22,
|
| 373 |
+
"chunk_bleu": 0.9959500765338409,
|
| 374 |
+
"chunk_rougeL": 0.9935042247297372
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 23,
|
| 378 |
+
"train_loss": 0.00789498681670399,
|
| 379 |
+
"val_loss": 0.0012020115095115866,
|
| 380 |
+
"epoch_time_seconds": 71.11297059059143,
|
| 381 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 382 |
+
"line_sequence_accuracy": 81.15942028985508,
|
| 383 |
+
"line_bit_accuracy": 0.999894182765357,
|
| 384 |
+
"line_levenshtein": 0.30434782608695654,
|
| 385 |
+
"line_bleu": 0.9956939520240992,
|
| 386 |
+
"line_rougeL": 0.9987022002229444,
|
| 387 |
+
"chunk_sequence_accuracy": 87.0,
|
| 388 |
+
"chunk_bit_accuracy": 0.9998679099788655,
|
| 389 |
+
"chunk_levenshtein": 0.2,
|
| 390 |
+
"chunk_bleu": 0.9965542996329765,
|
| 391 |
+
"chunk_rougeL": 0.995163275063635
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 24,
|
| 395 |
+
"train_loss": 0.007538550854461947,
|
| 396 |
+
"val_loss": 0.0014473491137323435,
|
| 397 |
+
"epoch_time_seconds": 70.61388158798218,
|
| 398 |
+
"peak_gpu_memory_mb": 8283.18701171875,
|
| 399 |
+
"line_sequence_accuracy": 78.26086956521739,
|
| 400 |
+
"line_bit_accuracy": 0.9998616236162362,
|
| 401 |
+
"line_levenshtein": 0.36231884057971014,
|
| 402 |
+
"line_bleu": 0.9942586359512653,
|
| 403 |
+
"line_rougeL": 0.9982684516235144,
|
| 404 |
+
"chunk_sequence_accuracy": 86.0,
|
| 405 |
+
"chunk_bit_accuracy": 0.9998322099731536,
|
| 406 |
+
"chunk_levenshtein": 0.23,
|
| 407 |
+
"chunk_bleu": 0.9953466141133159,
|
| 408 |
+
"chunk_rougeL": 0.9949468397745659
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 25,
|
| 412 |
+
"train_loss": 0.007191763790236053,
|
| 413 |
+
"val_loss": 0.001238447749658787,
|
| 414 |
+
"epoch_time_seconds": 71.38782167434692,
|
| 415 |
+
"peak_gpu_memory_mb": 8283.14013671875,
|
| 416 |
+
"line_sequence_accuracy": 79.71014492753623,
|
| 417 |
+
"line_bit_accuracy": 0.9998806164532233,
|
| 418 |
+
"line_levenshtein": 0.30434782608695654,
|
| 419 |
+
"line_bleu": 0.9953674472092737,
|
| 420 |
+
"line_rougeL": 0.9985574892335567,
|
| 421 |
+
"chunk_sequence_accuracy": 88.0,
|
| 422 |
+
"chunk_bit_accuracy": 0.999857199977152,
|
| 423 |
+
"chunk_levenshtein": 0.19,
|
| 424 |
+
"chunk_bleu": 0.9965542996329765,
|
| 425 |
+
"chunk_rougeL": 0.994434677895909
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"test_results": {
|
| 429 |
+
"test_loss": 0.0009054133489761236,
|
| 430 |
+
"test_line_sequence_accuracy": 95.77464788732394,
|
| 431 |
+
"test_line_bit_accuracy": 0.9999780740221014,
|
| 432 |
+
"test_line_levenshtein": 0.056338028169014086,
|
| 433 |
+
"test_line_bleu": 0.9990102354303078,
|
| 434 |
+
"test_line_rougeL": 0.9997843289397004,
|
| 435 |
+
"test_chunk_sequence_accuracy": 98.0,
|
| 436 |
+
"test_chunk_bit_accuracy": 0.9999789461864526,
|
| 437 |
+
"test_chunk_levenshtein": 0.03,
|
| 438 |
+
"test_chunk_bleu": 0.9994031977126676,
|
| 439 |
+
"test_chunk_rougeL": 0.9997420634920635
|
| 440 |
+
}
|
| 441 |
+
}
|
| 442 |
+
]
|