varun-v-rao commited on
Commit
e2db3e4
·
verified ·
1 Parent(s): fa1440f

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-large-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: bert-large-cased-lora-1.58M-snli-model2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bert-large-cased-lora-1.58M-snli-model2
17
+
18
+ This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8331
21
+ - Accuracy: 0.687
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 256
42
+ - eval_batch_size: 256
43
+ - seed: 6
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.5164 | 1.0 | 2146 | 0.4262 | 0.8406 |
53
+ | 0.4687 | 2.0 | 4292 | 0.3904 | 0.8540 |
54
+ | 0.4562 | 3.0 | 6438 | 0.3824 | 0.8575 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.35.2
60
+ - Pytorch 2.1.1+cu121
61
+ - Datasets 2.15.0
62
+ - Tokenizers 0.15.0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7c608c4b0d309589f76d77589ae833589d43fbeb658c6ca399d71e4b6783303
3
  size 6317652
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630d9e716ed40cf8f85b6ba8bf2d1f5c797321b5ffde432c0cc0d1d346b1d786
3
  size 6317652
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.35.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 28996
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef4ecb6129b7b71e84b3c2dec35b8cc0c93bcc41ffcb38bec482181c931e684
3
+ size 1334376364
runs/Feb06_01-57-05_gl1527.arc-ts.umich.edu/events.out.tfevents.1707202633.gl1527.arc-ts.umich.edu.964259.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c771f3b3b2db75089a48105fb7c5da44652fc87155f283d7e093ab554afcd772
3
- size 6928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119c00a50a6de4c29de28a386f3e2e0d3ebaf8fabef838219c6bc691b4ef59cf
3
+ size 8233
runs/Feb06_01-57-05_gl1527.arc-ts.umich.edu/events.out.tfevents.1707206586.gl1527.arc-ts.umich.edu.964259.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6640e36eb32a164dded1042163dc49123f5a7d0571899e3e21b1a2342775bd53
3
+ size 1380