End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.986342943854325,
|
| 3 |
+
"eval_loss": 0.35858574509620667,
|
| 4 |
+
"eval_recall": 0.9782797567332754,
|
| 5 |
+
"eval_runtime": 60.2263,
|
| 6 |
+
"eval_samples_per_second": 38.87,
|
| 7 |
+
"eval_steps_per_second": 1.229,
|
| 8 |
+
"total_flos": 1.1154611028241981e+19,
|
| 9 |
+
"train_loss": 0.4681245271510225,
|
| 10 |
+
"train_runtime": 1816.2465,
|
| 11 |
+
"train_samples_per_second": 34.801,
|
| 12 |
+
"train_steps_per_second": 0.271
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.986342943854325,
|
| 3 |
+
"eval_loss": 0.35858574509620667,
|
| 4 |
+
"eval_recall": 0.9782797567332754,
|
| 5 |
+
"eval_runtime": 60.2263,
|
| 6 |
+
"eval_samples_per_second": 38.87,
|
| 7 |
+
"eval_steps_per_second": 1.229
|
| 8 |
+
}
|
runs/Nov07_10-09-48_b095e30be617/events.out.tfevents.1730976191.b095e30be617.192.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e6e256b2fab5c081461ea1f3359098df7f02e8d92abb505017c90be1b53cc46
|
| 3 |
+
size 409
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.986342943854325,
|
| 3 |
+
"total_flos": 1.1154611028241981e+19,
|
| 4 |
+
"train_loss": 0.4681245271510225,
|
| 5 |
+
"train_runtime": 1816.2465,
|
| 6 |
+
"train_samples_per_second": 34.801,
|
| 7 |
+
"train_steps_per_second": 0.271
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9782797567332754,
|
| 3 |
+
"best_model_checkpoint": "convnext-large-224-finetuned-dog-vs-cat/checkpoint-492",
|
| 4 |
+
"epoch": 2.986342943854325,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 492,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06069802731411229,
|
| 13 |
+
"grad_norm": 1.2104277610778809,
|
| 14 |
+
"learning_rate": 1e-05,
|
| 15 |
+
"loss": 0.6885,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.12139605462822459,
|
| 20 |
+
"grad_norm": 1.1519063711166382,
|
| 21 |
+
"learning_rate": 2e-05,
|
| 22 |
+
"loss": 0.6854,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.18209408194233687,
|
| 27 |
+
"grad_norm": 1.203668475151062,
|
| 28 |
+
"learning_rate": 3e-05,
|
| 29 |
+
"loss": 0.6788,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.24279210925644917,
|
| 34 |
+
"grad_norm": 1.3230795860290527,
|
| 35 |
+
"learning_rate": 4e-05,
|
| 36 |
+
"loss": 0.6664,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.30349013657056145,
|
| 41 |
+
"grad_norm": 1.1332818269729614,
|
| 42 |
+
"learning_rate": 5e-05,
|
| 43 |
+
"loss": 0.6511,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.36418816388467373,
|
| 48 |
+
"grad_norm": 1.1424264907836914,
|
| 49 |
+
"learning_rate": 4.8868778280542986e-05,
|
| 50 |
+
"loss": 0.6321,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.424886191198786,
|
| 55 |
+
"grad_norm": 1.1293511390686035,
|
| 56 |
+
"learning_rate": 4.7737556561085976e-05,
|
| 57 |
+
"loss": 0.6115,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.48558421851289835,
|
| 62 |
+
"grad_norm": 1.1212339401245117,
|
| 63 |
+
"learning_rate": 4.660633484162896e-05,
|
| 64 |
+
"loss": 0.5957,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.5462822458270106,
|
| 69 |
+
"grad_norm": 0.9936708807945251,
|
| 70 |
+
"learning_rate": 4.547511312217195e-05,
|
| 71 |
+
"loss": 0.5815,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.6069802731411229,
|
| 76 |
+
"grad_norm": 1.0561779737472534,
|
| 77 |
+
"learning_rate": 4.434389140271493e-05,
|
| 78 |
+
"loss": 0.5583,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6676783004552352,
|
| 83 |
+
"grad_norm": 0.9779506921768188,
|
| 84 |
+
"learning_rate": 4.321266968325792e-05,
|
| 85 |
+
"loss": 0.5541,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.7283763277693475,
|
| 90 |
+
"grad_norm": 0.8941373825073242,
|
| 91 |
+
"learning_rate": 4.2081447963800907e-05,
|
| 92 |
+
"loss": 0.5408,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7890743550834598,
|
| 97 |
+
"grad_norm": 0.9414535164833069,
|
| 98 |
+
"learning_rate": 4.095022624434389e-05,
|
| 99 |
+
"loss": 0.5288,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.849772382397572,
|
| 104 |
+
"grad_norm": 0.8809621334075928,
|
| 105 |
+
"learning_rate": 3.981900452488688e-05,
|
| 106 |
+
"loss": 0.5194,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.9104704097116844,
|
| 111 |
+
"grad_norm": 0.8484501838684082,
|
| 112 |
+
"learning_rate": 3.868778280542987e-05,
|
| 113 |
+
"loss": 0.5038,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.9711684370257967,
|
| 118 |
+
"grad_norm": 0.8708747625350952,
|
| 119 |
+
"learning_rate": 3.7556561085972854e-05,
|
| 120 |
+
"loss": 0.496,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9954476479514416,
|
| 125 |
+
"eval_loss": 0.4791725277900696,
|
| 126 |
+
"eval_recall": 0.9200695047784535,
|
| 127 |
+
"eval_runtime": 60.2024,
|
| 128 |
+
"eval_samples_per_second": 38.885,
|
| 129 |
+
"eval_steps_per_second": 1.229,
|
| 130 |
+
"step": 164
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.031866464339909,
|
| 134 |
+
"grad_norm": 0.8436847925186157,
|
| 135 |
+
"learning_rate": 3.642533936651584e-05,
|
| 136 |
+
"loss": 0.4861,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.0925644916540211,
|
| 141 |
+
"grad_norm": 0.7819939851760864,
|
| 142 |
+
"learning_rate": 3.529411764705883e-05,
|
| 143 |
+
"loss": 0.4844,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.1532625189681336,
|
| 148 |
+
"grad_norm": 0.847568929195404,
|
| 149 |
+
"learning_rate": 3.416289592760181e-05,
|
| 150 |
+
"loss": 0.4673,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.2139605462822458,
|
| 155 |
+
"grad_norm": 0.7669057846069336,
|
| 156 |
+
"learning_rate": 3.3031674208144794e-05,
|
| 157 |
+
"loss": 0.4583,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.274658573596358,
|
| 162 |
+
"grad_norm": 0.766395092010498,
|
| 163 |
+
"learning_rate": 3.1900452488687784e-05,
|
| 164 |
+
"loss": 0.4473,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.3353566009104705,
|
| 169 |
+
"grad_norm": 0.8044094443321228,
|
| 170 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 171 |
+
"loss": 0.4531,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.3960546282245827,
|
| 176 |
+
"grad_norm": 0.7774869799613953,
|
| 177 |
+
"learning_rate": 2.9638009049773758e-05,
|
| 178 |
+
"loss": 0.439,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.456752655538695,
|
| 183 |
+
"grad_norm": 0.7320767641067505,
|
| 184 |
+
"learning_rate": 2.850678733031674e-05,
|
| 185 |
+
"loss": 0.436,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.5174506828528074,
|
| 190 |
+
"grad_norm": 0.7127722501754761,
|
| 191 |
+
"learning_rate": 2.737556561085973e-05,
|
| 192 |
+
"loss": 0.4314,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.5781487101669196,
|
| 197 |
+
"grad_norm": 0.7172250151634216,
|
| 198 |
+
"learning_rate": 2.6244343891402718e-05,
|
| 199 |
+
"loss": 0.4302,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.6388467374810318,
|
| 204 |
+
"grad_norm": 0.7075967192649841,
|
| 205 |
+
"learning_rate": 2.51131221719457e-05,
|
| 206 |
+
"loss": 0.4174,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.699544764795144,
|
| 211 |
+
"grad_norm": 0.7165055871009827,
|
| 212 |
+
"learning_rate": 2.3981900452488688e-05,
|
| 213 |
+
"loss": 0.4174,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.7602427921092565,
|
| 218 |
+
"grad_norm": 0.6554096341133118,
|
| 219 |
+
"learning_rate": 2.2850678733031675e-05,
|
| 220 |
+
"loss": 0.4193,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.8209408194233687,
|
| 225 |
+
"grad_norm": 0.7225818037986755,
|
| 226 |
+
"learning_rate": 2.1719457013574662e-05,
|
| 227 |
+
"loss": 0.3996,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.8816388467374812,
|
| 232 |
+
"grad_norm": 0.6873008012771606,
|
| 233 |
+
"learning_rate": 2.058823529411765e-05,
|
| 234 |
+
"loss": 0.4011,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.9423368740515934,
|
| 239 |
+
"grad_norm": 0.6827677488327026,
|
| 240 |
+
"learning_rate": 1.9457013574660635e-05,
|
| 241 |
+
"loss": 0.3996,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.9969650986342944,
|
| 246 |
+
"eval_loss": 0.3836117684841156,
|
| 247 |
+
"eval_recall": 0.9765421372719374,
|
| 248 |
+
"eval_runtime": 60.251,
|
| 249 |
+
"eval_samples_per_second": 38.854,
|
| 250 |
+
"eval_steps_per_second": 1.228,
|
| 251 |
+
"step": 329
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.0030349013657056,
|
| 255 |
+
"grad_norm": 0.6939449906349182,
|
| 256 |
+
"learning_rate": 1.832579185520362e-05,
|
| 257 |
+
"loss": 0.4015,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.063732928679818,
|
| 262 |
+
"grad_norm": 0.6604830026626587,
|
| 263 |
+
"learning_rate": 1.7194570135746606e-05,
|
| 264 |
+
"loss": 0.3934,
|
| 265 |
+
"step": 340
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.12443095599393,
|
| 269 |
+
"grad_norm": 0.6591904759407043,
|
| 270 |
+
"learning_rate": 1.6063348416289596e-05,
|
| 271 |
+
"loss": 0.3956,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.1851289833080423,
|
| 276 |
+
"grad_norm": 0.6776930689811707,
|
| 277 |
+
"learning_rate": 1.493212669683258e-05,
|
| 278 |
+
"loss": 0.3904,
|
| 279 |
+
"step": 360
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.245827010622155,
|
| 283 |
+
"grad_norm": 0.6641884446144104,
|
| 284 |
+
"learning_rate": 1.3800904977375568e-05,
|
| 285 |
+
"loss": 0.3836,
|
| 286 |
+
"step": 370
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.306525037936267,
|
| 290 |
+
"grad_norm": 0.6640185117721558,
|
| 291 |
+
"learning_rate": 1.2669683257918553e-05,
|
| 292 |
+
"loss": 0.3849,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.3672230652503794,
|
| 297 |
+
"grad_norm": 0.6439262628555298,
|
| 298 |
+
"learning_rate": 1.153846153846154e-05,
|
| 299 |
+
"loss": 0.3847,
|
| 300 |
+
"step": 390
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.4279210925644916,
|
| 304 |
+
"grad_norm": 0.6991675496101379,
|
| 305 |
+
"learning_rate": 1.0407239819004526e-05,
|
| 306 |
+
"loss": 0.3789,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.488619119878604,
|
| 311 |
+
"grad_norm": 0.6298201680183411,
|
| 312 |
+
"learning_rate": 9.276018099547511e-06,
|
| 313 |
+
"loss": 0.3769,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.549317147192716,
|
| 318 |
+
"grad_norm": 0.6205734014511108,
|
| 319 |
+
"learning_rate": 8.144796380090498e-06,
|
| 320 |
+
"loss": 0.3769,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.6100151745068283,
|
| 325 |
+
"grad_norm": 0.6230446696281433,
|
| 326 |
+
"learning_rate": 7.013574660633485e-06,
|
| 327 |
+
"loss": 0.3802,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.670713201820941,
|
| 332 |
+
"grad_norm": 0.6412050127983093,
|
| 333 |
+
"learning_rate": 5.882352941176471e-06,
|
| 334 |
+
"loss": 0.3805,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.731411229135053,
|
| 339 |
+
"grad_norm": 0.6700997948646545,
|
| 340 |
+
"learning_rate": 4.751131221719457e-06,
|
| 341 |
+
"loss": 0.3725,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.7921092564491654,
|
| 346 |
+
"grad_norm": 0.6392331123352051,
|
| 347 |
+
"learning_rate": 3.619909502262444e-06,
|
| 348 |
+
"loss": 0.3729,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.8528072837632776,
|
| 353 |
+
"grad_norm": 0.6410810351371765,
|
| 354 |
+
"learning_rate": 2.48868778280543e-06,
|
| 355 |
+
"loss": 0.3582,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.91350531107739,
|
| 360 |
+
"grad_norm": 0.6067666411399841,
|
| 361 |
+
"learning_rate": 1.3574660633484164e-06,
|
| 362 |
+
"loss": 0.3758,
|
| 363 |
+
"step": 480
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.9742033383915025,
|
| 367 |
+
"grad_norm": 0.6219173669815063,
|
| 368 |
+
"learning_rate": 2.2624434389140275e-07,
|
| 369 |
+
"loss": 0.373,
|
| 370 |
+
"step": 490
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.986342943854325,
|
| 374 |
+
"eval_loss": 0.35858574509620667,
|
| 375 |
+
"eval_recall": 0.9782797567332754,
|
| 376 |
+
"eval_runtime": 61.7184,
|
| 377 |
+
"eval_samples_per_second": 37.93,
|
| 378 |
+
"eval_steps_per_second": 1.199,
|
| 379 |
+
"step": 492
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.986342943854325,
|
| 383 |
+
"step": 492,
|
| 384 |
+
"total_flos": 1.1154611028241981e+19,
|
| 385 |
+
"train_loss": 0.4681245271510225,
|
| 386 |
+
"train_runtime": 1816.2465,
|
| 387 |
+
"train_samples_per_second": 34.801,
|
| 388 |
+
"train_steps_per_second": 0.271
|
| 389 |
+
}
|
| 390 |
+
],
|
| 391 |
+
"logging_steps": 10,
|
| 392 |
+
"max_steps": 492,
|
| 393 |
+
"num_input_tokens_seen": 0,
|
| 394 |
+
"num_train_epochs": 3,
|
| 395 |
+
"save_steps": 500,
|
| 396 |
+
"stateful_callbacks": {
|
| 397 |
+
"TrainerControl": {
|
| 398 |
+
"args": {
|
| 399 |
+
"should_epoch_stop": false,
|
| 400 |
+
"should_evaluate": false,
|
| 401 |
+
"should_log": false,
|
| 402 |
+
"should_save": true,
|
| 403 |
+
"should_training_stop": true
|
| 404 |
+
},
|
| 405 |
+
"attributes": {}
|
| 406 |
+
}
|
| 407 |
+
},
|
| 408 |
+
"total_flos": 1.1154611028241981e+19,
|
| 409 |
+
"train_batch_size": 32,
|
| 410 |
+
"trial_name": null,
|
| 411 |
+
"trial_params": null
|
| 412 |
+
}
|