morten-j commited on
Commit
6329cb7
·
verified ·
1 Parent(s): 2371a85

mehdie/base_BERT

Browse files
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: full_bert
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # full_bert
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 1.9118
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 16
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - num_devices: 4
41
+ - total_train_batch_size: 64
42
+ - total_eval_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 10000
46
+ - num_epochs: 40.0
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-------:|:---------------:|
52
+ | 6.778 | 1.0 | 55319 | 6.4618 |
53
+ | 6.4271 | 2.0 | 110638 | 6.3701 |
54
+ | 6.3616 | 3.0 | 165957 | 6.3217 |
55
+ | 6.3257 | 4.0 | 221276 | 6.2966 |
56
+ | 6.3001 | 5.0 | 276595 | 6.2759 |
57
+ | 6.2834 | 6.0 | 331914 | 6.2610 |
58
+ | 6.2699 | 7.0 | 387233 | 6.2465 |
59
+ | 6.2565 | 8.0 | 442552 | 6.1939 |
60
+ | 6.2221 | 9.0 | 497871 | 6.1154 |
61
+ | 6.0721 | 10.0 | 553190 | 5.9524 |
62
+ | 5.9212 | 11.0 | 608509 | 5.7947 |
63
+ | 5.8113 | 12.0 | 663828 | 5.7161 |
64
+ | 5.7509 | 13.0 | 719147 | 5.6614 |
65
+ | 5.7053 | 14.0 | 774466 | 5.6158 |
66
+ | 5.6665 | 15.0 | 829785 | 5.5774 |
67
+ | 5.634 | 16.0 | 885104 | 5.5448 |
68
+ | 5.6055 | 17.0 | 940423 | 2.7563 |
69
+ | 3.3308 | 18.0 | 995742 | 2.5443 |
70
+ | 2.6179 | 19.0 | 1051061 | 2.4196 |
71
+ | 2.5324 | 20.0 | 1106380 | 2.3393 |
72
+ | 2.4791 | 21.0 | 1161699 | 2.2755 |
73
+ | 2.4105 | 22.0 | 1217018 | 2.2241 |
74
+ | 2.3582 | 23.0 | 1272337 | 2.1772 |
75
+ | 2.3281 | 24.0 | 1327656 | 2.1416 |
76
+ | 2.2987 | 25.0 | 1382975 | 2.1137 |
77
+ | 2.7859 | 26.0 | 1438294 | 2.0950 |
78
+ | 2.2728 | 27.0 | 1493613 | 2.0685 |
79
+ | 2.2308 | 28.0 | 1548932 | 2.0499 |
80
+ | 2.1739 | 29.0 | 1604251 | 2.0082 |
81
+ | 2.1569 | 30.0 | 1659570 | 1.9939 |
82
+ | 2.1425 | 31.0 | 1714889 | 1.9802 |
83
+ | 2.1318 | 32.0 | 1770208 | 1.9669 |
84
+ | 2.1207 | 33.0 | 1825527 | 1.9583 |
85
+ | 2.1111 | 34.0 | 1880846 | 1.9477 |
86
+ | 2.102 | 35.0 | 1936165 | 1.9409 |
87
+ | 2.0943 | 36.0 | 1991484 | 1.9313 |
88
+ | 2.0871 | 37.0 | 2046803 | 1.9236 |
89
+ | 2.0736 | 38.0 | 2102122 | 1.9191 |
90
+ | 2.0693 | 39.0 | 2157441 | 1.9147 |
91
+ | 2.0653 | 40.0 | 2212760 | 1.9118 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.38.2
97
+ - Pytorch 2.3.0a0+ebedce2
98
+ - Datasets 2.17.1
99
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
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
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.38.2",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 52000
24
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.38.2"
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72787f52b3bf74964eb67e3cb104ed728099dcc157d2b3b96a6129e57ae33002
3
+ size 504147232
runs/Apr02_11-05-52_i256-a10-06.srv.aau.dk/events.out.tfevents.1712048756.i256-a10-06.srv.aau.dk.108503.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60486cc7cc58c2e4b6137a0fbfddad847ddc02072cf839ac39e6db3dae54b680
3
+ size 4396
runs/Apr02_11-10-50_i256-a10-06.srv.aau.dk/events.out.tfevents.1712049051.i256-a10-06.srv.aau.dk.109429.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b590e02e81fbb552e46666edcf235fe13731554dab1c51e2a8dbd08f9df239d
3
+ size 4398
runs/Apr02_11-22-42_i256-a10-06.srv.aau.dk/events.out.tfevents.1712049763.i256-a10-06.srv.aau.dk.110352.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65eaca64e04a96e643ae78e3e089d0e5aaef150f5a4bdf1d4c95d261cfd6dc50
3
+ size 4402
runs/Apr02_11-36-21_i256-a10-06.srv.aau.dk/events.out.tfevents.1712050583.i256-a10-06.srv.aau.dk.111850.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56c2eced62b25da9f78a6a0d6e793aa1efbe09a2c310d7bb32032dcaf712121
3
+ size 4395
runs/Apr02_11-37-50_i256-a10-06.srv.aau.dk/events.out.tfevents.1712050671.i256-a10-06.srv.aau.dk.112771.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41a68575c39260e062ea202037703cfeec1e75e483b3e4fcd56ab907316068e2
3
+ size 4395
runs/Apr02_11-47-17_i256-a10-06.srv.aau.dk/events.out.tfevents.1712051238.i256-a10-06.srv.aau.dk.115413.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f6451ca22ae2871ca86981dc09cd276b2d2fc2960ddf60811bb0e458eb8c036
3
+ size 4395
runs/Apr02_11-48-58_i256-a10-06.srv.aau.dk/events.out.tfevents.1712051339.i256-a10-06.srv.aau.dk.116280.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2189efff93d950baea734f5bd45f480c864ce66f4aad18439419ac97b2a14a
3
+ size 15627
runs/Apr09_08-27-36_i256-a10-06.srv.aau.dk/events.out.tfevents.1712644082.i256-a10-06.srv.aau.dk.225073.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc0edc8e9c808fdd067f29be6f7d77d48ae9e8be431089fa539c563bd5365267
3
+ size 16409
runs/Apr16_15-06-06_i256-a10-09.srv.aau.dk/events.out.tfevents.1713272791.i256-a10-09.srv.aau.dk.71966.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3831ba1660438ce903d68e12c17fc4341fb4e528e8ba282441741993a63ba7
3
+ size 5807
runs/Apr17_08-06-07_i256-a10-08.srv.aau.dk/events.out.tfevents.1713333989.i256-a10-08.srv.aau.dk.113652.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6fac95a34b22ddb1c0a6fffcab84195eb849d81b2a7ba98d99f27212441d0bb
3
+ size 4395
runs/Apr17_08-12-16_i256-a10-09.srv.aau.dk/events.out.tfevents.1713334359.i256-a10-09.srv.aau.dk.77191.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56700c1c8e589d09a2cd96903e7dd5753512a982d83589a093ecee038db31636
3
+ size 11112
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189bf5baa3b6150c16b4b3e626be669cb2a8df88261b70ddbcd795735cb8a503
3
+ size 4920