gentilrenard
commited on
Commit
•
1eecfc5
1
Parent(s):
fa40301
multi-e5-base_lmd-comments_v1
Browse files- README.md +110 -0
- config.json +39 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: intfloat/multilingual-e5-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: multi-e5-base_lmd-comments_v1
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# multi-e5-base_lmd-comments_v1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6013
|
22 |
+
- F1: 0.8539
|
23 |
+
- Accuracy: 0.8505
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 8
|
44 |
+
- eval_batch_size: 8
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 2
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
|
55 |
+
| 1.0859 | 0.04 | 100 | 1.0531 | 0.6574 | 0.6716 |
|
56 |
+
| 0.9993 | 0.08 | 200 | 0.8669 | 0.7260 | 0.7266 |
|
57 |
+
| 0.7514 | 0.12 | 300 | 0.7077 | 0.7582 | 0.7699 |
|
58 |
+
| 0.6928 | 0.17 | 400 | 0.8825 | 0.7521 | 0.7856 |
|
59 |
+
| 0.6349 | 0.21 | 500 | 0.6178 | 0.7947 | 0.7778 |
|
60 |
+
| 0.5939 | 0.25 | 600 | 0.6509 | 0.7977 | 0.7847 |
|
61 |
+
| 0.6461 | 0.29 | 700 | 0.5820 | 0.7951 | 0.7778 |
|
62 |
+
| 0.5346 | 0.33 | 800 | 0.7509 | 0.8022 | 0.8014 |
|
63 |
+
| 0.622 | 0.37 | 900 | 0.8165 | 0.7902 | 0.7935 |
|
64 |
+
| 0.6124 | 0.41 | 1000 | 0.6754 | 0.7885 | 0.7788 |
|
65 |
+
| 0.6285 | 0.46 | 1100 | 0.5179 | 0.8284 | 0.8210 |
|
66 |
+
| 0.5838 | 0.5 | 1200 | 0.5335 | 0.8149 | 0.8024 |
|
67 |
+
| 0.6116 | 0.54 | 1300 | 0.5584 | 0.8301 | 0.8240 |
|
68 |
+
| 0.5578 | 0.58 | 1400 | 0.6135 | 0.7670 | 0.7404 |
|
69 |
+
| 0.534 | 0.62 | 1500 | 0.6407 | 0.8153 | 0.8063 |
|
70 |
+
| 0.5343 | 0.66 | 1600 | 0.5500 | 0.8381 | 0.8279 |
|
71 |
+
| 0.5575 | 0.7 | 1700 | 0.6355 | 0.8170 | 0.8102 |
|
72 |
+
| 0.5961 | 0.75 | 1800 | 0.5465 | 0.8450 | 0.8446 |
|
73 |
+
| 0.5623 | 0.79 | 1900 | 0.5787 | 0.7875 | 0.7719 |
|
74 |
+
| 0.5436 | 0.83 | 2000 | 0.6035 | 0.8494 | 0.8525 |
|
75 |
+
| 0.5662 | 0.87 | 2100 | 0.4979 | 0.8210 | 0.8083 |
|
76 |
+
| 0.5227 | 0.91 | 2200 | 0.6157 | 0.8320 | 0.8328 |
|
77 |
+
| 0.557 | 0.95 | 2300 | 0.5721 | 0.8488 | 0.8505 |
|
78 |
+
| 0.5369 | 0.99 | 2400 | 0.5191 | 0.8222 | 0.8112 |
|
79 |
+
| 0.4846 | 1.04 | 2500 | 0.4966 | 0.8304 | 0.8201 |
|
80 |
+
| 0.4094 | 1.08 | 2600 | 0.6385 | 0.8368 | 0.8328 |
|
81 |
+
| 0.4045 | 1.12 | 2700 | 0.6165 | 0.8476 | 0.8456 |
|
82 |
+
| 0.4835 | 1.16 | 2800 | 0.6792 | 0.8536 | 0.8535 |
|
83 |
+
| 0.3949 | 1.2 | 2900 | 0.7400 | 0.8559 | 0.8574 |
|
84 |
+
| 0.4157 | 1.24 | 3000 | 0.6305 | 0.8319 | 0.8279 |
|
85 |
+
| 0.4638 | 1.28 | 3100 | 0.5507 | 0.8438 | 0.8387 |
|
86 |
+
| 0.4438 | 1.33 | 3200 | 0.5208 | 0.8426 | 0.8348 |
|
87 |
+
| 0.4224 | 1.37 | 3300 | 0.6534 | 0.8330 | 0.8279 |
|
88 |
+
| 0.4703 | 1.41 | 3400 | 0.6486 | 0.8456 | 0.8427 |
|
89 |
+
| 0.4912 | 1.45 | 3500 | 0.6370 | 0.8544 | 0.8505 |
|
90 |
+
| 0.4396 | 1.49 | 3600 | 0.6866 | 0.8520 | 0.8505 |
|
91 |
+
| 0.437 | 1.53 | 3700 | 0.6436 | 0.8536 | 0.8505 |
|
92 |
+
| 0.3993 | 1.57 | 3800 | 0.6910 | 0.8517 | 0.8515 |
|
93 |
+
| 0.3712 | 1.62 | 3900 | 0.6449 | 0.8588 | 0.8564 |
|
94 |
+
| 0.4156 | 1.66 | 4000 | 0.6478 | 0.8560 | 0.8535 |
|
95 |
+
| 0.4564 | 1.7 | 4100 | 0.6475 | 0.8577 | 0.8555 |
|
96 |
+
| 0.4273 | 1.74 | 4200 | 0.6044 | 0.8456 | 0.8397 |
|
97 |
+
| 0.4284 | 1.78 | 4300 | 0.6219 | 0.8499 | 0.8466 |
|
98 |
+
| 0.4466 | 1.82 | 4400 | 0.5871 | 0.8535 | 0.8496 |
|
99 |
+
| 0.3932 | 1.86 | 4500 | 0.5940 | 0.8551 | 0.8515 |
|
100 |
+
| 0.3848 | 1.91 | 4600 | 0.5995 | 0.8559 | 0.8525 |
|
101 |
+
| 0.4337 | 1.95 | 4700 | 0.6023 | 0.8539 | 0.8505 |
|
102 |
+
| 0.3991 | 1.99 | 4800 | 0.6013 | 0.8539 | 0.8505 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- Transformers 4.38.1
|
108 |
+
- Pytorch 2.1.2
|
109 |
+
- Datasets 2.1.0
|
110 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "intfloat/multilingual-e5-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-05,
|
26 |
+
"max_position_embeddings": 514,
|
27 |
+
"model_type": "xlm-roberta",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"output_past": true,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.38.1",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250002
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6364629546595aa3154bf00cad69cdfd0695fe06f0f6e72c3234fa050e97e6d
|
3 |
+
size 1112208084
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5baf6e7361b584742f64641e8a8cbf2b3e1ce1ca4c06a115bfdde6113d7e11a4
|
3 |
+
size 4856
|