igor commited on
Commit
6aad337
·
verified ·
1 Parent(s): 2608f35

End of training

Browse files
Files changed (4) hide show
  1. README.md +10 -17
  2. config.json +15 -12
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: distilbert/distilbert-base-uncased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -16,10 +16,10 @@ 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/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.2189
22
- - F1: 0.6287
23
 
24
  ## Model description
25
 
@@ -44,22 +44,15 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 10
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | F1 |
52
- |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
- | 0.6602 | 1.0 | 1367 | 0.6489 | 0.6277 |
54
- | 0.6232 | 2.0 | 2734 | 0.6546 | 0.6535 |
55
- | 0.5985 | 3.0 | 4101 | 0.7058 | 0.6510 |
56
- | 0.5515 | 4.0 | 5468 | 0.6955 | 0.6478 |
57
- | 0.505 | 5.0 | 6835 | 0.7862 | 0.6461 |
58
- | 0.4617 | 6.0 | 8202 | 0.8992 | 0.6470 |
59
- | 0.4538 | 7.0 | 9569 | 1.0468 | 0.6330 |
60
- | 0.3878 | 8.0 | 10936 | 1.0613 | 0.6311 |
61
- | 0.3665 | 9.0 | 12303 | 1.1309 | 0.6261 |
62
- | 0.3483 | 10.0 | 13670 | 1.2189 | 0.6287 |
63
 
64
 
65
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: bert-base-uncased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
16
 
17
  # test_trainer
18
 
19
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8774
22
+ - F1: 0.6466
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 3
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.6575 | 1.0 | 1367 | 0.6360 | 0.6384 |
54
+ | 0.5764 | 2.0 | 2734 | 0.6432 | 0.6656 |
55
+ | 0.4055 | 3.0 | 4101 | 0.8774 | 0.6466 |
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
config.json CHANGED
@@ -1,24 +1,27 @@
1
  {
2
- "_name_or_path": "distilbert/distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
  "dropout": 0.5,
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
  "torch_dtype": "float32",
22
  "transformers_version": "4.46.3",
 
 
23
  "vocab_size": 30522
24
  }
 
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
  "dropout": 0.5,
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": "4.46.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
  "vocab_size": 30522
27
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:def1f7c6187f7f65dc0c43f6f35b2f47ba5429a3ad017d1499b81a68cd1dcff8
3
- size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da927020f68909cff2818564a95d94558632262df0338cc013822d5346fdb05f
3
+ size 437958648
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4540b317871d86be6385a2e2a6aee44be3b0dac30b22b816003e3e3588b1b47c
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5dbb77d875b82656652acbb8381860540b1f2095d152dea24575e3650fdb6f
3
  size 5240