End of training
Browse files- README.md +79 -0
- all_results.json +18 -0
- config.json +79 -0
- eval_results.json +13 -0
- model.safetensors +3 -0
- preprocessor_config.json +28 -0
- train_results.json +8 -0
- trainer_state.json +276 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: beit-base-patch16-224-pt22k-ft22k-finetuned-barkley
|
14 |
+
results: []
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# beit-base-patch16-224-pt22k-ft22k-finetuned-barkley
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.0079
|
25 |
+
- Precision: 1.0
|
26 |
+
- Recall: 1.0
|
27 |
+
- F1: 1.0
|
28 |
+
- Accuracy: 1.0
|
29 |
+
- Top1 Accuracy: 1.0
|
30 |
+
- Error Rate: 0.0
|
31 |
+
|
32 |
+
## Model description
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Intended uses & limitations
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training and evaluation data
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training procedure
|
45 |
+
|
46 |
+
### Training hyperparameters
|
47 |
+
|
48 |
+
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 0.0002
|
50 |
+
- train_batch_size: 32
|
51 |
+
- eval_batch_size: 32
|
52 |
+
- seed: 42
|
53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
+
- lr_scheduler_type: linear
|
55 |
+
- lr_scheduler_warmup_ratio: 0.1
|
56 |
+
- num_epochs: 30
|
57 |
+
- mixed_precision_training: Native AMP
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|
62 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:-------------:|:----------:|
|
63 |
+
| 1.5547 | 1.0 | 38 | 1.4018 | 0.5683 | 0.4539 | 0.4240 | 0.4728 | 0.4539 | 0.5272 |
|
64 |
+
| 1.1732 | 2.0 | 76 | 0.9193 | 0.8095 | 0.7961 | 0.7985 | 0.8077 | 0.7961 | 0.1923 |
|
65 |
+
| 0.6764 | 3.0 | 114 | 0.3644 | 0.9488 | 0.9474 | 0.9470 | 0.9483 | 0.9474 | 0.0517 |
|
66 |
+
| 0.2566 | 4.0 | 152 | 0.0871 | 0.9937 | 0.9934 | 0.9934 | 0.9944 | 0.9934 | 0.0056 |
|
67 |
+
| 0.1014 | 5.0 | 190 | 0.0533 | 0.9809 | 0.9803 | 0.9802 | 0.9811 | 0.9803 | 0.0189 |
|
68 |
+
| 0.0538 | 6.0 | 228 | 0.0208 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 |
|
69 |
+
| 0.0304 | 7.0 | 266 | 0.0079 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 |
|
70 |
+
| 0.0571 | 8.0 | 304 | 0.0088 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 |
|
71 |
+
| 0.0608 | 9.0 | 342 | 0.0226 | 0.9936 | 0.9934 | 0.9934 | 0.9933 | 0.9934 | 0.0067 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.44.2
|
77 |
+
- Pytorch 2.3.1+cu121
|
78 |
+
- Datasets 3.0.1
|
79 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_error_rate": 0.0,
|
5 |
+
"eval_f1": 1.0,
|
6 |
+
"eval_loss": 0.007897687144577503,
|
7 |
+
"eval_precision": 1.0,
|
8 |
+
"eval_recall": 1.0,
|
9 |
+
"eval_runtime": 44.0386,
|
10 |
+
"eval_samples_per_second": 3.452,
|
11 |
+
"eval_steps_per_second": 0.114,
|
12 |
+
"eval_top1_accuracy": 1.0,
|
13 |
+
"total_flos": 8.477326613832008e+17,
|
14 |
+
"train_loss": 0.4405021691880031,
|
15 |
+
"train_runtime": 8765.8937,
|
16 |
+
"train_samples_per_second": 4.162,
|
17 |
+
"train_steps_per_second": 0.13
|
18 |
+
}
|
config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
|
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": "Iinstia bijuga",
|
18 |
+
"1": "Mangifera indica",
|
19 |
+
"2": "Pterocarpus indicus",
|
20 |
+
"3": "Roystonea regia",
|
21 |
+
"4": "Tabebuia"
|
22 |
+
},
|
23 |
+
"image_size": 224,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"Iinstia bijuga": 0,
|
28 |
+
"Mangifera indica": 1,
|
29 |
+
"Pterocarpus indicus": 2,
|
30 |
+
"Roystonea regia": 3,
|
31 |
+
"Tabebuia": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"layer_scale_init_value": 0.1,
|
35 |
+
"model_type": "beit",
|
36 |
+
"num_attention_heads": 12,
|
37 |
+
"num_channels": 3,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"out_features": [
|
40 |
+
"stage12"
|
41 |
+
],
|
42 |
+
"out_indices": [
|
43 |
+
12
|
44 |
+
],
|
45 |
+
"patch_size": 16,
|
46 |
+
"pool_scales": [
|
47 |
+
1,
|
48 |
+
2,
|
49 |
+
3,
|
50 |
+
6
|
51 |
+
],
|
52 |
+
"problem_type": "single_label_classification",
|
53 |
+
"reshape_hidden_states": true,
|
54 |
+
"semantic_loss_ignore_index": 255,
|
55 |
+
"stage_names": [
|
56 |
+
"stem",
|
57 |
+
"stage1",
|
58 |
+
"stage2",
|
59 |
+
"stage3",
|
60 |
+
"stage4",
|
61 |
+
"stage5",
|
62 |
+
"stage6",
|
63 |
+
"stage7",
|
64 |
+
"stage8",
|
65 |
+
"stage9",
|
66 |
+
"stage10",
|
67 |
+
"stage11",
|
68 |
+
"stage12"
|
69 |
+
],
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.44.2",
|
72 |
+
"use_absolute_position_embeddings": false,
|
73 |
+
"use_auxiliary_head": true,
|
74 |
+
"use_mask_token": false,
|
75 |
+
"use_mean_pooling": true,
|
76 |
+
"use_relative_position_bias": true,
|
77 |
+
"use_shared_relative_position_bias": false,
|
78 |
+
"vocab_size": 8192
|
79 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"eval_accuracy": 1.0,
|
4 |
+
"eval_error_rate": 0.0,
|
5 |
+
"eval_f1": 1.0,
|
6 |
+
"eval_loss": 0.007897687144577503,
|
7 |
+
"eval_precision": 1.0,
|
8 |
+
"eval_recall": 1.0,
|
9 |
+
"eval_runtime": 44.0386,
|
10 |
+
"eval_samples_per_second": 3.452,
|
11 |
+
"eval_steps_per_second": 0.114,
|
12 |
+
"eval_top1_accuracy": 1.0
|
13 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb29d38667592d9d6399400c6135abd3f2eb95163b499ac1964339b9adf30c00
|
3 |
+
size 343089556
|
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 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"total_flos": 8.477326613832008e+17,
|
4 |
+
"train_loss": 0.4405021691880031,
|
5 |
+
"train_runtime": 8765.8937,
|
6 |
+
"train_samples_per_second": 4.162,
|
7 |
+
"train_steps_per_second": 0.13
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.007897687144577503,
|
3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-barkley\\checkpoint-266",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 342,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"train_accuracy": 0.31167763157894735
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"epoch": 1.0,
|
17 |
+
"grad_norm": 12.05273151397705,
|
18 |
+
"learning_rate": 1.3523651731772227e-06,
|
19 |
+
"loss": 1.5547,
|
20 |
+
"step": 38
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.472770236299648,
|
25 |
+
"eval_error_rate": 0.527229763700352,
|
26 |
+
"eval_f1": 0.4239844424393964,
|
27 |
+
"eval_loss": 1.4018361568450928,
|
28 |
+
"eval_precision": 0.568315238272393,
|
29 |
+
"eval_recall": 0.45394736842105265,
|
30 |
+
"eval_runtime": 77.2729,
|
31 |
+
"eval_samples_per_second": 1.967,
|
32 |
+
"eval_steps_per_second": 0.065,
|
33 |
+
"eval_top1_accuracy": 0.45394736842105265,
|
34 |
+
"step": 38
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.0,
|
38 |
+
"train_accuracy": 0.6059941520467836
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.0,
|
42 |
+
"grad_norm": Infinity,
|
43 |
+
"learning_rate": 2.945896675096576e-06,
|
44 |
+
"loss": 1.1732,
|
45 |
+
"step": 76
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.0,
|
49 |
+
"eval_accuracy": 0.8077275012569132,
|
50 |
+
"eval_error_rate": 0.19227249874308683,
|
51 |
+
"eval_f1": 0.798546834840623,
|
52 |
+
"eval_loss": 0.9193388223648071,
|
53 |
+
"eval_precision": 0.8095493933458997,
|
54 |
+
"eval_recall": 0.7960526315789473,
|
55 |
+
"eval_runtime": 74.7172,
|
56 |
+
"eval_samples_per_second": 2.034,
|
57 |
+
"eval_steps_per_second": 0.067,
|
58 |
+
"eval_top1_accuracy": 0.7960526315789473,
|
59 |
+
"step": 76
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 3.0,
|
63 |
+
"train_accuracy": 0.8654970760233918
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 3.0,
|
67 |
+
"grad_norm": 9.15374755859375,
|
68 |
+
"learning_rate": 5.472913419787674e-06,
|
69 |
+
"loss": 0.6764,
|
70 |
+
"step": 114
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 3.0,
|
74 |
+
"eval_accuracy": 0.9483207642031172,
|
75 |
+
"eval_error_rate": 0.05167923579688283,
|
76 |
+
"eval_f1": 0.9470289415786431,
|
77 |
+
"eval_loss": 0.36436742544174194,
|
78 |
+
"eval_precision": 0.9488354259225403,
|
79 |
+
"eval_recall": 0.9473684210526315,
|
80 |
+
"eval_runtime": 76.1752,
|
81 |
+
"eval_samples_per_second": 1.995,
|
82 |
+
"eval_steps_per_second": 0.066,
|
83 |
+
"eval_top1_accuracy": 0.9473684210526315,
|
84 |
+
"step": 114
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 4.0,
|
88 |
+
"train_accuracy": 0.9649122807017544
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 4.0,
|
92 |
+
"grad_norm": 8.670642852783203,
|
93 |
+
"learning_rate": 8.59766441885347e-06,
|
94 |
+
"loss": 0.2566,
|
95 |
+
"step": 152
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 4.0,
|
99 |
+
"eval_accuracy": 0.9944444444444445,
|
100 |
+
"eval_error_rate": 0.005555555555555536,
|
101 |
+
"eval_f1": 0.99343678755752,
|
102 |
+
"eval_loss": 0.08713744580745697,
|
103 |
+
"eval_precision": 0.9936647173489279,
|
104 |
+
"eval_recall": 0.993421052631579,
|
105 |
+
"eval_runtime": 72.4529,
|
106 |
+
"eval_samples_per_second": 2.098,
|
107 |
+
"eval_steps_per_second": 0.069,
|
108 |
+
"eval_top1_accuracy": 0.993421052631579,
|
109 |
+
"step": 152
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 5.0,
|
113 |
+
"train_accuracy": 0.9839181286549707
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 5.0,
|
117 |
+
"grad_norm": 8.482632637023926,
|
118 |
+
"learning_rate": 1.1941067495001943e-05,
|
119 |
+
"loss": 0.1014,
|
120 |
+
"step": 190
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 5.0,
|
124 |
+
"eval_accuracy": 0.981111111111111,
|
125 |
+
"eval_error_rate": 0.018888888888888955,
|
126 |
+
"eval_f1": 0.980233547031901,
|
127 |
+
"eval_loss": 0.05328463390469551,
|
128 |
+
"eval_precision": 0.9808624413887572,
|
129 |
+
"eval_recall": 0.9802631578947368,
|
130 |
+
"eval_runtime": 73.3921,
|
131 |
+
"eval_samples_per_second": 2.071,
|
132 |
+
"eval_steps_per_second": 0.068,
|
133 |
+
"eval_top1_accuracy": 0.9802631578947368,
|
134 |
+
"step": 190
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 6.0,
|
138 |
+
"train_accuracy": 0.9897660818713451
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 6.0,
|
142 |
+
"grad_norm": 0.8424493670463562,
|
143 |
+
"learning_rate": 1.50975144835985e-05,
|
144 |
+
"loss": 0.0538,
|
145 |
+
"step": 228
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 6.0,
|
149 |
+
"eval_accuracy": 1.0,
|
150 |
+
"eval_error_rate": 0.0,
|
151 |
+
"eval_f1": 1.0,
|
152 |
+
"eval_loss": 0.020772233605384827,
|
153 |
+
"eval_precision": 1.0,
|
154 |
+
"eval_recall": 1.0,
|
155 |
+
"eval_runtime": 74.2604,
|
156 |
+
"eval_samples_per_second": 2.047,
|
157 |
+
"eval_steps_per_second": 0.067,
|
158 |
+
"eval_top1_accuracy": 1.0,
|
159 |
+
"step": 228
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 7.0,
|
163 |
+
"train_accuracy": 0.9941520467836257
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 7.0,
|
167 |
+
"grad_norm": 0.9595191478729248,
|
168 |
+
"learning_rate": 1.7684077977850795e-05,
|
169 |
+
"loss": 0.0304,
|
170 |
+
"step": 266
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 7.0,
|
174 |
+
"eval_accuracy": 1.0,
|
175 |
+
"eval_error_rate": 0.0,
|
176 |
+
"eval_f1": 1.0,
|
177 |
+
"eval_loss": 0.007897687144577503,
|
178 |
+
"eval_precision": 1.0,
|
179 |
+
"eval_recall": 1.0,
|
180 |
+
"eval_runtime": 69.1824,
|
181 |
+
"eval_samples_per_second": 2.197,
|
182 |
+
"eval_steps_per_second": 0.072,
|
183 |
+
"eval_top1_accuracy": 1.0,
|
184 |
+
"step": 266
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 8.0,
|
188 |
+
"train_accuracy": 0.9861111111111112
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 8.0,
|
192 |
+
"grad_norm": 2.93084454536438,
|
193 |
+
"learning_rate": 1.9386966536009276e-05,
|
194 |
+
"loss": 0.0571,
|
195 |
+
"step": 304
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 8.0,
|
199 |
+
"eval_accuracy": 1.0,
|
200 |
+
"eval_error_rate": 0.0,
|
201 |
+
"eval_f1": 1.0,
|
202 |
+
"eval_loss": 0.008802073076367378,
|
203 |
+
"eval_precision": 1.0,
|
204 |
+
"eval_recall": 1.0,
|
205 |
+
"eval_runtime": 59.208,
|
206 |
+
"eval_samples_per_second": 2.567,
|
207 |
+
"eval_steps_per_second": 0.084,
|
208 |
+
"eval_top1_accuracy": 1.0,
|
209 |
+
"step": 304
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 9.0,
|
213 |
+
"train_accuracy": 0.9817251461988304
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 9.0,
|
217 |
+
"grad_norm": 0.27030402421951294,
|
218 |
+
"learning_rate": 1.9998370404079306e-05,
|
219 |
+
"loss": 0.0608,
|
220 |
+
"step": 342
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 9.0,
|
224 |
+
"eval_accuracy": 0.9933333333333334,
|
225 |
+
"eval_error_rate": 0.006666666666666599,
|
226 |
+
"eval_f1": 0.9934103601236665,
|
227 |
+
"eval_loss": 0.022643933072686195,
|
228 |
+
"eval_precision": 0.9935988620199147,
|
229 |
+
"eval_recall": 0.993421052631579,
|
230 |
+
"eval_runtime": 54.0581,
|
231 |
+
"eval_samples_per_second": 2.812,
|
232 |
+
"eval_steps_per_second": 0.092,
|
233 |
+
"eval_top1_accuracy": 0.993421052631579,
|
234 |
+
"step": 342
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 9.0,
|
238 |
+
"step": 342,
|
239 |
+
"total_flos": 8.477326613832008e+17,
|
240 |
+
"train_loss": 0.4405021691880031,
|
241 |
+
"train_runtime": 8765.8937,
|
242 |
+
"train_samples_per_second": 4.162,
|
243 |
+
"train_steps_per_second": 0.13
|
244 |
+
}
|
245 |
+
],
|
246 |
+
"logging_steps": 10,
|
247 |
+
"max_steps": 1140,
|
248 |
+
"num_input_tokens_seen": 0,
|
249 |
+
"num_train_epochs": 30,
|
250 |
+
"save_steps": 500,
|
251 |
+
"stateful_callbacks": {
|
252 |
+
"EarlyStoppingCallback": {
|
253 |
+
"args": {
|
254 |
+
"early_stopping_patience": 2,
|
255 |
+
"early_stopping_threshold": 0.0
|
256 |
+
},
|
257 |
+
"attributes": {
|
258 |
+
"early_stopping_patience_counter": 0
|
259 |
+
}
|
260 |
+
},
|
261 |
+
"TrainerControl": {
|
262 |
+
"args": {
|
263 |
+
"should_epoch_stop": false,
|
264 |
+
"should_evaluate": false,
|
265 |
+
"should_log": false,
|
266 |
+
"should_save": true,
|
267 |
+
"should_training_stop": true
|
268 |
+
},
|
269 |
+
"attributes": {}
|
270 |
+
}
|
271 |
+
},
|
272 |
+
"total_flos": 8.477326613832008e+17,
|
273 |
+
"train_batch_size": 32,
|
274 |
+
"trial_name": null,
|
275 |
+
"trial_params": null
|
276 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3db2e50743efae30a7e86a2e2dcbcd6e1e65f7aa5345f29196518285ac5a8880
|
3 |
+
size 5176
|