End of training
Browse files- README.md +3 -3
- all_results.json +18 -0
- eval_results.json +8 -0
- test_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +448 -0
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8127853881278538
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.5154
|
| 36 |
+
- Accuracy: 0.8128
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.51,
|
| 3 |
+
"eval_accuracy": 0.8127853881278538,
|
| 4 |
+
"eval_loss": 0.5153664350509644,
|
| 5 |
+
"eval_runtime": 0.8201,
|
| 6 |
+
"eval_samples_per_second": 267.033,
|
| 7 |
+
"eval_steps_per_second": 34.141,
|
| 8 |
+
"test_accuracy": 0.7534246575342466,
|
| 9 |
+
"test_loss": 0.7015746235847473,
|
| 10 |
+
"test_runtime": 1.1393,
|
| 11 |
+
"test_samples_per_second": 192.215,
|
| 12 |
+
"test_steps_per_second": 24.575,
|
| 13 |
+
"total_flos": 6.358977448272691e+16,
|
| 14 |
+
"train_loss": 0.40896380335092547,
|
| 15 |
+
"train_runtime": 131.9389,
|
| 16 |
+
"train_samples_per_second": 98.985,
|
| 17 |
+
"train_steps_per_second": 3.032
|
| 18 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.51,
|
| 3 |
+
"eval_accuracy": 0.8127853881278538,
|
| 4 |
+
"eval_loss": 0.5153664350509644,
|
| 5 |
+
"eval_runtime": 0.8201,
|
| 6 |
+
"eval_samples_per_second": 267.033,
|
| 7 |
+
"eval_steps_per_second": 34.141
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"test_accuracy": 0.7534246575342466,
|
| 3 |
+
"test_loss": 0.7015746235847473,
|
| 4 |
+
"test_runtime": 1.1393,
|
| 5 |
+
"test_samples_per_second": 192.215,
|
| 6 |
+
"test_steps_per_second": 24.575
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.51,
|
| 3 |
+
"total_flos": 6.358977448272691e+16,
|
| 4 |
+
"train_loss": 0.40896380335092547,
|
| 5 |
+
"train_runtime": 131.9389,
|
| 6 |
+
"train_samples_per_second": 98.985,
|
| 7 |
+
"train_steps_per_second": 3.032
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8127853881278538,
|
| 3 |
+
"best_model_checkpoint": "deit-tiny-patch16-224-finetuned-piid/checkpoint-266",
|
| 4 |
+
"epoch": 19.51219512195122,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.49,
|
| 13 |
+
"learning_rate": 1.25e-05,
|
| 14 |
+
"loss": 1.5326,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.98,
|
| 19 |
+
"learning_rate": 2.5e-05,
|
| 20 |
+
"loss": 1.2298,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.98,
|
| 25 |
+
"eval_accuracy": 0.4703196347031963,
|
| 26 |
+
"eval_loss": 1.1137923002243042,
|
| 27 |
+
"eval_runtime": 0.7498,
|
| 28 |
+
"eval_samples_per_second": 292.079,
|
| 29 |
+
"eval_steps_per_second": 37.343,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.46,
|
| 34 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 35 |
+
"loss": 0.9126,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.95,
|
| 40 |
+
"learning_rate": 5e-05,
|
| 41 |
+
"loss": 0.7642,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.0,
|
| 46 |
+
"eval_accuracy": 0.5981735159817352,
|
| 47 |
+
"eval_loss": 0.9123256206512451,
|
| 48 |
+
"eval_runtime": 0.7291,
|
| 49 |
+
"eval_samples_per_second": 300.354,
|
| 50 |
+
"eval_steps_per_second": 38.401,
|
| 51 |
+
"step": 41
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.44,
|
| 55 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 56 |
+
"loss": 0.6623,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.93,
|
| 61 |
+
"learning_rate": 4.722222222222222e-05,
|
| 62 |
+
"loss": 0.6167,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.98,
|
| 67 |
+
"eval_accuracy": 0.684931506849315,
|
| 68 |
+
"eval_loss": 0.6735855937004089,
|
| 69 |
+
"eval_runtime": 1.0942,
|
| 70 |
+
"eval_samples_per_second": 200.146,
|
| 71 |
+
"eval_steps_per_second": 25.589,
|
| 72 |
+
"step": 61
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.41,
|
| 76 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 77 |
+
"loss": 0.5708,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.9,
|
| 82 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 83 |
+
"loss": 0.5628,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.0,
|
| 88 |
+
"eval_accuracy": 0.7031963470319634,
|
| 89 |
+
"eval_loss": 0.6615465879440308,
|
| 90 |
+
"eval_runtime": 0.7444,
|
| 91 |
+
"eval_samples_per_second": 294.203,
|
| 92 |
+
"eval_steps_per_second": 37.615,
|
| 93 |
+
"step": 82
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.39,
|
| 97 |
+
"learning_rate": 4.305555555555556e-05,
|
| 98 |
+
"loss": 0.6059,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.88,
|
| 103 |
+
"learning_rate": 4.166666666666667e-05,
|
| 104 |
+
"loss": 0.5616,
|
| 105 |
+
"step": 100
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.98,
|
| 109 |
+
"eval_accuracy": 0.7351598173515982,
|
| 110 |
+
"eval_loss": 0.5984886288642883,
|
| 111 |
+
"eval_runtime": 0.9744,
|
| 112 |
+
"eval_samples_per_second": 224.752,
|
| 113 |
+
"eval_steps_per_second": 28.735,
|
| 114 |
+
"step": 102
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 5.37,
|
| 118 |
+
"learning_rate": 4.027777777777778e-05,
|
| 119 |
+
"loss": 0.5088,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.85,
|
| 124 |
+
"learning_rate": 3.888888888888889e-05,
|
| 125 |
+
"loss": 0.4742,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 6.0,
|
| 130 |
+
"eval_accuracy": 0.7853881278538812,
|
| 131 |
+
"eval_loss": 0.4980608820915222,
|
| 132 |
+
"eval_runtime": 0.7506,
|
| 133 |
+
"eval_samples_per_second": 291.763,
|
| 134 |
+
"eval_steps_per_second": 37.303,
|
| 135 |
+
"step": 123
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.34,
|
| 139 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 140 |
+
"loss": 0.4212,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.83,
|
| 145 |
+
"learning_rate": 3.611111111111111e-05,
|
| 146 |
+
"loss": 0.3434,
|
| 147 |
+
"step": 140
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.98,
|
| 151 |
+
"eval_accuracy": 0.7488584474885844,
|
| 152 |
+
"eval_loss": 0.5729327201843262,
|
| 153 |
+
"eval_runtime": 0.7717,
|
| 154 |
+
"eval_samples_per_second": 283.805,
|
| 155 |
+
"eval_steps_per_second": 36.286,
|
| 156 |
+
"step": 143
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 7.32,
|
| 160 |
+
"learning_rate": 3.472222222222222e-05,
|
| 161 |
+
"loss": 0.3907,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 7.8,
|
| 166 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 167 |
+
"loss": 0.3691,
|
| 168 |
+
"step": 160
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 8.0,
|
| 172 |
+
"eval_accuracy": 0.7397260273972602,
|
| 173 |
+
"eval_loss": 0.5779256820678711,
|
| 174 |
+
"eval_runtime": 0.7364,
|
| 175 |
+
"eval_samples_per_second": 297.399,
|
| 176 |
+
"eval_steps_per_second": 38.024,
|
| 177 |
+
"step": 164
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.29,
|
| 181 |
+
"learning_rate": 3.194444444444444e-05,
|
| 182 |
+
"loss": 0.3043,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 8.78,
|
| 187 |
+
"learning_rate": 3.055555555555556e-05,
|
| 188 |
+
"loss": 0.3375,
|
| 189 |
+
"step": 180
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.98,
|
| 193 |
+
"eval_accuracy": 0.7579908675799086,
|
| 194 |
+
"eval_loss": 0.541674792766571,
|
| 195 |
+
"eval_runtime": 0.7286,
|
| 196 |
+
"eval_samples_per_second": 300.584,
|
| 197 |
+
"eval_steps_per_second": 38.431,
|
| 198 |
+
"step": 184
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 9.27,
|
| 202 |
+
"learning_rate": 2.916666666666667e-05,
|
| 203 |
+
"loss": 0.2907,
|
| 204 |
+
"step": 190
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 9.76,
|
| 208 |
+
"learning_rate": 2.777777777777778e-05,
|
| 209 |
+
"loss": 0.3192,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 10.0,
|
| 214 |
+
"eval_accuracy": 0.7534246575342466,
|
| 215 |
+
"eval_loss": 0.5554245710372925,
|
| 216 |
+
"eval_runtime": 0.7702,
|
| 217 |
+
"eval_samples_per_second": 284.349,
|
| 218 |
+
"eval_steps_per_second": 36.355,
|
| 219 |
+
"step": 205
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 10.24,
|
| 223 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 224 |
+
"loss": 0.3006,
|
| 225 |
+
"step": 210
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.73,
|
| 229 |
+
"learning_rate": 2.5e-05,
|
| 230 |
+
"loss": 0.2795,
|
| 231 |
+
"step": 220
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 10.98,
|
| 235 |
+
"eval_accuracy": 0.776255707762557,
|
| 236 |
+
"eval_loss": 0.5656077265739441,
|
| 237 |
+
"eval_runtime": 0.7297,
|
| 238 |
+
"eval_samples_per_second": 300.112,
|
| 239 |
+
"eval_steps_per_second": 38.37,
|
| 240 |
+
"step": 225
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 11.22,
|
| 244 |
+
"learning_rate": 2.361111111111111e-05,
|
| 245 |
+
"loss": 0.2999,
|
| 246 |
+
"step": 230
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 11.71,
|
| 250 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 251 |
+
"loss": 0.242,
|
| 252 |
+
"step": 240
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 12.0,
|
| 256 |
+
"eval_accuracy": 0.7990867579908676,
|
| 257 |
+
"eval_loss": 0.5318821668624878,
|
| 258 |
+
"eval_runtime": 0.9729,
|
| 259 |
+
"eval_samples_per_second": 225.104,
|
| 260 |
+
"eval_steps_per_second": 28.78,
|
| 261 |
+
"step": 246
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 12.2,
|
| 265 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 266 |
+
"loss": 0.2281,
|
| 267 |
+
"step": 250
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 12.68,
|
| 271 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 272 |
+
"loss": 0.2557,
|
| 273 |
+
"step": 260
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.98,
|
| 277 |
+
"eval_accuracy": 0.8127853881278538,
|
| 278 |
+
"eval_loss": 0.5153664350509644,
|
| 279 |
+
"eval_runtime": 0.7247,
|
| 280 |
+
"eval_samples_per_second": 302.183,
|
| 281 |
+
"eval_steps_per_second": 38.635,
|
| 282 |
+
"step": 266
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 13.17,
|
| 286 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 287 |
+
"loss": 0.2134,
|
| 288 |
+
"step": 270
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 13.66,
|
| 292 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 293 |
+
"loss": 0.2465,
|
| 294 |
+
"step": 280
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 14.0,
|
| 298 |
+
"eval_accuracy": 0.7990867579908676,
|
| 299 |
+
"eval_loss": 0.5763050317764282,
|
| 300 |
+
"eval_runtime": 0.7251,
|
| 301 |
+
"eval_samples_per_second": 302.014,
|
| 302 |
+
"eval_steps_per_second": 38.614,
|
| 303 |
+
"step": 287
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 14.15,
|
| 307 |
+
"learning_rate": 1.527777777777778e-05,
|
| 308 |
+
"loss": 0.3016,
|
| 309 |
+
"step": 290
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 14.63,
|
| 313 |
+
"learning_rate": 1.388888888888889e-05,
|
| 314 |
+
"loss": 0.221,
|
| 315 |
+
"step": 300
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 14.98,
|
| 319 |
+
"eval_accuracy": 0.8036529680365296,
|
| 320 |
+
"eval_loss": 0.5682752132415771,
|
| 321 |
+
"eval_runtime": 0.7177,
|
| 322 |
+
"eval_samples_per_second": 305.151,
|
| 323 |
+
"eval_steps_per_second": 39.015,
|
| 324 |
+
"step": 307
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 15.12,
|
| 328 |
+
"learning_rate": 1.25e-05,
|
| 329 |
+
"loss": 0.2028,
|
| 330 |
+
"step": 310
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 15.61,
|
| 334 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 335 |
+
"loss": 0.2058,
|
| 336 |
+
"step": 320
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 16.0,
|
| 340 |
+
"eval_accuracy": 0.8127853881278538,
|
| 341 |
+
"eval_loss": 0.5852413177490234,
|
| 342 |
+
"eval_runtime": 0.7065,
|
| 343 |
+
"eval_samples_per_second": 309.982,
|
| 344 |
+
"eval_steps_per_second": 39.632,
|
| 345 |
+
"step": 328
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 16.1,
|
| 349 |
+
"learning_rate": 9.722222222222223e-06,
|
| 350 |
+
"loss": 0.1959,
|
| 351 |
+
"step": 330
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 16.59,
|
| 355 |
+
"learning_rate": 8.333333333333334e-06,
|
| 356 |
+
"loss": 0.1809,
|
| 357 |
+
"step": 340
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 16.98,
|
| 361 |
+
"eval_accuracy": 0.8082191780821918,
|
| 362 |
+
"eval_loss": 0.6281502842903137,
|
| 363 |
+
"eval_runtime": 0.7065,
|
| 364 |
+
"eval_samples_per_second": 309.973,
|
| 365 |
+
"eval_steps_per_second": 39.631,
|
| 366 |
+
"step": 348
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 17.07,
|
| 370 |
+
"learning_rate": 6.944444444444445e-06,
|
| 371 |
+
"loss": 0.19,
|
| 372 |
+
"step": 350
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 17.56,
|
| 376 |
+
"learning_rate": 5.555555555555556e-06,
|
| 377 |
+
"loss": 0.1638,
|
| 378 |
+
"step": 360
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 18.0,
|
| 382 |
+
"eval_accuracy": 0.7945205479452054,
|
| 383 |
+
"eval_loss": 0.6289016604423523,
|
| 384 |
+
"eval_runtime": 0.7099,
|
| 385 |
+
"eval_samples_per_second": 308.501,
|
| 386 |
+
"eval_steps_per_second": 39.443,
|
| 387 |
+
"step": 369
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 18.05,
|
| 391 |
+
"learning_rate": 4.166666666666667e-06,
|
| 392 |
+
"loss": 0.2779,
|
| 393 |
+
"step": 370
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 18.54,
|
| 397 |
+
"learning_rate": 2.777777777777778e-06,
|
| 398 |
+
"loss": 0.155,
|
| 399 |
+
"step": 380
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 18.98,
|
| 403 |
+
"eval_accuracy": 0.8036529680365296,
|
| 404 |
+
"eval_loss": 0.613444447517395,
|
| 405 |
+
"eval_runtime": 0.9887,
|
| 406 |
+
"eval_samples_per_second": 221.506,
|
| 407 |
+
"eval_steps_per_second": 28.32,
|
| 408 |
+
"step": 389
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 19.02,
|
| 412 |
+
"learning_rate": 1.388888888888889e-06,
|
| 413 |
+
"loss": 0.2105,
|
| 414 |
+
"step": 390
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 19.51,
|
| 418 |
+
"learning_rate": 0.0,
|
| 419 |
+
"loss": 0.2094,
|
| 420 |
+
"step": 400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 19.51,
|
| 424 |
+
"eval_accuracy": 0.8082191780821918,
|
| 425 |
+
"eval_loss": 0.6113923192024231,
|
| 426 |
+
"eval_runtime": 0.6901,
|
| 427 |
+
"eval_samples_per_second": 317.344,
|
| 428 |
+
"eval_steps_per_second": 40.574,
|
| 429 |
+
"step": 400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 19.51,
|
| 433 |
+
"step": 400,
|
| 434 |
+
"total_flos": 6.358977448272691e+16,
|
| 435 |
+
"train_loss": 0.40896380335092547,
|
| 436 |
+
"train_runtime": 131.9389,
|
| 437 |
+
"train_samples_per_second": 98.985,
|
| 438 |
+
"train_steps_per_second": 3.032
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 10,
|
| 442 |
+
"max_steps": 400,
|
| 443 |
+
"num_train_epochs": 20,
|
| 444 |
+
"save_steps": 500,
|
| 445 |
+
"total_flos": 6.358977448272691e+16,
|
| 446 |
+
"trial_name": null,
|
| 447 |
+
"trial_params": null
|
| 448 |
+
}
|