End of training
Browse files- README.md +42 -42
- all_results.json +9 -9
- eval_results.json +5 -5
- model.safetensors +1 -1
- runs/Oct11_17-14-38_DESKTOP-SKBE9FB/events.out.tfevents.1728688479.DESKTOP-SKBE9FB.10424.0 +3 -0
- runs/Oct11_17-14-38_DESKTOP-SKBE9FB/events.out.tfevents.1728689179.DESKTOP-SKBE9FB.10424.1 +3 -0
- runs/Oct11_17-28-45_DESKTOP-SKBE9FB/events.out.tfevents.1728689327.DESKTOP-SKBE9FB.15824.0 +3 -0
- runs/Oct11_17-30-54_DESKTOP-SKBE9FB/events.out.tfevents.1728689455.DESKTOP-SKBE9FB.9024.0 +3 -0
- runs/Oct11_17-30-54_DESKTOP-SKBE9FB/events.out.tfevents.1728690167.DESKTOP-SKBE9FB.9024.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +229 -229
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -17,12 +17,12 @@ model-index:
|
|
| 17 |
name: imagefolder
|
| 18 |
type: imagefolder
|
| 19 |
config: default
|
| 20 |
-
split:
|
| 21 |
args: default
|
| 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 |
|
|
@@ -52,7 +52,7 @@ More information needed
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
-
- learning_rate:
|
| 56 |
- train_batch_size: 16
|
| 57 |
- eval_batch_size: 16
|
| 58 |
- seed: 42
|
|
@@ -67,43 +67,43 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| No log | 0.91 | 5 | 1.
|
| 71 |
-
| 1.
|
| 72 |
-
| 1.
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
| 1.
|
| 76 |
-
| 1.
|
| 77 |
-
| 1.
|
| 78 |
-
| 1.
|
| 79 |
-
| 1.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
|
| 108 |
|
| 109 |
### Framework versions
|
|
|
|
| 17 |
name: imagefolder
|
| 18 |
type: imagefolder
|
| 19 |
config: default
|
| 20 |
+
split: train
|
| 21 |
args: default
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.9032258064516129
|
| 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: 0.4274
|
| 36 |
+
- Accuracy: 0.9032
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
- train_batch_size: 16
|
| 57 |
- eval_batch_size: 16
|
| 58 |
- seed: 42
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 0.91 | 5 | 1.7093 | 0.1774 |
|
| 71 |
+
| 1.7744 | 2.0 | 11 | 1.6178 | 0.1774 |
|
| 72 |
+
| 1.7744 | 2.91 | 16 | 1.4730 | 0.1774 |
|
| 73 |
+
| 1.5823 | 4.0 | 22 | 1.2754 | 0.1774 |
|
| 74 |
+
| 1.5823 | 4.91 | 27 | 1.1455 | 0.5645 |
|
| 75 |
+
| 1.27 | 6.0 | 33 | 1.0147 | 0.6290 |
|
| 76 |
+
| 1.27 | 6.91 | 38 | 0.9790 | 0.5484 |
|
| 77 |
+
| 1.079 | 8.0 | 44 | 1.0474 | 0.4516 |
|
| 78 |
+
| 1.079 | 8.91 | 49 | 0.8796 | 0.7581 |
|
| 79 |
+
| 1.005 | 10.0 | 55 | 0.7759 | 0.7742 |
|
| 80 |
+
| 0.8479 | 10.91 | 60 | 0.7421 | 0.8226 |
|
| 81 |
+
| 0.8479 | 12.0 | 66 | 0.6760 | 0.8548 |
|
| 82 |
+
| 0.7695 | 12.91 | 71 | 0.5933 | 0.8387 |
|
| 83 |
+
| 0.7695 | 14.0 | 77 | 0.6372 | 0.7742 |
|
| 84 |
+
| 0.6591 | 14.91 | 82 | 0.5653 | 0.8387 |
|
| 85 |
+
| 0.6591 | 16.0 | 88 | 0.4950 | 0.8710 |
|
| 86 |
+
| 0.5675 | 16.91 | 93 | 0.5040 | 0.8226 |
|
| 87 |
+
| 0.5675 | 18.0 | 99 | 0.4274 | 0.9032 |
|
| 88 |
+
| 0.5134 | 18.91 | 104 | 0.4617 | 0.8548 |
|
| 89 |
+
| 0.4418 | 20.0 | 110 | 0.4245 | 0.8871 |
|
| 90 |
+
| 0.4418 | 20.91 | 115 | 0.4922 | 0.8387 |
|
| 91 |
+
| 0.402 | 22.0 | 121 | 0.5112 | 0.8226 |
|
| 92 |
+
| 0.402 | 22.91 | 126 | 0.4696 | 0.8548 |
|
| 93 |
+
| 0.4039 | 24.0 | 132 | 0.4014 | 0.8710 |
|
| 94 |
+
| 0.4039 | 24.91 | 137 | 0.5006 | 0.8226 |
|
| 95 |
+
| 0.4216 | 26.0 | 143 | 0.5351 | 0.8548 |
|
| 96 |
+
| 0.4216 | 26.91 | 148 | 0.5203 | 0.8548 |
|
| 97 |
+
| 0.3593 | 28.0 | 154 | 0.4082 | 0.8548 |
|
| 98 |
+
| 0.3593 | 28.91 | 159 | 0.4017 | 0.8710 |
|
| 99 |
+
| 0.3638 | 30.0 | 165 | 0.4068 | 0.8871 |
|
| 100 |
+
| 0.3509 | 30.91 | 170 | 0.3991 | 0.8871 |
|
| 101 |
+
| 0.3509 | 32.0 | 176 | 0.3965 | 0.8710 |
|
| 102 |
+
| 0.3426 | 32.91 | 181 | 0.3921 | 0.8710 |
|
| 103 |
+
| 0.3426 | 34.0 | 187 | 0.3998 | 0.8710 |
|
| 104 |
+
| 0.3253 | 34.91 | 192 | 0.4102 | 0.8871 |
|
| 105 |
+
| 0.3253 | 36.0 | 198 | 0.4081 | 0.8871 |
|
| 106 |
+
| 0.3085 | 36.36 | 200 | 0.4083 | 0.8871 |
|
| 107 |
|
| 108 |
|
| 109 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 36.36,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 36.36,
|
| 3 |
+
"eval_accuracy": 0.9032258064516129,
|
| 4 |
+
"eval_loss": 0.4273931682109833,
|
| 5 |
+
"eval_runtime": 2.4718,
|
| 6 |
+
"eval_samples_per_second": 25.083,
|
| 7 |
+
"eval_steps_per_second": 1.618,
|
| 8 |
+
"train_loss": 0.6893912732601166,
|
| 9 |
+
"train_runtime": 709.0628,
|
| 10 |
+
"train_samples_per_second": 19.744,
|
| 11 |
+
"train_steps_per_second": 0.282
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 36.36,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 36.36,
|
| 3 |
+
"eval_accuracy": 0.9032258064516129,
|
| 4 |
+
"eval_loss": 0.4273931682109833,
|
| 5 |
+
"eval_runtime": 2.4718,
|
| 6 |
+
"eval_samples_per_second": 25.083,
|
| 7 |
+
"eval_steps_per_second": 1.618
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343086480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d96908ad48e4d7c197f6f3197c8f8e7fa17c3e3387440d03677a0382a863f75
|
| 3 |
size 343086480
|
runs/Oct11_17-14-38_DESKTOP-SKBE9FB/events.out.tfevents.1728688479.DESKTOP-SKBE9FB.10424.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5f1edd262d1cad2045fec2fc53ab4f9e4a38b18f4e3b5ef65738e1076a6887e
|
| 3 |
+
size 20604
|
runs/Oct11_17-14-38_DESKTOP-SKBE9FB/events.out.tfevents.1728689179.DESKTOP-SKBE9FB.10424.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69e9e033122585d2c4755c85276ecb8c1151e21ffb8335db8ab14af9ff167f43
|
| 3 |
+
size 411
|
runs/Oct11_17-28-45_DESKTOP-SKBE9FB/events.out.tfevents.1728689327.DESKTOP-SKBE9FB.15824.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7572a843c89ad80a11666ae3032c7bbfdc0b847c9da2496fcae4ab06890dcb7d
|
| 3 |
+
size 6909
|
runs/Oct11_17-30-54_DESKTOP-SKBE9FB/events.out.tfevents.1728689455.DESKTOP-SKBE9FB.9024.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bb5741a9bcd3606a3c061a02230595b52f382c9383a79bb712bce3eb54451d5
|
| 3 |
+
size 20604
|
runs/Oct11_17-30-54_DESKTOP-SKBE9FB/events.out.tfevents.1728690167.DESKTOP-SKBE9FB.9024.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc0f93adcf4af56501d2cb9befeb4c41b5bc602e95448ab9fcab16efd6528b83
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 36.36,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 36.36,
|
| 3 |
+
"train_loss": 0.6893912732601166,
|
| 4 |
+
"train_runtime": 709.0628,
|
| 5 |
+
"train_samples_per_second": 19.744,
|
| 6 |
+
"train_steps_per_second": 0.282
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "beit-base-patch16-224-OT-alt\\checkpoint-
|
| 4 |
"epoch": 36.36363636363637,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 200,
|
|
@@ -10,465 +10,465 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.91,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_runtime": 2.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second": 1.
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.82,
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 1.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_loss": 1.
|
| 30 |
-
"eval_runtime": 2.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 1.
|
| 33 |
"step": 11
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.91,
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 1.
|
| 39 |
-
"eval_runtime": 2.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second": 1.
|
| 42 |
"step": 16
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.64,
|
| 46 |
-
"learning_rate":
|
| 47 |
-
"loss": 1.
|
| 48 |
"step": 20
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
-
"eval_accuracy": 0.
|
| 53 |
-
"eval_loss": 1.
|
| 54 |
-
"eval_runtime": 2.
|
| 55 |
-
"eval_samples_per_second":
|
| 56 |
-
"eval_steps_per_second": 1.
|
| 57 |
"step": 22
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.91,
|
| 61 |
-
"eval_accuracy": 0.
|
| 62 |
-
"eval_loss": 1.
|
| 63 |
-
"eval_runtime": 2.
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second": 1.
|
| 66 |
"step": 27
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 5.45,
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 30
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 6.0,
|
| 76 |
-
"eval_accuracy": 0.
|
| 77 |
-
"eval_loss": 1.
|
| 78 |
-
"eval_runtime": 2.
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second": 1.
|
| 81 |
"step": 33
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.91,
|
| 85 |
-
"eval_accuracy": 0.
|
| 86 |
-
"eval_loss":
|
| 87 |
-
"eval_runtime": 2.
|
| 88 |
-
"eval_samples_per_second":
|
| 89 |
-
"eval_steps_per_second": 1.
|
| 90 |
"step": 38
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 7.27,
|
| 94 |
-
"learning_rate":
|
| 95 |
-
"loss": 1.
|
| 96 |
"step": 40
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 8.0,
|
| 100 |
-
"eval_accuracy": 0.
|
| 101 |
-
"eval_loss": 1.
|
| 102 |
-
"eval_runtime": 2.
|
| 103 |
-
"eval_samples_per_second":
|
| 104 |
-
"eval_steps_per_second": 1.
|
| 105 |
"step": 44
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 8.91,
|
| 109 |
-
"eval_accuracy": 0.
|
| 110 |
-
"eval_loss":
|
| 111 |
-
"eval_runtime": 2.
|
| 112 |
-
"eval_samples_per_second":
|
| 113 |
-
"eval_steps_per_second": 1.
|
| 114 |
"step": 49
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 9.09,
|
| 118 |
-
"learning_rate":
|
| 119 |
-
"loss": 1.
|
| 120 |
"step": 50
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 10.0,
|
| 124 |
-
"eval_accuracy": 0.
|
| 125 |
-
"eval_loss": 0.
|
| 126 |
-
"eval_runtime": 2.
|
| 127 |
-
"eval_samples_per_second":
|
| 128 |
-
"eval_steps_per_second": 1.
|
| 129 |
"step": 55
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 10.91,
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 60
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 10.91,
|
| 139 |
-
"eval_accuracy": 0.
|
| 140 |
-
"eval_loss": 0.
|
| 141 |
-
"eval_runtime": 2.
|
| 142 |
-
"eval_samples_per_second":
|
| 143 |
-
"eval_steps_per_second": 1.
|
| 144 |
"step": 60
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 12.0,
|
| 148 |
-
"eval_accuracy": 0.
|
| 149 |
-
"eval_loss": 0.
|
| 150 |
-
"eval_runtime": 2.
|
| 151 |
-
"eval_samples_per_second": 26.
|
| 152 |
-
"eval_steps_per_second": 1.
|
| 153 |
"step": 66
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 12.73,
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 70
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 12.91,
|
| 163 |
-
"eval_accuracy": 0.
|
| 164 |
-
"eval_loss": 0.
|
| 165 |
-
"eval_runtime": 2.
|
| 166 |
-
"eval_samples_per_second":
|
| 167 |
-
"eval_steps_per_second": 1.
|
| 168 |
"step": 71
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 14.0,
|
| 172 |
-
"eval_accuracy": 0.
|
| 173 |
-
"eval_loss": 0.
|
| 174 |
-
"eval_runtime": 2.
|
| 175 |
-
"eval_samples_per_second": 26.
|
| 176 |
-
"eval_steps_per_second": 1.
|
| 177 |
"step": 77
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 14.55,
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 80
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 14.91,
|
| 187 |
-
"eval_accuracy": 0.
|
| 188 |
-
"eval_loss": 0.
|
| 189 |
-
"eval_runtime": 2.
|
| 190 |
-
"eval_samples_per_second": 27.
|
| 191 |
-
"eval_steps_per_second": 1.
|
| 192 |
"step": 82
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 16.0,
|
| 196 |
-
"eval_accuracy": 0.
|
| 197 |
-
"eval_loss": 0.
|
| 198 |
-
"eval_runtime": 2.
|
| 199 |
-
"eval_samples_per_second":
|
| 200 |
-
"eval_steps_per_second": 1.
|
| 201 |
"step": 88
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 16.36,
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 90
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 16.91,
|
| 211 |
-
"eval_accuracy": 0.
|
| 212 |
-
"eval_loss": 0.
|
| 213 |
-
"eval_runtime": 2.
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second": 1.
|
| 216 |
"step": 93
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 18.0,
|
| 220 |
-
"eval_accuracy": 0.
|
| 221 |
-
"eval_loss": 0.
|
| 222 |
-
"eval_runtime": 2.
|
| 223 |
-
"eval_samples_per_second":
|
| 224 |
-
"eval_steps_per_second": 1.
|
| 225 |
"step": 99
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 18.18,
|
| 229 |
-
"learning_rate": 2.
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 100
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 18.91,
|
| 235 |
-
"eval_accuracy": 0.
|
| 236 |
-
"eval_loss": 0.
|
| 237 |
-
"eval_runtime": 2.
|
| 238 |
-
"eval_samples_per_second":
|
| 239 |
-
"eval_steps_per_second": 1.
|
| 240 |
"step": 104
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 20.0,
|
| 244 |
-
"learning_rate":
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 110
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 20.0,
|
| 250 |
-
"eval_accuracy": 0.
|
| 251 |
-
"eval_loss": 0.
|
| 252 |
-
"eval_runtime": 2.
|
| 253 |
-
"eval_samples_per_second":
|
| 254 |
-
"eval_steps_per_second": 1.
|
| 255 |
"step": 110
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 20.91,
|
| 259 |
-
"eval_accuracy": 0.
|
| 260 |
-
"eval_loss": 0.
|
| 261 |
-
"eval_runtime": 2.
|
| 262 |
-
"eval_samples_per_second":
|
| 263 |
-
"eval_steps_per_second": 1.
|
| 264 |
"step": 115
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 21.82,
|
| 268 |
-
"learning_rate":
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 120
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 22.0,
|
| 274 |
-
"eval_accuracy": 0.
|
| 275 |
-
"eval_loss": 0.
|
| 276 |
-
"eval_runtime": 2.
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second": 1.
|
| 279 |
"step": 121
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 22.91,
|
| 283 |
-
"eval_accuracy": 0.
|
| 284 |
-
"eval_loss": 0.
|
| 285 |
-
"eval_runtime": 2.
|
| 286 |
-
"eval_samples_per_second": 27.
|
| 287 |
-
"eval_steps_per_second": 1.
|
| 288 |
"step": 126
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 23.64,
|
| 292 |
-
"learning_rate": 1.
|
| 293 |
-
"loss": 0.
|
| 294 |
"step": 130
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 24.0,
|
| 298 |
-
"eval_accuracy": 0.
|
| 299 |
-
"eval_loss": 0.
|
| 300 |
-
"eval_runtime": 2.
|
| 301 |
-
"eval_samples_per_second":
|
| 302 |
-
"eval_steps_per_second": 1.
|
| 303 |
"step": 132
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 24.91,
|
| 307 |
-
"eval_accuracy": 0.
|
| 308 |
-
"eval_loss": 0.
|
| 309 |
-
"eval_runtime": 2.
|
| 310 |
-
"eval_samples_per_second":
|
| 311 |
-
"eval_steps_per_second": 1.
|
| 312 |
"step": 137
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 25.45,
|
| 316 |
-
"learning_rate": 1.
|
| 317 |
-
"loss": 0.
|
| 318 |
"step": 140
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 26.0,
|
| 322 |
-
"eval_accuracy": 0.
|
| 323 |
-
"eval_loss": 0.
|
| 324 |
-
"eval_runtime": 2.
|
| 325 |
-
"eval_samples_per_second":
|
| 326 |
-
"eval_steps_per_second": 1.
|
| 327 |
"step": 143
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 26.91,
|
| 331 |
-
"eval_accuracy": 0.
|
| 332 |
-
"eval_loss": 0.
|
| 333 |
-
"eval_runtime": 2.
|
| 334 |
-
"eval_samples_per_second":
|
| 335 |
-
"eval_steps_per_second": 1.
|
| 336 |
"step": 148
|
| 337 |
},
|
| 338 |
{
|
| 339 |
"epoch": 27.27,
|
| 340 |
-
"learning_rate": 1.
|
| 341 |
-
"loss": 0.
|
| 342 |
"step": 150
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 28.0,
|
| 346 |
-
"eval_accuracy": 0.
|
| 347 |
-
"eval_loss": 0.
|
| 348 |
-
"eval_runtime": 2.
|
| 349 |
-
"eval_samples_per_second":
|
| 350 |
-
"eval_steps_per_second": 1.
|
| 351 |
"step": 154
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 28.91,
|
| 355 |
-
"eval_accuracy": 0.
|
| 356 |
-
"eval_loss": 0.
|
| 357 |
-
"eval_runtime": 2.
|
| 358 |
-
"eval_samples_per_second":
|
| 359 |
-
"eval_steps_per_second": 1.
|
| 360 |
"step": 159
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 29.09,
|
| 364 |
-
"learning_rate":
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 160
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 30.0,
|
| 370 |
-
"eval_accuracy": 0.
|
| 371 |
-
"eval_loss": 0.
|
| 372 |
-
"eval_runtime": 2.
|
| 373 |
-
"eval_samples_per_second":
|
| 374 |
-
"eval_steps_per_second": 1.
|
| 375 |
"step": 165
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 30.91,
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 170
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 30.91,
|
| 385 |
-
"eval_accuracy": 0.
|
| 386 |
-
"eval_loss": 0.
|
| 387 |
-
"eval_runtime": 2.
|
| 388 |
-
"eval_samples_per_second":
|
| 389 |
-
"eval_steps_per_second": 1.
|
| 390 |
"step": 170
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 32.0,
|
| 394 |
-
"eval_accuracy": 0.
|
| 395 |
-
"eval_loss": 0.
|
| 396 |
-
"eval_runtime": 2.
|
| 397 |
-
"eval_samples_per_second": 26.
|
| 398 |
"eval_steps_per_second": 1.681,
|
| 399 |
"step": 176
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 32.73,
|
| 403 |
-
"learning_rate":
|
| 404 |
-
"loss": 0.
|
| 405 |
"step": 180
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 32.91,
|
| 409 |
-
"eval_accuracy": 0.
|
| 410 |
-
"eval_loss": 0.
|
| 411 |
-
"eval_runtime": 2.
|
| 412 |
-
"eval_samples_per_second": 26.
|
| 413 |
-
"eval_steps_per_second": 1.
|
| 414 |
"step": 181
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 34.0,
|
| 418 |
-
"eval_accuracy": 0.
|
| 419 |
-
"eval_loss": 0.
|
| 420 |
-
"eval_runtime": 2.
|
| 421 |
-
"eval_samples_per_second":
|
| 422 |
-
"eval_steps_per_second": 1.
|
| 423 |
"step": 187
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 34.55,
|
| 427 |
-
"learning_rate": 2.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 190
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 34.91,
|
| 433 |
-
"eval_accuracy": 0.
|
| 434 |
-
"eval_loss": 0.
|
| 435 |
-
"eval_runtime": 2.
|
| 436 |
-
"eval_samples_per_second":
|
| 437 |
-
"eval_steps_per_second": 1.
|
| 438 |
"step": 192
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 36.0,
|
| 442 |
-
"eval_accuracy": 0.
|
| 443 |
-
"eval_loss": 0.
|
| 444 |
-
"eval_runtime": 2.
|
| 445 |
-
"eval_samples_per_second":
|
| 446 |
-
"eval_steps_per_second": 1.
|
| 447 |
"step": 198
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 36.36,
|
| 451 |
"learning_rate": 0.0,
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 200
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 36.36,
|
| 457 |
-
"eval_accuracy": 0.
|
| 458 |
-
"eval_loss": 0.
|
| 459 |
-
"eval_runtime": 2.
|
| 460 |
-
"eval_samples_per_second":
|
| 461 |
-
"eval_steps_per_second": 1.
|
| 462 |
"step": 200
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 36.36,
|
| 466 |
"step": 200,
|
| 467 |
"total_flos": 9.859141601338982e+17,
|
| 468 |
-
"train_loss": 0.
|
| 469 |
-
"train_runtime":
|
| 470 |
-
"train_samples_per_second":
|
| 471 |
-
"train_steps_per_second": 0.
|
| 472 |
}
|
| 473 |
],
|
| 474 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9032258064516129,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-OT-alt\\checkpoint-99",
|
| 4 |
"epoch": 36.36363636363637,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 200,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.91,
|
| 13 |
+
"eval_accuracy": 0.1774193548387097,
|
| 14 |
+
"eval_loss": 1.7093149423599243,
|
| 15 |
+
"eval_runtime": 2.3415,
|
| 16 |
+
"eval_samples_per_second": 26.478,
|
| 17 |
+
"eval_steps_per_second": 1.708,
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.82,
|
| 22 |
+
"learning_rate": 2.5e-05,
|
| 23 |
+
"loss": 1.7744,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.1774193548387097,
|
| 29 |
+
"eval_loss": 1.6177618503570557,
|
| 30 |
+
"eval_runtime": 2.3771,
|
| 31 |
+
"eval_samples_per_second": 26.083,
|
| 32 |
+
"eval_steps_per_second": 1.683,
|
| 33 |
"step": 11
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.91,
|
| 37 |
+
"eval_accuracy": 0.1774193548387097,
|
| 38 |
+
"eval_loss": 1.473004698753357,
|
| 39 |
+
"eval_runtime": 2.3411,
|
| 40 |
+
"eval_samples_per_second": 26.484,
|
| 41 |
+
"eval_steps_per_second": 1.709,
|
| 42 |
"step": 16
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.64,
|
| 46 |
+
"learning_rate": 5e-05,
|
| 47 |
+
"loss": 1.5823,
|
| 48 |
"step": 20
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.1774193548387097,
|
| 53 |
+
"eval_loss": 1.2754011154174805,
|
| 54 |
+
"eval_runtime": 2.3296,
|
| 55 |
+
"eval_samples_per_second": 26.614,
|
| 56 |
+
"eval_steps_per_second": 1.717,
|
| 57 |
"step": 22
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.91,
|
| 61 |
+
"eval_accuracy": 0.5645161290322581,
|
| 62 |
+
"eval_loss": 1.1454869508743286,
|
| 63 |
+
"eval_runtime": 2.374,
|
| 64 |
+
"eval_samples_per_second": 26.117,
|
| 65 |
+
"eval_steps_per_second": 1.685,
|
| 66 |
"step": 27
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 5.45,
|
| 70 |
+
"learning_rate": 4.722222222222222e-05,
|
| 71 |
+
"loss": 1.27,
|
| 72 |
"step": 30
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.6290322580645161,
|
| 77 |
+
"eval_loss": 1.0146747827529907,
|
| 78 |
+
"eval_runtime": 2.4966,
|
| 79 |
+
"eval_samples_per_second": 24.834,
|
| 80 |
+
"eval_steps_per_second": 1.602,
|
| 81 |
"step": 33
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.91,
|
| 85 |
+
"eval_accuracy": 0.5483870967741935,
|
| 86 |
+
"eval_loss": 0.9789792895317078,
|
| 87 |
+
"eval_runtime": 2.3346,
|
| 88 |
+
"eval_samples_per_second": 26.557,
|
| 89 |
+
"eval_steps_per_second": 1.713,
|
| 90 |
"step": 38
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 7.27,
|
| 94 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 95 |
+
"loss": 1.079,
|
| 96 |
"step": 40
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 8.0,
|
| 100 |
+
"eval_accuracy": 0.45161290322580644,
|
| 101 |
+
"eval_loss": 1.0473968982696533,
|
| 102 |
+
"eval_runtime": 2.3881,
|
| 103 |
+
"eval_samples_per_second": 25.962,
|
| 104 |
+
"eval_steps_per_second": 1.675,
|
| 105 |
"step": 44
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 8.91,
|
| 109 |
+
"eval_accuracy": 0.7580645161290323,
|
| 110 |
+
"eval_loss": 0.8796324729919434,
|
| 111 |
+
"eval_runtime": 2.3814,
|
| 112 |
+
"eval_samples_per_second": 26.035,
|
| 113 |
+
"eval_steps_per_second": 1.68,
|
| 114 |
"step": 49
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 9.09,
|
| 118 |
+
"learning_rate": 4.166666666666667e-05,
|
| 119 |
+
"loss": 1.005,
|
| 120 |
"step": 50
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 10.0,
|
| 124 |
+
"eval_accuracy": 0.7741935483870968,
|
| 125 |
+
"eval_loss": 0.7759426832199097,
|
| 126 |
+
"eval_runtime": 2.3246,
|
| 127 |
+
"eval_samples_per_second": 26.672,
|
| 128 |
+
"eval_steps_per_second": 1.721,
|
| 129 |
"step": 55
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 10.91,
|
| 133 |
+
"learning_rate": 3.888888888888889e-05,
|
| 134 |
+
"loss": 0.8479,
|
| 135 |
"step": 60
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 10.91,
|
| 139 |
+
"eval_accuracy": 0.8225806451612904,
|
| 140 |
+
"eval_loss": 0.7421430349349976,
|
| 141 |
+
"eval_runtime": 2.3181,
|
| 142 |
+
"eval_samples_per_second": 26.747,
|
| 143 |
+
"eval_steps_per_second": 1.726,
|
| 144 |
"step": 60
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 12.0,
|
| 148 |
+
"eval_accuracy": 0.8548387096774194,
|
| 149 |
+
"eval_loss": 0.6759869456291199,
|
| 150 |
+
"eval_runtime": 2.3471,
|
| 151 |
+
"eval_samples_per_second": 26.416,
|
| 152 |
+
"eval_steps_per_second": 1.704,
|
| 153 |
"step": 66
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 12.73,
|
| 157 |
+
"learning_rate": 3.611111111111111e-05,
|
| 158 |
+
"loss": 0.7695,
|
| 159 |
"step": 70
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 12.91,
|
| 163 |
+
"eval_accuracy": 0.8387096774193549,
|
| 164 |
+
"eval_loss": 0.5932707190513611,
|
| 165 |
+
"eval_runtime": 2.3526,
|
| 166 |
+
"eval_samples_per_second": 26.354,
|
| 167 |
+
"eval_steps_per_second": 1.7,
|
| 168 |
"step": 71
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 14.0,
|
| 172 |
+
"eval_accuracy": 0.7741935483870968,
|
| 173 |
+
"eval_loss": 0.6372359991073608,
|
| 174 |
+
"eval_runtime": 2.2975,
|
| 175 |
+
"eval_samples_per_second": 26.985,
|
| 176 |
+
"eval_steps_per_second": 1.741,
|
| 177 |
"step": 77
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 14.55,
|
| 181 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 182 |
+
"loss": 0.6591,
|
| 183 |
"step": 80
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 14.91,
|
| 187 |
+
"eval_accuracy": 0.8387096774193549,
|
| 188 |
+
"eval_loss": 0.5653398633003235,
|
| 189 |
+
"eval_runtime": 2.2901,
|
| 190 |
+
"eval_samples_per_second": 27.074,
|
| 191 |
+
"eval_steps_per_second": 1.747,
|
| 192 |
"step": 82
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 16.0,
|
| 196 |
+
"eval_accuracy": 0.8709677419354839,
|
| 197 |
+
"eval_loss": 0.4950495958328247,
|
| 198 |
+
"eval_runtime": 2.4381,
|
| 199 |
+
"eval_samples_per_second": 25.43,
|
| 200 |
+
"eval_steps_per_second": 1.641,
|
| 201 |
"step": 88
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 16.36,
|
| 205 |
+
"learning_rate": 3.055555555555556e-05,
|
| 206 |
+
"loss": 0.5675,
|
| 207 |
"step": 90
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 16.91,
|
| 211 |
+
"eval_accuracy": 0.8225806451612904,
|
| 212 |
+
"eval_loss": 0.5040029287338257,
|
| 213 |
+
"eval_runtime": 2.3556,
|
| 214 |
+
"eval_samples_per_second": 26.321,
|
| 215 |
+
"eval_steps_per_second": 1.698,
|
| 216 |
"step": 93
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 18.0,
|
| 220 |
+
"eval_accuracy": 0.9032258064516129,
|
| 221 |
+
"eval_loss": 0.4273931682109833,
|
| 222 |
+
"eval_runtime": 2.3296,
|
| 223 |
+
"eval_samples_per_second": 26.614,
|
| 224 |
+
"eval_steps_per_second": 1.717,
|
| 225 |
"step": 99
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 18.18,
|
| 229 |
+
"learning_rate": 2.777777777777778e-05,
|
| 230 |
+
"loss": 0.5134,
|
| 231 |
"step": 100
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 18.91,
|
| 235 |
+
"eval_accuracy": 0.8548387096774194,
|
| 236 |
+
"eval_loss": 0.461721807718277,
|
| 237 |
+
"eval_runtime": 2.4876,
|
| 238 |
+
"eval_samples_per_second": 24.923,
|
| 239 |
+
"eval_steps_per_second": 1.608,
|
| 240 |
"step": 104
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 20.0,
|
| 244 |
+
"learning_rate": 2.5e-05,
|
| 245 |
+
"loss": 0.4418,
|
| 246 |
"step": 110
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 20.0,
|
| 250 |
+
"eval_accuracy": 0.8870967741935484,
|
| 251 |
+
"eval_loss": 0.4244731366634369,
|
| 252 |
+
"eval_runtime": 2.3501,
|
| 253 |
+
"eval_samples_per_second": 26.382,
|
| 254 |
+
"eval_steps_per_second": 1.702,
|
| 255 |
"step": 110
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 20.91,
|
| 259 |
+
"eval_accuracy": 0.8387096774193549,
|
| 260 |
+
"eval_loss": 0.4922010600566864,
|
| 261 |
+
"eval_runtime": 2.4186,
|
| 262 |
+
"eval_samples_per_second": 25.635,
|
| 263 |
+
"eval_steps_per_second": 1.654,
|
| 264 |
"step": 115
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 21.82,
|
| 268 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 269 |
+
"loss": 0.402,
|
| 270 |
"step": 120
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 22.0,
|
| 274 |
+
"eval_accuracy": 0.8225806451612904,
|
| 275 |
+
"eval_loss": 0.5112457275390625,
|
| 276 |
+
"eval_runtime": 2.4655,
|
| 277 |
+
"eval_samples_per_second": 25.147,
|
| 278 |
+
"eval_steps_per_second": 1.622,
|
| 279 |
"step": 121
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 22.91,
|
| 283 |
+
"eval_accuracy": 0.8548387096774194,
|
| 284 |
+
"eval_loss": 0.46961790323257446,
|
| 285 |
+
"eval_runtime": 2.2816,
|
| 286 |
+
"eval_samples_per_second": 27.174,
|
| 287 |
+
"eval_steps_per_second": 1.753,
|
| 288 |
"step": 126
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 23.64,
|
| 292 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 293 |
+
"loss": 0.4039,
|
| 294 |
"step": 130
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 24.0,
|
| 298 |
+
"eval_accuracy": 0.8709677419354839,
|
| 299 |
+
"eval_loss": 0.40138500928878784,
|
| 300 |
+
"eval_runtime": 2.3996,
|
| 301 |
+
"eval_samples_per_second": 25.838,
|
| 302 |
+
"eval_steps_per_second": 1.667,
|
| 303 |
"step": 132
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 24.91,
|
| 307 |
+
"eval_accuracy": 0.8225806451612904,
|
| 308 |
+
"eval_loss": 0.5005894899368286,
|
| 309 |
+
"eval_runtime": 2.3451,
|
| 310 |
+
"eval_samples_per_second": 26.439,
|
| 311 |
+
"eval_steps_per_second": 1.706,
|
| 312 |
"step": 137
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 25.45,
|
| 316 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 317 |
+
"loss": 0.4216,
|
| 318 |
"step": 140
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 26.0,
|
| 322 |
+
"eval_accuracy": 0.8548387096774194,
|
| 323 |
+
"eval_loss": 0.5351113080978394,
|
| 324 |
+
"eval_runtime": 2.4946,
|
| 325 |
+
"eval_samples_per_second": 24.853,
|
| 326 |
+
"eval_steps_per_second": 1.603,
|
| 327 |
"step": 143
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 26.91,
|
| 331 |
+
"eval_accuracy": 0.8548387096774194,
|
| 332 |
+
"eval_loss": 0.5202920436859131,
|
| 333 |
+
"eval_runtime": 2.3236,
|
| 334 |
+
"eval_samples_per_second": 26.683,
|
| 335 |
+
"eval_steps_per_second": 1.721,
|
| 336 |
"step": 148
|
| 337 |
},
|
| 338 |
{
|
| 339 |
"epoch": 27.27,
|
| 340 |
+
"learning_rate": 1.388888888888889e-05,
|
| 341 |
+
"loss": 0.3593,
|
| 342 |
"step": 150
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 28.0,
|
| 346 |
+
"eval_accuracy": 0.8548387096774194,
|
| 347 |
+
"eval_loss": 0.4081813395023346,
|
| 348 |
+
"eval_runtime": 2.3351,
|
| 349 |
+
"eval_samples_per_second": 26.552,
|
| 350 |
+
"eval_steps_per_second": 1.713,
|
| 351 |
"step": 154
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 28.91,
|
| 355 |
+
"eval_accuracy": 0.8709677419354839,
|
| 356 |
+
"eval_loss": 0.40170377492904663,
|
| 357 |
+
"eval_runtime": 2.3078,
|
| 358 |
+
"eval_samples_per_second": 26.865,
|
| 359 |
+
"eval_steps_per_second": 1.733,
|
| 360 |
"step": 159
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 29.09,
|
| 364 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 365 |
+
"loss": 0.3638,
|
| 366 |
"step": 160
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 30.0,
|
| 370 |
+
"eval_accuracy": 0.8870967741935484,
|
| 371 |
+
"eval_loss": 0.40682506561279297,
|
| 372 |
+
"eval_runtime": 2.5896,
|
| 373 |
+
"eval_samples_per_second": 23.942,
|
| 374 |
+
"eval_steps_per_second": 1.545,
|
| 375 |
"step": 165
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 30.91,
|
| 379 |
+
"learning_rate": 8.333333333333334e-06,
|
| 380 |
+
"loss": 0.3509,
|
| 381 |
"step": 170
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 30.91,
|
| 385 |
+
"eval_accuracy": 0.8870967741935484,
|
| 386 |
+
"eval_loss": 0.3990916311740875,
|
| 387 |
+
"eval_runtime": 2.75,
|
| 388 |
+
"eval_samples_per_second": 22.546,
|
| 389 |
+
"eval_steps_per_second": 1.455,
|
| 390 |
"step": 170
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 32.0,
|
| 394 |
+
"eval_accuracy": 0.8709677419354839,
|
| 395 |
+
"eval_loss": 0.3964940309524536,
|
| 396 |
+
"eval_runtime": 2.3794,
|
| 397 |
+
"eval_samples_per_second": 26.056,
|
| 398 |
"eval_steps_per_second": 1.681,
|
| 399 |
"step": 176
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 32.73,
|
| 403 |
+
"learning_rate": 5.555555555555556e-06,
|
| 404 |
+
"loss": 0.3426,
|
| 405 |
"step": 180
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 32.91,
|
| 409 |
+
"eval_accuracy": 0.8709677419354839,
|
| 410 |
+
"eval_loss": 0.3921041190624237,
|
| 411 |
+
"eval_runtime": 2.3356,
|
| 412 |
+
"eval_samples_per_second": 26.546,
|
| 413 |
+
"eval_steps_per_second": 1.713,
|
| 414 |
"step": 181
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 34.0,
|
| 418 |
+
"eval_accuracy": 0.8709677419354839,
|
| 419 |
+
"eval_loss": 0.39981809258461,
|
| 420 |
+
"eval_runtime": 2.4784,
|
| 421 |
+
"eval_samples_per_second": 25.016,
|
| 422 |
+
"eval_steps_per_second": 1.614,
|
| 423 |
"step": 187
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 34.55,
|
| 427 |
+
"learning_rate": 2.777777777777778e-06,
|
| 428 |
+
"loss": 0.3253,
|
| 429 |
"step": 190
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 34.91,
|
| 433 |
+
"eval_accuracy": 0.8870967741935484,
|
| 434 |
+
"eval_loss": 0.41015544533729553,
|
| 435 |
+
"eval_runtime": 2.3626,
|
| 436 |
+
"eval_samples_per_second": 26.243,
|
| 437 |
+
"eval_steps_per_second": 1.693,
|
| 438 |
"step": 192
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 36.0,
|
| 442 |
+
"eval_accuracy": 0.8870967741935484,
|
| 443 |
+
"eval_loss": 0.4080694913864136,
|
| 444 |
+
"eval_runtime": 2.3858,
|
| 445 |
+
"eval_samples_per_second": 25.987,
|
| 446 |
+
"eval_steps_per_second": 1.677,
|
| 447 |
"step": 198
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 36.36,
|
| 451 |
"learning_rate": 0.0,
|
| 452 |
+
"loss": 0.3085,
|
| 453 |
"step": 200
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 36.36,
|
| 457 |
+
"eval_accuracy": 0.8870967741935484,
|
| 458 |
+
"eval_loss": 0.40834033489227295,
|
| 459 |
+
"eval_runtime": 2.3711,
|
| 460 |
+
"eval_samples_per_second": 26.149,
|
| 461 |
+
"eval_steps_per_second": 1.687,
|
| 462 |
"step": 200
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 36.36,
|
| 466 |
"step": 200,
|
| 467 |
"total_flos": 9.859141601338982e+17,
|
| 468 |
+
"train_loss": 0.6893912732601166,
|
| 469 |
+
"train_runtime": 709.0628,
|
| 470 |
+
"train_samples_per_second": 19.744,
|
| 471 |
+
"train_steps_per_second": 0.282
|
| 472 |
}
|
| 473 |
],
|
| 474 |
"logging_steps": 10,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9485465125f9e78e6dd67b509633fd1622ddef7452bb952f0688e13435966aee
|
| 3 |
size 4728
|