End of training
Browse files- README.md +55 -55
- config.json +15 -17
- model.safetensors +2 -2
- runs/Jan22_11-04-37_e9a77ba5e600/events.out.tfevents.1705921485.e9a77ba5e600.245.1 +3 -0
- tokenizer_config.json +2 -2
- training_args.bin +1 -1
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# DIALOGUE_one
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 1.
|
| 24 |
-
- Precision: 0.
|
| 25 |
-
- Recall: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Accuracy: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -55,54 +55,54 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
-
| 1.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
|
| 107 |
|
| 108 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: distilbert-base-uncased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 18 |
|
| 19 |
# DIALOGUE_one
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.0122
|
| 24 |
+
- Precision: 0.8231
|
| 25 |
+
- Recall: 0.8158
|
| 26 |
+
- F1: 0.8165
|
| 27 |
+
- Accuracy: 0.8158
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 1.319 | 0.62 | 30 | 1.2219 | 0.6364 | 0.4868 | 0.4265 | 0.4868 |
|
| 59 |
+
| 0.9623 | 1.25 | 60 | 0.9164 | 0.6857 | 0.6842 | 0.6804 | 0.6842 |
|
| 60 |
+
| 0.6629 | 1.88 | 90 | 0.6595 | 0.7604 | 0.7237 | 0.7224 | 0.7237 |
|
| 61 |
+
| 0.5046 | 2.5 | 120 | 0.5740 | 0.7927 | 0.7763 | 0.7760 | 0.7763 |
|
| 62 |
+
| 0.3602 | 3.12 | 150 | 0.6172 | 0.7636 | 0.7632 | 0.7621 | 0.7632 |
|
| 63 |
+
| 0.2774 | 3.75 | 180 | 0.6772 | 0.7717 | 0.7632 | 0.7645 | 0.7632 |
|
| 64 |
+
| 0.3058 | 4.38 | 210 | 0.6732 | 0.7974 | 0.7632 | 0.7632 | 0.7632 |
|
| 65 |
+
| 0.2064 | 5.0 | 240 | 0.7566 | 0.7947 | 0.7632 | 0.7534 | 0.7632 |
|
| 66 |
+
| 0.1447 | 5.62 | 270 | 0.6615 | 0.7908 | 0.7895 | 0.7892 | 0.7895 |
|
| 67 |
+
| 0.1764 | 6.25 | 300 | 0.6646 | 0.7908 | 0.7895 | 0.7892 | 0.7895 |
|
| 68 |
+
| 0.1059 | 6.88 | 330 | 0.6377 | 0.8522 | 0.8421 | 0.8417 | 0.8421 |
|
| 69 |
+
| 0.0871 | 7.5 | 360 | 0.6075 | 0.8311 | 0.8289 | 0.8286 | 0.8289 |
|
| 70 |
+
| 0.0861 | 8.12 | 390 | 0.6845 | 0.8484 | 0.8421 | 0.8410 | 0.8421 |
|
| 71 |
+
| 0.0693 | 8.75 | 420 | 0.6484 | 0.8598 | 0.8553 | 0.8553 | 0.8553 |
|
| 72 |
+
| 0.0481 | 9.38 | 450 | 0.6957 | 0.8469 | 0.8421 | 0.8419 | 0.8421 |
|
| 73 |
+
| 0.0405 | 10.0 | 480 | 0.7195 | 0.8598 | 0.8553 | 0.8553 | 0.8553 |
|
| 74 |
+
| 0.039 | 10.62 | 510 | 0.8293 | 0.8548 | 0.8421 | 0.8442 | 0.8421 |
|
| 75 |
+
| 0.0441 | 11.25 | 540 | 0.7293 | 0.8598 | 0.8553 | 0.8553 | 0.8553 |
|
| 76 |
+
| 0.0203 | 11.88 | 570 | 0.8127 | 0.8530 | 0.8421 | 0.8437 | 0.8421 |
|
| 77 |
+
| 0.0207 | 12.5 | 600 | 0.8381 | 0.8482 | 0.8421 | 0.8415 | 0.8421 |
|
| 78 |
+
| 0.0183 | 13.12 | 630 | 0.7808 | 0.8598 | 0.8553 | 0.8553 | 0.8553 |
|
| 79 |
+
| 0.0184 | 13.75 | 660 | 0.8203 | 0.8486 | 0.8421 | 0.8414 | 0.8421 |
|
| 80 |
+
| 0.0178 | 14.38 | 690 | 0.8099 | 0.8598 | 0.8553 | 0.8553 | 0.8553 |
|
| 81 |
+
| 0.009 | 15.0 | 720 | 0.8476 | 0.8469 | 0.8421 | 0.8425 | 0.8421 |
|
| 82 |
+
| 0.0029 | 15.62 | 750 | 0.8834 | 0.8375 | 0.8289 | 0.8291 | 0.8289 |
|
| 83 |
+
| 0.0126 | 16.25 | 780 | 0.9205 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 84 |
+
| 0.0026 | 16.88 | 810 | 0.9224 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 85 |
+
| 0.0024 | 17.5 | 840 | 0.8937 | 0.8469 | 0.8421 | 0.8425 | 0.8421 |
|
| 86 |
+
| 0.0029 | 18.12 | 870 | 1.0012 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 87 |
+
| 0.0021 | 18.75 | 900 | 0.9384 | 0.7969 | 0.7895 | 0.7912 | 0.7895 |
|
| 88 |
+
| 0.0019 | 19.38 | 930 | 0.9420 | 0.8097 | 0.8026 | 0.8039 | 0.8026 |
|
| 89 |
+
| 0.0019 | 20.0 | 960 | 0.9681 | 0.7969 | 0.7895 | 0.7912 | 0.7895 |
|
| 90 |
+
| 0.0018 | 20.62 | 990 | 0.9838 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 91 |
+
| 0.0016 | 21.25 | 1020 | 0.9798 | 0.7969 | 0.7895 | 0.7912 | 0.7895 |
|
| 92 |
+
| 0.0016 | 21.88 | 1050 | 0.9765 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 93 |
+
| 0.0014 | 22.5 | 1080 | 0.9906 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 94 |
+
| 0.0014 | 23.12 | 1110 | 0.9857 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 95 |
+
| 0.0015 | 23.75 | 1140 | 1.0050 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 96 |
+
| 0.0013 | 24.38 | 1170 | 1.0049 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 97 |
+
| 0.0013 | 25.0 | 1200 | 1.0078 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 98 |
+
| 0.0013 | 25.62 | 1230 | 1.0083 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 99 |
+
| 0.0012 | 26.25 | 1260 | 1.0051 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 100 |
+
| 0.0013 | 26.88 | 1290 | 1.0121 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 101 |
+
| 0.0012 | 27.5 | 1320 | 1.0127 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 102 |
+
| 0.0012 | 28.12 | 1350 | 1.0134 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 103 |
+
| 0.0012 | 28.75 | 1380 | 1.0119 | 0.8347 | 0.8289 | 0.8296 | 0.8289 |
|
| 104 |
+
| 0.0012 | 29.38 | 1410 | 1.0122 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 105 |
+
| 0.0012 | 30.0 | 1440 | 1.0122 | 0.8231 | 0.8158 | 0.8165 | 0.8158 |
|
| 106 |
|
| 107 |
|
| 108 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,14 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"hidden_dropout_prob": 0.1,
|
| 11 |
-
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
"0": "Hospital-Inform",
|
| 14 |
"1": "Hospital-Request",
|
|
@@ -16,24 +15,23 @@
|
|
| 16 |
"3": "general-thank"
|
| 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 |
"LABEL_3": 3
|
| 25 |
},
|
| 26 |
-
"layer_norm_eps": 1e-12,
|
| 27 |
"max_position_embeddings": 512,
|
| 28 |
-
"model_type": "
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
"pad_token_id": 0,
|
| 32 |
-
"position_embedding_type": "absolute",
|
| 33 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
"transformers_version": "4.36.2",
|
| 36 |
-
"
|
| 37 |
-
"use_cache": true,
|
| 38 |
-
"vocab_size": 28996
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
|
|
|
|
|
|
| 11 |
"id2label": {
|
| 12 |
"0": "Hospital-Inform",
|
| 13 |
"1": "Hospital-Request",
|
|
|
|
| 15 |
"3": "general-thank"
|
| 16 |
},
|
| 17 |
"initializer_range": 0.02,
|
|
|
|
| 18 |
"label2id": {
|
| 19 |
"LABEL_0": 0,
|
| 20 |
"LABEL_1": 1,
|
| 21 |
"LABEL_2": 2,
|
| 22 |
"LABEL_3": 3
|
| 23 |
},
|
|
|
|
| 24 |
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "distilbert",
|
| 26 |
+
"n_heads": 12,
|
| 27 |
+
"n_layers": 6,
|
| 28 |
"pad_token_id": 0,
|
|
|
|
| 29 |
"problem_type": "single_label_classification",
|
| 30 |
+
"qa_dropout": 0.1,
|
| 31 |
+
"seq_classif_dropout": 0.2,
|
| 32 |
+
"sinusoidal_pos_embds": false,
|
| 33 |
+
"tie_weights_": true,
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
"transformers_version": "4.36.2",
|
| 36 |
+
"vocab_size": 30522
|
|
|
|
|
|
|
| 37 |
}
|
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:b2757aaa3df86b4f95a544bb0d0fd3a1717cee110c447139a5b84272ce0de25c
|
| 3 |
+
size 267838720
|
runs/Jan22_11-04-37_e9a77ba5e600/events.out.tfevents.1705921485.e9a77ba5e600.245.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f891e93610c46d62b82aeea4089c50009dda7845a32a36e1c34d31479c56d684
|
| 3 |
+
size 34933
|
tokenizer_config.json
CHANGED
|
@@ -44,7 +44,7 @@
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
-
"do_lower_case":
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
"never_split": null,
|
|
@@ -52,6 +52,6 @@
|
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
-
"tokenizer_class": "
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
"never_split": null,
|
|
|
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b24232bd4e67118b51e017ddf00d540d493c23deae8feb6183ca89139478a5b
|
| 3 |
size 4664
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|