yiyang0101
commited on
Commit
•
bb836ed
1
Parent(s):
086bf71
delete model and results
Browse files- model/config.json +0 -27
- model/model.safetensors +0 -3
- model/training_args.bin +0 -3
- results/README.md +0 -60
- results/checkpoint-3/config.json +0 -27
- results/checkpoint-3/model.safetensors +0 -3
- results/checkpoint-3/optimizer.pt +0 -3
- results/checkpoint-3/rng_state.pth +0 -3
- results/checkpoint-3/scheduler.pt +0 -3
- results/checkpoint-3/trainer_state.json +0 -49
- results/checkpoint-3/training_args.bin +0 -3
- results/config.json +0 -27
- results/model.safetensors +0 -3
- results/training_args.bin +0 -3
- train.py +1 -1
model/config.json
DELETED
@@ -1,27 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "bert-base-uncased",
|
3 |
-
"architectures": [
|
4 |
-
"BertForSequenceClassification"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
-
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-12,
|
15 |
-
"max_position_embeddings": 512,
|
16 |
-
"model_type": "bert",
|
17 |
-
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers": 12,
|
19 |
-
"pad_token_id": 0,
|
20 |
-
"position_embedding_type": "absolute",
|
21 |
-
"problem_type": "single_label_classification",
|
22 |
-
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.44.2",
|
24 |
-
"type_vocab_size": 2,
|
25 |
-
"use_cache": true,
|
26 |
-
"vocab_size": 30522
|
27 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7dc72efb9c58c63a2a22eca2c8849af594e90340f92ef173e6a9f9f67c3f50d9
|
3 |
-
size 437958648
|
|
|
|
|
|
|
|
model/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8161f02c7d4a427bc4bf643995f120e4491e21b31de80f246a09d34d93d79cf9
|
3 |
-
size 4731
|
|
|
|
|
|
|
|
results/README.md
DELETED
@@ -1,60 +0,0 @@
|
|
1 |
-
---
|
2 |
-
library_name: transformers
|
3 |
-
license: apache-2.0
|
4 |
-
base_model: bert-base-uncased
|
5 |
-
tags:
|
6 |
-
- generated_from_trainer
|
7 |
-
model-index:
|
8 |
-
- name: results
|
9 |
-
results: []
|
10 |
-
---
|
11 |
-
|
12 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
-
should probably proofread and complete it, then remove this comment. -->
|
14 |
-
|
15 |
-
# results
|
16 |
-
|
17 |
-
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
18 |
-
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.4989
|
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: 2e-05
|
39 |
-
- train_batch_size: 16
|
40 |
-
- eval_batch_size: 16
|
41 |
-
- seed: 42
|
42 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
-
- lr_scheduler_type: linear
|
44 |
-
- num_epochs: 3
|
45 |
-
|
46 |
-
### Training results
|
47 |
-
|
48 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| No log | 1.0 | 1 | 0.4914 |
|
51 |
-
| No log | 2.0 | 2 | 0.4972 |
|
52 |
-
| No log | 3.0 | 3 | 0.4989 |
|
53 |
-
|
54 |
-
|
55 |
-
### Framework versions
|
56 |
-
|
57 |
-
- Transformers 4.44.2
|
58 |
-
- Pytorch 2.0.0
|
59 |
-
- Datasets 2.21.0
|
60 |
-
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/checkpoint-3/config.json
DELETED
@@ -1,27 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "bert-base-uncased",
|
3 |
-
"architectures": [
|
4 |
-
"BertForSequenceClassification"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
-
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-12,
|
15 |
-
"max_position_embeddings": 512,
|
16 |
-
"model_type": "bert",
|
17 |
-
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers": 12,
|
19 |
-
"pad_token_id": 0,
|
20 |
-
"position_embedding_type": "absolute",
|
21 |
-
"problem_type": "single_label_classification",
|
22 |
-
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.44.2",
|
24 |
-
"type_vocab_size": 2,
|
25 |
-
"use_cache": true,
|
26 |
-
"vocab_size": 30522
|
27 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/checkpoint-3/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7dc72efb9c58c63a2a22eca2c8849af594e90340f92ef173e6a9f9f67c3f50d9
|
3 |
-
size 437958648
|
|
|
|
|
|
|
|
results/checkpoint-3/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:fac9b19e1ba82f541cfe13f380521026d981494f8d9d3cd8422b81011de11d08
|
3 |
-
size 876032325
|
|
|
|
|
|
|
|
results/checkpoint-3/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:82977179d430821bc5ad62c4dad438b40ff2cfe3c37564615b0628f6185da60a
|
3 |
-
size 13553
|
|
|
|
|
|
|
|
results/checkpoint-3/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:d2f33563639c06f9199097871f01c259e75a9ea0c5270cbc21060c4e9830fb47
|
3 |
-
size 627
|
|
|
|
|
|
|
|
results/checkpoint-3/trainer_state.json
DELETED
@@ -1,49 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.0,
|
5 |
-
"eval_steps": 500,
|
6 |
-
"global_step": 3,
|
7 |
-
"is_hyper_param_search": false,
|
8 |
-
"is_local_process_zero": true,
|
9 |
-
"is_world_process_zero": true,
|
10 |
-
"log_history": [
|
11 |
-
{
|
12 |
-
"epoch": 1.0,
|
13 |
-
"eval_loss": 0.4913959503173828,
|
14 |
-
"eval_runtime": 0.1359,
|
15 |
-
"eval_samples_per_second": 7.358,
|
16 |
-
"eval_steps_per_second": 7.358,
|
17 |
-
"step": 1
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"epoch": 2.0,
|
21 |
-
"eval_loss": 0.4971807599067688,
|
22 |
-
"eval_runtime": 0.0514,
|
23 |
-
"eval_samples_per_second": 19.466,
|
24 |
-
"eval_steps_per_second": 19.466,
|
25 |
-
"step": 2
|
26 |
-
}
|
27 |
-
],
|
28 |
-
"logging_steps": 500,
|
29 |
-
"max_steps": 3,
|
30 |
-
"num_input_tokens_seen": 0,
|
31 |
-
"num_train_epochs": 3,
|
32 |
-
"save_steps": 500,
|
33 |
-
"stateful_callbacks": {
|
34 |
-
"TrainerControl": {
|
35 |
-
"args": {
|
36 |
-
"should_epoch_stop": false,
|
37 |
-
"should_evaluate": false,
|
38 |
-
"should_log": false,
|
39 |
-
"should_save": true,
|
40 |
-
"should_training_stop": true
|
41 |
-
},
|
42 |
-
"attributes": {}
|
43 |
-
}
|
44 |
-
},
|
45 |
-
"total_flos": 1578666332160.0,
|
46 |
-
"train_batch_size": 16,
|
47 |
-
"trial_name": null,
|
48 |
-
"trial_params": null
|
49 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/checkpoint-3/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8161f02c7d4a427bc4bf643995f120e4491e21b31de80f246a09d34d93d79cf9
|
3 |
-
size 4731
|
|
|
|
|
|
|
|
results/config.json
DELETED
@@ -1,27 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "bert-base-uncased",
|
3 |
-
"architectures": [
|
4 |
-
"BertForSequenceClassification"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"classifier_dropout": null,
|
8 |
-
"gradient_checkpointing": false,
|
9 |
-
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-12,
|
15 |
-
"max_position_embeddings": 512,
|
16 |
-
"model_type": "bert",
|
17 |
-
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers": 12,
|
19 |
-
"pad_token_id": 0,
|
20 |
-
"position_embedding_type": "absolute",
|
21 |
-
"problem_type": "single_label_classification",
|
22 |
-
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.44.2",
|
24 |
-
"type_vocab_size": 2,
|
25 |
-
"use_cache": true,
|
26 |
-
"vocab_size": 30522
|
27 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
results/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7dc72efb9c58c63a2a22eca2c8849af594e90340f92ef173e6a9f9f67c3f50d9
|
3 |
-
size 437958648
|
|
|
|
|
|
|
|
results/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8161f02c7d4a427bc4bf643995f120e4491e21b31de80f246a09d34d93d79cf9
|
3 |
-
size 4731
|
|
|
|
|
|
|
|
train.py
CHANGED
@@ -45,7 +45,7 @@ trainer = Trainer(
|
|
45 |
trainer.train()
|
46 |
|
47 |
# 모델 저장
|
48 |
-
trainer.save_model("./
|
49 |
|
50 |
# 모델 푸시
|
51 |
trainer.push_to_hub("yiyang0101/yiyang-test")
|
|
|
45 |
trainer.train()
|
46 |
|
47 |
# 모델 저장
|
48 |
+
trainer.save_model("./")
|
49 |
|
50 |
# 모델 푸시
|
51 |
trainer.push_to_hub("yiyang0101/yiyang-test")
|