End of training
Browse files- all_results.json +16 -0
- eval_results.json +10 -0
- runs/Oct04_16-35-53_Turing/events.out.tfevents.1728088566.Turing.1254601.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +410 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9996095275283094,
|
| 3 |
+
"eval_accuracy": 0.6325420522781227,
|
| 4 |
+
"eval_loss": 1.5053555965423584,
|
| 5 |
+
"eval_runtime": 516.8924,
|
| 6 |
+
"eval_samples": 15400,
|
| 7 |
+
"eval_samples_per_second": 29.793,
|
| 8 |
+
"eval_steps_per_second": 7.448,
|
| 9 |
+
"perplexity": 4.505755576552062,
|
| 10 |
+
"total_flos": 9.6346733543424e+16,
|
| 11 |
+
"train_loss": 1.6814149037051365,
|
| 12 |
+
"train_runtime": 28276.4686,
|
| 13 |
+
"train_samples": 61463,
|
| 14 |
+
"train_samples_per_second": 6.521,
|
| 15 |
+
"train_steps_per_second": 0.408
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9996095275283094,
|
| 3 |
+
"eval_accuracy": 0.6325420522781227,
|
| 4 |
+
"eval_loss": 1.5053555965423584,
|
| 5 |
+
"eval_runtime": 516.8924,
|
| 6 |
+
"eval_samples": 15400,
|
| 7 |
+
"eval_samples_per_second": 29.793,
|
| 8 |
+
"eval_steps_per_second": 7.448,
|
| 9 |
+
"perplexity": 4.505755576552062
|
| 10 |
+
}
|
runs/Oct04_16-35-53_Turing/events.out.tfevents.1728088566.Turing.1254601.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69d5fb7c2dcdf245c690bf10cb2e288269f3c6d3f125da97c5d9a2f191ca56cf
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9996095275283094,
|
| 3 |
+
"total_flos": 9.6346733543424e+16,
|
| 4 |
+
"train_loss": 1.6814149037051365,
|
| 5 |
+
"train_runtime": 28276.4686,
|
| 6 |
+
"train_samples": 61463,
|
| 7 |
+
"train_samples_per_second": 6.521,
|
| 8 |
+
"train_steps_per_second": 0.408
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,410 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5053555965423584,
|
| 3 |
+
"best_model_checkpoint": "./tmp/clm-gpt2/checkpoint-11500",
|
| 4 |
+
"epoch": 2.9996095275283094,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11523,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13015749056358195,
|
| 13 |
+
"grad_norm": 0.3655782639980316,
|
| 14 |
+
"learning_rate": 0.0015,
|
| 15 |
+
"loss": 2.4536,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.13015749056358195,
|
| 20 |
+
"eval_accuracy": 0.4954853308958881,
|
| 21 |
+
"eval_loss": 2.1316182613372803,
|
| 22 |
+
"eval_runtime": 630.0742,
|
| 23 |
+
"eval_samples_per_second": 24.442,
|
| 24 |
+
"eval_steps_per_second": 6.11,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.2603149811271639,
|
| 29 |
+
"grad_norm": 0.2795959711074829,
|
| 30 |
+
"learning_rate": 0.003,
|
| 31 |
+
"loss": 2.1054,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2603149811271639,
|
| 36 |
+
"eval_accuracy": 0.5220788107298371,
|
| 37 |
+
"eval_loss": 2.0124123096466064,
|
| 38 |
+
"eval_runtime": 571.1208,
|
| 39 |
+
"eval_samples_per_second": 26.965,
|
| 40 |
+
"eval_steps_per_second": 6.741,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.3904724716907458,
|
| 45 |
+
"grad_norm": 0.2532959282398224,
|
| 46 |
+
"learning_rate": 0.0028574550983559823,
|
| 47 |
+
"loss": 1.9756,
|
| 48 |
+
"step": 1500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.3904724716907458,
|
| 52 |
+
"eval_accuracy": 0.5452574551548158,
|
| 53 |
+
"eval_loss": 1.902522087097168,
|
| 54 |
+
"eval_runtime": 521.1164,
|
| 55 |
+
"eval_samples_per_second": 29.552,
|
| 56 |
+
"eval_steps_per_second": 7.388,
|
| 57 |
+
"step": 1500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.5206299622543278,
|
| 61 |
+
"grad_norm": 0.1999560445547104,
|
| 62 |
+
"learning_rate": 0.002714910196711964,
|
| 63 |
+
"loss": 1.8863,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.5206299622543278,
|
| 68 |
+
"eval_accuracy": 0.5600627134351475,
|
| 69 |
+
"eval_loss": 1.836737871170044,
|
| 70 |
+
"eval_runtime": 521.7562,
|
| 71 |
+
"eval_samples_per_second": 29.516,
|
| 72 |
+
"eval_steps_per_second": 7.379,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6507874528179096,
|
| 77 |
+
"grad_norm": 0.18795448541641235,
|
| 78 |
+
"learning_rate": 0.0025723652950679463,
|
| 79 |
+
"loss": 1.8283,
|
| 80 |
+
"step": 2500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.6507874528179096,
|
| 84 |
+
"eval_accuracy": 0.5686439806527783,
|
| 85 |
+
"eval_loss": 1.7926692962646484,
|
| 86 |
+
"eval_runtime": 521.5355,
|
| 87 |
+
"eval_samples_per_second": 29.528,
|
| 88 |
+
"eval_steps_per_second": 7.382,
|
| 89 |
+
"step": 2500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.7809449433814916,
|
| 93 |
+
"grad_norm": 0.21605215966701508,
|
| 94 |
+
"learning_rate": 0.0024298203934239285,
|
| 95 |
+
"loss": 1.7893,
|
| 96 |
+
"step": 3000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.7809449433814916,
|
| 100 |
+
"eval_accuracy": 0.5759645681786444,
|
| 101 |
+
"eval_loss": 1.758531093597412,
|
| 102 |
+
"eval_runtime": 521.9502,
|
| 103 |
+
"eval_samples_per_second": 29.505,
|
| 104 |
+
"eval_steps_per_second": 7.376,
|
| 105 |
+
"step": 3000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.9111024339450735,
|
| 109 |
+
"grad_norm": 0.17780712246894836,
|
| 110 |
+
"learning_rate": 0.0022872754917799107,
|
| 111 |
+
"loss": 1.7555,
|
| 112 |
+
"step": 3500
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.9111024339450735,
|
| 116 |
+
"eval_accuracy": 0.581453644107603,
|
| 117 |
+
"eval_loss": 1.732818841934204,
|
| 118 |
+
"eval_runtime": 521.3914,
|
| 119 |
+
"eval_samples_per_second": 29.536,
|
| 120 |
+
"eval_steps_per_second": 7.384,
|
| 121 |
+
"step": 3500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0412599245086556,
|
| 125 |
+
"grad_norm": 0.17426873743534088,
|
| 126 |
+
"learning_rate": 0.002144730590135893,
|
| 127 |
+
"loss": 1.7143,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.0412599245086556,
|
| 132 |
+
"eval_accuracy": 0.5881837859110587,
|
| 133 |
+
"eval_loss": 1.701590895652771,
|
| 134 |
+
"eval_runtime": 522.4527,
|
| 135 |
+
"eval_samples_per_second": 29.476,
|
| 136 |
+
"eval_steps_per_second": 7.369,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1714174150722374,
|
| 141 |
+
"grad_norm": 0.1862766295671463,
|
| 142 |
+
"learning_rate": 0.002002185688491875,
|
| 143 |
+
"loss": 1.6697,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1714174150722374,
|
| 148 |
+
"eval_accuracy": 0.592953625065062,
|
| 149 |
+
"eval_loss": 1.6812903881072998,
|
| 150 |
+
"eval_runtime": 520.916,
|
| 151 |
+
"eval_samples_per_second": 29.563,
|
| 152 |
+
"eval_steps_per_second": 7.391,
|
| 153 |
+
"step": 4500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.3015749056358192,
|
| 157 |
+
"grad_norm": 0.17118503153324127,
|
| 158 |
+
"learning_rate": 0.0018596407868478571,
|
| 159 |
+
"loss": 1.6584,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.3015749056358192,
|
| 164 |
+
"eval_accuracy": 0.5972079191580658,
|
| 165 |
+
"eval_loss": 1.6614623069763184,
|
| 166 |
+
"eval_runtime": 520.2098,
|
| 167 |
+
"eval_samples_per_second": 29.603,
|
| 168 |
+
"eval_steps_per_second": 7.401,
|
| 169 |
+
"step": 5000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.4317323961994013,
|
| 173 |
+
"grad_norm": 0.17990975081920624,
|
| 174 |
+
"learning_rate": 0.0017170958852038393,
|
| 175 |
+
"loss": 1.6438,
|
| 176 |
+
"step": 5500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.4317323961994013,
|
| 180 |
+
"eval_accuracy": 0.6009242614667835,
|
| 181 |
+
"eval_loss": 1.6421809196472168,
|
| 182 |
+
"eval_runtime": 520.0082,
|
| 183 |
+
"eval_samples_per_second": 29.615,
|
| 184 |
+
"eval_steps_per_second": 7.404,
|
| 185 |
+
"step": 5500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.5618898867629833,
|
| 189 |
+
"grad_norm": 0.1535763144493103,
|
| 190 |
+
"learning_rate": 0.0015745509835598213,
|
| 191 |
+
"loss": 1.6184,
|
| 192 |
+
"step": 6000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.5618898867629833,
|
| 196 |
+
"eval_accuracy": 0.6048871412067893,
|
| 197 |
+
"eval_loss": 1.6235625743865967,
|
| 198 |
+
"eval_runtime": 518.9862,
|
| 199 |
+
"eval_samples_per_second": 29.673,
|
| 200 |
+
"eval_steps_per_second": 7.418,
|
| 201 |
+
"step": 6000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.6920473773265652,
|
| 205 |
+
"grad_norm": 0.16722074151039124,
|
| 206 |
+
"learning_rate": 0.0014320060819158036,
|
| 207 |
+
"loss": 1.6086,
|
| 208 |
+
"step": 6500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.6920473773265652,
|
| 212 |
+
"eval_accuracy": 0.6081556664254611,
|
| 213 |
+
"eval_loss": 1.6102288961410522,
|
| 214 |
+
"eval_runtime": 519.7651,
|
| 215 |
+
"eval_samples_per_second": 29.629,
|
| 216 |
+
"eval_steps_per_second": 7.407,
|
| 217 |
+
"step": 6500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.822204867890147,
|
| 221 |
+
"grad_norm": 0.1687261015176773,
|
| 222 |
+
"learning_rate": 0.0012894611802717856,
|
| 223 |
+
"loss": 1.5882,
|
| 224 |
+
"step": 7000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.822204867890147,
|
| 228 |
+
"eval_accuracy": 0.6113670005458862,
|
| 229 |
+
"eval_loss": 1.5938153266906738,
|
| 230 |
+
"eval_runtime": 518.0575,
|
| 231 |
+
"eval_samples_per_second": 29.726,
|
| 232 |
+
"eval_steps_per_second": 7.432,
|
| 233 |
+
"step": 7000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.9523623584537289,
|
| 237 |
+
"grad_norm": 0.17714297771453857,
|
| 238 |
+
"learning_rate": 0.0011469162786277678,
|
| 239 |
+
"loss": 1.5719,
|
| 240 |
+
"step": 7500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.9523623584537289,
|
| 244 |
+
"eval_accuracy": 0.6148032270759544,
|
| 245 |
+
"eval_loss": 1.578608751296997,
|
| 246 |
+
"eval_runtime": 518.0664,
|
| 247 |
+
"eval_samples_per_second": 29.726,
|
| 248 |
+
"eval_steps_per_second": 7.431,
|
| 249 |
+
"step": 7500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.082519849017311,
|
| 253 |
+
"grad_norm": 0.16494958102703094,
|
| 254 |
+
"learning_rate": 0.00100437137698375,
|
| 255 |
+
"loss": 1.5272,
|
| 256 |
+
"step": 8000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.082519849017311,
|
| 260 |
+
"eval_accuracy": 0.617450838506557,
|
| 261 |
+
"eval_loss": 1.5717881917953491,
|
| 262 |
+
"eval_runtime": 518.5565,
|
| 263 |
+
"eval_samples_per_second": 29.698,
|
| 264 |
+
"eval_steps_per_second": 7.424,
|
| 265 |
+
"step": 8000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.212677339580893,
|
| 269 |
+
"grad_norm": 0.14182300865650177,
|
| 270 |
+
"learning_rate": 0.0008618264753397321,
|
| 271 |
+
"loss": 1.4971,
|
| 272 |
+
"step": 8500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.212677339580893,
|
| 276 |
+
"eval_accuracy": 0.6203893564890632,
|
| 277 |
+
"eval_loss": 1.5592997074127197,
|
| 278 |
+
"eval_runtime": 517.6299,
|
| 279 |
+
"eval_samples_per_second": 29.751,
|
| 280 |
+
"eval_steps_per_second": 7.438,
|
| 281 |
+
"step": 8500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.342834830144475,
|
| 285 |
+
"grad_norm": 0.15439514815807343,
|
| 286 |
+
"learning_rate": 0.0007192815736957142,
|
| 287 |
+
"loss": 1.4893,
|
| 288 |
+
"step": 9000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.342834830144475,
|
| 292 |
+
"eval_accuracy": 0.6227424432849653,
|
| 293 |
+
"eval_loss": 1.5474613904953003,
|
| 294 |
+
"eval_runtime": 517.7895,
|
| 295 |
+
"eval_samples_per_second": 29.742,
|
| 296 |
+
"eval_steps_per_second": 7.435,
|
| 297 |
+
"step": 9000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.4729923207080566,
|
| 301 |
+
"grad_norm": 0.1444994956254959,
|
| 302 |
+
"learning_rate": 0.0005767366720516963,
|
| 303 |
+
"loss": 1.4808,
|
| 304 |
+
"step": 9500
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.4729923207080566,
|
| 308 |
+
"eval_accuracy": 0.6250960378819617,
|
| 309 |
+
"eval_loss": 1.5381561517715454,
|
| 310 |
+
"eval_runtime": 518.2423,
|
| 311 |
+
"eval_samples_per_second": 29.716,
|
| 312 |
+
"eval_steps_per_second": 7.429,
|
| 313 |
+
"step": 9500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.6031498112716385,
|
| 317 |
+
"grad_norm": 0.14975884556770325,
|
| 318 |
+
"learning_rate": 0.00043419177040767847,
|
| 319 |
+
"loss": 1.4689,
|
| 320 |
+
"step": 10000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.6031498112716385,
|
| 324 |
+
"eval_accuracy": 0.6274774980640083,
|
| 325 |
+
"eval_loss": 1.5274103879928589,
|
| 326 |
+
"eval_runtime": 518.577,
|
| 327 |
+
"eval_samples_per_second": 29.697,
|
| 328 |
+
"eval_steps_per_second": 7.424,
|
| 329 |
+
"step": 10000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.7333073018352207,
|
| 333 |
+
"grad_norm": 0.14258165657520294,
|
| 334 |
+
"learning_rate": 0.00029164686876366057,
|
| 335 |
+
"loss": 1.4572,
|
| 336 |
+
"step": 10500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.7333073018352207,
|
| 340 |
+
"eval_accuracy": 0.6297954196341293,
|
| 341 |
+
"eval_loss": 1.5169227123260498,
|
| 342 |
+
"eval_runtime": 518.5892,
|
| 343 |
+
"eval_samples_per_second": 29.696,
|
| 344 |
+
"eval_steps_per_second": 7.424,
|
| 345 |
+
"step": 10500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.8634647923988026,
|
| 349 |
+
"grad_norm": 0.14571569859981537,
|
| 350 |
+
"learning_rate": 0.00014910196711964268,
|
| 351 |
+
"loss": 1.4488,
|
| 352 |
+
"step": 11000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.8634647923988026,
|
| 356 |
+
"eval_accuracy": 0.6314827791953892,
|
| 357 |
+
"eval_loss": 1.5106253623962402,
|
| 358 |
+
"eval_runtime": 519.3798,
|
| 359 |
+
"eval_samples_per_second": 29.651,
|
| 360 |
+
"eval_steps_per_second": 7.413,
|
| 361 |
+
"step": 11000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.9936222829623844,
|
| 365 |
+
"grad_norm": 0.15030799806118011,
|
| 366 |
+
"learning_rate": 6.557065475624823e-06,
|
| 367 |
+
"loss": 1.4465,
|
| 368 |
+
"step": 11500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.9936222829623844,
|
| 372 |
+
"eval_accuracy": 0.6325420522781227,
|
| 373 |
+
"eval_loss": 1.5053555965423584,
|
| 374 |
+
"eval_runtime": 518.7173,
|
| 375 |
+
"eval_samples_per_second": 29.689,
|
| 376 |
+
"eval_steps_per_second": 7.422,
|
| 377 |
+
"step": 11500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.9996095275283094,
|
| 381 |
+
"step": 11523,
|
| 382 |
+
"total_flos": 9.6346733543424e+16,
|
| 383 |
+
"train_loss": 1.6814149037051365,
|
| 384 |
+
"train_runtime": 28276.4686,
|
| 385 |
+
"train_samples_per_second": 6.521,
|
| 386 |
+
"train_steps_per_second": 0.408
|
| 387 |
+
}
|
| 388 |
+
],
|
| 389 |
+
"logging_steps": 500,
|
| 390 |
+
"max_steps": 11523,
|
| 391 |
+
"num_input_tokens_seen": 0,
|
| 392 |
+
"num_train_epochs": 3,
|
| 393 |
+
"save_steps": 500,
|
| 394 |
+
"stateful_callbacks": {
|
| 395 |
+
"TrainerControl": {
|
| 396 |
+
"args": {
|
| 397 |
+
"should_epoch_stop": false,
|
| 398 |
+
"should_evaluate": false,
|
| 399 |
+
"should_log": false,
|
| 400 |
+
"should_save": true,
|
| 401 |
+
"should_training_stop": true
|
| 402 |
+
},
|
| 403 |
+
"attributes": {}
|
| 404 |
+
}
|
| 405 |
+
},
|
| 406 |
+
"total_flos": 9.6346733543424e+16,
|
| 407 |
+
"train_batch_size": 4,
|
| 408 |
+
"trial_name": null,
|
| 409 |
+
"trial_params": null
|
| 410 |
+
}
|