End of training
Browse files
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -49,31 +49,21 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
| No log | 0.01 | 50 | 0.
|
53 |
-
| No log | 0.02 | 100 | 0.
|
54 |
-
| No log | 0.03 | 150 | 0.
|
55 |
-
| No log | 0.04 | 200 | 0.
|
56 |
-
| No log | 0.05 | 250 | 0.
|
57 |
-
| No log | 0.06 | 300 | 0.
|
58 |
-
| No log | 0.07 | 350 | 0.
|
59 |
-
| No log | 0.08 | 400 | 0.
|
60 |
-
| No log | 0.09 | 450 | 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.6127 | 0.16 | 800 | 0.1944 | 0.95 |
|
68 |
-
| 0.6127 | 0.17 | 850 | 0.1942 | 0.95 |
|
69 |
-
| 0.6127 | 0.18 | 900 | 0.1938 | 0.95 |
|
70 |
-
| 0.6127 | 0.19 | 950 | 0.1950 | 0.95 |
|
71 |
-
| 0.2388 | 0.2 | 1000 | 0.1943 | 0.95 |
|
72 |
-
| 0.2388 | 0.2 | 1050 | 0.1939 | 0.95 |
|
73 |
-
| 0.2388 | 0.21 | 1100 | 0.1939 | 0.95 |
|
74 |
-
| 0.2388 | 0.22 | 1150 | 0.1928 | 0.95 |
|
75 |
-
| 0.2388 | 0.23 | 1200 | 0.1937 | 0.95 |
|
76 |
-
| 0.2388 | 0.24 | 1250 | 0.1958 | 0.95 |
|
77 |
|
78 |
|
79 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2385
|
21 |
+
- Accuracy: 0.93
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 0.01 | 50 | 0.6925 | 0.45 |
|
53 |
+
| No log | 0.02 | 100 | 0.6758 | 0.62 |
|
54 |
+
| No log | 0.03 | 150 | 0.6384 | 0.66 |
|
55 |
+
| No log | 0.04 | 200 | 0.6241 | 0.66 |
|
56 |
+
| No log | 0.05 | 250 | 0.6081 | 0.66 |
|
57 |
+
| No log | 0.06 | 300 | 0.5643 | 0.87 |
|
58 |
+
| No log | 0.07 | 350 | 0.5200 | 0.87 |
|
59 |
+
| No log | 0.08 | 400 | 0.4989 | 0.81 |
|
60 |
+
| No log | 0.09 | 450 | 0.4370 | 0.87 |
|
61 |
+
| 0.6058 | 0.1 | 500 | 0.3298 | 0.94 |
|
62 |
+
| 0.6058 | 0.11 | 550 | 0.2876 | 0.94 |
|
63 |
+
| 0.6058 | 0.12 | 600 | 0.2701 | 0.93 |
|
64 |
+
| 0.6058 | 0.13 | 650 | 0.2533 | 0.93 |
|
65 |
+
| 0.6058 | 0.14 | 700 | 0.2452 | 0.93 |
|
66 |
+
| 0.6058 | 0.15 | 750 | 0.2385 | 0.93 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
|
69 |
### Framework versions
|
config.json
CHANGED
@@ -1,20 +1,15 @@
|
|
1 |
{
|
2 |
"_name_or_path": "prajjwal1/bert-tiny",
|
|
|
|
|
|
|
3 |
"attention_probs_dropout_prob": 0.1,
|
4 |
"classifier_dropout": null,
|
5 |
"hidden_act": "gelu",
|
6 |
"hidden_dropout_prob": 0.1,
|
7 |
"hidden_size": 128,
|
8 |
-
"id2label": {
|
9 |
-
"0": "Taken",
|
10 |
-
"1": "Not Taken"
|
11 |
-
},
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 512,
|
14 |
-
"label2id": {
|
15 |
-
"Not Taken": 1,
|
16 |
-
"Taken": 0
|
17 |
-
},
|
18 |
"layer_norm_eps": 1e-12,
|
19 |
"max_position_embeddings": 512,
|
20 |
"model_type": "bert",
|
@@ -22,6 +17,8 @@
|
|
22 |
"num_hidden_layers": 2,
|
23 |
"pad_token_id": 0,
|
24 |
"position_embedding_type": "absolute",
|
|
|
|
|
25 |
"transformers_version": "4.35.2",
|
26 |
"type_vocab_size": 2,
|
27 |
"use_cache": true,
|
|
|
1 |
{
|
2 |
"_name_or_path": "prajjwal1/bert-tiny",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
"hidden_size": 128,
|
|
|
|
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 512,
|
|
|
|
|
|
|
|
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
"max_position_embeddings": 512,
|
15 |
"model_type": "bert",
|
|
|
17 |
"num_hidden_layers": 2,
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
+
"problem_type": "single_label_classification",
|
21 |
+
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.35.2",
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
events.out.tfevents.1701159530.d13e323c9852.424.0
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:c5cc4443f3978aaa22dd720e6d78f8494179b5459cd804b1a2d6fe3acf42e97e
|
3 |
+
size 748
|
runs/Nov28_08-18-50_d13e323c9852/events.out.tfevents.1701159530.d13e323c9852.424.1
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 sha256:0384ce533e1b9f9e751e4007c50fda49a7a07c724efab30411b93563400ae65f
|
3 |
+
size 9440
|
runs/Nov28_08-18-50_d13e323c9852/events.out.tfevents.1701159530.d13e323c9852.424.2
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 sha256:64f1a5c765177e6a996dc81b529c6ba17e63b2445072dd5e741f9822719311ee
|
3 |
+
size 9440
|