Model save
Browse files- README.md +11 -11
- all_results.json +10 -10
- config.json +31 -35
- eval_results.json +5 -5
- model.safetensors +2 -2
- preprocessor_config.json +11 -17
- runs/Dec01_13-11-56_610b2a9400b8/events.out.tfevents.1701436839.610b2a9400b8.3653.6 +3 -0
- runs/Dec01_13-35-54_610b2a9400b8/events.out.tfevents.1701437772.610b2a9400b8.3653.7 +3 -0
- train_results.json +5 -5
- trainer_state.json +173 -173
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
@@ -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
|
|
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
|
| 31 |
# finetuned-Leukemia-cell
|
| 32 |
|
| 33 |
-
This model is a fine-tuned version of [
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -65,12 +65,12 @@ The following hyperparameters were used during training:
|
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
|
| 75 |
|
| 76 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnext-tiny-224
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.981203007518797
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# finetuned-Leukemia-cell
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.0595
|
| 36 |
+
- Accuracy: 0.9812
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 68 |
+
| 0.2926 | 2.94 | 100 | 0.1524 | 0.9436 |
|
| 69 |
+
| 0.1844 | 5.88 | 200 | 0.1718 | 0.9436 |
|
| 70 |
+
| 0.1189 | 8.82 | 300 | 0.0886 | 0.9662 |
|
| 71 |
+
| 0.0682 | 11.76 | 400 | 0.0978 | 0.9699 |
|
| 72 |
+
| 0.0439 | 14.71 | 500 | 0.0812 | 0.9737 |
|
| 73 |
+
| 0.0544 | 17.65 | 600 | 0.0595 | 0.9812 |
|
| 74 |
|
| 75 |
|
| 76 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos": 1.
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 1.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9624060150375939,
|
| 4 |
+
"eval_loss": 0.0946127399802208,
|
| 5 |
+
"eval_runtime": 2.633,
|
| 6 |
+
"eval_samples_per_second": 101.024,
|
| 7 |
+
"eval_steps_per_second": 12.913,
|
| 8 |
+
"total_flos": 1.6434612963230515e+18,
|
| 9 |
+
"train_loss": 0.5515072485103326,
|
| 10 |
+
"train_runtime": 465.2023,
|
| 11 |
+
"train_samples_per_second": 45.658,
|
| 12 |
+
"train_steps_per_second": 1.462
|
| 13 |
}
|
config.json
CHANGED
|
@@ -1,17 +1,22 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
|
|
|
| 12 |
"hidden_act": "gelu",
|
| 13 |
-
"
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"id2label": {
|
| 16 |
"0": "LLA",
|
| 17 |
"1": "folicular",
|
|
@@ -23,7 +28,6 @@
|
|
| 23 |
},
|
| 24 |
"image_size": 224,
|
| 25 |
"initializer_range": 0.02,
|
| 26 |
-
"intermediate_size": 3072,
|
| 27 |
"label2id": {
|
| 28 |
"LLA": "0",
|
| 29 |
"folicular": "1",
|
|
@@ -34,33 +38,25 @@
|
|
| 34 |
"trico": "6"
|
| 35 |
},
|
| 36 |
"layer_norm_eps": 1e-12,
|
| 37 |
-
"layer_scale_init_value":
|
| 38 |
-
"model_type": "
|
| 39 |
-
"num_attention_heads": 12,
|
| 40 |
"num_channels": 3,
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
|
| 44 |
-
5,
|
| 45 |
-
7,
|
| 46 |
-
11
|
| 47 |
],
|
| 48 |
-
"
|
| 49 |
-
|
| 50 |
-
1,
|
| 51 |
-
2,
|
| 52 |
-
3,
|
| 53 |
-
6
|
| 54 |
],
|
|
|
|
| 55 |
"problem_type": "single_label_classification",
|
| 56 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"torch_dtype": "float32",
|
| 58 |
-
"transformers_version": "4.35.2"
|
| 59 |
-
"use_absolute_position_embeddings": false,
|
| 60 |
-
"use_auxiliary_head": true,
|
| 61 |
-
"use_mask_token": true,
|
| 62 |
-
"use_mean_pooling": true,
|
| 63 |
-
"use_relative_position_bias": false,
|
| 64 |
-
"use_shared_relative_position_bias": true,
|
| 65 |
-
"vocab_size": 8192
|
| 66 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/convnext-tiny-224",
|
| 3 |
"architectures": [
|
| 4 |
+
"ConvNextForImageClassification"
|
| 5 |
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
3,
|
| 9 |
+
9,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"drop_path_rate": 0.0,
|
| 13 |
"hidden_act": "gelu",
|
| 14 |
+
"hidden_sizes": [
|
| 15 |
+
96,
|
| 16 |
+
192,
|
| 17 |
+
384,
|
| 18 |
+
768
|
| 19 |
+
],
|
| 20 |
"id2label": {
|
| 21 |
"0": "LLA",
|
| 22 |
"1": "folicular",
|
|
|
|
| 28 |
},
|
| 29 |
"image_size": 224,
|
| 30 |
"initializer_range": 0.02,
|
|
|
|
| 31 |
"label2id": {
|
| 32 |
"LLA": "0",
|
| 33 |
"folicular": "1",
|
|
|
|
| 38 |
"trico": "6"
|
| 39 |
},
|
| 40 |
"layer_norm_eps": 1e-12,
|
| 41 |
+
"layer_scale_init_value": 1e-06,
|
| 42 |
+
"model_type": "convnext",
|
|
|
|
| 43 |
"num_channels": 3,
|
| 44 |
+
"num_stages": 4,
|
| 45 |
+
"out_features": [
|
| 46 |
+
"stage4"
|
|
|
|
|
|
|
|
|
|
| 47 |
],
|
| 48 |
+
"out_indices": [
|
| 49 |
+
4
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
],
|
| 51 |
+
"patch_size": 4,
|
| 52 |
"problem_type": "single_label_classification",
|
| 53 |
+
"stage_names": [
|
| 54 |
+
"stem",
|
| 55 |
+
"stage1",
|
| 56 |
+
"stage2",
|
| 57 |
+
"stage3",
|
| 58 |
+
"stage4"
|
| 59 |
+
],
|
| 60 |
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.35.2"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.9624060150375939,
|
| 4 |
+
"eval_loss": 0.0946127399802208,
|
| 5 |
+
"eval_runtime": 2.633,
|
| 6 |
+
"eval_samples_per_second": 101.024,
|
| 7 |
+
"eval_steps_per_second": 12.913
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fa14359c275d65dc97a7f3b269406a2a20534033e6cd3c3319d98d6a78eba7f
|
| 3 |
+
size 111323316
|
preprocessor_config.json
CHANGED
|
@@ -1,29 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 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 |
-
"feature_extractor_type": "
|
| 12 |
"image_mean": [
|
| 13 |
-
0.
|
| 14 |
-
0.
|
| 15 |
-
0.
|
| 16 |
],
|
| 17 |
-
"image_processor_type": "
|
| 18 |
"image_std": [
|
| 19 |
-
0.
|
| 20 |
-
0.
|
| 21 |
-
0.
|
| 22 |
],
|
| 23 |
-
"resample":
|
| 24 |
"rescale_factor": 0.00392156862745098,
|
| 25 |
"size": {
|
| 26 |
-
"
|
| 27 |
-
"width": 224
|
| 28 |
}
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"crop_pct": 0.875,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"do_normalize": true,
|
|
|
|
| 4 |
"do_rescale": true,
|
| 5 |
"do_resize": true,
|
| 6 |
+
"feature_extractor_type": "ConvNextFeatureExtractor",
|
| 7 |
"image_mean": [
|
| 8 |
+
0.485,
|
| 9 |
+
0.456,
|
| 10 |
+
0.406
|
| 11 |
],
|
| 12 |
+
"image_processor_type": "ConvNextFeatureExtractor",
|
| 13 |
"image_std": [
|
| 14 |
+
0.229,
|
| 15 |
+
0.224,
|
| 16 |
+
0.225
|
| 17 |
],
|
| 18 |
+
"resample": 3,
|
| 19 |
"rescale_factor": 0.00392156862745098,
|
| 20 |
"size": {
|
| 21 |
+
"shortest_edge": 224
|
|
|
|
| 22 |
}
|
| 23 |
}
|
runs/Dec01_13-11-56_610b2a9400b8/events.out.tfevents.1701436839.610b2a9400b8.3653.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced1ed782ae47e34565d004bd2516bfc4697edd2f6ad6e28ebc884121a0ac21b
|
| 3 |
+
size 411
|
runs/Dec01_13-35-54_610b2a9400b8/events.out.tfevents.1701437772.610b2a9400b8.3653.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f36524b90caf446e74df5af5bd286d28e0acec054d7d94fea880ae46be56f921
|
| 3 |
+
size 17529
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"total_flos": 1.6434612963230515e+18,
|
| 4 |
+
"train_loss": 0.5515072485103326,
|
| 5 |
+
"train_runtime": 465.2023,
|
| 6 |
+
"train_samples_per_second": 45.658,
|
| 7 |
+
"train_steps_per_second": 1.462
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-600",
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 100,
|
|
@@ -10,481 +10,481 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.29,
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.59,
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.88,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss":
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 1.18,
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss":
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 1.47,
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss":
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 1.76,
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss":
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 2.06,
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss":
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 2.35,
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss":
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 2.65,
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss":
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 2.94,
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 2.94,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_loss": 0.
|
| 75 |
-
"eval_runtime":
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second":
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 3.24,
|
| 82 |
-
"learning_rate": 0.
|
| 83 |
-
"loss": 0.
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 3.53,
|
| 88 |
-
"learning_rate": 0.
|
| 89 |
-
"loss": 0.
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 3.82,
|
| 94 |
-
"learning_rate": 0.
|
| 95 |
-
"loss": 0.
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 4.12,
|
| 100 |
-
"learning_rate": 0.
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 4.41,
|
| 106 |
-
"learning_rate": 0.
|
| 107 |
-
"loss": 0.
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 4.71,
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 5.0,
|
| 118 |
-
"learning_rate": 0.
|
| 119 |
-
"loss": 0.
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 5.29,
|
| 124 |
-
"learning_rate": 0.
|
| 125 |
-
"loss": 0.
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 5.59,
|
| 130 |
-
"learning_rate": 0.
|
| 131 |
-
"loss": 0.
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 5.88,
|
| 136 |
-
"learning_rate": 0.
|
| 137 |
-
"loss": 0.
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 5.88,
|
| 142 |
-
"eval_accuracy": 0.
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_runtime": 2.
|
| 145 |
-
"eval_samples_per_second":
|
| 146 |
-
"eval_steps_per_second":
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 6.18,
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 6.47,
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 6.76,
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 7.06,
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 7.35,
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 7.65,
|
| 181 |
-
"learning_rate": 0.
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 7.94,
|
| 187 |
-
"learning_rate": 0.
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 8.24,
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 8.53,
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 8.82,
|
| 205 |
-
"learning_rate": 0.
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 8.82,
|
| 211 |
-
"eval_accuracy": 0.
|
| 212 |
-
"eval_loss": 0.
|
| 213 |
-
"eval_runtime": 2.
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second":
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 9.12,
|
| 220 |
-
"learning_rate": 0.
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 9.41,
|
| 226 |
-
"learning_rate": 0.
|
| 227 |
-
"loss": 0.
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 9.71,
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 10.0,
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 10.29,
|
| 244 |
-
"learning_rate": 9.
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 10.59,
|
| 250 |
-
"learning_rate": 9.
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 10.88,
|
| 256 |
-
"learning_rate": 9.
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 11.18,
|
| 262 |
-
"learning_rate": 8.
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 11.47,
|
| 268 |
-
"learning_rate": 8.
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 11.76,
|
| 274 |
-
"learning_rate": 8.
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 400
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 11.76,
|
| 280 |
-
"eval_accuracy": 0.
|
| 281 |
-
"eval_loss": 0.
|
| 282 |
-
"eval_runtime": 2.
|
| 283 |
-
"eval_samples_per_second":
|
| 284 |
-
"eval_steps_per_second":
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 12.06,
|
| 289 |
-
"learning_rate":
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 12.35,
|
| 295 |
-
"learning_rate": 7.
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 12.65,
|
| 301 |
-
"learning_rate": 7.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 12.94,
|
| 307 |
-
"learning_rate": 7.
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 13.24,
|
| 313 |
-
"learning_rate": 6.
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 13.53,
|
| 319 |
-
"learning_rate": 6.
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 460
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 13.82,
|
| 325 |
-
"learning_rate": 6.
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 470
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 14.12,
|
| 331 |
-
"learning_rate": 5.
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 480
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 14.41,
|
| 337 |
-
"learning_rate": 5.
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 490
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 14.71,
|
| 343 |
-
"learning_rate": 5.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 500
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 14.71,
|
| 349 |
-
"eval_accuracy": 0.
|
| 350 |
-
"eval_loss": 0.
|
| 351 |
-
"eval_runtime": 2.
|
| 352 |
-
"eval_samples_per_second":
|
| 353 |
-
"eval_steps_per_second":
|
| 354 |
"step": 500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 15.0,
|
| 358 |
-
"learning_rate": 5.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 510
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 15.29,
|
| 364 |
-
"learning_rate": 4.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 520
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 15.59,
|
| 370 |
-
"learning_rate": 4.
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 530
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 15.88,
|
| 376 |
-
"learning_rate": 4.
|
| 377 |
-
"loss": 0.
|
| 378 |
"step": 540
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 16.18,
|
| 382 |
-
"learning_rate": 3.
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 550
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 16.47,
|
| 388 |
-
"learning_rate": 3.
|
| 389 |
-
"loss": 0.
|
| 390 |
"step": 560
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 16.76,
|
| 394 |
-
"learning_rate": 3.
|
| 395 |
-
"loss": 0.
|
| 396 |
"step": 570
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 17.06,
|
| 400 |
-
"learning_rate":
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 580
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 17.35,
|
| 406 |
-
"learning_rate": 2.
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 590
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 17.65,
|
| 412 |
-
"learning_rate": 2.
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 600
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 17.65,
|
| 418 |
-
"eval_accuracy": 0.
|
| 419 |
-
"eval_loss": 0.
|
| 420 |
-
"eval_runtime": 2.
|
| 421 |
-
"eval_samples_per_second":
|
| 422 |
-
"eval_steps_per_second":
|
| 423 |
"step": 600
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 17.94,
|
| 427 |
-
"learning_rate": 2.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 610
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 18.24,
|
| 433 |
-
"learning_rate": 1.
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 620
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 18.53,
|
| 439 |
-
"learning_rate": 1.
|
| 440 |
-
"loss": 0.
|
| 441 |
"step": 630
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 18.82,
|
| 445 |
-
"learning_rate": 1.
|
| 446 |
-
"loss": 0.
|
| 447 |
"step": 640
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 19.12,
|
| 451 |
-
"learning_rate": 9.
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 650
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 19.41,
|
| 457 |
-
"learning_rate": 6.
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 660
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 19.71,
|
| 463 |
-
"learning_rate": 3.
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 670
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 20.0,
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 680
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 20.0,
|
| 475 |
"step": 680,
|
| 476 |
-
"total_flos": 1.
|
| 477 |
-
"train_loss": 0.
|
| 478 |
-
"train_runtime":
|
| 479 |
-
"train_samples_per_second":
|
| 480 |
-
"train_steps_per_second": 1.
|
| 481 |
}
|
| 482 |
],
|
| 483 |
"logging_steps": 10,
|
| 484 |
"max_steps": 680,
|
| 485 |
"num_train_epochs": 20,
|
| 486 |
"save_steps": 100,
|
| 487 |
-
"total_flos": 1.
|
| 488 |
"trial_name": null,
|
| 489 |
"trial_params": null
|
| 490 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.0946127399802208,
|
| 3 |
"best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-600",
|
| 4 |
"epoch": 20.0,
|
| 5 |
"eval_steps": 100,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.29,
|
| 13 |
+
"learning_rate": 0.00019794117647058826,
|
| 14 |
+
"loss": 1.9655,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.59,
|
| 19 |
+
"learning_rate": 0.000195,
|
| 20 |
+
"loss": 1.7836,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.88,
|
| 25 |
+
"learning_rate": 0.0001920588235294118,
|
| 26 |
+
"loss": 1.5744,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 1.18,
|
| 31 |
+
"learning_rate": 0.00018911764705882353,
|
| 32 |
+
"loss": 1.3903,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 1.47,
|
| 37 |
+
"learning_rate": 0.00018617647058823532,
|
| 38 |
+
"loss": 1.3596,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 1.76,
|
| 43 |
+
"learning_rate": 0.00018323529411764706,
|
| 44 |
+
"loss": 1.3915,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 2.06,
|
| 49 |
+
"learning_rate": 0.00018029411764705885,
|
| 50 |
+
"loss": 1.2525,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 2.35,
|
| 55 |
+
"learning_rate": 0.00017735294117647059,
|
| 56 |
+
"loss": 1.167,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 2.65,
|
| 61 |
+
"learning_rate": 0.00017441176470588235,
|
| 62 |
+
"loss": 1.0339,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 2.94,
|
| 67 |
+
"learning_rate": 0.00017147058823529412,
|
| 68 |
+
"loss": 0.9733,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 2.94,
|
| 73 |
+
"eval_accuracy": 0.7255639097744361,
|
| 74 |
+
"eval_loss": 0.8894439339637756,
|
| 75 |
+
"eval_runtime": 2.491,
|
| 76 |
+
"eval_samples_per_second": 106.783,
|
| 77 |
+
"eval_steps_per_second": 13.649,
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 3.24,
|
| 82 |
+
"learning_rate": 0.00016852941176470588,
|
| 83 |
+
"loss": 0.9561,
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 3.53,
|
| 88 |
+
"learning_rate": 0.00016558823529411765,
|
| 89 |
+
"loss": 0.9493,
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 3.82,
|
| 94 |
+
"learning_rate": 0.0001626470588235294,
|
| 95 |
+
"loss": 0.8258,
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 4.12,
|
| 100 |
+
"learning_rate": 0.0001597058823529412,
|
| 101 |
+
"loss": 0.8111,
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 4.41,
|
| 106 |
+
"learning_rate": 0.00015676470588235294,
|
| 107 |
+
"loss": 0.9361,
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 4.71,
|
| 112 |
+
"learning_rate": 0.00015382352941176473,
|
| 113 |
+
"loss": 0.7733,
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 5.0,
|
| 118 |
+
"learning_rate": 0.00015088235294117647,
|
| 119 |
+
"loss": 0.5113,
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 5.29,
|
| 124 |
+
"learning_rate": 0.00014794117647058826,
|
| 125 |
+
"loss": 0.7088,
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 5.59,
|
| 130 |
+
"learning_rate": 0.000145,
|
| 131 |
+
"loss": 0.6652,
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 5.88,
|
| 136 |
+
"learning_rate": 0.00014205882352941177,
|
| 137 |
+
"loss": 0.7184,
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 5.88,
|
| 142 |
+
"eval_accuracy": 0.7293233082706767,
|
| 143 |
+
"eval_loss": 0.7875903248786926,
|
| 144 |
+
"eval_runtime": 2.5205,
|
| 145 |
+
"eval_samples_per_second": 105.533,
|
| 146 |
+
"eval_steps_per_second": 13.489,
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 6.18,
|
| 151 |
+
"learning_rate": 0.00013911764705882353,
|
| 152 |
+
"loss": 0.9143,
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 6.47,
|
| 157 |
+
"learning_rate": 0.0001361764705882353,
|
| 158 |
+
"loss": 0.7709,
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 6.76,
|
| 163 |
+
"learning_rate": 0.00013323529411764706,
|
| 164 |
+
"loss": 0.5797,
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 7.06,
|
| 169 |
+
"learning_rate": 0.00013029411764705883,
|
| 170 |
+
"loss": 0.5424,
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 7.35,
|
| 175 |
+
"learning_rate": 0.0001273529411764706,
|
| 176 |
+
"loss": 0.6525,
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 7.65,
|
| 181 |
+
"learning_rate": 0.00012441176470588236,
|
| 182 |
+
"loss": 0.3516,
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 7.94,
|
| 187 |
+
"learning_rate": 0.00012147058823529412,
|
| 188 |
+
"loss": 0.4829,
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 8.24,
|
| 193 |
+
"learning_rate": 0.00011852941176470589,
|
| 194 |
+
"loss": 0.5154,
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 8.53,
|
| 199 |
+
"learning_rate": 0.00011558823529411764,
|
| 200 |
+
"loss": 0.3485,
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 8.82,
|
| 205 |
+
"learning_rate": 0.00011264705882352942,
|
| 206 |
+
"loss": 0.5299,
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 8.82,
|
| 211 |
+
"eval_accuracy": 0.8609022556390977,
|
| 212 |
+
"eval_loss": 0.5183172821998596,
|
| 213 |
+
"eval_runtime": 2.8712,
|
| 214 |
+
"eval_samples_per_second": 92.644,
|
| 215 |
+
"eval_steps_per_second": 11.842,
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 9.12,
|
| 220 |
+
"learning_rate": 0.0001097058823529412,
|
| 221 |
+
"loss": 0.5263,
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 9.41,
|
| 226 |
+
"learning_rate": 0.00010676470588235295,
|
| 227 |
+
"loss": 0.4048,
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 9.71,
|
| 232 |
+
"learning_rate": 0.00010382352941176472,
|
| 233 |
+
"loss": 0.4386,
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 10.0,
|
| 238 |
+
"learning_rate": 0.00010088235294117648,
|
| 239 |
+
"loss": 0.4728,
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 10.29,
|
| 244 |
+
"learning_rate": 9.794117647058824e-05,
|
| 245 |
+
"loss": 0.379,
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 10.59,
|
| 250 |
+
"learning_rate": 9.5e-05,
|
| 251 |
+
"loss": 0.4361,
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 10.88,
|
| 256 |
+
"learning_rate": 9.205882352941177e-05,
|
| 257 |
+
"loss": 0.2929,
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 11.18,
|
| 262 |
+
"learning_rate": 8.911764705882354e-05,
|
| 263 |
+
"loss": 0.2848,
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 11.47,
|
| 268 |
+
"learning_rate": 8.61764705882353e-05,
|
| 269 |
+
"loss": 0.4282,
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 11.76,
|
| 274 |
+
"learning_rate": 8.323529411764707e-05,
|
| 275 |
+
"loss": 0.3991,
|
| 276 |
"step": 400
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 11.76,
|
| 280 |
+
"eval_accuracy": 0.8947368421052632,
|
| 281 |
+
"eval_loss": 0.31206753849983215,
|
| 282 |
+
"eval_runtime": 2.9634,
|
| 283 |
+
"eval_samples_per_second": 89.761,
|
| 284 |
+
"eval_steps_per_second": 11.473,
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 12.06,
|
| 289 |
+
"learning_rate": 8.029411764705883e-05,
|
| 290 |
+
"loss": 0.3552,
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 12.35,
|
| 295 |
+
"learning_rate": 7.73529411764706e-05,
|
| 296 |
+
"loss": 0.2886,
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 12.65,
|
| 301 |
+
"learning_rate": 7.441176470588236e-05,
|
| 302 |
+
"loss": 0.2809,
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 12.94,
|
| 307 |
+
"learning_rate": 7.147058823529412e-05,
|
| 308 |
+
"loss": 0.3627,
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 13.24,
|
| 313 |
+
"learning_rate": 6.852941176470589e-05,
|
| 314 |
+
"loss": 0.3137,
|
| 315 |
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 13.53,
|
| 319 |
+
"learning_rate": 6.558823529411765e-05,
|
| 320 |
+
"loss": 0.198,
|
| 321 |
"step": 460
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 13.82,
|
| 325 |
+
"learning_rate": 6.264705882352942e-05,
|
| 326 |
+
"loss": 0.3268,
|
| 327 |
"step": 470
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 14.12,
|
| 331 |
+
"learning_rate": 5.970588235294118e-05,
|
| 332 |
+
"loss": 0.256,
|
| 333 |
"step": 480
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 14.41,
|
| 337 |
+
"learning_rate": 5.676470588235294e-05,
|
| 338 |
+
"loss": 0.2544,
|
| 339 |
"step": 490
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 14.71,
|
| 343 |
+
"learning_rate": 5.382352941176471e-05,
|
| 344 |
+
"loss": 0.2263,
|
| 345 |
"step": 500
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 14.71,
|
| 349 |
+
"eval_accuracy": 0.9548872180451128,
|
| 350 |
+
"eval_loss": 0.13367173075675964,
|
| 351 |
+
"eval_runtime": 2.4729,
|
| 352 |
+
"eval_samples_per_second": 107.566,
|
| 353 |
+
"eval_steps_per_second": 13.749,
|
| 354 |
"step": 500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 15.0,
|
| 358 |
+
"learning_rate": 5.088235294117647e-05,
|
| 359 |
+
"loss": 0.4011,
|
| 360 |
"step": 510
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 15.29,
|
| 364 |
+
"learning_rate": 4.794117647058824e-05,
|
| 365 |
+
"loss": 0.2051,
|
| 366 |
"step": 520
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 15.59,
|
| 370 |
+
"learning_rate": 4.5e-05,
|
| 371 |
+
"loss": 0.2563,
|
| 372 |
"step": 530
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 15.88,
|
| 376 |
+
"learning_rate": 4.205882352941177e-05,
|
| 377 |
+
"loss": 0.2428,
|
| 378 |
"step": 540
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 16.18,
|
| 382 |
+
"learning_rate": 3.911764705882353e-05,
|
| 383 |
+
"loss": 0.189,
|
| 384 |
"step": 550
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 16.47,
|
| 388 |
+
"learning_rate": 3.61764705882353e-05,
|
| 389 |
+
"loss": 0.19,
|
| 390 |
"step": 560
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 16.76,
|
| 394 |
+
"learning_rate": 3.3235294117647056e-05,
|
| 395 |
+
"loss": 0.1696,
|
| 396 |
"step": 570
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 17.06,
|
| 400 |
+
"learning_rate": 3.0294117647058824e-05,
|
| 401 |
+
"loss": 0.1336,
|
| 402 |
"step": 580
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 17.35,
|
| 406 |
+
"learning_rate": 2.7352941176470593e-05,
|
| 407 |
+
"loss": 0.1532,
|
| 408 |
"step": 590
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 17.65,
|
| 412 |
+
"learning_rate": 2.4411764705882354e-05,
|
| 413 |
+
"loss": 0.1782,
|
| 414 |
"step": 600
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 17.65,
|
| 418 |
+
"eval_accuracy": 0.9624060150375939,
|
| 419 |
+
"eval_loss": 0.0946127399802208,
|
| 420 |
+
"eval_runtime": 2.8201,
|
| 421 |
+
"eval_samples_per_second": 94.322,
|
| 422 |
+
"eval_steps_per_second": 12.056,
|
| 423 |
"step": 600
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 17.94,
|
| 427 |
+
"learning_rate": 2.1470588235294116e-05,
|
| 428 |
+
"loss": 0.1511,
|
| 429 |
"step": 610
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 18.24,
|
| 433 |
+
"learning_rate": 1.8529411764705884e-05,
|
| 434 |
+
"loss": 0.0837,
|
| 435 |
"step": 620
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 18.53,
|
| 439 |
+
"learning_rate": 1.558823529411765e-05,
|
| 440 |
+
"loss": 0.1084,
|
| 441 |
"step": 630
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 18.82,
|
| 445 |
+
"learning_rate": 1.2647058823529412e-05,
|
| 446 |
+
"loss": 0.1313,
|
| 447 |
"step": 640
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 19.12,
|
| 451 |
+
"learning_rate": 9.705882352941177e-06,
|
| 452 |
+
"loss": 0.1135,
|
| 453 |
"step": 650
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 19.41,
|
| 457 |
+
"learning_rate": 6.7647058823529414e-06,
|
| 458 |
+
"loss": 0.0844,
|
| 459 |
"step": 660
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 19.71,
|
| 463 |
+
"learning_rate": 3.823529411764706e-06,
|
| 464 |
+
"loss": 0.1765,
|
| 465 |
"step": 670
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 20.0,
|
| 469 |
+
"learning_rate": 8.823529411764706e-07,
|
| 470 |
+
"loss": 0.1745,
|
| 471 |
"step": 680
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 20.0,
|
| 475 |
"step": 680,
|
| 476 |
+
"total_flos": 1.6434612963230515e+18,
|
| 477 |
+
"train_loss": 0.5515072485103326,
|
| 478 |
+
"train_runtime": 465.2023,
|
| 479 |
+
"train_samples_per_second": 45.658,
|
| 480 |
+
"train_steps_per_second": 1.462
|
| 481 |
}
|
| 482 |
],
|
| 483 |
"logging_steps": 10,
|
| 484 |
"max_steps": 680,
|
| 485 |
"num_train_epochs": 20,
|
| 486 |
"save_steps": 100,
|
| 487 |
+
"total_flos": 1.6434612963230515e+18,
|
| 488 |
"trial_name": null,
|
| 489 |
"trial_params": null
|
| 490 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7453b4d852d9cd2e5e3323177f837efc3e7f9c2f92828be34bc2ab59e6d6d25a
|
| 3 |
size 4600
|