End of training
Browse files- README.md +24 -6
- all_results.json +11 -11
- config.json +1 -0
- eval_results.json +7 -7
- train_results.json +4 -4
- trainer_state.json +4 -4
README.md
CHANGED
@@ -1,15 +1,33 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: bert-base-uncased
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
- f1
|
10 |
model-index:
|
11 |
- name: bert-base-cased-finetuned-sst2
|
12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# bert-base-cased-finetuned-sst2
|
19 |
|
20 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
-
|
23 |
-
-
|
24 |
-
- F1: 0.
|
25 |
-
-
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
language:
|
4 |
+
- en
|
5 |
license: apache-2.0
|
6 |
base_model: bert-base-uncased
|
7 |
tags:
|
8 |
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- glue
|
11 |
metrics:
|
12 |
- accuracy
|
13 |
- f1
|
14 |
model-index:
|
15 |
- name: bert-base-cased-finetuned-sst2
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
name: Text Classification
|
19 |
+
type: text-classification
|
20 |
+
dataset:
|
21 |
+
name: GLUE QQP
|
22 |
+
type: glue
|
23 |
+
args: qqp
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.910784071234232
|
28 |
+
- name: F1
|
29 |
+
type: f1
|
30 |
+
value: 0.8782365054180873
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# bert-base-cased-finetuned-sst2
|
37 |
|
38 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE QQP dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.3776
|
41 |
+
- Accuracy: 0.9108
|
42 |
+
- F1: 0.8782
|
43 |
+
- Combined Score: 0.8945
|
44 |
|
45 |
## Model description
|
46 |
|
all_results.json
CHANGED
@@ -1,17 +1,17 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_combined_score": 0.
|
5 |
-
"eval_f1": 0.
|
6 |
-
"eval_loss": 0.
|
7 |
-
"eval_runtime":
|
8 |
"eval_samples": 40430,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second":
|
11 |
"total_flos": 2.8719571514554368e+17,
|
12 |
-
"train_loss": 0.
|
13 |
-
"train_runtime":
|
14 |
"train_samples": 363846,
|
15 |
-
"train_samples_per_second":
|
16 |
-
"train_steps_per_second":
|
17 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.910784071234232,
|
4 |
+
"eval_combined_score": 0.8945102883261596,
|
5 |
+
"eval_f1": 0.8782365054180873,
|
6 |
+
"eval_loss": 0.3775930106639862,
|
7 |
+
"eval_runtime": 1120.9866,
|
8 |
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 36.066,
|
10 |
+
"eval_steps_per_second": 4.509,
|
11 |
"total_flos": 2.8719571514554368e+17,
|
12 |
+
"train_loss": 0.0,
|
13 |
+
"train_runtime": 0.002,
|
14 |
"train_samples": 363846,
|
15 |
+
"train_samples_per_second": 559413758.499,
|
16 |
+
"train_steps_per_second": 34964320.845
|
17 |
}
|
config.json
CHANGED
@@ -23,6 +23,7 @@
|
|
23 |
"num_hidden_layers": 12,
|
24 |
"pad_token_id": 0,
|
25 |
"position_embedding_type": "absolute",
|
|
|
26 |
"torch_dtype": "float32",
|
27 |
"transformers_version": "4.45.0.dev0",
|
28 |
"type_vocab_size": 2,
|
|
|
23 |
"num_hidden_layers": 12,
|
24 |
"pad_token_id": 0,
|
25 |
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "single_label_classification",
|
27 |
"torch_dtype": "float32",
|
28 |
"transformers_version": "4.45.0.dev0",
|
29 |
"type_vocab_size": 2,
|
eval_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_combined_score": 0.
|
5 |
-
"eval_f1": 0.
|
6 |
-
"eval_loss": 0.
|
7 |
-
"eval_runtime":
|
8 |
"eval_samples": 40430,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second":
|
11 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.910784071234232,
|
4 |
+
"eval_combined_score": 0.8945102883261596,
|
5 |
+
"eval_f1": 0.8782365054180873,
|
6 |
+
"eval_loss": 0.3775930106639862,
|
7 |
+
"eval_runtime": 1120.9866,
|
8 |
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 36.066,
|
10 |
+
"eval_steps_per_second": 4.509
|
11 |
}
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 2.8719571514554368e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 363846,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 2.8719571514554368e+17,
|
4 |
+
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.002,
|
6 |
"train_samples": 363846,
|
7 |
+
"train_samples_per_second": 559413758.499,
|
8 |
+
"train_steps_per_second": 34964320.845
|
9 |
}
|
trainer_state.json
CHANGED
@@ -66,10 +66,10 @@
|
|
66 |
"epoch": 3.0,
|
67 |
"step": 68223,
|
68 |
"total_flos": 2.8719571514554368e+17,
|
69 |
-
"train_loss": 0.
|
70 |
-
"train_runtime":
|
71 |
-
"train_samples_per_second":
|
72 |
-
"train_steps_per_second":
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 500,
|
|
|
66 |
"epoch": 3.0,
|
67 |
"step": 68223,
|
68 |
"total_flos": 2.8719571514554368e+17,
|
69 |
+
"train_loss": 0.0,
|
70 |
+
"train_runtime": 0.002,
|
71 |
+
"train_samples_per_second": 559413758.499,
|
72 |
+
"train_steps_per_second": 34964320.845
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 500,
|