Commit
•
7970571
1
Parent(s):
e5b707e
End of training
Browse files- README.md +103 -0
- config.json +27 -0
- model.safetensors +3 -0
- runs/May02_05-05-03_19135c3d3381/events.out.tfevents.1714626303.19135c3d3381.571.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: BERT_top5_bm25_rr5_10_epoch
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# BERT_top5_bm25_rr5_10_epoch
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.0294
|
24 |
+
- Accuracy: 0.7708
|
25 |
+
- F1: 0.6486
|
26 |
+
- Precision: 0.5385
|
27 |
+
- Recall: 0.8155
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- lr_scheduler_warmup_steps: 100
|
53 |
+
- num_epochs: 10
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
58 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
59 |
+
| No log | 0.2623 | 16 | 0.6133 | 0.8237 | 0.5270 | 0.8667 | 0.3786 |
|
60 |
+
| No log | 0.5246 | 32 | 0.5112 | 0.7758 | 0.2393 | 1.0 | 0.1359 |
|
61 |
+
| No log | 0.7869 | 48 | 0.4725 | 0.8363 | 0.6448 | 0.7375 | 0.5728 |
|
62 |
+
| No log | 1.0492 | 64 | 0.3894 | 0.8539 | 0.6882 | 0.7711 | 0.6214 |
|
63 |
+
| No log | 1.3115 | 80 | 0.7018 | 0.5013 | 0.5 | 0.3379 | 0.9612 |
|
64 |
+
| No log | 1.5738 | 96 | 0.4207 | 0.8338 | 0.7054 | 0.6529 | 0.7670 |
|
65 |
+
| No log | 1.8361 | 112 | 0.4159 | 0.7834 | 0.6587 | 0.5570 | 0.8058 |
|
66 |
+
| No log | 2.0984 | 128 | 0.4052 | 0.8060 | 0.6831 | 0.5929 | 0.8058 |
|
67 |
+
| No log | 2.3607 | 144 | 0.4456 | 0.7859 | 0.6743 | 0.5570 | 0.8544 |
|
68 |
+
| No log | 2.6230 | 160 | 0.3880 | 0.8564 | 0.7016 | 0.7614 | 0.6505 |
|
69 |
+
| No log | 2.8852 | 176 | 0.5137 | 0.8262 | 0.5660 | 0.8036 | 0.4369 |
|
70 |
+
| No log | 3.1475 | 192 | 0.4837 | 0.7935 | 0.6496 | 0.5802 | 0.7379 |
|
71 |
+
| No log | 3.4098 | 208 | 0.7301 | 0.7280 | 0.6197 | 0.4862 | 0.8544 |
|
72 |
+
| No log | 3.6721 | 224 | 0.6014 | 0.8413 | 0.6866 | 0.7041 | 0.6699 |
|
73 |
+
| No log | 3.9344 | 240 | 0.7912 | 0.7456 | 0.6481 | 0.5054 | 0.9029 |
|
74 |
+
| No log | 4.1967 | 256 | 0.6779 | 0.7834 | 0.6587 | 0.5570 | 0.8058 |
|
75 |
+
| No log | 4.4590 | 272 | 0.6352 | 0.8010 | 0.6749 | 0.5857 | 0.7961 |
|
76 |
+
| No log | 4.7213 | 288 | 0.9313 | 0.7229 | 0.6207 | 0.4813 | 0.8738 |
|
77 |
+
| No log | 4.9836 | 304 | 0.7459 | 0.7758 | 0.6454 | 0.5473 | 0.7864 |
|
78 |
+
| No log | 5.2459 | 320 | 0.6967 | 0.8186 | 0.6636 | 0.6396 | 0.6893 |
|
79 |
+
| No log | 5.5082 | 336 | 0.7340 | 0.8086 | 0.6780 | 0.6015 | 0.7767 |
|
80 |
+
| No log | 5.7705 | 352 | 0.9585 | 0.7506 | 0.6374 | 0.5118 | 0.8447 |
|
81 |
+
| No log | 6.0328 | 368 | 0.8556 | 0.8010 | 0.6749 | 0.5857 | 0.7961 |
|
82 |
+
| No log | 6.2951 | 384 | 1.0044 | 0.7758 | 0.6590 | 0.5443 | 0.8350 |
|
83 |
+
| No log | 6.5574 | 400 | 1.0174 | 0.7809 | 0.6641 | 0.5513 | 0.8350 |
|
84 |
+
| No log | 6.8197 | 416 | 0.8044 | 0.8111 | 0.6888 | 0.6014 | 0.8058 |
|
85 |
+
| No log | 7.0820 | 432 | 1.0973 | 0.7204 | 0.6159 | 0.4785 | 0.8641 |
|
86 |
+
| No log | 7.3443 | 448 | 0.9667 | 0.7758 | 0.6537 | 0.5455 | 0.8155 |
|
87 |
+
| No log | 7.6066 | 464 | 0.7502 | 0.8438 | 0.7130 | 0.6814 | 0.7476 |
|
88 |
+
| No log | 7.8689 | 480 | 1.0102 | 0.7733 | 0.6617 | 0.5399 | 0.8544 |
|
89 |
+
| No log | 8.1311 | 496 | 0.9457 | 0.7783 | 0.6589 | 0.5484 | 0.8252 |
|
90 |
+
| 0.2259 | 8.3934 | 512 | 0.9533 | 0.7834 | 0.656 | 0.5578 | 0.7961 |
|
91 |
+
| 0.2259 | 8.6557 | 528 | 1.0134 | 0.7783 | 0.6589 | 0.5484 | 0.8252 |
|
92 |
+
| 0.2259 | 8.9180 | 544 | 1.0594 | 0.7632 | 0.6466 | 0.5276 | 0.8350 |
|
93 |
+
| 0.2259 | 9.1803 | 560 | 1.0415 | 0.7708 | 0.6566 | 0.5370 | 0.8447 |
|
94 |
+
| 0.2259 | 9.4426 | 576 | 1.0485 | 0.7683 | 0.6515 | 0.5342 | 0.8350 |
|
95 |
+
| 0.2259 | 9.7049 | 592 | 1.0386 | 0.7708 | 0.6540 | 0.5375 | 0.8350 |
|
96 |
+
| 0.2259 | 9.9672 | 608 | 1.0294 | 0.7708 | 0.6486 | 0.5385 | 0.8155 |
|
97 |
+
|
98 |
+
|
99 |
+
### Framework versions
|
100 |
+
|
101 |
+
- Transformers 4.40.1
|
102 |
+
- Pytorch 2.2.1+cu121
|
103 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.1",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13e282f4b228be3af587dd89c081855b42aa352f5f623a4d2726e969bfc9570c
|
3 |
+
size 437958648
|
runs/May02_05-05-03_19135c3d3381/events.out.tfevents.1714626303.19135c3d3381.571.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41a987a7af4bd50c589659928e7f32c034fd9318c30aa425a3d59b0cd8cf1532
|
3 |
+
size 23157
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae98f203fe60e62489a3fefa72610d290a0f3f79257cb1f0ee8fdf40f6b32813
|
3 |
+
size 4984
|