Hugging Face's logo

ashabrawy
/
bert-large-uncased_peft_distillation

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
ashabrawy commited on
Commit
2306c8f
•
1 Parent(s): 3817539

NLP702-bert-large-uncased_peft-distillation_hs768-nh8-nl6

Browse files
Files changed (7) hide show
  1. README.md +64 -0
  2. best/config.json +148 -0
  3. best/model.safetensors +3 -0
  4. best/training_args.bin +3 -0
  5. config.json +148 -0
  6. model.safetensors +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: bert-large-uncased_peft_distillation
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
+ # bert-large-uncased_peft_distillation
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4723
19
+ - Accuracy: 0.8467
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: 0.0001
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 6
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.7825 | 1.39 | 500 | 0.7498 | 0.7659 |
54
+ | 0.5085 | 2.78 | 1000 | 0.5277 | 0.8264 |
55
+ | 0.2382 | 4.17 | 1500 | 0.4778 | 0.8421 |
56
+ | 0.1322 | 5.56 | 2000 | 0.4512 | 0.8485 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.37.2
62
+ - Pytorch 2.2.0+cu121
63
+ - Datasets 2.16.1
64
+ - Tokenizers 0.15.1
best/config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29",
41
+ "30": "LABEL_30",
42
+ "31": "LABEL_31",
43
+ "32": "LABEL_32",
44
+ "33": "LABEL_33",
45
+ "34": "LABEL_34",
46
+ "35": "LABEL_35",
47
+ "36": "LABEL_36",
48
+ "37": "LABEL_37",
49
+ "38": "LABEL_38",
50
+ "39": "LABEL_39",
51
+ "40": "LABEL_40",
52
+ "41": "LABEL_41",
53
+ "42": "LABEL_42",
54
+ "43": "LABEL_43",
55
+ "44": "LABEL_44",
56
+ "45": "LABEL_45",
57
+ "46": "LABEL_46",
58
+ "47": "LABEL_47",
59
+ "48": "LABEL_48",
60
+ "49": "LABEL_49",
61
+ "50": "LABEL_50",
62
+ "51": "LABEL_51",
63
+ "52": "LABEL_52",
64
+ "53": "LABEL_53",
65
+ "54": "LABEL_54",
66
+ "55": "LABEL_55",
67
+ "56": "LABEL_56",
68
+ "57": "LABEL_57",
69
+ "58": "LABEL_58",
70
+ "59": "LABEL_59"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 3072,
74
+ "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1,
77
+ "LABEL_10": 10,
78
+ "LABEL_11": 11,
79
+ "LABEL_12": 12,
80
+ "LABEL_13": 13,
81
+ "LABEL_14": 14,
82
+ "LABEL_15": 15,
83
+ "LABEL_16": 16,
84
+ "LABEL_17": 17,
85
+ "LABEL_18": 18,
86
+ "LABEL_19": 19,
87
+ "LABEL_2": 2,
88
+ "LABEL_20": 20,
89
+ "LABEL_21": 21,
90
+ "LABEL_22": 22,
91
+ "LABEL_23": 23,
92
+ "LABEL_24": 24,
93
+ "LABEL_25": 25,
94
+ "LABEL_26": 26,
95
+ "LABEL_27": 27,
96
+ "LABEL_28": 28,
97
+ "LABEL_29": 29,
98
+ "LABEL_3": 3,
99
+ "LABEL_30": 30,
100
+ "LABEL_31": 31,
101
+ "LABEL_32": 32,
102
+ "LABEL_33": 33,
103
+ "LABEL_34": 34,
104
+ "LABEL_35": 35,
105
+ "LABEL_36": 36,
106
+ "LABEL_37": 37,
107
+ "LABEL_38": 38,
108
+ "LABEL_39": 39,
109
+ "LABEL_4": 4,
110
+ "LABEL_40": 40,
111
+ "LABEL_41": 41,
112
+ "LABEL_42": 42,
113
+ "LABEL_43": 43,
114
+ "LABEL_44": 44,
115
+ "LABEL_45": 45,
116
+ "LABEL_46": 46,
117
+ "LABEL_47": 47,
118
+ "LABEL_48": 48,
119
+ "LABEL_49": 49,
120
+ "LABEL_5": 5,
121
+ "LABEL_50": 50,
122
+ "LABEL_51": 51,
123
+ "LABEL_52": 52,
124
+ "LABEL_53": 53,
125
+ "LABEL_54": 54,
126
+ "LABEL_55": 55,
127
+ "LABEL_56": 56,
128
+ "LABEL_57": 57,
129
+ "LABEL_58": 58,
130
+ "LABEL_59": 59,
131
+ "LABEL_6": 6,
132
+ "LABEL_7": 7,
133
+ "LABEL_8": 8,
134
+ "LABEL_9": 9
135
+ },
136
+ "layer_norm_eps": 1e-12,
137
+ "max_position_embeddings": 512,
138
+ "model_type": "bert",
139
+ "num_attention_heads": 8,
140
+ "num_hidden_layers": 6,
141
+ "pad_token_id": 0,
142
+ "position_embedding_type": "absolute",
143
+ "torch_dtype": "float32",
144
+ "transformers_version": "4.37.2",
145
+ "type_vocab_size": 2,
146
+ "use_cache": true,
147
+ "vocab_size": 30522
148
+ }
best/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cfd26e48a93669a5de49689c1131f9069bf811a5acd9d75797d3392d6fc504
3
+ size 268016800
best/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37af999a4815f57722a52307d2aaefdbbbd69a922ee86fd93b0f41319325e90
3
+ size 4664
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13",
25
+ "14": "LABEL_14",
26
+ "15": "LABEL_15",
27
+ "16": "LABEL_16",
28
+ "17": "LABEL_17",
29
+ "18": "LABEL_18",
30
+ "19": "LABEL_19",
31
+ "20": "LABEL_20",
32
+ "21": "LABEL_21",
33
+ "22": "LABEL_22",
34
+ "23": "LABEL_23",
35
+ "24": "LABEL_24",
36
+ "25": "LABEL_25",
37
+ "26": "LABEL_26",
38
+ "27": "LABEL_27",
39
+ "28": "LABEL_28",
40
+ "29": "LABEL_29",
41
+ "30": "LABEL_30",
42
+ "31": "LABEL_31",
43
+ "32": "LABEL_32",
44
+ "33": "LABEL_33",
45
+ "34": "LABEL_34",
46
+ "35": "LABEL_35",
47
+ "36": "LABEL_36",
48
+ "37": "LABEL_37",
49
+ "38": "LABEL_38",
50
+ "39": "LABEL_39",
51
+ "40": "LABEL_40",
52
+ "41": "LABEL_41",
53
+ "42": "LABEL_42",
54
+ "43": "LABEL_43",
55
+ "44": "LABEL_44",
56
+ "45": "LABEL_45",
57
+ "46": "LABEL_46",
58
+ "47": "LABEL_47",
59
+ "48": "LABEL_48",
60
+ "49": "LABEL_49",
61
+ "50": "LABEL_50",
62
+ "51": "LABEL_51",
63
+ "52": "LABEL_52",
64
+ "53": "LABEL_53",
65
+ "54": "LABEL_54",
66
+ "55": "LABEL_55",
67
+ "56": "LABEL_56",
68
+ "57": "LABEL_57",
69
+ "58": "LABEL_58",
70
+ "59": "LABEL_59"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 3072,
74
+ "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1,
77
+ "LABEL_10": 10,
78
+ "LABEL_11": 11,
79
+ "LABEL_12": 12,
80
+ "LABEL_13": 13,
81
+ "LABEL_14": 14,
82
+ "LABEL_15": 15,
83
+ "LABEL_16": 16,
84
+ "LABEL_17": 17,
85
+ "LABEL_18": 18,
86
+ "LABEL_19": 19,
87
+ "LABEL_2": 2,
88
+ "LABEL_20": 20,
89
+ "LABEL_21": 21,
90
+ "LABEL_22": 22,
91
+ "LABEL_23": 23,
92
+ "LABEL_24": 24,
93
+ "LABEL_25": 25,
94
+ "LABEL_26": 26,
95
+ "LABEL_27": 27,
96
+ "LABEL_28": 28,
97
+ "LABEL_29": 29,
98
+ "LABEL_3": 3,
99
+ "LABEL_30": 30,
100
+ "LABEL_31": 31,
101
+ "LABEL_32": 32,
102
+ "LABEL_33": 33,
103
+ "LABEL_34": 34,
104
+ "LABEL_35": 35,
105
+ "LABEL_36": 36,
106
+ "LABEL_37": 37,
107
+ "LABEL_38": 38,
108
+ "LABEL_39": 39,
109
+ "LABEL_4": 4,
110
+ "LABEL_40": 40,
111
+ "LABEL_41": 41,
112
+ "LABEL_42": 42,
113
+ "LABEL_43": 43,
114
+ "LABEL_44": 44,
115
+ "LABEL_45": 45,
116
+ "LABEL_46": 46,
117
+ "LABEL_47": 47,
118
+ "LABEL_48": 48,
119
+ "LABEL_49": 49,
120
+ "LABEL_5": 5,
121
+ "LABEL_50": 50,
122
+ "LABEL_51": 51,
123
+ "LABEL_52": 52,
124
+ "LABEL_53": 53,
125
+ "LABEL_54": 54,
126
+ "LABEL_55": 55,
127
+ "LABEL_56": 56,
128
+ "LABEL_57": 57,
129
+ "LABEL_58": 58,
130
+ "LABEL_59": 59,
131
+ "LABEL_6": 6,
132
+ "LABEL_7": 7,
133
+ "LABEL_8": 8,
134
+ "LABEL_9": 9
135
+ },
136
+ "layer_norm_eps": 1e-12,
137
+ "max_position_embeddings": 512,
138
+ "model_type": "bert",
139
+ "num_attention_heads": 8,
140
+ "num_hidden_layers": 6,
141
+ "pad_token_id": 0,
142
+ "position_embedding_type": "absolute",
143
+ "torch_dtype": "float32",
144
+ "transformers_version": "4.37.2",
145
+ "type_vocab_size": 2,
146
+ "use_cache": true,
147
+ "vocab_size": 30522
148
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45cfd26e48a93669a5de49689c1131f9069bf811a5acd9d75797d3392d6fc504
3
+ size 268016800
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37af999a4815f57722a52307d2aaefdbbbd69a922ee86fd93b0f41319325e90
3
+ size 4664