Commit
·
333cd73
1
Parent(s):
a0b363c
🍻 cheers
Browse files- README.md +2 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Dec05_16-19-19_22fa0422bd56/events.out.tfevents.1701794206.22fa0422bd56.11071.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +478 -0
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# finetuned-indian-food
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.2249
|
| 21 |
- Accuracy: 0.9416
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
|
|
| 16 |
|
| 17 |
# finetuned-indian-food
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the indian_food_images dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.2249
|
| 22 |
- Accuracy: 0.9416
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9415515409139213,
|
| 4 |
+
"eval_loss": 0.22492648661136627,
|
| 5 |
+
"eval_runtime": 33.7365,
|
| 6 |
+
"eval_samples_per_second": 27.893,
|
| 7 |
+
"eval_steps_per_second": 3.498,
|
| 8 |
+
"total_flos": 1.651775717862015e+18,
|
| 9 |
+
"train_loss": 0.27738739541190827,
|
| 10 |
+
"train_runtime": 949.4922,
|
| 11 |
+
"train_samples_per_second": 22.446,
|
| 12 |
+
"train_steps_per_second": 0.704
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9415515409139213,
|
| 4 |
+
"eval_loss": 0.22492648661136627,
|
| 5 |
+
"eval_runtime": 33.7365,
|
| 6 |
+
"eval_samples_per_second": 27.893,
|
| 7 |
+
"eval_steps_per_second": 3.498
|
| 8 |
+
}
|
runs/Dec05_16-19-19_22fa0422bd56/events.out.tfevents.1701794206.22fa0422bd56.11071.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb85ca25f88b46a4c06f8c8a88e3ab24e4364135e8cb4fbfb6c594cab9904a5
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.651775717862015e+18,
|
| 4 |
+
"train_loss": 0.27738739541190827,
|
| 5 |
+
"train_runtime": 949.4922,
|
| 6 |
+
"train_samples_per_second": 22.446,
|
| 7 |
+
"train_steps_per_second": 0.704
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,478 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.22492648661136627,
|
| 3 |
+
"best_model_checkpoint": "finetuned-indian-food/checkpoint-600",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 668,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 0.0001970059880239521,
|
| 14 |
+
"loss": 0.7242,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 0.00019401197604790419,
|
| 20 |
+
"loss": 0.5,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.18,
|
| 25 |
+
"learning_rate": 0.0001910179640718563,
|
| 26 |
+
"loss": 0.4122,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.24,
|
| 31 |
+
"learning_rate": 0.0001880239520958084,
|
| 32 |
+
"loss": 0.3271,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.3,
|
| 37 |
+
"learning_rate": 0.0001850299401197605,
|
| 38 |
+
"loss": 0.2387,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.36,
|
| 43 |
+
"learning_rate": 0.00018203592814371256,
|
| 44 |
+
"loss": 0.2743,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.42,
|
| 49 |
+
"learning_rate": 0.0001790419161676647,
|
| 50 |
+
"loss": 0.2427,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.48,
|
| 55 |
+
"learning_rate": 0.0001760479041916168,
|
| 56 |
+
"loss": 0.2863,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.54,
|
| 61 |
+
"learning_rate": 0.00017305389221556887,
|
| 62 |
+
"loss": 0.2558,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.6,
|
| 67 |
+
"learning_rate": 0.00017005988023952097,
|
| 68 |
+
"loss": 0.3083,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.6,
|
| 73 |
+
"eval_accuracy": 0.9139213602550478,
|
| 74 |
+
"eval_loss": 0.36738213896751404,
|
| 75 |
+
"eval_runtime": 29.7859,
|
| 76 |
+
"eval_samples_per_second": 31.592,
|
| 77 |
+
"eval_steps_per_second": 3.962,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.66,
|
| 82 |
+
"learning_rate": 0.00016706586826347307,
|
| 83 |
+
"loss": 0.4045,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.72,
|
| 88 |
+
"learning_rate": 0.00016407185628742517,
|
| 89 |
+
"loss": 0.2997,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.78,
|
| 94 |
+
"learning_rate": 0.00016107784431137724,
|
| 95 |
+
"loss": 0.6153,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.84,
|
| 100 |
+
"learning_rate": 0.00015808383233532935,
|
| 101 |
+
"loss": 0.5334,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.9,
|
| 106 |
+
"learning_rate": 0.00015508982035928145,
|
| 107 |
+
"loss": 0.4115,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.96,
|
| 112 |
+
"learning_rate": 0.00015209580838323355,
|
| 113 |
+
"loss": 0.5174,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.02,
|
| 118 |
+
"learning_rate": 0.00014910179640718565,
|
| 119 |
+
"loss": 0.4409,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.08,
|
| 124 |
+
"learning_rate": 0.00014610778443113772,
|
| 125 |
+
"loss": 0.3202,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.14,
|
| 130 |
+
"learning_rate": 0.00014311377245508983,
|
| 131 |
+
"loss": 0.4374,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.2,
|
| 136 |
+
"learning_rate": 0.00014011976047904193,
|
| 137 |
+
"loss": 0.3447,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.2,
|
| 142 |
+
"eval_accuracy": 0.9277364505844846,
|
| 143 |
+
"eval_loss": 0.291175901889801,
|
| 144 |
+
"eval_runtime": 28.6559,
|
| 145 |
+
"eval_samples_per_second": 32.838,
|
| 146 |
+
"eval_steps_per_second": 4.118,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.26,
|
| 151 |
+
"learning_rate": 0.00013712574850299403,
|
| 152 |
+
"loss": 0.2344,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.32,
|
| 157 |
+
"learning_rate": 0.0001341317365269461,
|
| 158 |
+
"loss": 0.3497,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.38,
|
| 163 |
+
"learning_rate": 0.0001311377245508982,
|
| 164 |
+
"loss": 0.3752,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.44,
|
| 169 |
+
"learning_rate": 0.0001281437125748503,
|
| 170 |
+
"loss": 0.3246,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.5,
|
| 175 |
+
"learning_rate": 0.0001251497005988024,
|
| 176 |
+
"loss": 0.3515,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.56,
|
| 181 |
+
"learning_rate": 0.0001221556886227545,
|
| 182 |
+
"loss": 0.3613,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.62,
|
| 187 |
+
"learning_rate": 0.0001191616766467066,
|
| 188 |
+
"loss": 0.3377,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.68,
|
| 193 |
+
"learning_rate": 0.0001161676646706587,
|
| 194 |
+
"loss": 0.1799,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.74,
|
| 199 |
+
"learning_rate": 0.00011317365269461077,
|
| 200 |
+
"loss": 0.3553,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.8,
|
| 205 |
+
"learning_rate": 0.00011017964071856288,
|
| 206 |
+
"loss": 0.3753,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.8,
|
| 211 |
+
"eval_accuracy": 0.924548352816153,
|
| 212 |
+
"eval_loss": 0.28174886107444763,
|
| 213 |
+
"eval_runtime": 28.984,
|
| 214 |
+
"eval_samples_per_second": 32.466,
|
| 215 |
+
"eval_steps_per_second": 4.071,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.86,
|
| 220 |
+
"learning_rate": 0.00010718562874251496,
|
| 221 |
+
"loss": 0.2564,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.92,
|
| 226 |
+
"learning_rate": 0.00010419161676646707,
|
| 227 |
+
"loss": 0.4214,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.98,
|
| 232 |
+
"learning_rate": 0.00010119760479041918,
|
| 233 |
+
"loss": 0.2334,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 2.04,
|
| 238 |
+
"learning_rate": 9.820359281437126e-05,
|
| 239 |
+
"loss": 0.2205,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.1,
|
| 244 |
+
"learning_rate": 9.520958083832335e-05,
|
| 245 |
+
"loss": 0.2027,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.16,
|
| 250 |
+
"learning_rate": 9.221556886227547e-05,
|
| 251 |
+
"loss": 0.2422,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.22,
|
| 256 |
+
"learning_rate": 8.922155688622755e-05,
|
| 257 |
+
"loss": 0.2055,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.28,
|
| 262 |
+
"learning_rate": 8.622754491017964e-05,
|
| 263 |
+
"loss": 0.2053,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.34,
|
| 268 |
+
"learning_rate": 8.323353293413174e-05,
|
| 269 |
+
"loss": 0.2482,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.4,
|
| 274 |
+
"learning_rate": 8.023952095808383e-05,
|
| 275 |
+
"loss": 0.1742,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.4,
|
| 280 |
+
"eval_accuracy": 0.9319872476089267,
|
| 281 |
+
"eval_loss": 0.250567227602005,
|
| 282 |
+
"eval_runtime": 29.9273,
|
| 283 |
+
"eval_samples_per_second": 31.443,
|
| 284 |
+
"eval_steps_per_second": 3.943,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.46,
|
| 289 |
+
"learning_rate": 7.724550898203593e-05,
|
| 290 |
+
"loss": 0.259,
|
| 291 |
+
"step": 410
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.51,
|
| 295 |
+
"learning_rate": 7.425149700598802e-05,
|
| 296 |
+
"loss": 0.2942,
|
| 297 |
+
"step": 420
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.57,
|
| 301 |
+
"learning_rate": 7.125748502994012e-05,
|
| 302 |
+
"loss": 0.2989,
|
| 303 |
+
"step": 430
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.63,
|
| 307 |
+
"learning_rate": 6.826347305389222e-05,
|
| 308 |
+
"loss": 0.1775,
|
| 309 |
+
"step": 440
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.69,
|
| 313 |
+
"learning_rate": 6.526946107784432e-05,
|
| 314 |
+
"loss": 0.1276,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.75,
|
| 319 |
+
"learning_rate": 6.227544910179641e-05,
|
| 320 |
+
"loss": 0.1553,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.81,
|
| 325 |
+
"learning_rate": 5.9281437125748505e-05,
|
| 326 |
+
"loss": 0.2272,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.87,
|
| 331 |
+
"learning_rate": 5.62874251497006e-05,
|
| 332 |
+
"loss": 0.2583,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.93,
|
| 337 |
+
"learning_rate": 5.3293413173652694e-05,
|
| 338 |
+
"loss": 0.167,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.99,
|
| 343 |
+
"learning_rate": 5.029940119760479e-05,
|
| 344 |
+
"loss": 0.1844,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.99,
|
| 349 |
+
"eval_accuracy": 0.9415515409139213,
|
| 350 |
+
"eval_loss": 0.2510787546634674,
|
| 351 |
+
"eval_runtime": 29.362,
|
| 352 |
+
"eval_samples_per_second": 32.048,
|
| 353 |
+
"eval_steps_per_second": 4.019,
|
| 354 |
+
"step": 500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.05,
|
| 358 |
+
"learning_rate": 4.7604790419161675e-05,
|
| 359 |
+
"loss": 0.2104,
|
| 360 |
+
"step": 510
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.11,
|
| 364 |
+
"learning_rate": 4.4610778443113777e-05,
|
| 365 |
+
"loss": 0.183,
|
| 366 |
+
"step": 520
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.17,
|
| 370 |
+
"learning_rate": 4.161676646706587e-05,
|
| 371 |
+
"loss": 0.1606,
|
| 372 |
+
"step": 530
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.23,
|
| 376 |
+
"learning_rate": 3.8622754491017966e-05,
|
| 377 |
+
"loss": 0.1711,
|
| 378 |
+
"step": 540
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.29,
|
| 382 |
+
"learning_rate": 3.562874251497006e-05,
|
| 383 |
+
"loss": 0.1211,
|
| 384 |
+
"step": 550
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.35,
|
| 388 |
+
"learning_rate": 3.263473053892216e-05,
|
| 389 |
+
"loss": 0.1289,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.41,
|
| 394 |
+
"learning_rate": 2.9640718562874252e-05,
|
| 395 |
+
"loss": 0.1742,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.47,
|
| 400 |
+
"learning_rate": 2.6646706586826347e-05,
|
| 401 |
+
"loss": 0.2005,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.53,
|
| 406 |
+
"learning_rate": 2.3652694610778445e-05,
|
| 407 |
+
"loss": 0.1092,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.59,
|
| 412 |
+
"learning_rate": 2.065868263473054e-05,
|
| 413 |
+
"loss": 0.1797,
|
| 414 |
+
"step": 600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.59,
|
| 418 |
+
"eval_accuracy": 0.9415515409139213,
|
| 419 |
+
"eval_loss": 0.22492648661136627,
|
| 420 |
+
"eval_runtime": 28.7472,
|
| 421 |
+
"eval_samples_per_second": 32.734,
|
| 422 |
+
"eval_steps_per_second": 4.105,
|
| 423 |
+
"step": 600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.65,
|
| 427 |
+
"learning_rate": 1.7664670658682637e-05,
|
| 428 |
+
"loss": 0.1906,
|
| 429 |
+
"step": 610
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.71,
|
| 433 |
+
"learning_rate": 1.467065868263473e-05,
|
| 434 |
+
"loss": 0.1834,
|
| 435 |
+
"step": 620
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.77,
|
| 439 |
+
"learning_rate": 1.1676646706586828e-05,
|
| 440 |
+
"loss": 0.1454,
|
| 441 |
+
"step": 630
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.83,
|
| 445 |
+
"learning_rate": 8.682634730538922e-06,
|
| 446 |
+
"loss": 0.2321,
|
| 447 |
+
"step": 640
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.89,
|
| 451 |
+
"learning_rate": 5.688622754491018e-06,
|
| 452 |
+
"loss": 0.1515,
|
| 453 |
+
"step": 650
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.95,
|
| 457 |
+
"learning_rate": 2.6946107784431138e-06,
|
| 458 |
+
"loss": 0.1474,
|
| 459 |
+
"step": 660
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.0,
|
| 463 |
+
"step": 668,
|
| 464 |
+
"total_flos": 1.651775717862015e+18,
|
| 465 |
+
"train_loss": 0.27738739541190827,
|
| 466 |
+
"train_runtime": 949.4922,
|
| 467 |
+
"train_samples_per_second": 22.446,
|
| 468 |
+
"train_steps_per_second": 0.704
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 10,
|
| 472 |
+
"max_steps": 668,
|
| 473 |
+
"num_train_epochs": 4,
|
| 474 |
+
"save_steps": 100,
|
| 475 |
+
"total_flos": 1.651775717862015e+18,
|
| 476 |
+
"trial_name": null,
|
| 477 |
+
"trial_params": null
|
| 478 |
+
}
|