End of training
Browse files- README.md +114 -0
- all_results.json +12 -0
- config.json +77 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- runs/Oct11_09-00-01_DESKTOP-SKBE9FB/events.out.tfevents.1728658803.DESKTOP-SKBE9FB.1940.0 +3 -0
- runs/Oct11_09-00-01_DESKTOP-SKBE9FB/events.out.tfevents.1728659525.DESKTOP-SKBE9FB.1940.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +483 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/beit-base-patch16-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: beit-base-patch16-224-OT-2
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 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: 0.8387096774193549
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# beit-base-patch16-224-OT-2
|
| 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: 0.5047
|
| 36 |
+
- Accuracy: 0.8387
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 3.5e-05
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 16
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 64
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 40
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 0.91 | 5 | 1.8532 | 0.0806 |
|
| 71 |
+
| 1.7494 | 2.0 | 11 | 1.7818 | 0.0806 |
|
| 72 |
+
| 1.7494 | 2.91 | 16 | 1.6613 | 0.0806 |
|
| 73 |
+
| 1.6235 | 4.0 | 22 | 1.4651 | 0.0806 |
|
| 74 |
+
| 1.6235 | 4.91 | 27 | 1.3293 | 0.0806 |
|
| 75 |
+
| 1.3836 | 6.0 | 33 | 1.2034 | 0.5161 |
|
| 76 |
+
| 1.3836 | 6.91 | 38 | 1.1748 | 0.3710 |
|
| 77 |
+
| 1.2192 | 8.0 | 44 | 1.0815 | 0.4677 |
|
| 78 |
+
| 1.2192 | 8.91 | 49 | 1.0238 | 0.5 |
|
| 79 |
+
| 1.093 | 10.0 | 55 | 1.0225 | 0.4516 |
|
| 80 |
+
| 0.9938 | 10.91 | 60 | 0.9650 | 0.6452 |
|
| 81 |
+
| 0.9938 | 12.0 | 66 | 0.9314 | 0.6935 |
|
| 82 |
+
| 0.9235 | 12.91 | 71 | 0.9490 | 0.6452 |
|
| 83 |
+
| 0.9235 | 14.0 | 77 | 0.8234 | 0.7258 |
|
| 84 |
+
| 0.8258 | 14.91 | 82 | 0.8159 | 0.7258 |
|
| 85 |
+
| 0.8258 | 16.0 | 88 | 0.7514 | 0.7419 |
|
| 86 |
+
| 0.716 | 16.91 | 93 | 0.7469 | 0.7419 |
|
| 87 |
+
| 0.716 | 18.0 | 99 | 0.6734 | 0.7903 |
|
| 88 |
+
| 0.6026 | 18.91 | 104 | 0.6926 | 0.7581 |
|
| 89 |
+
| 0.5725 | 20.0 | 110 | 0.7952 | 0.7258 |
|
| 90 |
+
| 0.5725 | 20.91 | 115 | 0.6284 | 0.7742 |
|
| 91 |
+
| 0.554 | 22.0 | 121 | 0.6317 | 0.7742 |
|
| 92 |
+
| 0.554 | 22.91 | 126 | 0.6361 | 0.7419 |
|
| 93 |
+
| 0.5162 | 24.0 | 132 | 0.5501 | 0.8226 |
|
| 94 |
+
| 0.5162 | 24.91 | 137 | 0.6278 | 0.7581 |
|
| 95 |
+
| 0.4768 | 26.0 | 143 | 0.5868 | 0.7903 |
|
| 96 |
+
| 0.4768 | 26.91 | 148 | 0.5047 | 0.8387 |
|
| 97 |
+
| 0.4488 | 28.0 | 154 | 0.5264 | 0.7903 |
|
| 98 |
+
| 0.4488 | 28.91 | 159 | 0.4942 | 0.8387 |
|
| 99 |
+
| 0.4281 | 30.0 | 165 | 0.5127 | 0.8387 |
|
| 100 |
+
| 0.4126 | 30.91 | 170 | 0.5027 | 0.8387 |
|
| 101 |
+
| 0.4126 | 32.0 | 176 | 0.5387 | 0.7742 |
|
| 102 |
+
| 0.4326 | 32.91 | 181 | 0.5251 | 0.7903 |
|
| 103 |
+
| 0.4326 | 34.0 | 187 | 0.5091 | 0.8065 |
|
| 104 |
+
| 0.3765 | 34.91 | 192 | 0.5142 | 0.8065 |
|
| 105 |
+
| 0.3765 | 36.0 | 198 | 0.5142 | 0.7903 |
|
| 106 |
+
| 0.3913 | 36.36 | 200 | 0.5144 | 0.7903 |
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
### Framework versions
|
| 110 |
+
|
| 111 |
+
- Transformers 4.36.2
|
| 112 |
+
- Pytorch 2.1.2+cu118
|
| 113 |
+
- Datasets 2.16.1
|
| 114 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 36.36,
|
| 3 |
+
"eval_accuracy": 0.8387096774193549,
|
| 4 |
+
"eval_loss": 0.5047271251678467,
|
| 5 |
+
"eval_runtime": 2.5816,
|
| 6 |
+
"eval_samples_per_second": 24.016,
|
| 7 |
+
"eval_steps_per_second": 1.549,
|
| 8 |
+
"train_loss": 0.786993111371994,
|
| 9 |
+
"train_runtime": 718.789,
|
| 10 |
+
"train_samples_per_second": 19.477,
|
| 11 |
+
"train_steps_per_second": 0.278
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/beit-base-patch16-224",
|
| 3 |
+
"add_fpn": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BeitForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"auxiliary_channels": 256,
|
| 9 |
+
"auxiliary_concat_input": false,
|
| 10 |
+
"auxiliary_loss_weight": 0.4,
|
| 11 |
+
"auxiliary_num_convs": 1,
|
| 12 |
+
"drop_path_rate": 0.1,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.0,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "active",
|
| 18 |
+
"1": "active-inactive",
|
| 19 |
+
"2": "healthy",
|
| 20 |
+
"3": "inactive"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"active": 0,
|
| 27 |
+
"active-inactive": 1,
|
| 28 |
+
"healthy": 2,
|
| 29 |
+
"inactive": 3
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"layer_scale_init_value": 0.1,
|
| 33 |
+
"model_type": "beit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"out_features": [
|
| 38 |
+
"stage12"
|
| 39 |
+
],
|
| 40 |
+
"out_indices": [
|
| 41 |
+
12
|
| 42 |
+
],
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pool_scales": [
|
| 45 |
+
1,
|
| 46 |
+
2,
|
| 47 |
+
3,
|
| 48 |
+
6
|
| 49 |
+
],
|
| 50 |
+
"problem_type": "single_label_classification",
|
| 51 |
+
"reshape_hidden_states": true,
|
| 52 |
+
"semantic_loss_ignore_index": 255,
|
| 53 |
+
"stage_names": [
|
| 54 |
+
"stem",
|
| 55 |
+
"stage1",
|
| 56 |
+
"stage2",
|
| 57 |
+
"stage3",
|
| 58 |
+
"stage4",
|
| 59 |
+
"stage5",
|
| 60 |
+
"stage6",
|
| 61 |
+
"stage7",
|
| 62 |
+
"stage8",
|
| 63 |
+
"stage9",
|
| 64 |
+
"stage10",
|
| 65 |
+
"stage11",
|
| 66 |
+
"stage12"
|
| 67 |
+
],
|
| 68 |
+
"torch_dtype": "float32",
|
| 69 |
+
"transformers_version": "4.36.2",
|
| 70 |
+
"use_absolute_position_embeddings": false,
|
| 71 |
+
"use_auxiliary_head": true,
|
| 72 |
+
"use_mask_token": false,
|
| 73 |
+
"use_mean_pooling": true,
|
| 74 |
+
"use_relative_position_bias": true,
|
| 75 |
+
"use_shared_relative_position_bias": false,
|
| 76 |
+
"vocab_size": 8192
|
| 77 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 36.36,
|
| 3 |
+
"eval_accuracy": 0.8387096774193549,
|
| 4 |
+
"eval_loss": 0.5047271251678467,
|
| 5 |
+
"eval_runtime": 2.5816,
|
| 6 |
+
"eval_samples_per_second": 24.016,
|
| 7 |
+
"eval_steps_per_second": 1.549
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93dde8d21ab8ea2857b23b374bc6d37e993a6935173a9fdb1d0fd88d358c1479
|
| 3 |
+
size 343086480
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": false,
|
| 7 |
+
"do_normalize": true,
|
| 8 |
+
"do_reduce_labels": false,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BeitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.5,
|
| 19 |
+
0.5,
|
| 20 |
+
0.5
|
| 21 |
+
],
|
| 22 |
+
"resample": 2,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"height": 224,
|
| 26 |
+
"width": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
runs/Oct11_09-00-01_DESKTOP-SKBE9FB/events.out.tfevents.1728658803.DESKTOP-SKBE9FB.1940.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a588f4a1e22228d8787c4c1cc1e531561b3cc30771d1f98c59d780049418a4cd
|
| 3 |
+
size 20600
|
runs/Oct11_09-00-01_DESKTOP-SKBE9FB/events.out.tfevents.1728659525.DESKTOP-SKBE9FB.1940.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69a2bff249dba7a18d0930e95e4a83309621d3a82e52743fe3399615fcf573f3
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 36.36,
|
| 3 |
+
"train_loss": 0.786993111371994,
|
| 4 |
+
"train_runtime": 718.789,
|
| 5 |
+
"train_samples_per_second": 19.477,
|
| 6 |
+
"train_steps_per_second": 0.278
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8387096774193549,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-OT-2\\checkpoint-148",
|
| 4 |
+
"epoch": 36.36363636363637,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.91,
|
| 13 |
+
"eval_accuracy": 0.08064516129032258,
|
| 14 |
+
"eval_loss": 1.853175163269043,
|
| 15 |
+
"eval_runtime": 2.2425,
|
| 16 |
+
"eval_samples_per_second": 27.647,
|
| 17 |
+
"eval_steps_per_second": 1.784,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.82,
|
| 22 |
+
"learning_rate": 1.75e-05,
|
| 23 |
+
"loss": 1.7494,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.08064516129032258,
|
| 29 |
+
"eval_loss": 1.7818024158477783,
|
| 30 |
+
"eval_runtime": 2.2481,
|
| 31 |
+
"eval_samples_per_second": 27.579,
|
| 32 |
+
"eval_steps_per_second": 1.779,
|
| 33 |
+
"step": 11
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.91,
|
| 37 |
+
"eval_accuracy": 0.08064516129032258,
|
| 38 |
+
"eval_loss": 1.6613073348999023,
|
| 39 |
+
"eval_runtime": 2.2572,
|
| 40 |
+
"eval_samples_per_second": 27.468,
|
| 41 |
+
"eval_steps_per_second": 1.772,
|
| 42 |
+
"step": 16
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.64,
|
| 46 |
+
"learning_rate": 3.5e-05,
|
| 47 |
+
"loss": 1.6235,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.08064516129032258,
|
| 53 |
+
"eval_loss": 1.4651364088058472,
|
| 54 |
+
"eval_runtime": 2.2621,
|
| 55 |
+
"eval_samples_per_second": 27.409,
|
| 56 |
+
"eval_steps_per_second": 1.768,
|
| 57 |
+
"step": 22
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.91,
|
| 61 |
+
"eval_accuracy": 0.08064516129032258,
|
| 62 |
+
"eval_loss": 1.3293113708496094,
|
| 63 |
+
"eval_runtime": 2.221,
|
| 64 |
+
"eval_samples_per_second": 27.915,
|
| 65 |
+
"eval_steps_per_second": 1.801,
|
| 66 |
+
"step": 27
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.45,
|
| 70 |
+
"learning_rate": 3.3055555555555553e-05,
|
| 71 |
+
"loss": 1.3836,
|
| 72 |
+
"step": 30
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.5161290322580645,
|
| 77 |
+
"eval_loss": 1.2034481763839722,
|
| 78 |
+
"eval_runtime": 2.214,
|
| 79 |
+
"eval_samples_per_second": 28.003,
|
| 80 |
+
"eval_steps_per_second": 1.807,
|
| 81 |
+
"step": 33
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.91,
|
| 85 |
+
"eval_accuracy": 0.3709677419354839,
|
| 86 |
+
"eval_loss": 1.1748452186584473,
|
| 87 |
+
"eval_runtime": 2.2906,
|
| 88 |
+
"eval_samples_per_second": 27.068,
|
| 89 |
+
"eval_steps_per_second": 1.746,
|
| 90 |
+
"step": 38
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 7.27,
|
| 94 |
+
"learning_rate": 3.111111111111111e-05,
|
| 95 |
+
"loss": 1.2192,
|
| 96 |
+
"step": 40
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 8.0,
|
| 100 |
+
"eval_accuracy": 0.46774193548387094,
|
| 101 |
+
"eval_loss": 1.0814906358718872,
|
| 102 |
+
"eval_runtime": 2.3561,
|
| 103 |
+
"eval_samples_per_second": 26.315,
|
| 104 |
+
"eval_steps_per_second": 1.698,
|
| 105 |
+
"step": 44
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.91,
|
| 109 |
+
"eval_accuracy": 0.5,
|
| 110 |
+
"eval_loss": 1.0237908363342285,
|
| 111 |
+
"eval_runtime": 2.2371,
|
| 112 |
+
"eval_samples_per_second": 27.715,
|
| 113 |
+
"eval_steps_per_second": 1.788,
|
| 114 |
+
"step": 49
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.09,
|
| 118 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 119 |
+
"loss": 1.093,
|
| 120 |
+
"step": 50
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.0,
|
| 124 |
+
"eval_accuracy": 0.45161290322580644,
|
| 125 |
+
"eval_loss": 1.0225210189819336,
|
| 126 |
+
"eval_runtime": 2.1705,
|
| 127 |
+
"eval_samples_per_second": 28.565,
|
| 128 |
+
"eval_steps_per_second": 1.843,
|
| 129 |
+
"step": 55
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 10.91,
|
| 133 |
+
"learning_rate": 2.722222222222222e-05,
|
| 134 |
+
"loss": 0.9938,
|
| 135 |
+
"step": 60
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.91,
|
| 139 |
+
"eval_accuracy": 0.6451612903225806,
|
| 140 |
+
"eval_loss": 0.9649767279624939,
|
| 141 |
+
"eval_runtime": 2.178,
|
| 142 |
+
"eval_samples_per_second": 28.466,
|
| 143 |
+
"eval_steps_per_second": 1.837,
|
| 144 |
+
"step": 60
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 12.0,
|
| 148 |
+
"eval_accuracy": 0.6935483870967742,
|
| 149 |
+
"eval_loss": 0.9313719868659973,
|
| 150 |
+
"eval_runtime": 2.2561,
|
| 151 |
+
"eval_samples_per_second": 27.482,
|
| 152 |
+
"eval_steps_per_second": 1.773,
|
| 153 |
+
"step": 66
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 12.73,
|
| 157 |
+
"learning_rate": 2.5277777777777776e-05,
|
| 158 |
+
"loss": 0.9235,
|
| 159 |
+
"step": 70
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.91,
|
| 163 |
+
"eval_accuracy": 0.6451612903225806,
|
| 164 |
+
"eval_loss": 0.9490375518798828,
|
| 165 |
+
"eval_runtime": 2.2295,
|
| 166 |
+
"eval_samples_per_second": 27.809,
|
| 167 |
+
"eval_steps_per_second": 1.794,
|
| 168 |
+
"step": 71
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 14.0,
|
| 172 |
+
"eval_accuracy": 0.7258064516129032,
|
| 173 |
+
"eval_loss": 0.8233911395072937,
|
| 174 |
+
"eval_runtime": 2.1996,
|
| 175 |
+
"eval_samples_per_second": 28.187,
|
| 176 |
+
"eval_steps_per_second": 1.819,
|
| 177 |
+
"step": 77
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 14.55,
|
| 181 |
+
"learning_rate": 2.333333333333333e-05,
|
| 182 |
+
"loss": 0.8258,
|
| 183 |
+
"step": 80
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 14.91,
|
| 187 |
+
"eval_accuracy": 0.7258064516129032,
|
| 188 |
+
"eval_loss": 0.8159334659576416,
|
| 189 |
+
"eval_runtime": 2.2264,
|
| 190 |
+
"eval_samples_per_second": 27.848,
|
| 191 |
+
"eval_steps_per_second": 1.797,
|
| 192 |
+
"step": 82
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 16.0,
|
| 196 |
+
"eval_accuracy": 0.7419354838709677,
|
| 197 |
+
"eval_loss": 0.7513789534568787,
|
| 198 |
+
"eval_runtime": 2.242,
|
| 199 |
+
"eval_samples_per_second": 27.653,
|
| 200 |
+
"eval_steps_per_second": 1.784,
|
| 201 |
+
"step": 88
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 16.36,
|
| 205 |
+
"learning_rate": 2.138888888888889e-05,
|
| 206 |
+
"loss": 0.716,
|
| 207 |
+
"step": 90
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.91,
|
| 211 |
+
"eval_accuracy": 0.7419354838709677,
|
| 212 |
+
"eval_loss": 0.7468788027763367,
|
| 213 |
+
"eval_runtime": 2.2824,
|
| 214 |
+
"eval_samples_per_second": 27.165,
|
| 215 |
+
"eval_steps_per_second": 1.753,
|
| 216 |
+
"step": 93
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 18.0,
|
| 220 |
+
"eval_accuracy": 0.7903225806451613,
|
| 221 |
+
"eval_loss": 0.6733937859535217,
|
| 222 |
+
"eval_runtime": 2.2143,
|
| 223 |
+
"eval_samples_per_second": 28.0,
|
| 224 |
+
"eval_steps_per_second": 1.806,
|
| 225 |
+
"step": 99
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 18.18,
|
| 229 |
+
"learning_rate": 1.9444444444444442e-05,
|
| 230 |
+
"loss": 0.6026,
|
| 231 |
+
"step": 100
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 18.91,
|
| 235 |
+
"eval_accuracy": 0.7580645161290323,
|
| 236 |
+
"eval_loss": 0.6926217079162598,
|
| 237 |
+
"eval_runtime": 2.2096,
|
| 238 |
+
"eval_samples_per_second": 28.06,
|
| 239 |
+
"eval_steps_per_second": 1.81,
|
| 240 |
+
"step": 104
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 20.0,
|
| 244 |
+
"learning_rate": 1.75e-05,
|
| 245 |
+
"loss": 0.5725,
|
| 246 |
+
"step": 110
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 20.0,
|
| 250 |
+
"eval_accuracy": 0.7258064516129032,
|
| 251 |
+
"eval_loss": 0.7951985001564026,
|
| 252 |
+
"eval_runtime": 2.1841,
|
| 253 |
+
"eval_samples_per_second": 28.388,
|
| 254 |
+
"eval_steps_per_second": 1.831,
|
| 255 |
+
"step": 110
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 20.91,
|
| 259 |
+
"eval_accuracy": 0.7741935483870968,
|
| 260 |
+
"eval_loss": 0.6283877491950989,
|
| 261 |
+
"eval_runtime": 2.2365,
|
| 262 |
+
"eval_samples_per_second": 27.721,
|
| 263 |
+
"eval_steps_per_second": 1.788,
|
| 264 |
+
"step": 115
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 21.82,
|
| 268 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 269 |
+
"loss": 0.554,
|
| 270 |
+
"step": 120
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 22.0,
|
| 274 |
+
"eval_accuracy": 0.7741935483870968,
|
| 275 |
+
"eval_loss": 0.6316818594932556,
|
| 276 |
+
"eval_runtime": 2.1575,
|
| 277 |
+
"eval_samples_per_second": 28.737,
|
| 278 |
+
"eval_steps_per_second": 1.854,
|
| 279 |
+
"step": 121
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 22.91,
|
| 283 |
+
"eval_accuracy": 0.7419354838709677,
|
| 284 |
+
"eval_loss": 0.6361408233642578,
|
| 285 |
+
"eval_runtime": 2.2285,
|
| 286 |
+
"eval_samples_per_second": 27.821,
|
| 287 |
+
"eval_steps_per_second": 1.795,
|
| 288 |
+
"step": 126
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 23.64,
|
| 292 |
+
"learning_rate": 1.361111111111111e-05,
|
| 293 |
+
"loss": 0.5162,
|
| 294 |
+
"step": 130
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 24.0,
|
| 298 |
+
"eval_accuracy": 0.8225806451612904,
|
| 299 |
+
"eval_loss": 0.5500665903091431,
|
| 300 |
+
"eval_runtime": 2.2304,
|
| 301 |
+
"eval_samples_per_second": 27.798,
|
| 302 |
+
"eval_steps_per_second": 1.793,
|
| 303 |
+
"step": 132
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 24.91,
|
| 307 |
+
"eval_accuracy": 0.7580645161290323,
|
| 308 |
+
"eval_loss": 0.6277778744697571,
|
| 309 |
+
"eval_runtime": 2.2482,
|
| 310 |
+
"eval_samples_per_second": 27.577,
|
| 311 |
+
"eval_steps_per_second": 1.779,
|
| 312 |
+
"step": 137
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 25.45,
|
| 316 |
+
"learning_rate": 1.1666666666666665e-05,
|
| 317 |
+
"loss": 0.4768,
|
| 318 |
+
"step": 140
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 26.0,
|
| 322 |
+
"eval_accuracy": 0.7903225806451613,
|
| 323 |
+
"eval_loss": 0.5867522358894348,
|
| 324 |
+
"eval_runtime": 2.211,
|
| 325 |
+
"eval_samples_per_second": 28.041,
|
| 326 |
+
"eval_steps_per_second": 1.809,
|
| 327 |
+
"step": 143
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 26.91,
|
| 331 |
+
"eval_accuracy": 0.8387096774193549,
|
| 332 |
+
"eval_loss": 0.5047271251678467,
|
| 333 |
+
"eval_runtime": 2.199,
|
| 334 |
+
"eval_samples_per_second": 28.194,
|
| 335 |
+
"eval_steps_per_second": 1.819,
|
| 336 |
+
"step": 148
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 27.27,
|
| 340 |
+
"learning_rate": 9.722222222222221e-06,
|
| 341 |
+
"loss": 0.4488,
|
| 342 |
+
"step": 150
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 28.0,
|
| 346 |
+
"eval_accuracy": 0.7903225806451613,
|
| 347 |
+
"eval_loss": 0.5263858437538147,
|
| 348 |
+
"eval_runtime": 2.226,
|
| 349 |
+
"eval_samples_per_second": 27.852,
|
| 350 |
+
"eval_steps_per_second": 1.797,
|
| 351 |
+
"step": 154
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 28.91,
|
| 355 |
+
"eval_accuracy": 0.8387096774193549,
|
| 356 |
+
"eval_loss": 0.49419379234313965,
|
| 357 |
+
"eval_runtime": 2.2036,
|
| 358 |
+
"eval_samples_per_second": 28.136,
|
| 359 |
+
"eval_steps_per_second": 1.815,
|
| 360 |
+
"step": 159
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 29.09,
|
| 364 |
+
"learning_rate": 7.777777777777777e-06,
|
| 365 |
+
"loss": 0.4281,
|
| 366 |
+
"step": 160
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 30.0,
|
| 370 |
+
"eval_accuracy": 0.8387096774193549,
|
| 371 |
+
"eval_loss": 0.5126697421073914,
|
| 372 |
+
"eval_runtime": 2.1663,
|
| 373 |
+
"eval_samples_per_second": 28.62,
|
| 374 |
+
"eval_steps_per_second": 1.846,
|
| 375 |
+
"step": 165
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 30.91,
|
| 379 |
+
"learning_rate": 5.833333333333332e-06,
|
| 380 |
+
"loss": 0.4126,
|
| 381 |
+
"step": 170
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 30.91,
|
| 385 |
+
"eval_accuracy": 0.8387096774193549,
|
| 386 |
+
"eval_loss": 0.5026701092720032,
|
| 387 |
+
"eval_runtime": 2.1795,
|
| 388 |
+
"eval_samples_per_second": 28.447,
|
| 389 |
+
"eval_steps_per_second": 1.835,
|
| 390 |
+
"step": 170
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 32.0,
|
| 394 |
+
"eval_accuracy": 0.7741935483870968,
|
| 395 |
+
"eval_loss": 0.5387425422668457,
|
| 396 |
+
"eval_runtime": 2.5256,
|
| 397 |
+
"eval_samples_per_second": 24.549,
|
| 398 |
+
"eval_steps_per_second": 1.584,
|
| 399 |
+
"step": 176
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 32.73,
|
| 403 |
+
"learning_rate": 3.888888888888889e-06,
|
| 404 |
+
"loss": 0.4326,
|
| 405 |
+
"step": 180
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 32.91,
|
| 409 |
+
"eval_accuracy": 0.7903225806451613,
|
| 410 |
+
"eval_loss": 0.5250905156135559,
|
| 411 |
+
"eval_runtime": 2.2035,
|
| 412 |
+
"eval_samples_per_second": 28.137,
|
| 413 |
+
"eval_steps_per_second": 1.815,
|
| 414 |
+
"step": 181
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 34.0,
|
| 418 |
+
"eval_accuracy": 0.8064516129032258,
|
| 419 |
+
"eval_loss": 0.5091389417648315,
|
| 420 |
+
"eval_runtime": 2.3211,
|
| 421 |
+
"eval_samples_per_second": 26.712,
|
| 422 |
+
"eval_steps_per_second": 1.723,
|
| 423 |
+
"step": 187
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 34.55,
|
| 427 |
+
"learning_rate": 1.9444444444444444e-06,
|
| 428 |
+
"loss": 0.3765,
|
| 429 |
+
"step": 190
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 34.91,
|
| 433 |
+
"eval_accuracy": 0.8064516129032258,
|
| 434 |
+
"eval_loss": 0.5141739845275879,
|
| 435 |
+
"eval_runtime": 2.2025,
|
| 436 |
+
"eval_samples_per_second": 28.15,
|
| 437 |
+
"eval_steps_per_second": 1.816,
|
| 438 |
+
"step": 192
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 36.0,
|
| 442 |
+
"eval_accuracy": 0.7903225806451613,
|
| 443 |
+
"eval_loss": 0.514202356338501,
|
| 444 |
+
"eval_runtime": 2.1798,
|
| 445 |
+
"eval_samples_per_second": 28.443,
|
| 446 |
+
"eval_steps_per_second": 1.835,
|
| 447 |
+
"step": 198
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 36.36,
|
| 451 |
+
"learning_rate": 0.0,
|
| 452 |
+
"loss": 0.3913,
|
| 453 |
+
"step": 200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 36.36,
|
| 457 |
+
"eval_accuracy": 0.7903225806451613,
|
| 458 |
+
"eval_loss": 0.5144444108009338,
|
| 459 |
+
"eval_runtime": 2.196,
|
| 460 |
+
"eval_samples_per_second": 28.233,
|
| 461 |
+
"eval_steps_per_second": 1.821,
|
| 462 |
+
"step": 200
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 36.36,
|
| 466 |
+
"step": 200,
|
| 467 |
+
"total_flos": 9.859141601338982e+17,
|
| 468 |
+
"train_loss": 0.786993111371994,
|
| 469 |
+
"train_runtime": 718.789,
|
| 470 |
+
"train_samples_per_second": 19.477,
|
| 471 |
+
"train_steps_per_second": 0.278
|
| 472 |
+
}
|
| 473 |
+
],
|
| 474 |
+
"logging_steps": 10,
|
| 475 |
+
"max_steps": 200,
|
| 476 |
+
"num_input_tokens_seen": 0,
|
| 477 |
+
"num_train_epochs": 40,
|
| 478 |
+
"save_steps": 500,
|
| 479 |
+
"total_flos": 9.859141601338982e+17,
|
| 480 |
+
"train_batch_size": 16,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36e96da6446cba44d6ae08cb924e141f94e6c3bff23eb872eca89a73e9a155de
|
| 3 |
+
size 4728
|