Training in progress epoch 0
Browse files
README.md
CHANGED
@@ -17,11 +17,11 @@ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingf
|
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Train Loss: nan
|
19 |
- Validation Loss: nan
|
20 |
-
- Train Precision: 0.
|
21 |
-
- Train Recall: 0.
|
22 |
-
- Train F1: 0.
|
23 |
-
- Train Accuracy: 0.
|
24 |
-
- Epoch:
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -47,13 +47,12 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|
49 |
|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
|
50 |
-
| nan | nan | 0.
|
51 |
-
| nan | nan | 0.0864 | 0.2258 | 0.1249 | 0.1781 | 1 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
-
- Transformers 4.41.
|
57 |
- TensorFlow 2.15.0
|
58 |
- Datasets 2.19.2
|
59 |
- Tokenizers 0.19.1
|
|
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Train Loss: nan
|
19 |
- Validation Loss: nan
|
20 |
+
- Train Precision: 0.0275
|
21 |
+
- Train Recall: 0.0668
|
22 |
+
- Train F1: 0.0389
|
23 |
+
- Train Accuracy: 0.0566
|
24 |
+
- Epoch: 0
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
47 |
|
48 |
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|
49 |
|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
|
50 |
+
| nan | nan | 0.0275 | 0.0668 | 0.0389 | 0.0566 | 0 |
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
+
- Transformers 4.41.2
|
56 |
- TensorFlow 2.15.0
|
57 |
- Datasets 2.19.2
|
58 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -15,17 +15,19 @@
|
|
15 |
"3": "I-PERSON",
|
16 |
"4": "B-TRANSFER",
|
17 |
"5": "I-TRANSFER",
|
18 |
-
"6": "
|
|
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
"label2id": {
|
|
|
22 |
"B-ORGANISATION": 0,
|
23 |
"B-PERSON": 2,
|
24 |
"B-TRANSFER": 4,
|
25 |
"I-ORGANISATION": 1,
|
26 |
"I-PERSON": 3,
|
27 |
"I-TRANSFER": 5,
|
28 |
-
"O":
|
29 |
},
|
30 |
"max_position_embeddings": 512,
|
31 |
"model_type": "distilbert",
|
@@ -36,6 +38,6 @@
|
|
36 |
"seq_classif_dropout": 0.2,
|
37 |
"sinusoidal_pos_embds": false,
|
38 |
"tie_weights_": true,
|
39 |
-
"transformers_version": "4.41.
|
40 |
"vocab_size": 30522
|
41 |
}
|
|
|
15 |
"3": "I-PERSON",
|
16 |
"4": "B-TRANSFER",
|
17 |
"5": "I-TRANSFER",
|
18 |
+
"6": "B-IFSCCODE",
|
19 |
+
"7": "O"
|
20 |
},
|
21 |
"initializer_range": 0.02,
|
22 |
"label2id": {
|
23 |
+
"B-IFSCCODE": 6,
|
24 |
"B-ORGANISATION": 0,
|
25 |
"B-PERSON": 2,
|
26 |
"B-TRANSFER": 4,
|
27 |
"I-ORGANISATION": 1,
|
28 |
"I-PERSON": 3,
|
29 |
"I-TRANSFER": 5,
|
30 |
+
"O": 7
|
31 |
},
|
32 |
"max_position_embeddings": 512,
|
33 |
"model_type": "distilbert",
|
|
|
38 |
"seq_classif_dropout": 0.2,
|
39 |
"sinusoidal_pos_embds": false,
|
40 |
"tie_weights_": true,
|
41 |
+
"transformers_version": "4.41.2",
|
42 |
"vocab_size": 30522
|
43 |
}
|
logs/train/events.out.tfevents.1717654165.8a3e9ad428c6.2439.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7694139b8a7f03bacdfaba8bc44aefeaf318774f192845d7f48694f821f70a37
|
3 |
+
size 1647862
|
logs/validation/events.out.tfevents.1717654329.8a3e9ad428c6.2439.1.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a3959c5d4812ad79f50aa7de9236aaf6586d283b4f600aaad1dffa1f5dac86c
|
3 |
+
size 232
|
tf_model.h5
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:d6666690afd10369317dc7777c807260f5c88dccaad3eb42e5818f48f52518fb
|
3 |
+
size 265603344
|