Training complete
Browse files
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
base_model: camembert-base
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -18,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# relatives_psr_seq-cbert_finetuned
|
20 |
|
21 |
-
This model is a fine-tuned version of [camembert-
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -55,11 +54,11 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
-
| No log | 1.0 | 49 |
|
59 |
-
| No log | 2.0 | 98 | 0.
|
60 |
-
| No log | 3.0 | 147 | 0.
|
61 |
-
| No log | 4.0 | 196 | 0.
|
62 |
-
| No log | 5.0 | 245 | 0.
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: camembert/camembert-large
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
metrics:
|
|
|
17 |
|
18 |
# relatives_psr_seq-cbert_finetuned
|
19 |
|
20 |
+
This model is a fine-tuned version of [camembert/camembert-large](https://huggingface.co/camembert/camembert-large) on an unknown dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 0.6317
|
23 |
+
- Precision: 0.7005
|
24 |
+
- Recall: 0.2671
|
25 |
+
- F1: 0.2695
|
26 |
+
- Accuracy: 0.7798
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| No log | 1.0 | 49 | 0.7987 | 0.9511 | 0.2 | 0.1722 | 0.7557 |
|
58 |
+
| No log | 2.0 | 98 | 0.7748 | 0.8306 | 0.2107 | 0.1935 | 0.7590 |
|
59 |
+
| No log | 3.0 | 147 | 0.6992 | 0.8346 | 0.2178 | 0.2051 | 0.7617 |
|
60 |
+
| No log | 4.0 | 196 | 0.6507 | 0.6659 | 0.2580 | 0.2513 | 0.7742 |
|
61 |
+
| No log | 5.0 | 245 | 0.6317 | 0.7005 | 0.2671 | 0.2695 | 0.7798 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
config.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "camembert-
|
3 |
"architectures": [
|
4 |
"CamembertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id":
|
8 |
"classifier_dropout": null,
|
9 |
-
"eos_token_id":
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0",
|
15 |
"1": "LABEL_1",
|
@@ -20,7 +20,7 @@
|
|
20 |
"6": "LABEL_6"
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
-
"intermediate_size":
|
24 |
"label2id": {
|
25 |
"LABEL_0": 0,
|
26 |
"LABEL_1": 1,
|
@@ -33,8 +33,8 @@
|
|
33 |
"layer_norm_eps": 1e-05,
|
34 |
"max_position_embeddings": 514,
|
35 |
"model_type": "camembert",
|
36 |
-
"num_attention_heads":
|
37 |
-
"num_hidden_layers":
|
38 |
"output_past": true,
|
39 |
"pad_token_id": 1,
|
40 |
"position_embedding_type": "absolute",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "camembert/camembert-large",
|
3 |
"architectures": [
|
4 |
"CamembertForTokenClassification"
|
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": 1024,
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0",
|
15 |
"1": "LABEL_1",
|
|
|
20 |
"6": "LABEL_6"
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 4096,
|
24 |
"label2id": {
|
25 |
"LABEL_0": 0,
|
26 |
"LABEL_1": 1,
|
|
|
33 |
"layer_norm_eps": 1e-05,
|
34 |
"max_position_embeddings": 514,
|
35 |
"model_type": "camembert",
|
36 |
+
"num_attention_heads": 16,
|
37 |
+
"num_hidden_layers": 24,
|
38 |
"output_past": true,
|
39 |
"pad_token_id": 1,
|
40 |
"position_embedding_type": "absolute",
|
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 sha256:088bef76544e9affdbf114cb35b5b2b95e0312a9d5b3a4a4f3f2d080f85d9673
|
3 |
+
size 1342524276
|
runs/Jun04_21-58-41_8aee68de80dd/events.out.tfevents.1717538330.8aee68de80dd.2906.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1d7d82d1323ad2262487d07d14f718d1d65b4668486d40bc137f6a696fdc3aa
|
3 |
+
size 5149
|
runs/Jun04_21-59-56_8aee68de80dd/events.out.tfevents.1717538404.8aee68de80dd.2906.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73fb4d9de76754d6a6a96266c9c815caff0dc9e6417ed9241b2aa42bcedd1964
|
3 |
+
size 7845
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24899b86068cbd3a8de60c82fd114ba4ff49f6365c8aa96729b840ffe2ae6325
|
3 |
size 5112
|