tjasad commited on
Commit
eb01849
1 Parent(s): 2e772a2

tjasad/prompt_fine_tuned_boolq

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: bigscience-bloom-rail-1.0
3
- base_model: bigscience/bloomz-560m
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # prompt_fine_tuned_boolq
17
 
18
- This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 77.8396
21
- - Accuracy: 0.2222
22
 
23
  ## Model description
24
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 12 | 79.0937 | 0.2222 |
53
- | No log | 2.0 | 24 | 77.8396 | 0.2222 |
54
 
55
 
56
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: distilbert/distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # prompt_fine_tuned_boolq
17
 
18
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6685
21
+ - Accuracy: 0.7778
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 12 | 0.6783 | 0.7778 |
53
+ | No log | 2.0 | 24 | 0.6685 | 0.7778 |
54
 
55
 
56
  ### Framework versions
config.json CHANGED
@@ -1,16 +1,13 @@
1
  {
2
- "_name_or_path": "bigscience/bloomz-560m",
3
- "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
- "BloomForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.0,
8
- "attention_softmax_in_fp32": true,
9
- "bias_dropout_fusion": true,
10
- "bos_token_id": 1,
11
- "eos_token_id": 2,
12
- "hidden_dropout": 0.0,
13
- "hidden_size": 1024,
14
  "id2label": {
15
  "0": false,
16
  "1": true
@@ -20,23 +17,18 @@
20
  "false": 0,
21
  "true": 1
22
  },
23
- "layer_norm_epsilon": 1e-05,
24
- "masked_softmax_fusion": true,
25
- "model_type": "bloom",
26
- "n_head": 16,
27
- "n_inner": null,
28
- "n_layer": 24,
29
- "offset_alibi": 100,
30
- "pad_token_id": 3,
31
- "pretraining_tp": 1,
32
  "problem_type": "single_label_classification",
33
- "seq_length": 2048,
34
- "skip_bias_add": true,
35
- "skip_bias_add_qkv": false,
36
- "slow_but_exact": false,
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.40.1",
39
- "unk_token_id": 0,
40
  "use_cache": false,
41
- "vocab_size": 250880
42
  }
 
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": 0.1,
10
+ "hidden_dim": 3072,
 
 
 
11
  "id2label": {
12
  "0": false,
13
  "1": true
 
17
  "false": 0,
18
  "true": 1
19
  },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
 
 
 
 
25
  "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.40.1",
 
32
  "use_cache": false,
33
+ "vocab_size": 30522
34
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dba595894a8f676ef348c15eb582c813c4a5a0806b1b326f5f224c9a427e664
3
- size 2236908888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfea330d07ebfdee6ef58478b4fb4815c25b394af9c87bb44653a26ad097edcd
3
+ size 270201584
runs/May02_08-10-09_f1a43a007cba/events.out.tfevents.1714637427.f1a43a007cba.1887.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4467d859209363b16fb5ec4942ae55618bc2c9ed09cf2fc3e471991d1936c5b5
3
+ size 5696
special_tokens_map.json CHANGED
@@ -1,30 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<pad>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c15972849c91c78dfab27e2ef0eb53b17f95c4fe81be6664f7e85c6a7fffde0e
3
- size 14500499
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f1def9b9391fdabe028cd3f3fcc4efd34e5d1f08c3bf2de513ebb5911a1854
3
+ size 711649
tokenizer_config.json CHANGED
@@ -1,32 +1,39 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<unk>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "1": {
13
- "content": "<s>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "3": {
29
- "content": "<pad>",
 
 
 
 
 
 
 
 
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
@@ -34,12 +41,15 @@
34
  "special": true
35
  }
36
  },
37
- "bos_token": "<s>",
38
- "clean_up_tokenization_spaces": false,
39
- "eos_token": "</s>",
 
40
  "model_max_length": 1000000000000000019884624838656,
41
- "pad_token": "<pad>",
42
- "padding_side": "left",
43
- "tokenizer_class": "BloomTokenizer",
44
- "unk_token": "<unk>"
 
 
45
  }
 
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,
 
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": 1000000000000000019884624838656,
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
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d97bca7446fd4f7d9100f5a20eca94dc23f43837eaa5b4f3109c01308364ef26
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0323cde6e58819fdbe4a91f2860b457db5eff032df2f58e5026ef98f6b7323e3
3
  size 4984
vocab.txt ADDED
The diff for this file is too large to render. See raw diff