End of training
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: distilbert-base-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# test_trainer
|
18 |
|
19 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
-
- F1: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased-finetuned-sst-2-english
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
|
|
16 |
|
17 |
# test_trainer
|
18 |
|
19 |
+
This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5228
|
22 |
+
- Accuracy: 0.912
|
23 |
+
- F1: 0.9426
|
24 |
|
25 |
## Model description
|
26 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
@@ -7,12 +7,22 @@
|
|
7 |
"attention_dropout": 0.1,
|
8 |
"dim": 768,
|
9 |
"dropout": 0.1,
|
|
|
10 |
"hidden_dim": 3072,
|
|
|
|
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
12 |
"max_position_embeddings": 512,
|
13 |
"model_type": "distilbert",
|
14 |
"n_heads": 12,
|
15 |
"n_layers": 6,
|
|
|
16 |
"pad_token_id": 0,
|
17 |
"problem_type": "single_label_classification",
|
18 |
"qa_dropout": 0.1,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
7 |
"attention_dropout": 0.1,
|
8 |
"dim": 768,
|
9 |
"dropout": 0.1,
|
10 |
+
"finetuning_task": "sst-2",
|
11 |
"hidden_dim": 3072,
|
12 |
+
"id2label": {
|
13 |
+
"0": "NEGATIVE",
|
14 |
+
"1": "POSITIVE"
|
15 |
+
},
|
16 |
"initializer_range": 0.02,
|
17 |
+
"label2id": {
|
18 |
+
"NEGATIVE": 0,
|
19 |
+
"POSITIVE": 1
|
20 |
+
},
|
21 |
"max_position_embeddings": 512,
|
22 |
"model_type": "distilbert",
|
23 |
"n_heads": 12,
|
24 |
"n_layers": 6,
|
25 |
+
"output_past": true,
|
26 |
"pad_token_id": 0,
|
27 |
"problem_type": "single_label_classification",
|
28 |
"qa_dropout": 0.1,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50d6d02d800ab640ba5d4022ea411cdbc9d1a8f43c868611d36ed66c8a06b491
|
3 |
size 267832560
|
runs/Jun16_20-49-39_80beb8947a73/events.out.tfevents.1718570979.80beb8947a73.4231.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e71f0887a35a9811046330ddfdae6aea8c427d5fe9b8be3d8d4cb862e87be518
|
3 |
+
size 5870
|
runs/Jun16_20-49-39_80beb8947a73/events.out.tfevents.1718571373.80beb8947a73.4231.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dad4dc380121e908e520430b435886ce4e13d09fd0749b7cb10c6e99b3a7c902
|
3 |
+
size 457
|
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:f46468a2c330dc2bdf0844a6d121132bb352e75877e62826c86c84ea5feaebfd
|
3 |
size 5112
|