Commit
•
a9f5d27
1
Parent(s):
83bf8e5
Upload with huggingface_hub
Browse files- README.md +62 -0
- added_tokens.json +3 -0
- all_results.json +14 -0
- config.json +0 -0
- eval_results.json +9 -0
- inference_tweak_params.json +1 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +54 -0
- tokenizer.json +0 -0
- tokenizer_config.json +68 -0
- train_results.json +8 -0
- trainer_state.json +67 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: deberta-large_lemon_5k_2_p3
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# deberta-large_lemon_5k_2_p3
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [model_saves/deberta-large_lemon_5k_2_p2](https://huggingface.co/model_saves/deberta-large_lemon_5k_2_p2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4293
|
19 |
+
- Accuracy: 0.9405
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 1e-05
|
39 |
+
- train_batch_size: 128
|
40 |
+
- eval_batch_size: 128
|
41 |
+
- seed: 52
|
42 |
+
- distributed_type: multi-GPU
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: constant
|
45 |
+
- num_epochs: 15.0
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
51 |
+
| No log | 1.0 | 268 | 0.4293 | 0.9405 |
|
52 |
+
| No log | 2.0 | 536 | 0.4665 | 0.9391 |
|
53 |
+
| No log | 3.0 | 804 | 0.5086 | 0.9388 |
|
54 |
+
| 0.2208 | 4.0 | 1072 | 0.5621 | 0.9394 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.21.0.dev0
|
60 |
+
- Pytorch 1.11.0+cu113
|
61 |
+
- Datasets 2.3.2
|
62 |
+
- Tokenizers 0.12.1
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"$START": 50265
|
3 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9405181184941692,
|
4 |
+
"eval_loss": 0.42925789952278137,
|
5 |
+
"eval_runtime": 4.6594,
|
6 |
+
"eval_samples": 4382,
|
7 |
+
"eval_samples_per_second": 940.468,
|
8 |
+
"eval_steps_per_second": 7.512,
|
9 |
+
"train_loss": 0.2150960520132264,
|
10 |
+
"train_runtime": 460.8647,
|
11 |
+
"train_samples": 34304,
|
12 |
+
"train_samples_per_second": 1116.51,
|
13 |
+
"train_steps_per_second": 8.723
|
14 |
+
}
|
config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9405181184941692,
|
4 |
+
"eval_loss": 0.42925789952278137,
|
5 |
+
"eval_runtime": 4.6594,
|
6 |
+
"eval_samples": 4382,
|
7 |
+
"eval_samples_per_second": 940.468,
|
8 |
+
"eval_steps_per_second": 7.512
|
9 |
+
}
|
inference_tweak_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"min_error_probability": 0.58, "additional_confidence": 0.0}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7e2b7a10696261b98fca2353834210a6fbe939ebbac1afc8b91c61445eed214
|
3 |
+
size 1641311087
|
special_tokens_map.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"$START"
|
4 |
+
],
|
5 |
+
"bos_token": {
|
6 |
+
"content": "[CLS]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"cls_token": {
|
13 |
+
"content": "[CLS]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"mask_token": {
|
27 |
+
"content": "[MASK]",
|
28 |
+
"lstrip": true,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"pad_token": {
|
34 |
+
"content": "[PAD]",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": true,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
},
|
40 |
+
"sep_token": {
|
41 |
+
"content": "[SEP]",
|
42 |
+
"lstrip": false,
|
43 |
+
"normalized": true,
|
44 |
+
"rstrip": false,
|
45 |
+
"single_word": false
|
46 |
+
},
|
47 |
+
"unk_token": {
|
48 |
+
"content": "[UNK]",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
}
|
54 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": true,
|
4 |
+
"add_special_tokens": false,
|
5 |
+
"bos_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "[CLS]",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "[CLS]",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"do_lower_case": false,
|
22 |
+
"eos_token": {
|
23 |
+
"__type": "AddedToken",
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"errors": "replace",
|
31 |
+
"mask_token": {
|
32 |
+
"__type": "AddedToken",
|
33 |
+
"content": "[MASK]",
|
34 |
+
"lstrip": true,
|
35 |
+
"normalized": true,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
},
|
39 |
+
"model_max_length": 512,
|
40 |
+
"name_or_path": "model_saves/deberta-large_lemon_5k_2_p2",
|
41 |
+
"pad_token": {
|
42 |
+
"__type": "AddedToken",
|
43 |
+
"content": "[PAD]",
|
44 |
+
"lstrip": false,
|
45 |
+
"normalized": true,
|
46 |
+
"rstrip": false,
|
47 |
+
"single_word": false
|
48 |
+
},
|
49 |
+
"sep_token": {
|
50 |
+
"__type": "AddedToken",
|
51 |
+
"content": "[SEP]",
|
52 |
+
"lstrip": false,
|
53 |
+
"normalized": true,
|
54 |
+
"rstrip": false,
|
55 |
+
"single_word": false
|
56 |
+
},
|
57 |
+
"special_tokens_map_file": null,
|
58 |
+
"tokenizer_class": "DebertaTokenizer",
|
59 |
+
"unk_token": {
|
60 |
+
"__type": "AddedToken",
|
61 |
+
"content": "[UNK]",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false
|
66 |
+
},
|
67 |
+
"vocab_type": "gpt2"
|
68 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.2150960520132264,
|
4 |
+
"train_runtime": 460.8647,
|
5 |
+
"train_samples": 34304,
|
6 |
+
"train_samples_per_second": 1116.51,
|
7 |
+
"train_steps_per_second": 8.723
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9405181184941692,
|
3 |
+
"best_model_checkpoint": "model_saves/deberta-large_lemon_5k_2_p3/checkpoint-268",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 1072,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_accuracy": 0.9405181184941692,
|
13 |
+
"eval_loss": 0.42925789952278137,
|
14 |
+
"eval_runtime": 4.6465,
|
15 |
+
"eval_samples_per_second": 943.085,
|
16 |
+
"eval_steps_per_second": 7.533,
|
17 |
+
"step": 268
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_accuracy": 0.9391428795044667,
|
22 |
+
"eval_loss": 0.4665437638759613,
|
23 |
+
"eval_runtime": 4.6371,
|
24 |
+
"eval_samples_per_second": 944.99,
|
25 |
+
"eval_steps_per_second": 7.548,
|
26 |
+
"step": 536
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.0,
|
30 |
+
"eval_accuracy": 0.9388242265678284,
|
31 |
+
"eval_loss": 0.5086150169372559,
|
32 |
+
"eval_runtime": 4.646,
|
33 |
+
"eval_samples_per_second": 943.168,
|
34 |
+
"eval_steps_per_second": 7.533,
|
35 |
+
"step": 804
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 3.73,
|
39 |
+
"learning_rate": 1e-05,
|
40 |
+
"loss": 0.2208,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 4.0,
|
45 |
+
"eval_accuracy": 0.9393888572099419,
|
46 |
+
"eval_loss": 0.5620639324188232,
|
47 |
+
"eval_runtime": 4.6383,
|
48 |
+
"eval_samples_per_second": 944.734,
|
49 |
+
"eval_steps_per_second": 7.546,
|
50 |
+
"step": 1072
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"step": 1072,
|
55 |
+
"total_flos": 1.6105037109395456e+16,
|
56 |
+
"train_loss": 0.2150960520132264,
|
57 |
+
"train_runtime": 460.8647,
|
58 |
+
"train_samples_per_second": 1116.51,
|
59 |
+
"train_steps_per_second": 8.723
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"max_steps": 4020,
|
63 |
+
"num_train_epochs": 15,
|
64 |
+
"total_flos": 1.6105037109395456e+16,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": null
|
67 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06469fc61ddc09979eb43b1e2f7ca6965f17fa5211f735ce5ce2244d0c5aad7e
|
3 |
+
size 3439
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|