Model save
Browse files- all_results.json +15 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- runs/Oct22_22-15-24_d0001feec92c/events.out.tfevents.1698012936.d0001feec92c.959.0 +2 -2
- runs/Oct22_22-15-24_d0001feec92c/events.out.tfevents.1698014620.d0001feec92c.959.2 +3 -0
- test_results.json +8 -0
- train_results.json +9 -0
- trainer_state.json +334 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.04,
|
| 3 |
+
"eval_accuracy": 0.6190476190476191,
|
| 4 |
+
"eval_loss": 0.9006302952766418,
|
| 5 |
+
"eval_runtime": 8.9559,
|
| 6 |
+
"eval_samples": 6,
|
| 7 |
+
"eval_samples_per_second": 2.345,
|
| 8 |
+
"eval_steps_per_second": 0.223,
|
| 9 |
+
"total_flos": 5.163737709298582e+18,
|
| 10 |
+
"train_loss": 0.4886108534836343,
|
| 11 |
+
"train_runtime": 1664.1582,
|
| 12 |
+
"train_samples": 94,
|
| 13 |
+
"train_samples_per_second": 2.524,
|
| 14 |
+
"train_steps_per_second": 0.21
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.04,
|
| 3 |
+
"eval_accuracy": 0.6,
|
| 4 |
+
"eval_loss": 0.9088060259819031,
|
| 5 |
+
"eval_runtime": 19.0866,
|
| 6 |
+
"eval_samples": 6,
|
| 7 |
+
"eval_samples_per_second": 1.31,
|
| 8 |
+
"eval_steps_per_second": 0.157
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344982450
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f083037aed69d3b24cc0ac78db6a7a81365ba09baae55a4d04b259d4b2f0c8e5
|
| 3 |
size 344982450
|
runs/Oct22_22-15-24_d0001feec92c/events.out.tfevents.1698012936.d0001feec92c.959.0
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 sha256:35a5c5f1d9ea8a75a9176c7ef22d6f99cd9931b9eb7ed06130b61ce205edd0cf
|
| 3 |
+
size 13052
|
runs/Oct22_22-15-24_d0001feec92c/events.out.tfevents.1698014620.d0001feec92c.959.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ccb13c4fc23306bdf41ab2fe64d4ca652e989cdadc2e65e1fea61b3711a2cb1
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.04,
|
| 3 |
+
"eval_accuracy": 0.6190476190476191,
|
| 4 |
+
"eval_loss": 0.9006302952766418,
|
| 5 |
+
"eval_runtime": 8.9559,
|
| 6 |
+
"eval_samples_per_second": 2.345,
|
| 7 |
+
"eval_steps_per_second": 0.223
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.04,
|
| 3 |
+
"total_flos": 5.163737709298582e+18,
|
| 4 |
+
"train_loss": 0.4886108534836343,
|
| 5 |
+
"train_runtime": 1664.1582,
|
| 6 |
+
"train_samples": 94,
|
| 7 |
+
"train_samples_per_second": 2.524,
|
| 8 |
+
"train_steps_per_second": 0.21
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-SSBD_Augm_v2/checkpoint-42",
|
| 4 |
+
"epoch": 8.04,
|
| 5 |
+
"global_step": 350,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 13 |
+
"loss": 1.1543,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 2.857142857142857e-05,
|
| 19 |
+
"loss": 1.1043,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 25 |
+
"loss": 1.1309,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 4.9206349206349204e-05,
|
| 31 |
+
"loss": 1.0891,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"eval_accuracy": 0.6,
|
| 37 |
+
"eval_loss": 0.9088060855865479,
|
| 38 |
+
"eval_runtime": 25.1399,
|
| 39 |
+
"eval_samples_per_second": 0.994,
|
| 40 |
+
"eval_steps_per_second": 0.119,
|
| 41 |
+
"step": 42
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.02,
|
| 45 |
+
"learning_rate": 4.761904761904762e-05,
|
| 46 |
+
"loss": 0.972,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.05,
|
| 51 |
+
"learning_rate": 4.603174603174603e-05,
|
| 52 |
+
"loss": 1.0649,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.08,
|
| 57 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 58 |
+
"loss": 0.9936,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.11,
|
| 63 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 64 |
+
"loss": 1.0414,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.12,
|
| 69 |
+
"eval_accuracy": 0.4,
|
| 70 |
+
"eval_loss": 1.1233173608779907,
|
| 71 |
+
"eval_runtime": 18.9992,
|
| 72 |
+
"eval_samples_per_second": 1.316,
|
| 73 |
+
"eval_steps_per_second": 0.158,
|
| 74 |
+
"step": 84
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.02,
|
| 78 |
+
"learning_rate": 4.126984126984127e-05,
|
| 79 |
+
"loss": 1.1475,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.05,
|
| 84 |
+
"learning_rate": 3.968253968253968e-05,
|
| 85 |
+
"loss": 1.3312,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.07,
|
| 90 |
+
"learning_rate": 3.809523809523809e-05,
|
| 91 |
+
"loss": 0.8461,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.1,
|
| 96 |
+
"learning_rate": 3.650793650793651e-05,
|
| 97 |
+
"loss": 0.7054,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.12,
|
| 102 |
+
"eval_accuracy": 0.44,
|
| 103 |
+
"eval_loss": 1.0407100915908813,
|
| 104 |
+
"eval_runtime": 18.9487,
|
| 105 |
+
"eval_samples_per_second": 1.319,
|
| 106 |
+
"eval_steps_per_second": 0.158,
|
| 107 |
+
"step": 126
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.01,
|
| 111 |
+
"learning_rate": 3.492063492063492e-05,
|
| 112 |
+
"loss": 0.7719,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.04,
|
| 117 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 118 |
+
"loss": 0.4189,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.07,
|
| 123 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 124 |
+
"loss": 0.369,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.1,
|
| 129 |
+
"learning_rate": 3.0158730158730158e-05,
|
| 130 |
+
"loss": 1.0071,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.12,
|
| 135 |
+
"eval_accuracy": 0.2,
|
| 136 |
+
"eval_loss": 1.6253796815872192,
|
| 137 |
+
"eval_runtime": 19.0795,
|
| 138 |
+
"eval_samples_per_second": 1.31,
|
| 139 |
+
"eval_steps_per_second": 0.157,
|
| 140 |
+
"step": 168
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.01,
|
| 144 |
+
"learning_rate": 2.857142857142857e-05,
|
| 145 |
+
"loss": 0.3392,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.03,
|
| 150 |
+
"learning_rate": 2.6984126984126984e-05,
|
| 151 |
+
"loss": 0.1986,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.06,
|
| 156 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 157 |
+
"loss": 0.4473,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.09,
|
| 162 |
+
"learning_rate": 2.380952380952381e-05,
|
| 163 |
+
"loss": 0.1842,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.12,
|
| 168 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 169 |
+
"loss": 0.2627,
|
| 170 |
+
"step": 210
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.12,
|
| 174 |
+
"eval_accuracy": 0.24,
|
| 175 |
+
"eval_loss": 2.7734763622283936,
|
| 176 |
+
"eval_runtime": 18.7713,
|
| 177 |
+
"eval_samples_per_second": 1.332,
|
| 178 |
+
"eval_steps_per_second": 0.16,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 5.03,
|
| 183 |
+
"learning_rate": 2.0634920634920636e-05,
|
| 184 |
+
"loss": 0.1376,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 5.06,
|
| 189 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 190 |
+
"loss": 0.2114,
|
| 191 |
+
"step": 230
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 5.09,
|
| 195 |
+
"learning_rate": 1.746031746031746e-05,
|
| 196 |
+
"loss": 0.0106,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 5.11,
|
| 201 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 202 |
+
"loss": 0.0226,
|
| 203 |
+
"step": 250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.12,
|
| 207 |
+
"eval_accuracy": 0.12,
|
| 208 |
+
"eval_loss": 4.147406578063965,
|
| 209 |
+
"eval_runtime": 18.8262,
|
| 210 |
+
"eval_samples_per_second": 1.328,
|
| 211 |
+
"eval_steps_per_second": 0.159,
|
| 212 |
+
"step": 252
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.02,
|
| 216 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 217 |
+
"loss": 0.0397,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.05,
|
| 222 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 223 |
+
"loss": 0.0067,
|
| 224 |
+
"step": 270
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.08,
|
| 228 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 229 |
+
"loss": 0.0386,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 6.11,
|
| 234 |
+
"learning_rate": 9.523809523809523e-06,
|
| 235 |
+
"loss": 0.0065,
|
| 236 |
+
"step": 290
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 6.12,
|
| 240 |
+
"eval_accuracy": 0.08,
|
| 241 |
+
"eval_loss": 4.598020553588867,
|
| 242 |
+
"eval_runtime": 18.8972,
|
| 243 |
+
"eval_samples_per_second": 1.323,
|
| 244 |
+
"eval_steps_per_second": 0.159,
|
| 245 |
+
"step": 294
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 7.02,
|
| 249 |
+
"learning_rate": 7.936507936507936e-06,
|
| 250 |
+
"loss": 0.0257,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 7.05,
|
| 255 |
+
"learning_rate": 6.349206349206349e-06,
|
| 256 |
+
"loss": 0.0028,
|
| 257 |
+
"step": 310
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 7.07,
|
| 261 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 262 |
+
"loss": 0.0024,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 7.1,
|
| 267 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 268 |
+
"loss": 0.012,
|
| 269 |
+
"step": 330
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.12,
|
| 273 |
+
"eval_accuracy": 0.08,
|
| 274 |
+
"eval_loss": 4.68769645690918,
|
| 275 |
+
"eval_runtime": 19.1009,
|
| 276 |
+
"eval_samples_per_second": 1.309,
|
| 277 |
+
"eval_steps_per_second": 0.157,
|
| 278 |
+
"step": 336
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 8.01,
|
| 282 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 283 |
+
"loss": 0.0026,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 8.04,
|
| 288 |
+
"learning_rate": 0.0,
|
| 289 |
+
"loss": 0.0027,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 8.04,
|
| 294 |
+
"eval_accuracy": 0.08,
|
| 295 |
+
"eval_loss": 4.665265083312988,
|
| 296 |
+
"eval_runtime": 19.0665,
|
| 297 |
+
"eval_samples_per_second": 1.311,
|
| 298 |
+
"eval_steps_per_second": 0.157,
|
| 299 |
+
"step": 350
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 8.04,
|
| 303 |
+
"step": 350,
|
| 304 |
+
"total_flos": 5.163737709298582e+18,
|
| 305 |
+
"train_loss": 0.4886108534836343,
|
| 306 |
+
"train_runtime": 1664.1582,
|
| 307 |
+
"train_samples_per_second": 2.524,
|
| 308 |
+
"train_steps_per_second": 0.21
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.04,
|
| 312 |
+
"eval_accuracy": 0.6,
|
| 313 |
+
"eval_loss": 0.9088060259819031,
|
| 314 |
+
"eval_runtime": 19.0866,
|
| 315 |
+
"eval_samples_per_second": 1.31,
|
| 316 |
+
"eval_steps_per_second": 0.157,
|
| 317 |
+
"step": 350
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 8.04,
|
| 321 |
+
"eval_accuracy": 0.6190476190476191,
|
| 322 |
+
"eval_loss": 0.9006302952766418,
|
| 323 |
+
"eval_runtime": 8.9559,
|
| 324 |
+
"eval_samples_per_second": 2.345,
|
| 325 |
+
"eval_steps_per_second": 0.223,
|
| 326 |
+
"step": 350
|
| 327 |
+
}
|
| 328 |
+
],
|
| 329 |
+
"max_steps": 350,
|
| 330 |
+
"num_train_epochs": 9223372036854775807,
|
| 331 |
+
"total_flos": 5.163737709298582e+18,
|
| 332 |
+
"trial_name": null,
|
| 333 |
+
"trial_params": null
|
| 334 |
+
}
|