sibstrider
commited on
Commit
•
363f301
1
Parent(s):
ea8c9a4
Training in progress, epoch 1
Browse files- README.md +9 -9
- config.json +1 -1
- model.safetensors +1 -1
- run-0/checkpoint-2138/config.json +25 -0
- run-0/checkpoint-2138/model.safetensors +3 -0
- run-0/checkpoint-2138/optimizer.pt +3 -0
- run-0/checkpoint-2138/rng_state.pth +3 -0
- run-0/checkpoint-2138/scheduler.pt +3 -0
- run-0/checkpoint-2138/special_tokens_map.json +7 -0
- run-0/checkpoint-2138/tokenizer.json +0 -0
- run-0/checkpoint-2138/tokenizer_config.json +55 -0
- run-0/checkpoint-2138/trainer_state.json +59 -0
- run-0/checkpoint-2138/training_args.bin +3 -0
- run-0/checkpoint-2138/vocab.txt +0 -0
- runs/Jan13_22-34-04_DESKTOP-RFEED41/events.out.tfevents.1705163845.DESKTOP-RFEED41.28156.2 +3 -0
- training_args.bin +2 -2
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Matthews Correlation: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -49,16 +49,16 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
-
- Transformers 4.
|
62 |
-
- Pytorch 2.1.
|
63 |
- Datasets 2.16.1
|
64 |
- Tokenizers 0.15.0
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8175
|
21 |
+
- Matthews Correlation: 0.5370
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
52 |
+
| 0.5266 | 1.0 | 535 | 0.4721 | 0.4559 |
|
53 |
+
| 0.3562 | 2.0 | 1070 | 0.5916 | 0.4358 |
|
54 |
+
| 0.2416 | 3.0 | 1605 | 0.6296 | 0.5182 |
|
55 |
+
| 0.1692 | 4.0 | 2140 | 0.7156 | 0.5330 |
|
56 |
+
| 0.1217 | 5.0 | 2675 | 0.8175 | 0.5370 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
+
- Transformers 4.36.2
|
62 |
+
- Pytorch 2.1.2+cpu
|
63 |
- Datasets 2.16.1
|
64 |
- Tokenizers 0.15.0
|
config.json
CHANGED
@@ -20,6 +20,6 @@
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 30522
|
25 |
}
|
|
|
20 |
"sinusoidal_pos_embds": false,
|
21 |
"tie_weights_": true,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
"vocab_size": 30522
|
25 |
}
|
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:e049a0bb30da1849282ec0d2d5030a6189c285cb614cefd272f6252ffac17172
|
3 |
size 267832560
|
run-0/checkpoint-2138/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
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,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-2138/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e049a0bb30da1849282ec0d2d5030a6189c285cb614cefd272f6252ffac17172
|
3 |
+
size 267832560
|
run-0/checkpoint-2138/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28659f16d8875444a14085d9671fea888c072edb33ff884ea54315f97884bbc4
|
3 |
+
size 535724410
|
run-0/checkpoint-2138/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8c3387534496fab8b68adeb2f30252d96ae79aa9d5aebd9780ccc480b90db8b
|
3 |
+
size 13990
|
run-0/checkpoint-2138/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ec3347ce4d2019db9e253f437042b98d81e32609c1b9b62dba3b2fcda78205
|
3 |
+
size 1064
|
run-0/checkpoint-2138/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-0/checkpoint-2138/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-2138/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-0/checkpoint-2138/trainer_state.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.38219189241772933,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola\\run-0\\checkpoint-2138",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2138,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23,
|
13 |
+
"learning_rate": 3.6312236581084424e-06,
|
14 |
+
"loss": 0.6073,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.47,
|
19 |
+
"learning_rate": 3.4530478161992938e-06,
|
20 |
+
"loss": 0.5532,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.7,
|
25 |
+
"learning_rate": 3.274871974290146e-06,
|
26 |
+
"loss": 0.5355,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.94,
|
31 |
+
"learning_rate": 3.0966961323809974e-06,
|
32 |
+
"loss": 0.525,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"eval_loss": 0.5965137481689453,
|
38 |
+
"eval_matthews_correlation": 0.38219189241772933,
|
39 |
+
"eval_runtime": 14.186,
|
40 |
+
"eval_samples_per_second": 73.523,
|
41 |
+
"eval_steps_per_second": 4.652,
|
42 |
+
"step": 2138
|
43 |
+
}
|
44 |
+
],
|
45 |
+
"logging_steps": 500,
|
46 |
+
"max_steps": 10690,
|
47 |
+
"num_input_tokens_seen": 0,
|
48 |
+
"num_train_epochs": 5,
|
49 |
+
"save_steps": 500,
|
50 |
+
"total_flos": 32817763115472.0,
|
51 |
+
"train_batch_size": 4,
|
52 |
+
"trial_name": null,
|
53 |
+
"trial_params": {
|
54 |
+
"learning_rate": 3.8093995000175905e-06,
|
55 |
+
"num_train_epochs": 5,
|
56 |
+
"per_device_train_batch_size": 4,
|
57 |
+
"seed": 2
|
58 |
+
}
|
59 |
+
}
|
run-0/checkpoint-2138/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:697b39335203f92964396c6ece9c8f6e3ba7258afd36451c7eead8f43e9818e4
|
3 |
+
size 4792
|
run-0/checkpoint-2138/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jan13_22-34-04_DESKTOP-RFEED41/events.out.tfevents.1705163845.DESKTOP-RFEED41.28156.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:787b27e5032ced52bb718258b985b20ef954979aa271df549c9d9c541ea7fe1c
|
3 |
+
size 5298
|
training_args.bin
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 sha256:697b39335203f92964396c6ece9c8f6e3ba7258afd36451c7eead8f43e9818e4
|
3 |
+
size 4792
|