Hugging Face's logo

HassanCS
/
ChemBERTa-77M-MLM-finetuned-bace

Fill-Mask
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
HassanCS commited on
Commit
1a16ca7
·
1 Parent(s): 1c2e413

End of training

Browse files
Files changed (9) hide show
  1. README.md +105 -0
  2. config.json +29 -0
  3. model.safetensors +3 -0
  4. runs/Nov13_12-57-08_99c5b47f9917/events.out.tfevents.1699880237.99c5b47f9917.546.0 +3 -0
  5. runs/Nov13_13-11-58_99c5b47f9917/events.out.tfevents.1699881119.99c5b47f9917.546.1 +3 -0
  6. runs/Nov13_13-11-58_99c5b47f9917/events.out.tfevents.1699882600.99c5b47f9917.546.2 +3 -0
  7. runs/Nov13_13-37-25_99c5b47f9917/events.out.tfevents.1699882646.99c5b47f9917.546.3 +3 -0
  8. runs/Nov13_13-37-25_99c5b47f9917/events.out.tfevents.1699882807.99c5b47f9917.546.4 +3 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DeepChem/ChemBERTa-77M-MLM
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ChemBERTa-77M-MLM-finetuned-bace
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # ChemBERTa-77M-MLM-finetuned-bace
14
+
15
+ This model is a fine-tuned version of [DeepChem/ChemBERTa-77M-MLM](https://huggingface.co/DeepChem/ChemBERTa-77M-MLM) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0592
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 152 | 0.1396 |
49
+ | No log | 2.0 | 304 | 0.1761 |
50
+ | No log | 3.0 | 456 | 0.1527 |
51
+ | 0.2304 | 4.0 | 608 | 0.1260 |
52
+ | 0.2304 | 5.0 | 760 | 0.1307 |
53
+ | 0.2304 | 6.0 | 912 | 0.1256 |
54
+ | 0.178 | 7.0 | 1064 | 0.1016 |
55
+ | 0.178 | 8.0 | 1216 | 0.0890 |
56
+ | 0.178 | 9.0 | 1368 | 0.1486 |
57
+ | 0.1588 | 10.0 | 1520 | 0.1047 |
58
+ | 0.1588 | 11.0 | 1672 | 0.1072 |
59
+ | 0.1588 | 12.0 | 1824 | 0.1336 |
60
+ | 0.1588 | 13.0 | 1976 | 0.0955 |
61
+ | 0.1473 | 14.0 | 2128 | 0.0946 |
62
+ | 0.1473 | 15.0 | 2280 | 0.0940 |
63
+ | 0.1473 | 16.0 | 2432 | 0.0756 |
64
+ | 0.1415 | 17.0 | 2584 | 0.1275 |
65
+ | 0.1415 | 18.0 | 2736 | 0.1175 |
66
+ | 0.1415 | 19.0 | 2888 | 0.0743 |
67
+ | 0.1237 | 20.0 | 3040 | 0.0811 |
68
+ | 0.1237 | 21.0 | 3192 | 0.1033 |
69
+ | 0.1237 | 22.0 | 3344 | 0.0877 |
70
+ | 0.1237 | 23.0 | 3496 | 0.0835 |
71
+ | 0.1254 | 24.0 | 3648 | 0.1107 |
72
+ | 0.1254 | 25.0 | 3800 | 0.1098 |
73
+ | 0.1254 | 26.0 | 3952 | 0.1138 |
74
+ | 0.1238 | 27.0 | 4104 | 0.0896 |
75
+ | 0.1238 | 28.0 | 4256 | 0.0923 |
76
+ | 0.1238 | 29.0 | 4408 | 0.1019 |
77
+ | 0.1161 | 30.0 | 4560 | 0.1115 |
78
+ | 0.1161 | 31.0 | 4712 | 0.0716 |
79
+ | 0.1161 | 32.0 | 4864 | 0.1300 |
80
+ | 0.114 | 33.0 | 5016 | 0.1017 |
81
+ | 0.114 | 34.0 | 5168 | 0.0922 |
82
+ | 0.114 | 35.0 | 5320 | 0.0458 |
83
+ | 0.114 | 36.0 | 5472 | 0.1335 |
84
+ | 0.1116 | 37.0 | 5624 | 0.0924 |
85
+ | 0.1116 | 38.0 | 5776 | 0.0828 |
86
+ | 0.1116 | 39.0 | 5928 | 0.0857 |
87
+ | 0.1082 | 40.0 | 6080 | 0.0847 |
88
+ | 0.1082 | 41.0 | 6232 | 0.0629 |
89
+ | 0.1082 | 42.0 | 6384 | 0.0685 |
90
+ | 0.11 | 43.0 | 6536 | 0.0918 |
91
+ | 0.11 | 44.0 | 6688 | 0.0829 |
92
+ | 0.11 | 45.0 | 6840 | 0.1118 |
93
+ | 0.11 | 46.0 | 6992 | 0.0561 |
94
+ | 0.1041 | 47.0 | 7144 | 0.0834 |
95
+ | 0.1041 | 48.0 | 7296 | 0.0940 |
96
+ | 0.1041 | 49.0 | 7448 | 0.1024 |
97
+ | 0.1103 | 50.0 | 7600 | 0.0809 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.35.0
103
+ - Pytorch 2.1.0+cu118
104
+ - Datasets 2.14.6
105
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DeepChem/ChemBERTa-77M-MLM",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.109,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.144,
13
+ "hidden_size": 384,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 464,
16
+ "is_gpu": true,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 515,
19
+ "model_type": "roberta",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 3,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.35.0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 600
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6c6deca6bf386928f2ddb72ea9c40d62e46bdcef802f9cbed27b826679ab3f
3
+ size 13721840
runs/Nov13_12-57-08_99c5b47f9917/events.out.tfevents.1699880237.99c5b47f9917.546.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd508dac4441bf8da98bc8a25f5d52752eedc4656ad21242379557b37b7c5ad3
3
+ size 4598
runs/Nov13_13-11-58_99c5b47f9917/events.out.tfevents.1699881119.99c5b47f9917.546.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de99906a1f23a3f37f51adffa02b6db8f15db345256a1b264ba5d4057e85a1d8
3
+ size 11042
runs/Nov13_13-11-58_99c5b47f9917/events.out.tfevents.1699882600.99c5b47f9917.546.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e0bb81b45cce079d377f5dcd0a8446ba06e53d9b648252a8761f3adbd6656e
3
+ size 359
runs/Nov13_13-37-25_99c5b47f9917/events.out.tfevents.1699882646.99c5b47f9917.546.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b738ba964b22703ad4b2c8804e7526111848405a9653a9be486920a7de24ade
3
+ size 20585
runs/Nov13_13-37-25_99c5b47f9917/events.out.tfevents.1699882807.99c5b47f9917.546.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27627e42b897c0ac785b66623757ccdcecd0ab2ef40423858e6dcd499c59c729
3
+ size 359
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4fa1e403595c2c5f0f181812a391e99034b00962c5e8d86f236cf3c572b61d6
3
+ size 4600