Training complete
Browse files- README.md +12 -12
- config.json +7 -8
- model.safetensors +2 -2
- runs/Jun04_22-42-32_dd4455f1defd/events.out.tfevents.1717540964.dd4455f1defd.1891.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: camembert/camembert-
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
metrics:
|
@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# relatives_psr-cbert_finetuned
|
19 |
|
20 |
-
This model is a fine-tuned version of [camembert/camembert-
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss: 0.
|
23 |
-
- Precision: 0.
|
24 |
-
- Recall: 0.
|
25 |
-
- F1: 0.
|
26 |
-
- Accuracy: 0.
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -54,11 +54,11 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
-
| No log | 1.0 | 49 | 0.
|
58 |
-
| No log | 2.0 | 98 | 0.
|
59 |
-
| No log | 3.0 | 147 | 0.
|
60 |
-
| No log | 4.0 | 196 | 0.
|
61 |
-
| No log | 5.0 | 245 | 0.
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: camembert/camembert-large
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
metrics:
|
|
|
17 |
|
18 |
# relatives_psr-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: 0.0532
|
23 |
+
- Precision: 0.6127
|
24 |
+
- Recall: 0.5628
|
25 |
+
- F1: 0.5835
|
26 |
+
- Accuracy: 0.9789
|
27 |
|
28 |
## Model description
|
29 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
57 |
+
| No log | 1.0 | 49 | 0.1420 | 0.9906 | 0.3333 | 0.3286 | 0.9718 |
|
58 |
+
| No log | 2.0 | 98 | 0.0846 | 0.7921 | 0.6010 | 0.5037 | 0.9733 |
|
59 |
+
| No log | 3.0 | 147 | 0.0590 | 0.6117 | 0.5888 | 0.5891 | 0.9782 |
|
60 |
+
| No log | 4.0 | 196 | 0.0555 | 0.6077 | 0.6158 | 0.5861 | 0.9794 |
|
61 |
+
| No log | 5.0 | 245 | 0.0532 | 0.6127 | 0.5628 | 0.5835 | 0.9789 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "camembert/camembert-
|
3 |
"architectures": [
|
4 |
"CamembertForTokenClassification"
|
5 |
],
|
@@ -7,10 +7,9 @@
|
|
7 |
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
-
"eos_token_ids": 0,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout_prob": 0.1,
|
13 |
-
"hidden_size":
|
14 |
"id2label": {
|
15 |
"0": "O",
|
16 |
"1": "DET",
|
@@ -18,7 +17,7 @@
|
|
18 |
"3": "AMBIGUE"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
-
"intermediate_size":
|
22 |
"label2id": {
|
23 |
"AMBIGUE": 3,
|
24 |
"APPO": 2,
|
@@ -28,14 +27,14 @@
|
|
28 |
"layer_norm_eps": 1e-05,
|
29 |
"max_position_embeddings": 514,
|
30 |
"model_type": "camembert",
|
31 |
-
"num_attention_heads":
|
32 |
-
"num_hidden_layers":
|
33 |
"output_past": true,
|
34 |
-
"pad_token_id":
|
35 |
"position_embedding_type": "absolute",
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.41.2",
|
38 |
"type_vocab_size": 1,
|
39 |
"use_cache": true,
|
40 |
-
"vocab_size":
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "camembert/camembert-large",
|
3 |
"architectures": [
|
4 |
"CamembertForTokenClassification"
|
5 |
],
|
|
|
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": "O",
|
15 |
"1": "DET",
|
|
|
17 |
"3": "AMBIGUE"
|
18 |
},
|
19 |
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 4096,
|
21 |
"label2id": {
|
22 |
"AMBIGUE": 3,
|
23 |
"APPO": 2,
|
|
|
27 |
"layer_norm_eps": 1e-05,
|
28 |
"max_position_embeddings": 514,
|
29 |
"model_type": "camembert",
|
30 |
+
"num_attention_heads": 16,
|
31 |
+
"num_hidden_layers": 24,
|
32 |
"output_past": true,
|
33 |
+
"pad_token_id": 1,
|
34 |
"position_embedding_type": "absolute",
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.41.2",
|
37 |
"type_vocab_size": 1,
|
38 |
"use_cache": true,
|
39 |
+
"vocab_size": 100000
|
40 |
}
|
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:be2a36d6f4db76b657b6d145cd7fc40e9289789b017ffa945fef7c78a80e811a
|
3 |
+
size 1621019680
|
runs/Jun04_22-42-32_dd4455f1defd/events.out.tfevents.1717540964.dd4455f1defd.1891.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91997c716a859e7a2eece1818afcf758e6958fdade7c9508fcf50e7b00434be2
|
3 |
+
size 7694
|
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 sha256:1bb43257ef2c6ef3f820ebe04c3bdfa572be0b6a428055080fbcaaa588f00480
|
3 |
size 5112
|