Training in progress, epoch 0
Browse files- Val_results.json +8 -0
- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Feb03_09-16-21_cfacbd567a9f/events.out.tfevents.1675419690.cfacbd567a9f.178.4 +2 -2
- runs/Feb03_11-03-44_cfacbd567a9f/1675422237.3283842/events.out.tfevents.1675422237.cfacbd567a9f.178.6 +3 -0
- runs/Feb03_11-03-44_cfacbd567a9f/events.out.tfevents.1675422237.cfacbd567a9f.178.5 +3 -0
- trainer_state.json +283 -0
- training_args.bin +1 -1
Val_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.1,
|
| 3 |
+
"eval_accuracy": 0.6666666666666666,
|
| 4 |
+
"eval_loss": 0.681856095790863,
|
| 5 |
+
"eval_runtime": 18.2305,
|
| 6 |
+
"eval_samples_per_second": 1.152,
|
| 7 |
+
"eval_steps_per_second": 0.165
|
| 8 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.1,
|
| 3 |
+
"eval_accuracy": 0.6666666666666666,
|
| 4 |
+
"eval_loss": 0.681856095790863,
|
| 5 |
+
"eval_runtime": 18.2305,
|
| 6 |
+
"eval_samples_per_second": 1.152,
|
| 7 |
+
"eval_steps_per_second": 0.165
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344978933
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b264ef79eb873308b19f57d48a1335caaefddadac8d31be54e629ceba6e14f
|
| 3 |
size 344978933
|
runs/Feb03_09-16-21_cfacbd567a9f/events.out.tfevents.1675419690.cfacbd567a9f.178.4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff8f0c34eac94ea4a5eafacb880ab2545821805063b9b1784ba81d610734a7af
|
| 3 |
+
size 686
|
runs/Feb03_11-03-44_cfacbd567a9f/1675422237.3283842/events.out.tfevents.1675422237.cfacbd567a9f.178.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9995861aa9c1479129e9ff1dc391c99028d1d07d6c1cbb43048a8d412e5dfebe
|
| 3 |
+
size 5746
|
runs/Feb03_11-03-44_cfacbd567a9f/events.out.tfevents.1675422237.cfacbd567a9f.178.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1be91aded0bdb717a92ac4cb727612e5654eac9bf00f8dd1ec9f237de81fa243
|
| 3 |
+
size 4941
|
trainer_state.json
ADDED
|
@@ -0,0 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6666666666666666,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf1012bovi-subset/checkpoint-144",
|
| 4 |
+
"epoch": 7.1,
|
| 5 |
+
"global_step": 280,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.785714285714286e-05,
|
| 13 |
+
"loss": 0.7036,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 3.571428571428572e-05,
|
| 19 |
+
"loss": 0.6919,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"learning_rate": 4.960317460317461e-05,
|
| 25 |
+
"loss": 0.7118,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"eval_accuracy": 0.5714285714285714,
|
| 31 |
+
"eval_loss": 0.6813519597053528,
|
| 32 |
+
"eval_runtime": 17.1635,
|
| 33 |
+
"eval_samples_per_second": 1.224,
|
| 34 |
+
"eval_steps_per_second": 0.175,
|
| 35 |
+
"step": 36
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.01,
|
| 39 |
+
"learning_rate": 4.761904761904762e-05,
|
| 40 |
+
"loss": 0.7934,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.05,
|
| 45 |
+
"learning_rate": 4.563492063492064e-05,
|
| 46 |
+
"loss": 0.7599,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.09,
|
| 51 |
+
"learning_rate": 4.3650793650793655e-05,
|
| 52 |
+
"loss": 0.6935,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.12,
|
| 57 |
+
"learning_rate": 4.166666666666667e-05,
|
| 58 |
+
"loss": 0.8238,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.13,
|
| 63 |
+
"eval_accuracy": 0.5714285714285714,
|
| 64 |
+
"eval_loss": 0.6640704274177551,
|
| 65 |
+
"eval_runtime": 17.0264,
|
| 66 |
+
"eval_samples_per_second": 1.233,
|
| 67 |
+
"eval_steps_per_second": 0.176,
|
| 68 |
+
"step": 72
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.03,
|
| 72 |
+
"learning_rate": 3.968253968253968e-05,
|
| 73 |
+
"loss": 0.6964,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.06,
|
| 78 |
+
"learning_rate": 3.76984126984127e-05,
|
| 79 |
+
"loss": 0.6997,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.1,
|
| 84 |
+
"learning_rate": 3.571428571428572e-05,
|
| 85 |
+
"loss": 0.6892,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.13,
|
| 90 |
+
"eval_accuracy": 0.47619047619047616,
|
| 91 |
+
"eval_loss": 0.6934835910797119,
|
| 92 |
+
"eval_runtime": 16.5245,
|
| 93 |
+
"eval_samples_per_second": 1.271,
|
| 94 |
+
"eval_steps_per_second": 0.182,
|
| 95 |
+
"step": 108
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.01,
|
| 99 |
+
"learning_rate": 3.3730158730158734e-05,
|
| 100 |
+
"loss": 0.7053,
|
| 101 |
+
"step": 110
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.04,
|
| 105 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 106 |
+
"loss": 0.6779,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.08,
|
| 111 |
+
"learning_rate": 2.9761904761904762e-05,
|
| 112 |
+
"loss": 0.6888,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.11,
|
| 117 |
+
"learning_rate": 2.777777777777778e-05,
|
| 118 |
+
"loss": 0.7013,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.13,
|
| 123 |
+
"eval_accuracy": 0.6666666666666666,
|
| 124 |
+
"eval_loss": 0.6818560361862183,
|
| 125 |
+
"eval_runtime": 17.5029,
|
| 126 |
+
"eval_samples_per_second": 1.2,
|
| 127 |
+
"eval_steps_per_second": 0.171,
|
| 128 |
+
"step": 144
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.02,
|
| 132 |
+
"learning_rate": 2.5793650793650796e-05,
|
| 133 |
+
"loss": 0.7085,
|
| 134 |
+
"step": 150
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.06,
|
| 138 |
+
"learning_rate": 2.380952380952381e-05,
|
| 139 |
+
"loss": 0.6941,
|
| 140 |
+
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.09,
|
| 144 |
+
"learning_rate": 2.1825396825396827e-05,
|
| 145 |
+
"loss": 0.6897,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.13,
|
| 150 |
+
"learning_rate": 1.984126984126984e-05,
|
| 151 |
+
"loss": 0.6871,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.13,
|
| 156 |
+
"eval_accuracy": 0.5714285714285714,
|
| 157 |
+
"eval_loss": 0.6750560998916626,
|
| 158 |
+
"eval_runtime": 18.5719,
|
| 159 |
+
"eval_samples_per_second": 1.131,
|
| 160 |
+
"eval_steps_per_second": 0.162,
|
| 161 |
+
"step": 180
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.04,
|
| 165 |
+
"learning_rate": 1.785714285714286e-05,
|
| 166 |
+
"loss": 0.6712,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 5.07,
|
| 171 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 172 |
+
"loss": 0.6929,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 5.11,
|
| 177 |
+
"learning_rate": 1.388888888888889e-05,
|
| 178 |
+
"loss": 0.7159,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 5.13,
|
| 183 |
+
"eval_accuracy": 0.5238095238095238,
|
| 184 |
+
"eval_loss": 0.6854279041290283,
|
| 185 |
+
"eval_runtime": 18.2412,
|
| 186 |
+
"eval_samples_per_second": 1.151,
|
| 187 |
+
"eval_steps_per_second": 0.164,
|
| 188 |
+
"step": 216
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 6.01,
|
| 192 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 193 |
+
"loss": 0.6867,
|
| 194 |
+
"step": 220
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 6.05,
|
| 198 |
+
"learning_rate": 9.92063492063492e-06,
|
| 199 |
+
"loss": 0.6832,
|
| 200 |
+
"step": 230
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.09,
|
| 204 |
+
"learning_rate": 7.936507936507936e-06,
|
| 205 |
+
"loss": 0.6992,
|
| 206 |
+
"step": 240
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.12,
|
| 210 |
+
"learning_rate": 5.9523809523809525e-06,
|
| 211 |
+
"loss": 0.6884,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.13,
|
| 216 |
+
"eval_accuracy": 0.6666666666666666,
|
| 217 |
+
"eval_loss": 0.6735024452209473,
|
| 218 |
+
"eval_runtime": 17.7454,
|
| 219 |
+
"eval_samples_per_second": 1.183,
|
| 220 |
+
"eval_steps_per_second": 0.169,
|
| 221 |
+
"step": 252
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 7.03,
|
| 225 |
+
"learning_rate": 3.968253968253968e-06,
|
| 226 |
+
"loss": 0.6854,
|
| 227 |
+
"step": 260
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 7.06,
|
| 231 |
+
"learning_rate": 1.984126984126984e-06,
|
| 232 |
+
"loss": 0.6846,
|
| 233 |
+
"step": 270
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.1,
|
| 237 |
+
"learning_rate": 0.0,
|
| 238 |
+
"loss": 0.6905,
|
| 239 |
+
"step": 280
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 7.1,
|
| 243 |
+
"eval_accuracy": 0.6190476190476191,
|
| 244 |
+
"eval_loss": 0.6739117503166199,
|
| 245 |
+
"eval_runtime": 16.357,
|
| 246 |
+
"eval_samples_per_second": 1.284,
|
| 247 |
+
"eval_steps_per_second": 0.183,
|
| 248 |
+
"step": 280
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.1,
|
| 252 |
+
"step": 280,
|
| 253 |
+
"total_flos": 2.783708292879876e+18,
|
| 254 |
+
"train_loss": 0.7040540405682155,
|
| 255 |
+
"train_runtime": 2623.4719,
|
| 256 |
+
"train_samples_per_second": 0.854,
|
| 257 |
+
"train_steps_per_second": 0.107
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 7.1,
|
| 261 |
+
"eval_accuracy": 0.6666666666666666,
|
| 262 |
+
"eval_loss": 0.6818560361862183,
|
| 263 |
+
"eval_runtime": 16.5475,
|
| 264 |
+
"eval_samples_per_second": 1.269,
|
| 265 |
+
"eval_steps_per_second": 0.181,
|
| 266 |
+
"step": 280
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 7.1,
|
| 270 |
+
"eval_accuracy": 0.6666666666666666,
|
| 271 |
+
"eval_loss": 0.681856095790863,
|
| 272 |
+
"eval_runtime": 18.2305,
|
| 273 |
+
"eval_samples_per_second": 1.152,
|
| 274 |
+
"eval_steps_per_second": 0.165,
|
| 275 |
+
"step": 280
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"max_steps": 280,
|
| 279 |
+
"num_train_epochs": 9223372036854775807,
|
| 280 |
+
"total_flos": 2.783708292879876e+18,
|
| 281 |
+
"trial_name": null,
|
| 282 |
+
"trial_params": null
|
| 283 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f4e322a63f39b30d58bcb0965eb55ed4363172699a1c85070eea1fba03d661b
|
| 3 |
size 3579
|