End of training
Browse files- README.md +3 -3
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec03_20-14-39_DESKTOP-SKBE9FB/events.out.tfevents.1733279336.DESKTOP-SKBE9FB.15032.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +645 -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 [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-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: 0.9130434782608695
|
| 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 [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4816
|
| 36 |
+
- Accuracy: 0.9130
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26,
|
| 3 |
+
"eval_accuracy": 0.9130434782608695,
|
| 4 |
+
"eval_loss": 0.48163074254989624,
|
| 5 |
+
"eval_runtime": 0.8822,
|
| 6 |
+
"eval_samples_per_second": 52.141,
|
| 7 |
+
"eval_steps_per_second": 3.401,
|
| 8 |
+
"train_loss": 0.2858855720270764,
|
| 9 |
+
"train_runtime": 727.0673,
|
| 10 |
+
"train_samples_per_second": 39.721,
|
| 11 |
+
"train_steps_per_second": 0.605
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26,
|
| 3 |
+
"eval_accuracy": 0.9130434782608695,
|
| 4 |
+
"eval_loss": 0.48163074254989624,
|
| 5 |
+
"eval_runtime": 0.8822,
|
| 6 |
+
"eval_samples_per_second": 52.141,
|
| 7 |
+
"eval_steps_per_second": 3.401
|
| 8 |
+
}
|
runs/Dec03_20-14-39_DESKTOP-SKBE9FB/events.out.tfevents.1733279336.DESKTOP-SKBE9FB.15032.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae21d1d005809c398bd1a54bf7452450c18ec3763e2d7813cc34aa8639a521a7
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26,
|
| 3 |
+
"train_loss": 0.2858855720270764,
|
| 4 |
+
"train_runtime": 727.0673,
|
| 5 |
+
"train_samples_per_second": 39.721,
|
| 6 |
+
"train_steps_per_second": 0.605
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,645 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9130434782608695,
|
| 3 |
+
"best_model_checkpoint": "BEiT-DMAE-DA\\checkpoint-379",
|
| 4 |
+
"epoch": 38.26086956521739,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 440,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.87,
|
| 13 |
+
"learning_rate": 4.886363636363637e-05,
|
| 14 |
+
"loss": 1.3475,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.96,
|
| 19 |
+
"eval_accuracy": 0.32608695652173914,
|
| 20 |
+
"eval_loss": 1.327863335609436,
|
| 21 |
+
"eval_runtime": 0.6895,
|
| 22 |
+
"eval_samples_per_second": 66.715,
|
| 23 |
+
"eval_steps_per_second": 4.351,
|
| 24 |
+
"step": 11
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.74,
|
| 28 |
+
"learning_rate": 4.772727272727273e-05,
|
| 29 |
+
"loss": 1.1875,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.34782608695652173,
|
| 35 |
+
"eval_loss": 1.13204824924469,
|
| 36 |
+
"eval_runtime": 0.7412,
|
| 37 |
+
"eval_samples_per_second": 62.06,
|
| 38 |
+
"eval_steps_per_second": 4.047,
|
| 39 |
+
"step": 23
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.61,
|
| 43 |
+
"learning_rate": 4.659090909090909e-05,
|
| 44 |
+
"loss": 0.9998,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.96,
|
| 49 |
+
"eval_accuracy": 0.5434782608695652,
|
| 50 |
+
"eval_loss": 0.9957121014595032,
|
| 51 |
+
"eval_runtime": 0.6867,
|
| 52 |
+
"eval_samples_per_second": 66.99,
|
| 53 |
+
"eval_steps_per_second": 4.369,
|
| 54 |
+
"step": 34
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.48,
|
| 58 |
+
"learning_rate": 4.545454545454546e-05,
|
| 59 |
+
"loss": 0.8836,
|
| 60 |
+
"step": 40
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"eval_accuracy": 0.5869565217391305,
|
| 65 |
+
"eval_loss": 0.8435541987419128,
|
| 66 |
+
"eval_runtime": 0.7072,
|
| 67 |
+
"eval_samples_per_second": 65.049,
|
| 68 |
+
"eval_steps_per_second": 4.242,
|
| 69 |
+
"step": 46
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.35,
|
| 73 |
+
"learning_rate": 4.431818181818182e-05,
|
| 74 |
+
"loss": 0.7593,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.96,
|
| 79 |
+
"eval_accuracy": 0.6304347826086957,
|
| 80 |
+
"eval_loss": 0.7904003262519836,
|
| 81 |
+
"eval_runtime": 0.7214,
|
| 82 |
+
"eval_samples_per_second": 63.763,
|
| 83 |
+
"eval_steps_per_second": 4.158,
|
| 84 |
+
"step": 57
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.22,
|
| 88 |
+
"learning_rate": 4.318181818181819e-05,
|
| 89 |
+
"loss": 0.6939,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.0,
|
| 94 |
+
"eval_accuracy": 0.8260869565217391,
|
| 95 |
+
"eval_loss": 0.6656226515769958,
|
| 96 |
+
"eval_runtime": 0.6452,
|
| 97 |
+
"eval_samples_per_second": 71.3,
|
| 98 |
+
"eval_steps_per_second": 4.65,
|
| 99 |
+
"step": 69
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.09,
|
| 103 |
+
"learning_rate": 4.204545454545455e-05,
|
| 104 |
+
"loss": 0.5942,
|
| 105 |
+
"step": 70
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.96,
|
| 109 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 110 |
+
"loss": 0.4924,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.96,
|
| 115 |
+
"eval_accuracy": 0.6739130434782609,
|
| 116 |
+
"eval_loss": 0.6724327206611633,
|
| 117 |
+
"eval_runtime": 0.6712,
|
| 118 |
+
"eval_samples_per_second": 68.537,
|
| 119 |
+
"eval_steps_per_second": 4.47,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 7.83,
|
| 124 |
+
"learning_rate": 3.9772727272727275e-05,
|
| 125 |
+
"loss": 0.4444,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.782608695652174,
|
| 131 |
+
"eval_loss": 0.5950984954833984,
|
| 132 |
+
"eval_runtime": 0.6562,
|
| 133 |
+
"eval_samples_per_second": 70.105,
|
| 134 |
+
"eval_steps_per_second": 4.572,
|
| 135 |
+
"step": 92
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.7,
|
| 139 |
+
"learning_rate": 3.8636363636363636e-05,
|
| 140 |
+
"loss": 0.337,
|
| 141 |
+
"step": 100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.96,
|
| 145 |
+
"eval_accuracy": 0.8260869565217391,
|
| 146 |
+
"eval_loss": 0.5222101211547852,
|
| 147 |
+
"eval_runtime": 0.6647,
|
| 148 |
+
"eval_samples_per_second": 69.208,
|
| 149 |
+
"eval_steps_per_second": 4.514,
|
| 150 |
+
"step": 103
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.57,
|
| 154 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 155 |
+
"loss": 0.3213,
|
| 156 |
+
"step": 110
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 10.0,
|
| 160 |
+
"eval_accuracy": 0.8043478260869565,
|
| 161 |
+
"eval_loss": 0.6813698410987854,
|
| 162 |
+
"eval_runtime": 0.6601,
|
| 163 |
+
"eval_samples_per_second": 69.681,
|
| 164 |
+
"eval_steps_per_second": 4.544,
|
| 165 |
+
"step": 115
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 10.43,
|
| 169 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 170 |
+
"loss": 0.2689,
|
| 171 |
+
"step": 120
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 10.96,
|
| 175 |
+
"eval_accuracy": 0.782608695652174,
|
| 176 |
+
"eval_loss": 0.5912956595420837,
|
| 177 |
+
"eval_runtime": 0.6652,
|
| 178 |
+
"eval_samples_per_second": 69.156,
|
| 179 |
+
"eval_steps_per_second": 4.51,
|
| 180 |
+
"step": 126
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 11.3,
|
| 184 |
+
"learning_rate": 3.522727272727273e-05,
|
| 185 |
+
"loss": 0.2538,
|
| 186 |
+
"step": 130
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 12.0,
|
| 190 |
+
"eval_accuracy": 0.782608695652174,
|
| 191 |
+
"eval_loss": 0.6227802634239197,
|
| 192 |
+
"eval_runtime": 0.6802,
|
| 193 |
+
"eval_samples_per_second": 67.63,
|
| 194 |
+
"eval_steps_per_second": 4.411,
|
| 195 |
+
"step": 138
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.17,
|
| 199 |
+
"learning_rate": 3.409090909090909e-05,
|
| 200 |
+
"loss": 0.2032,
|
| 201 |
+
"step": 140
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.96,
|
| 205 |
+
"eval_accuracy": 0.7608695652173914,
|
| 206 |
+
"eval_loss": 0.6992256045341492,
|
| 207 |
+
"eval_runtime": 0.6597,
|
| 208 |
+
"eval_samples_per_second": 69.734,
|
| 209 |
+
"eval_steps_per_second": 4.548,
|
| 210 |
+
"step": 149
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 13.04,
|
| 214 |
+
"learning_rate": 3.295454545454545e-05,
|
| 215 |
+
"loss": 0.2439,
|
| 216 |
+
"step": 150
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 13.91,
|
| 220 |
+
"learning_rate": 3.181818181818182e-05,
|
| 221 |
+
"loss": 0.2152,
|
| 222 |
+
"step": 160
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 14.0,
|
| 226 |
+
"eval_accuracy": 0.7608695652173914,
|
| 227 |
+
"eval_loss": 0.7730478048324585,
|
| 228 |
+
"eval_runtime": 0.7082,
|
| 229 |
+
"eval_samples_per_second": 64.956,
|
| 230 |
+
"eval_steps_per_second": 4.236,
|
| 231 |
+
"step": 161
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 14.78,
|
| 235 |
+
"learning_rate": 3.068181818181818e-05,
|
| 236 |
+
"loss": 0.1713,
|
| 237 |
+
"step": 170
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 14.96,
|
| 241 |
+
"eval_accuracy": 0.7608695652173914,
|
| 242 |
+
"eval_loss": 0.776236891746521,
|
| 243 |
+
"eval_runtime": 0.6617,
|
| 244 |
+
"eval_samples_per_second": 69.522,
|
| 245 |
+
"eval_steps_per_second": 4.534,
|
| 246 |
+
"step": 172
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.65,
|
| 250 |
+
"learning_rate": 2.954545454545455e-05,
|
| 251 |
+
"loss": 0.2042,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 16.0,
|
| 256 |
+
"eval_accuracy": 0.717391304347826,
|
| 257 |
+
"eval_loss": 0.7652217745780945,
|
| 258 |
+
"eval_runtime": 0.6431,
|
| 259 |
+
"eval_samples_per_second": 71.524,
|
| 260 |
+
"eval_steps_per_second": 4.665,
|
| 261 |
+
"step": 184
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 16.52,
|
| 265 |
+
"learning_rate": 2.8409090909090912e-05,
|
| 266 |
+
"loss": 0.1668,
|
| 267 |
+
"step": 190
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 16.96,
|
| 271 |
+
"eval_accuracy": 0.8478260869565217,
|
| 272 |
+
"eval_loss": 0.55118328332901,
|
| 273 |
+
"eval_runtime": 0.6664,
|
| 274 |
+
"eval_samples_per_second": 69.031,
|
| 275 |
+
"eval_steps_per_second": 4.502,
|
| 276 |
+
"step": 195
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 17.39,
|
| 280 |
+
"learning_rate": 2.7272727272727273e-05,
|
| 281 |
+
"loss": 0.1743,
|
| 282 |
+
"step": 200
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 18.0,
|
| 286 |
+
"eval_accuracy": 0.782608695652174,
|
| 287 |
+
"eval_loss": 0.7310671806335449,
|
| 288 |
+
"eval_runtime": 0.6702,
|
| 289 |
+
"eval_samples_per_second": 68.639,
|
| 290 |
+
"eval_steps_per_second": 4.476,
|
| 291 |
+
"step": 207
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 18.26,
|
| 295 |
+
"learning_rate": 2.6136363636363637e-05,
|
| 296 |
+
"loss": 0.1226,
|
| 297 |
+
"step": 210
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.96,
|
| 301 |
+
"eval_accuracy": 0.8043478260869565,
|
| 302 |
+
"eval_loss": 0.711499810218811,
|
| 303 |
+
"eval_runtime": 1.0547,
|
| 304 |
+
"eval_samples_per_second": 43.612,
|
| 305 |
+
"eval_steps_per_second": 2.844,
|
| 306 |
+
"step": 218
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 19.13,
|
| 310 |
+
"learning_rate": 2.5e-05,
|
| 311 |
+
"loss": 0.1628,
|
| 312 |
+
"step": 220
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 20.0,
|
| 316 |
+
"learning_rate": 2.3863636363636365e-05,
|
| 317 |
+
"loss": 0.1537,
|
| 318 |
+
"step": 230
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 20.0,
|
| 322 |
+
"eval_accuracy": 0.7608695652173914,
|
| 323 |
+
"eval_loss": 0.6799980998039246,
|
| 324 |
+
"eval_runtime": 0.7192,
|
| 325 |
+
"eval_samples_per_second": 63.962,
|
| 326 |
+
"eval_steps_per_second": 4.171,
|
| 327 |
+
"step": 230
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 20.87,
|
| 331 |
+
"learning_rate": 2.272727272727273e-05,
|
| 332 |
+
"loss": 0.1311,
|
| 333 |
+
"step": 240
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 20.96,
|
| 337 |
+
"eval_accuracy": 0.8478260869565217,
|
| 338 |
+
"eval_loss": 0.5863925218582153,
|
| 339 |
+
"eval_runtime": 0.7092,
|
| 340 |
+
"eval_samples_per_second": 64.866,
|
| 341 |
+
"eval_steps_per_second": 4.23,
|
| 342 |
+
"step": 241
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 21.74,
|
| 346 |
+
"learning_rate": 2.1590909090909093e-05,
|
| 347 |
+
"loss": 0.1335,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 22.0,
|
| 352 |
+
"eval_accuracy": 0.8260869565217391,
|
| 353 |
+
"eval_loss": 0.6345816254615784,
|
| 354 |
+
"eval_runtime": 0.6942,
|
| 355 |
+
"eval_samples_per_second": 66.266,
|
| 356 |
+
"eval_steps_per_second": 4.322,
|
| 357 |
+
"step": 253
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 22.61,
|
| 361 |
+
"learning_rate": 2.0454545454545457e-05,
|
| 362 |
+
"loss": 0.0981,
|
| 363 |
+
"step": 260
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 22.96,
|
| 367 |
+
"eval_accuracy": 0.8043478260869565,
|
| 368 |
+
"eval_loss": 0.6541118621826172,
|
| 369 |
+
"eval_runtime": 0.7142,
|
| 370 |
+
"eval_samples_per_second": 64.41,
|
| 371 |
+
"eval_steps_per_second": 4.201,
|
| 372 |
+
"step": 264
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 23.48,
|
| 376 |
+
"learning_rate": 1.9318181818181818e-05,
|
| 377 |
+
"loss": 0.1248,
|
| 378 |
+
"step": 270
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 24.0,
|
| 382 |
+
"eval_accuracy": 0.8260869565217391,
|
| 383 |
+
"eval_loss": 0.7017006874084473,
|
| 384 |
+
"eval_runtime": 0.7302,
|
| 385 |
+
"eval_samples_per_second": 62.999,
|
| 386 |
+
"eval_steps_per_second": 4.109,
|
| 387 |
+
"step": 276
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 24.35,
|
| 391 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 392 |
+
"loss": 0.1183,
|
| 393 |
+
"step": 280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 24.96,
|
| 397 |
+
"eval_accuracy": 0.8260869565217391,
|
| 398 |
+
"eval_loss": 0.69643634557724,
|
| 399 |
+
"eval_runtime": 0.6507,
|
| 400 |
+
"eval_samples_per_second": 70.698,
|
| 401 |
+
"eval_steps_per_second": 4.611,
|
| 402 |
+
"step": 287
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 25.22,
|
| 406 |
+
"learning_rate": 1.7045454545454546e-05,
|
| 407 |
+
"loss": 0.0946,
|
| 408 |
+
"step": 290
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 26.0,
|
| 412 |
+
"eval_accuracy": 0.8260869565217391,
|
| 413 |
+
"eval_loss": 0.6449636220932007,
|
| 414 |
+
"eval_runtime": 0.6636,
|
| 415 |
+
"eval_samples_per_second": 69.314,
|
| 416 |
+
"eval_steps_per_second": 4.52,
|
| 417 |
+
"step": 299
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 26.09,
|
| 421 |
+
"learning_rate": 1.590909090909091e-05,
|
| 422 |
+
"loss": 0.1312,
|
| 423 |
+
"step": 300
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 26.96,
|
| 427 |
+
"learning_rate": 1.4772727272727274e-05,
|
| 428 |
+
"loss": 0.0957,
|
| 429 |
+
"step": 310
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 26.96,
|
| 433 |
+
"eval_accuracy": 0.8043478260869565,
|
| 434 |
+
"eval_loss": 0.7056821584701538,
|
| 435 |
+
"eval_runtime": 0.6997,
|
| 436 |
+
"eval_samples_per_second": 65.746,
|
| 437 |
+
"eval_steps_per_second": 4.288,
|
| 438 |
+
"step": 310
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 27.83,
|
| 442 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 443 |
+
"loss": 0.1692,
|
| 444 |
+
"step": 320
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 28.0,
|
| 448 |
+
"eval_accuracy": 0.8043478260869565,
|
| 449 |
+
"eval_loss": 0.6635299324989319,
|
| 450 |
+
"eval_runtime": 0.6605,
|
| 451 |
+
"eval_samples_per_second": 69.644,
|
| 452 |
+
"eval_steps_per_second": 4.542,
|
| 453 |
+
"step": 322
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 28.7,
|
| 457 |
+
"learning_rate": 1.25e-05,
|
| 458 |
+
"loss": 0.0967,
|
| 459 |
+
"step": 330
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 28.96,
|
| 463 |
+
"eval_accuracy": 0.8695652173913043,
|
| 464 |
+
"eval_loss": 0.5040035843849182,
|
| 465 |
+
"eval_runtime": 0.6991,
|
| 466 |
+
"eval_samples_per_second": 65.8,
|
| 467 |
+
"eval_steps_per_second": 4.291,
|
| 468 |
+
"step": 333
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 29.57,
|
| 472 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 473 |
+
"loss": 0.094,
|
| 474 |
+
"step": 340
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 30.0,
|
| 478 |
+
"eval_accuracy": 0.8913043478260869,
|
| 479 |
+
"eval_loss": 0.5587611198425293,
|
| 480 |
+
"eval_runtime": 0.6827,
|
| 481 |
+
"eval_samples_per_second": 67.384,
|
| 482 |
+
"eval_steps_per_second": 4.395,
|
| 483 |
+
"step": 345
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 30.43,
|
| 487 |
+
"learning_rate": 1.0227272727272729e-05,
|
| 488 |
+
"loss": 0.0843,
|
| 489 |
+
"step": 350
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 30.96,
|
| 493 |
+
"eval_accuracy": 0.8695652173913043,
|
| 494 |
+
"eval_loss": 0.539750874042511,
|
| 495 |
+
"eval_runtime": 0.6677,
|
| 496 |
+
"eval_samples_per_second": 68.898,
|
| 497 |
+
"eval_steps_per_second": 4.493,
|
| 498 |
+
"step": 356
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 31.3,
|
| 502 |
+
"learning_rate": 9.090909090909091e-06,
|
| 503 |
+
"loss": 0.0851,
|
| 504 |
+
"step": 360
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 32.0,
|
| 508 |
+
"eval_accuracy": 0.8478260869565217,
|
| 509 |
+
"eval_loss": 0.5806054472923279,
|
| 510 |
+
"eval_runtime": 0.6481,
|
| 511 |
+
"eval_samples_per_second": 70.972,
|
| 512 |
+
"eval_steps_per_second": 4.629,
|
| 513 |
+
"step": 368
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 32.17,
|
| 517 |
+
"learning_rate": 7.954545454545455e-06,
|
| 518 |
+
"loss": 0.0955,
|
| 519 |
+
"step": 370
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 32.96,
|
| 523 |
+
"eval_accuracy": 0.9130434782608695,
|
| 524 |
+
"eval_loss": 0.48163074254989624,
|
| 525 |
+
"eval_runtime": 0.6626,
|
| 526 |
+
"eval_samples_per_second": 69.42,
|
| 527 |
+
"eval_steps_per_second": 4.527,
|
| 528 |
+
"step": 379
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 33.04,
|
| 532 |
+
"learning_rate": 6.818181818181818e-06,
|
| 533 |
+
"loss": 0.1194,
|
| 534 |
+
"step": 380
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 33.91,
|
| 538 |
+
"learning_rate": 5.681818181818182e-06,
|
| 539 |
+
"loss": 0.1157,
|
| 540 |
+
"step": 390
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 34.0,
|
| 544 |
+
"eval_accuracy": 0.8695652173913043,
|
| 545 |
+
"eval_loss": 0.5289022922515869,
|
| 546 |
+
"eval_runtime": 0.6557,
|
| 547 |
+
"eval_samples_per_second": 70.158,
|
| 548 |
+
"eval_steps_per_second": 4.576,
|
| 549 |
+
"step": 391
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 34.78,
|
| 553 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 554 |
+
"loss": 0.072,
|
| 555 |
+
"step": 400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 34.96,
|
| 559 |
+
"eval_accuracy": 0.8913043478260869,
|
| 560 |
+
"eval_loss": 0.5657246112823486,
|
| 561 |
+
"eval_runtime": 0.6672,
|
| 562 |
+
"eval_samples_per_second": 68.949,
|
| 563 |
+
"eval_steps_per_second": 4.497,
|
| 564 |
+
"step": 402
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 35.65,
|
| 568 |
+
"learning_rate": 3.409090909090909e-06,
|
| 569 |
+
"loss": 0.091,
|
| 570 |
+
"step": 410
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 36.0,
|
| 574 |
+
"eval_accuracy": 0.8478260869565217,
|
| 575 |
+
"eval_loss": 0.5566320419311523,
|
| 576 |
+
"eval_runtime": 0.6752,
|
| 577 |
+
"eval_samples_per_second": 68.133,
|
| 578 |
+
"eval_steps_per_second": 4.443,
|
| 579 |
+
"step": 414
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 36.52,
|
| 583 |
+
"learning_rate": 2.2727272727272728e-06,
|
| 584 |
+
"loss": 0.0891,
|
| 585 |
+
"step": 420
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 36.96,
|
| 589 |
+
"eval_accuracy": 0.8478260869565217,
|
| 590 |
+
"eval_loss": 0.5729131102561951,
|
| 591 |
+
"eval_runtime": 0.6672,
|
| 592 |
+
"eval_samples_per_second": 68.948,
|
| 593 |
+
"eval_steps_per_second": 4.497,
|
| 594 |
+
"step": 425
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 37.39,
|
| 598 |
+
"learning_rate": 1.1363636363636364e-06,
|
| 599 |
+
"loss": 0.0732,
|
| 600 |
+
"step": 430
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 38.0,
|
| 604 |
+
"eval_accuracy": 0.8260869565217391,
|
| 605 |
+
"eval_loss": 0.5915136933326721,
|
| 606 |
+
"eval_runtime": 0.6622,
|
| 607 |
+
"eval_samples_per_second": 69.469,
|
| 608 |
+
"eval_steps_per_second": 4.531,
|
| 609 |
+
"step": 437
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 38.26,
|
| 613 |
+
"learning_rate": 0.0,
|
| 614 |
+
"loss": 0.0647,
|
| 615 |
+
"step": 440
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 38.26,
|
| 619 |
+
"eval_accuracy": 0.8260869565217391,
|
| 620 |
+
"eval_loss": 0.5901583433151245,
|
| 621 |
+
"eval_runtime": 0.7022,
|
| 622 |
+
"eval_samples_per_second": 65.512,
|
| 623 |
+
"eval_steps_per_second": 4.273,
|
| 624 |
+
"step": 440
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 38.26,
|
| 628 |
+
"step": 440,
|
| 629 |
+
"total_flos": 2.1400720000140902e+18,
|
| 630 |
+
"train_loss": 0.2858855720270764,
|
| 631 |
+
"train_runtime": 727.0673,
|
| 632 |
+
"train_samples_per_second": 39.721,
|
| 633 |
+
"train_steps_per_second": 0.605
|
| 634 |
+
}
|
| 635 |
+
],
|
| 636 |
+
"logging_steps": 10,
|
| 637 |
+
"max_steps": 440,
|
| 638 |
+
"num_input_tokens_seen": 0,
|
| 639 |
+
"num_train_epochs": 40,
|
| 640 |
+
"save_steps": 500,
|
| 641 |
+
"total_flos": 2.1400720000140902e+18,
|
| 642 |
+
"train_batch_size": 16,
|
| 643 |
+
"trial_name": null,
|
| 644 |
+
"trial_params": null
|
| 645 |
+
}
|