End of training
Browse files
README.md
CHANGED
|
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
- Accuracy: 0.8418
|
| 37 |
|
| 38 |
## Model description
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4225
|
| 36 |
- Accuracy: 0.8418
|
| 37 |
|
| 38 |
## Model description
|
all_results.json
CHANGED
|
@@ -1,7 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8418079096045198,
|
| 4 |
+
"eval_loss": 0.4224812686443329,
|
| 5 |
+
"eval_runtime": 5.8686,
|
| 6 |
+
"eval_samples_per_second": 30.16,
|
| 7 |
+
"eval_steps_per_second": 15.165,
|
| 8 |
+
"train_loss": 0.4336023674368457,
|
| 9 |
+
"train_runtime": 545.8523,
|
| 10 |
+
"train_samples_per_second": 8.711,
|
| 11 |
+
"train_steps_per_second": 1.088
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.8418079096045198,
|
| 4 |
+
"eval_loss": 0.4224812686443329,
|
| 5 |
+
"eval_runtime": 5.8686,
|
| 6 |
+
"eval_samples_per_second": 30.16,
|
| 7 |
+
"eval_steps_per_second": 15.165
|
| 8 |
}
|
runs/Feb18_00-28-56_LPP00266034A.fsoft.fpt.vn/events.out.tfevents.1708191734.LPP00266034A.fsoft.fpt.vn.78873.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d61539e7d671ccf45ec15dbe8163acd306b0f6a60463f376362a19b91c9928f
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.4336023674368457,
|
| 4 |
+
"train_runtime": 545.8523,
|
| 5 |
+
"train_samples_per_second": 8.711,
|
| 6 |
+
"train_steps_per_second": 1.088
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,411 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8418079096045198,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-base-22k-224-finetuned-eurosat/checkpoint-396",
|
| 4 |
+
"epoch": 2.9962168978562422,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 594,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 8.333333333333334e-06,
|
| 14 |
+
"loss": 1.2525,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.1,
|
| 19 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 20 |
+
"loss": 0.9977,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.15,
|
| 25 |
+
"learning_rate": 2.5e-05,
|
| 26 |
+
"loss": 0.9665,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.2,
|
| 31 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 32 |
+
"loss": 0.7669,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.25,
|
| 37 |
+
"learning_rate": 4.166666666666667e-05,
|
| 38 |
+
"loss": 0.7126,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.3,
|
| 43 |
+
"learning_rate": 5e-05,
|
| 44 |
+
"loss": 0.728,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.35,
|
| 49 |
+
"learning_rate": 4.906367041198502e-05,
|
| 50 |
+
"loss": 0.7651,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.4,
|
| 55 |
+
"learning_rate": 4.812734082397004e-05,
|
| 56 |
+
"loss": 0.7771,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.45,
|
| 61 |
+
"learning_rate": 4.719101123595506e-05,
|
| 62 |
+
"loss": 0.6614,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.5,
|
| 67 |
+
"learning_rate": 4.625468164794008e-05,
|
| 68 |
+
"loss": 0.6218,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.55,
|
| 73 |
+
"learning_rate": 4.531835205992509e-05,
|
| 74 |
+
"loss": 0.6318,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.61,
|
| 79 |
+
"learning_rate": 4.438202247191011e-05,
|
| 80 |
+
"loss": 0.5905,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.66,
|
| 85 |
+
"learning_rate": 4.344569288389513e-05,
|
| 86 |
+
"loss": 0.6299,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.71,
|
| 91 |
+
"learning_rate": 4.250936329588015e-05,
|
| 92 |
+
"loss": 0.6222,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.76,
|
| 97 |
+
"learning_rate": 4.157303370786517e-05,
|
| 98 |
+
"loss": 0.5438,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.81,
|
| 103 |
+
"learning_rate": 4.063670411985019e-05,
|
| 104 |
+
"loss": 0.5207,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.86,
|
| 109 |
+
"learning_rate": 3.970037453183521e-05,
|
| 110 |
+
"loss": 0.5481,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.91,
|
| 115 |
+
"learning_rate": 3.876404494382023e-05,
|
| 116 |
+
"loss": 0.5603,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.96,
|
| 121 |
+
"learning_rate": 3.782771535580524e-05,
|
| 122 |
+
"loss": 0.5909,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.0,
|
| 127 |
+
"eval_accuracy": 0.7966101694915254,
|
| 128 |
+
"eval_loss": 0.5286521315574646,
|
| 129 |
+
"eval_runtime": 5.9941,
|
| 130 |
+
"eval_samples_per_second": 29.529,
|
| 131 |
+
"eval_steps_per_second": 14.848,
|
| 132 |
+
"step": 198
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.01,
|
| 136 |
+
"learning_rate": 3.689138576779027e-05,
|
| 137 |
+
"loss": 0.3812,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.06,
|
| 142 |
+
"learning_rate": 3.595505617977528e-05,
|
| 143 |
+
"loss": 0.3082,
|
| 144 |
+
"step": 210
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.11,
|
| 148 |
+
"learning_rate": 3.5018726591760305e-05,
|
| 149 |
+
"loss": 0.3588,
|
| 150 |
+
"step": 220
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.16,
|
| 154 |
+
"learning_rate": 3.408239700374532e-05,
|
| 155 |
+
"loss": 0.4855,
|
| 156 |
+
"step": 230
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.21,
|
| 160 |
+
"learning_rate": 3.314606741573034e-05,
|
| 161 |
+
"loss": 0.3966,
|
| 162 |
+
"step": 240
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.26,
|
| 166 |
+
"learning_rate": 3.220973782771536e-05,
|
| 167 |
+
"loss": 0.2686,
|
| 168 |
+
"step": 250
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.31,
|
| 172 |
+
"learning_rate": 3.1273408239700376e-05,
|
| 173 |
+
"loss": 0.4901,
|
| 174 |
+
"step": 260
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.36,
|
| 178 |
+
"learning_rate": 3.0337078651685396e-05,
|
| 179 |
+
"loss": 0.4859,
|
| 180 |
+
"step": 270
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.41,
|
| 184 |
+
"learning_rate": 2.940074906367041e-05,
|
| 185 |
+
"loss": 0.4439,
|
| 186 |
+
"step": 280
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.46,
|
| 190 |
+
"learning_rate": 2.846441947565543e-05,
|
| 191 |
+
"loss": 0.3942,
|
| 192 |
+
"step": 290
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.51,
|
| 196 |
+
"learning_rate": 2.752808988764045e-05,
|
| 197 |
+
"loss": 0.3957,
|
| 198 |
+
"step": 300
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.56,
|
| 202 |
+
"learning_rate": 2.6591760299625466e-05,
|
| 203 |
+
"loss": 0.4238,
|
| 204 |
+
"step": 310
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.61,
|
| 208 |
+
"learning_rate": 2.565543071161049e-05,
|
| 209 |
+
"loss": 0.4087,
|
| 210 |
+
"step": 320
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.66,
|
| 214 |
+
"learning_rate": 2.4719101123595505e-05,
|
| 215 |
+
"loss": 0.3913,
|
| 216 |
+
"step": 330
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.72,
|
| 220 |
+
"learning_rate": 2.3782771535580524e-05,
|
| 221 |
+
"loss": 0.301,
|
| 222 |
+
"step": 340
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.77,
|
| 226 |
+
"learning_rate": 2.2846441947565544e-05,
|
| 227 |
+
"loss": 0.3868,
|
| 228 |
+
"step": 350
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.82,
|
| 232 |
+
"learning_rate": 2.1910112359550563e-05,
|
| 233 |
+
"loss": 0.3086,
|
| 234 |
+
"step": 360
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.87,
|
| 238 |
+
"learning_rate": 2.0973782771535582e-05,
|
| 239 |
+
"loss": 0.3019,
|
| 240 |
+
"step": 370
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.92,
|
| 244 |
+
"learning_rate": 2.00374531835206e-05,
|
| 245 |
+
"loss": 0.3578,
|
| 246 |
+
"step": 380
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.97,
|
| 250 |
+
"learning_rate": 1.9101123595505618e-05,
|
| 251 |
+
"loss": 0.2224,
|
| 252 |
+
"step": 390
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.0,
|
| 256 |
+
"eval_accuracy": 0.8418079096045198,
|
| 257 |
+
"eval_loss": 0.4224812686443329,
|
| 258 |
+
"eval_runtime": 6.0015,
|
| 259 |
+
"eval_samples_per_second": 29.493,
|
| 260 |
+
"eval_steps_per_second": 14.83,
|
| 261 |
+
"step": 396
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.02,
|
| 265 |
+
"learning_rate": 1.8164794007490637e-05,
|
| 266 |
+
"loss": 0.2681,
|
| 267 |
+
"step": 400
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.07,
|
| 271 |
+
"learning_rate": 1.7228464419475657e-05,
|
| 272 |
+
"loss": 0.2608,
|
| 273 |
+
"step": 410
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.12,
|
| 277 |
+
"learning_rate": 1.6292134831460676e-05,
|
| 278 |
+
"loss": 0.2281,
|
| 279 |
+
"step": 420
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.17,
|
| 283 |
+
"learning_rate": 1.5355805243445692e-05,
|
| 284 |
+
"loss": 0.1541,
|
| 285 |
+
"step": 430
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.22,
|
| 289 |
+
"learning_rate": 1.4419475655430711e-05,
|
| 290 |
+
"loss": 0.4201,
|
| 291 |
+
"step": 440
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.27,
|
| 295 |
+
"learning_rate": 1.348314606741573e-05,
|
| 296 |
+
"loss": 0.2288,
|
| 297 |
+
"step": 450
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.32,
|
| 301 |
+
"learning_rate": 1.254681647940075e-05,
|
| 302 |
+
"loss": 0.23,
|
| 303 |
+
"step": 460
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.37,
|
| 307 |
+
"learning_rate": 1.161048689138577e-05,
|
| 308 |
+
"loss": 0.2587,
|
| 309 |
+
"step": 470
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.42,
|
| 313 |
+
"learning_rate": 1.0674157303370787e-05,
|
| 314 |
+
"loss": 0.0679,
|
| 315 |
+
"step": 480
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.47,
|
| 319 |
+
"learning_rate": 9.737827715355806e-06,
|
| 320 |
+
"loss": 0.3435,
|
| 321 |
+
"step": 490
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.52,
|
| 325 |
+
"learning_rate": 8.801498127340826e-06,
|
| 326 |
+
"loss": 0.2798,
|
| 327 |
+
"step": 500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.57,
|
| 331 |
+
"learning_rate": 7.865168539325843e-06,
|
| 332 |
+
"loss": 0.2222,
|
| 333 |
+
"step": 510
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.62,
|
| 337 |
+
"learning_rate": 6.928838951310862e-06,
|
| 338 |
+
"loss": 0.2538,
|
| 339 |
+
"step": 520
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.67,
|
| 343 |
+
"learning_rate": 5.9925093632958805e-06,
|
| 344 |
+
"loss": 0.2586,
|
| 345 |
+
"step": 530
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.72,
|
| 349 |
+
"learning_rate": 5.056179775280899e-06,
|
| 350 |
+
"loss": 0.1283,
|
| 351 |
+
"step": 540
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.77,
|
| 355 |
+
"learning_rate": 4.1198501872659175e-06,
|
| 356 |
+
"loss": 0.349,
|
| 357 |
+
"step": 550
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.82,
|
| 361 |
+
"learning_rate": 3.1835205992509364e-06,
|
| 362 |
+
"loss": 0.189,
|
| 363 |
+
"step": 560
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.88,
|
| 367 |
+
"learning_rate": 2.247191011235955e-06,
|
| 368 |
+
"loss": 0.1864,
|
| 369 |
+
"step": 570
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.93,
|
| 373 |
+
"learning_rate": 1.310861423220974e-06,
|
| 374 |
+
"loss": 0.2067,
|
| 375 |
+
"step": 580
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.98,
|
| 379 |
+
"learning_rate": 3.7453183520599253e-07,
|
| 380 |
+
"loss": 0.1975,
|
| 381 |
+
"step": 590
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.0,
|
| 385 |
+
"eval_accuracy": 0.8418079096045198,
|
| 386 |
+
"eval_loss": 0.4207219183444977,
|
| 387 |
+
"eval_runtime": 6.0523,
|
| 388 |
+
"eval_samples_per_second": 29.245,
|
| 389 |
+
"eval_steps_per_second": 14.705,
|
| 390 |
+
"step": 594
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.0,
|
| 394 |
+
"step": 594,
|
| 395 |
+
"total_flos": 3.76219513152e+17,
|
| 396 |
+
"train_loss": 0.4336023674368457,
|
| 397 |
+
"train_runtime": 545.8523,
|
| 398 |
+
"train_samples_per_second": 8.711,
|
| 399 |
+
"train_steps_per_second": 1.088
|
| 400 |
+
}
|
| 401 |
+
],
|
| 402 |
+
"logging_steps": 10,
|
| 403 |
+
"max_steps": 594,
|
| 404 |
+
"num_input_tokens_seen": 0,
|
| 405 |
+
"num_train_epochs": 3,
|
| 406 |
+
"save_steps": 500,
|
| 407 |
+
"total_flos": 3.76219513152e+17,
|
| 408 |
+
"train_batch_size": 2,
|
| 409 |
+
"trial_name": null,
|
| 410 |
+
"trial_params": null
|
| 411 |
+
}
|