End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan14_14-09-03_c583982b4f3d/events.out.tfevents.1736864086.c583982b4f3d.215.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +459 -0
README.md
CHANGED
|
@@ -23,7 +23,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.9047619047619048
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.2930
|
| 37 |
+
- Accuracy: 0.9048
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 36.92307692307692,
|
| 3 |
+
"eval_accuracy": 0.9047619047619048,
|
| 4 |
+
"eval_loss": 0.29301854968070984,
|
| 5 |
+
"eval_runtime": 1.227,
|
| 6 |
+
"eval_samples_per_second": 222.489,
|
| 7 |
+
"eval_steps_per_second": 4.075,
|
| 8 |
+
"total_flos": 5.905752132626842e+17,
|
| 9 |
+
"train_loss": 0.27296837071577706,
|
| 10 |
+
"train_runtime": 300.1153,
|
| 11 |
+
"train_samples_per_second": 108.891,
|
| 12 |
+
"train_steps_per_second": 0.4
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 36.92307692307692,
|
| 3 |
+
"eval_accuracy": 0.9047619047619048,
|
| 4 |
+
"eval_loss": 0.29301854968070984,
|
| 5 |
+
"eval_runtime": 1.227,
|
| 6 |
+
"eval_samples_per_second": 222.489,
|
| 7 |
+
"eval_steps_per_second": 4.075
|
| 8 |
+
}
|
runs/Jan14_14-09-03_c583982b4f3d/events.out.tfevents.1736864086.c583982b4f3d.215.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d59c6b91ad75f5110c3ff4e31cdc8f947f35867980e6b5286e593ba04775a87
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 36.92307692307692,
|
| 3 |
+
"total_flos": 5.905752132626842e+17,
|
| 4 |
+
"train_loss": 0.27296837071577706,
|
| 5 |
+
"train_runtime": 300.1153,
|
| 6 |
+
"train_samples_per_second": 108.891,
|
| 7 |
+
"train_steps_per_second": 0.4
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,459 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9047619047619048,
|
| 3 |
+
"best_model_checkpoint": "vit-msn-small-corect_dataset_lateral_flow_ivalidation/checkpoint-84",
|
| 4 |
+
"epoch": 36.92307692307692,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 120,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.9230769230769231,
|
| 13 |
+
"eval_accuracy": 0.6336996336996337,
|
| 14 |
+
"eval_loss": 0.6349812746047974,
|
| 15 |
+
"eval_runtime": 1.1638,
|
| 16 |
+
"eval_samples_per_second": 234.566,
|
| 17 |
+
"eval_steps_per_second": 4.296,
|
| 18 |
+
"step": 3
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.8461538461538463,
|
| 22 |
+
"eval_accuracy": 0.8021978021978022,
|
| 23 |
+
"eval_loss": 0.5046992301940918,
|
| 24 |
+
"eval_runtime": 1.119,
|
| 25 |
+
"eval_samples_per_second": 243.967,
|
| 26 |
+
"eval_steps_per_second": 4.468,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.769230769230769,
|
| 31 |
+
"eval_accuracy": 0.8791208791208791,
|
| 32 |
+
"eval_loss": 0.3700959086418152,
|
| 33 |
+
"eval_runtime": 1.119,
|
| 34 |
+
"eval_samples_per_second": 243.967,
|
| 35 |
+
"eval_steps_per_second": 4.468,
|
| 36 |
+
"step": 9
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.076923076923077,
|
| 40 |
+
"grad_norm": 46.272850036621094,
|
| 41 |
+
"learning_rate": 4.166666666666667e-05,
|
| 42 |
+
"loss": 0.5485,
|
| 43 |
+
"step": 10
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 4.0,
|
| 47 |
+
"eval_accuracy": 0.7435897435897436,
|
| 48 |
+
"eval_loss": 0.5379207134246826,
|
| 49 |
+
"eval_runtime": 1.1645,
|
| 50 |
+
"eval_samples_per_second": 234.43,
|
| 51 |
+
"eval_steps_per_second": 4.294,
|
| 52 |
+
"step": 13
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 4.923076923076923,
|
| 56 |
+
"eval_accuracy": 0.8937728937728938,
|
| 57 |
+
"eval_loss": 0.27481070160865784,
|
| 58 |
+
"eval_runtime": 1.1071,
|
| 59 |
+
"eval_samples_per_second": 246.598,
|
| 60 |
+
"eval_steps_per_second": 4.516,
|
| 61 |
+
"step": 16
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.846153846153846,
|
| 65 |
+
"eval_accuracy": 0.8974358974358975,
|
| 66 |
+
"eval_loss": 0.30044275522232056,
|
| 67 |
+
"eval_runtime": 1.1757,
|
| 68 |
+
"eval_samples_per_second": 232.199,
|
| 69 |
+
"eval_steps_per_second": 4.253,
|
| 70 |
+
"step": 19
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 6.153846153846154,
|
| 74 |
+
"grad_norm": 8.343905448913574,
|
| 75 |
+
"learning_rate": 4.62962962962963e-05,
|
| 76 |
+
"loss": 0.3335,
|
| 77 |
+
"step": 20
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.769230769230769,
|
| 81 |
+
"eval_accuracy": 0.8681318681318682,
|
| 82 |
+
"eval_loss": 0.34923306107521057,
|
| 83 |
+
"eval_runtime": 1.1527,
|
| 84 |
+
"eval_samples_per_second": 236.837,
|
| 85 |
+
"eval_steps_per_second": 4.338,
|
| 86 |
+
"step": 22
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.0,
|
| 90 |
+
"eval_accuracy": 0.8974358974358975,
|
| 91 |
+
"eval_loss": 0.24970969557762146,
|
| 92 |
+
"eval_runtime": 1.1752,
|
| 93 |
+
"eval_samples_per_second": 232.297,
|
| 94 |
+
"eval_steps_per_second": 4.255,
|
| 95 |
+
"step": 26
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 8.923076923076923,
|
| 99 |
+
"eval_accuracy": 0.8315018315018315,
|
| 100 |
+
"eval_loss": 0.43036821484565735,
|
| 101 |
+
"eval_runtime": 1.1393,
|
| 102 |
+
"eval_samples_per_second": 239.625,
|
| 103 |
+
"eval_steps_per_second": 4.389,
|
| 104 |
+
"step": 29
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 9.23076923076923,
|
| 108 |
+
"grad_norm": 14.322465896606445,
|
| 109 |
+
"learning_rate": 4.166666666666667e-05,
|
| 110 |
+
"loss": 0.3087,
|
| 111 |
+
"step": 30
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 9.846153846153847,
|
| 115 |
+
"eval_accuracy": 0.8791208791208791,
|
| 116 |
+
"eval_loss": 0.3478649854660034,
|
| 117 |
+
"eval_runtime": 1.2364,
|
| 118 |
+
"eval_samples_per_second": 220.797,
|
| 119 |
+
"eval_steps_per_second": 4.044,
|
| 120 |
+
"step": 32
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.76923076923077,
|
| 124 |
+
"eval_accuracy": 0.8644688644688645,
|
| 125 |
+
"eval_loss": 0.37963706254959106,
|
| 126 |
+
"eval_runtime": 1.2083,
|
| 127 |
+
"eval_samples_per_second": 225.946,
|
| 128 |
+
"eval_steps_per_second": 4.138,
|
| 129 |
+
"step": 35
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 12.0,
|
| 133 |
+
"eval_accuracy": 0.8351648351648352,
|
| 134 |
+
"eval_loss": 0.4151943325996399,
|
| 135 |
+
"eval_runtime": 1.1429,
|
| 136 |
+
"eval_samples_per_second": 238.873,
|
| 137 |
+
"eval_steps_per_second": 4.375,
|
| 138 |
+
"step": 39
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 12.307692307692308,
|
| 142 |
+
"grad_norm": 14.211008071899414,
|
| 143 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 144 |
+
"loss": 0.2614,
|
| 145 |
+
"step": 40
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 12.923076923076923,
|
| 149 |
+
"eval_accuracy": 0.9010989010989011,
|
| 150 |
+
"eval_loss": 0.31987789273262024,
|
| 151 |
+
"eval_runtime": 1.1044,
|
| 152 |
+
"eval_samples_per_second": 247.187,
|
| 153 |
+
"eval_steps_per_second": 4.527,
|
| 154 |
+
"step": 42
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 13.846153846153847,
|
| 158 |
+
"eval_accuracy": 0.8717948717948718,
|
| 159 |
+
"eval_loss": 0.34341761469841003,
|
| 160 |
+
"eval_runtime": 1.1686,
|
| 161 |
+
"eval_samples_per_second": 233.619,
|
| 162 |
+
"eval_steps_per_second": 4.279,
|
| 163 |
+
"step": 45
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 14.76923076923077,
|
| 167 |
+
"eval_accuracy": 0.8461538461538461,
|
| 168 |
+
"eval_loss": 0.400124728679657,
|
| 169 |
+
"eval_runtime": 1.2364,
|
| 170 |
+
"eval_samples_per_second": 220.801,
|
| 171 |
+
"eval_steps_per_second": 4.044,
|
| 172 |
+
"step": 48
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 15.384615384615385,
|
| 176 |
+
"grad_norm": 37.66127395629883,
|
| 177 |
+
"learning_rate": 3.240740740740741e-05,
|
| 178 |
+
"loss": 0.2471,
|
| 179 |
+
"step": 50
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 16.0,
|
| 183 |
+
"eval_accuracy": 0.8901098901098901,
|
| 184 |
+
"eval_loss": 0.322020947933197,
|
| 185 |
+
"eval_runtime": 1.1904,
|
| 186 |
+
"eval_samples_per_second": 229.338,
|
| 187 |
+
"eval_steps_per_second": 4.2,
|
| 188 |
+
"step": 52
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 16.923076923076923,
|
| 192 |
+
"eval_accuracy": 0.8717948717948718,
|
| 193 |
+
"eval_loss": 0.35403817892074585,
|
| 194 |
+
"eval_runtime": 1.1771,
|
| 195 |
+
"eval_samples_per_second": 231.923,
|
| 196 |
+
"eval_steps_per_second": 4.248,
|
| 197 |
+
"step": 55
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 17.846153846153847,
|
| 201 |
+
"eval_accuracy": 0.8534798534798534,
|
| 202 |
+
"eval_loss": 0.401885062456131,
|
| 203 |
+
"eval_runtime": 1.1593,
|
| 204 |
+
"eval_samples_per_second": 235.494,
|
| 205 |
+
"eval_steps_per_second": 4.313,
|
| 206 |
+
"step": 58
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 18.46153846153846,
|
| 210 |
+
"grad_norm": 17.38436508178711,
|
| 211 |
+
"learning_rate": 2.777777777777778e-05,
|
| 212 |
+
"loss": 0.2817,
|
| 213 |
+
"step": 60
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 18.76923076923077,
|
| 217 |
+
"eval_accuracy": 0.8974358974358975,
|
| 218 |
+
"eval_loss": 0.3152279257774353,
|
| 219 |
+
"eval_runtime": 1.1761,
|
| 220 |
+
"eval_samples_per_second": 232.121,
|
| 221 |
+
"eval_steps_per_second": 4.251,
|
| 222 |
+
"step": 61
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 20.0,
|
| 226 |
+
"eval_accuracy": 0.8571428571428571,
|
| 227 |
+
"eval_loss": 0.39776933193206787,
|
| 228 |
+
"eval_runtime": 1.1622,
|
| 229 |
+
"eval_samples_per_second": 234.895,
|
| 230 |
+
"eval_steps_per_second": 4.302,
|
| 231 |
+
"step": 65
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 20.923076923076923,
|
| 235 |
+
"eval_accuracy": 0.8388278388278388,
|
| 236 |
+
"eval_loss": 0.42894455790519714,
|
| 237 |
+
"eval_runtime": 1.1297,
|
| 238 |
+
"eval_samples_per_second": 241.661,
|
| 239 |
+
"eval_steps_per_second": 4.426,
|
| 240 |
+
"step": 68
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 21.53846153846154,
|
| 244 |
+
"grad_norm": 5.773376941680908,
|
| 245 |
+
"learning_rate": 2.314814814814815e-05,
|
| 246 |
+
"loss": 0.2353,
|
| 247 |
+
"step": 70
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 21.846153846153847,
|
| 251 |
+
"eval_accuracy": 0.8974358974358975,
|
| 252 |
+
"eval_loss": 0.31458553671836853,
|
| 253 |
+
"eval_runtime": 1.1608,
|
| 254 |
+
"eval_samples_per_second": 235.18,
|
| 255 |
+
"eval_steps_per_second": 4.307,
|
| 256 |
+
"step": 71
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 22.76923076923077,
|
| 260 |
+
"eval_accuracy": 0.8864468864468864,
|
| 261 |
+
"eval_loss": 0.3206166625022888,
|
| 262 |
+
"eval_runtime": 1.1912,
|
| 263 |
+
"eval_samples_per_second": 229.187,
|
| 264 |
+
"eval_steps_per_second": 4.198,
|
| 265 |
+
"step": 74
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 24.0,
|
| 269 |
+
"eval_accuracy": 0.8827838827838828,
|
| 270 |
+
"eval_loss": 0.3715476095676422,
|
| 271 |
+
"eval_runtime": 1.2718,
|
| 272 |
+
"eval_samples_per_second": 214.649,
|
| 273 |
+
"eval_steps_per_second": 3.931,
|
| 274 |
+
"step": 78
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 24.615384615384617,
|
| 278 |
+
"grad_norm": 7.774621963500977,
|
| 279 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 280 |
+
"loss": 0.2339,
|
| 281 |
+
"step": 80
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 24.923076923076923,
|
| 285 |
+
"eval_accuracy": 0.8937728937728938,
|
| 286 |
+
"eval_loss": 0.34460321068763733,
|
| 287 |
+
"eval_runtime": 1.1136,
|
| 288 |
+
"eval_samples_per_second": 245.157,
|
| 289 |
+
"eval_steps_per_second": 4.49,
|
| 290 |
+
"step": 81
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 25.846153846153847,
|
| 294 |
+
"eval_accuracy": 0.9047619047619048,
|
| 295 |
+
"eval_loss": 0.29301854968070984,
|
| 296 |
+
"eval_runtime": 1.1263,
|
| 297 |
+
"eval_samples_per_second": 242.377,
|
| 298 |
+
"eval_steps_per_second": 4.439,
|
| 299 |
+
"step": 84
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 26.76923076923077,
|
| 303 |
+
"eval_accuracy": 0.8205128205128205,
|
| 304 |
+
"eval_loss": 0.43494826555252075,
|
| 305 |
+
"eval_runtime": 1.1806,
|
| 306 |
+
"eval_samples_per_second": 231.241,
|
| 307 |
+
"eval_steps_per_second": 4.235,
|
| 308 |
+
"step": 87
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 27.692307692307693,
|
| 312 |
+
"grad_norm": 14.50500774383545,
|
| 313 |
+
"learning_rate": 1.388888888888889e-05,
|
| 314 |
+
"loss": 0.2301,
|
| 315 |
+
"step": 90
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 28.0,
|
| 319 |
+
"eval_accuracy": 0.8681318681318682,
|
| 320 |
+
"eval_loss": 0.3630487322807312,
|
| 321 |
+
"eval_runtime": 1.192,
|
| 322 |
+
"eval_samples_per_second": 229.021,
|
| 323 |
+
"eval_steps_per_second": 4.195,
|
| 324 |
+
"step": 91
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 28.923076923076923,
|
| 328 |
+
"eval_accuracy": 0.8644688644688645,
|
| 329 |
+
"eval_loss": 0.366910845041275,
|
| 330 |
+
"eval_runtime": 1.1667,
|
| 331 |
+
"eval_samples_per_second": 234.003,
|
| 332 |
+
"eval_steps_per_second": 4.286,
|
| 333 |
+
"step": 94
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 29.846153846153847,
|
| 337 |
+
"eval_accuracy": 0.7912087912087912,
|
| 338 |
+
"eval_loss": 0.5037412047386169,
|
| 339 |
+
"eval_runtime": 1.1322,
|
| 340 |
+
"eval_samples_per_second": 241.114,
|
| 341 |
+
"eval_steps_per_second": 4.416,
|
| 342 |
+
"step": 97
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 30.76923076923077,
|
| 346 |
+
"grad_norm": 5.89783239364624,
|
| 347 |
+
"learning_rate": 9.259259259259259e-06,
|
| 348 |
+
"loss": 0.2115,
|
| 349 |
+
"step": 100
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 30.76923076923077,
|
| 353 |
+
"eval_accuracy": 0.8827838827838828,
|
| 354 |
+
"eval_loss": 0.34486547112464905,
|
| 355 |
+
"eval_runtime": 1.1276,
|
| 356 |
+
"eval_samples_per_second": 242.098,
|
| 357 |
+
"eval_steps_per_second": 4.434,
|
| 358 |
+
"step": 100
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 32.0,
|
| 362 |
+
"eval_accuracy": 0.9010989010989011,
|
| 363 |
+
"eval_loss": 0.328006774187088,
|
| 364 |
+
"eval_runtime": 1.1424,
|
| 365 |
+
"eval_samples_per_second": 238.979,
|
| 366 |
+
"eval_steps_per_second": 4.377,
|
| 367 |
+
"step": 104
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 32.92307692307692,
|
| 371 |
+
"eval_accuracy": 0.8424908424908425,
|
| 372 |
+
"eval_loss": 0.40313562750816345,
|
| 373 |
+
"eval_runtime": 1.1332,
|
| 374 |
+
"eval_samples_per_second": 240.909,
|
| 375 |
+
"eval_steps_per_second": 4.412,
|
| 376 |
+
"step": 107
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 33.84615384615385,
|
| 380 |
+
"grad_norm": 13.135037422180176,
|
| 381 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 382 |
+
"loss": 0.2033,
|
| 383 |
+
"step": 110
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 33.84615384615385,
|
| 387 |
+
"eval_accuracy": 0.8534798534798534,
|
| 388 |
+
"eval_loss": 0.3611760437488556,
|
| 389 |
+
"eval_runtime": 1.1669,
|
| 390 |
+
"eval_samples_per_second": 233.958,
|
| 391 |
+
"eval_steps_per_second": 4.285,
|
| 392 |
+
"step": 110
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 34.76923076923077,
|
| 396 |
+
"eval_accuracy": 0.8901098901098901,
|
| 397 |
+
"eval_loss": 0.31633052229881287,
|
| 398 |
+
"eval_runtime": 1.1155,
|
| 399 |
+
"eval_samples_per_second": 244.743,
|
| 400 |
+
"eval_steps_per_second": 4.482,
|
| 401 |
+
"step": 113
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 36.0,
|
| 405 |
+
"eval_accuracy": 0.8864468864468864,
|
| 406 |
+
"eval_loss": 0.3233657777309418,
|
| 407 |
+
"eval_runtime": 1.1244,
|
| 408 |
+
"eval_samples_per_second": 242.803,
|
| 409 |
+
"eval_steps_per_second": 4.447,
|
| 410 |
+
"step": 117
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 36.92307692307692,
|
| 414 |
+
"grad_norm": 3.5747175216674805,
|
| 415 |
+
"learning_rate": 0.0,
|
| 416 |
+
"loss": 0.1807,
|
| 417 |
+
"step": 120
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 36.92307692307692,
|
| 421 |
+
"eval_accuracy": 0.8791208791208791,
|
| 422 |
+
"eval_loss": 0.33070895075798035,
|
| 423 |
+
"eval_runtime": 1.2006,
|
| 424 |
+
"eval_samples_per_second": 227.387,
|
| 425 |
+
"eval_steps_per_second": 4.165,
|
| 426 |
+
"step": 120
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 36.92307692307692,
|
| 430 |
+
"step": 120,
|
| 431 |
+
"total_flos": 5.905752132626842e+17,
|
| 432 |
+
"train_loss": 0.27296837071577706,
|
| 433 |
+
"train_runtime": 300.1153,
|
| 434 |
+
"train_samples_per_second": 108.891,
|
| 435 |
+
"train_steps_per_second": 0.4
|
| 436 |
+
}
|
| 437 |
+
],
|
| 438 |
+
"logging_steps": 10,
|
| 439 |
+
"max_steps": 120,
|
| 440 |
+
"num_input_tokens_seen": 0,
|
| 441 |
+
"num_train_epochs": 40,
|
| 442 |
+
"save_steps": 500,
|
| 443 |
+
"stateful_callbacks": {
|
| 444 |
+
"TrainerControl": {
|
| 445 |
+
"args": {
|
| 446 |
+
"should_epoch_stop": false,
|
| 447 |
+
"should_evaluate": false,
|
| 448 |
+
"should_log": false,
|
| 449 |
+
"should_save": true,
|
| 450 |
+
"should_training_stop": true
|
| 451 |
+
},
|
| 452 |
+
"attributes": {}
|
| 453 |
+
}
|
| 454 |
+
},
|
| 455 |
+
"total_flos": 5.905752132626842e+17,
|
| 456 |
+
"train_batch_size": 64,
|
| 457 |
+
"trial_name": null,
|
| 458 |
+
"trial_params": null
|
| 459 |
+
}
|