lauraha commited on
Commit
1da24f7
·
verified ·
1 Parent(s): ae7304a

Upload 10 files

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/esm2_t30_150M_UR50D",
3
+ "architectures": [
4
+ "EsmForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout": null,
8
+ "emb_layer_norm_before": false,
9
+ "esmfold_config": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 640,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2560,
15
+ "is_folding_model": false,
16
+ "layer_norm_eps": 1e-05,
17
+ "mask_token_id": 32,
18
+ "max_position_embeddings": 1026,
19
+ "model_type": "esm",
20
+ "num_attention_heads": 20,
21
+ "num_hidden_layers": 30,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "rotary",
24
+ "token_dropout": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.42.3",
27
+ "use_cache": true,
28
+ "vocab_list": null,
29
+ "vocab_size": 33
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ba4d71a812c105927020dd8aff8d74e45be6a85e265d775204a8e8d3694276
3
+ size 595249400
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8284446979e39209fd3ae1b1456572a29a226c37b368fa8c05b449c7dffcd2fb
3
+ size 1185525322
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b260d7c78d903417ccd15c6d9a4c8b6fe4fcf9670ca87a95c940cb594e83a109
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6923632fef38472c44be2851ece58a12345893d12b58cd2a4290bcbf14e4e3e7
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "<cls>",
3
+ "eos_token": "<eos>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<cls>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<eos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "<cls>",
46
+ "eos_token": "<eos>",
47
+ "mask_token": "<mask>",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "<pad>",
50
+ "tokenizer_class": "EsmTokenizer",
51
+ "unk_token": "<unk>"
52
+ }
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 43750,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 1.4176286458969116,
14
+ "learning_rate": 1.600137142857143e-05,
15
+ "loss": 2.6585,
16
+ "step": 8750
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 2.657306671142578,
21
+ "eval_runtime": 127.3226,
22
+ "eval_samples_per_second": 235.622,
23
+ "eval_steps_per_second": 29.453,
24
+ "step": 8750
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "grad_norm": 1.0878936052322388,
29
+ "learning_rate": 1.2002285714285716e-05,
30
+ "loss": 2.6535,
31
+ "step": 17500
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_loss": 2.653296947479248,
36
+ "eval_runtime": 139.0848,
37
+ "eval_samples_per_second": 215.696,
38
+ "eval_steps_per_second": 26.962,
39
+ "step": 17500
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "grad_norm": 1.0684641599655151,
44
+ "learning_rate": 8.00457142857143e-06,
45
+ "loss": 2.6505,
46
+ "step": 26250
47
+ },
48
+ {
49
+ "epoch": 3.0,
50
+ "eval_loss": 2.653186798095703,
51
+ "eval_runtime": 133.9609,
52
+ "eval_samples_per_second": 223.946,
53
+ "eval_steps_per_second": 27.993,
54
+ "step": 26250
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "grad_norm": 2.061199188232422,
59
+ "learning_rate": 4.0064e-06,
60
+ "loss": 2.6439,
61
+ "step": 35000
62
+ },
63
+ {
64
+ "epoch": 4.0,
65
+ "eval_loss": 2.6521787643432617,
66
+ "eval_runtime": 131.624,
67
+ "eval_samples_per_second": 227.922,
68
+ "eval_steps_per_second": 28.49,
69
+ "step": 35000
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "grad_norm": 1.321831226348877,
74
+ "learning_rate": 7.3142857142857155e-09,
75
+ "loss": 2.6401,
76
+ "step": 43750
77
+ }
78
+ ],
79
+ "logging_steps": 8750,
80
+ "max_steps": 43750,
81
+ "num_input_tokens_seen": 0,
82
+ "num_train_epochs": 5,
83
+ "save_steps": 500,
84
+ "stateful_callbacks": {
85
+ "TrainerControl": {
86
+ "args": {
87
+ "should_epoch_stop": false,
88
+ "should_evaluate": false,
89
+ "should_log": false,
90
+ "should_save": true,
91
+ "should_training_stop": true
92
+ },
93
+ "attributes": {}
94
+ }
95
+ },
96
+ "total_flos": 5333657398730976.0,
97
+ "train_batch_size": 8,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc19761260cea9773d4cd42ffe0bd9c26f789398a1f24834476305c834edf36d
3
+ size 5112
vocab.txt ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <cls>
2
+ <pad>
3
+ <eos>
4
+ <unk>
5
+ L
6
+ A
7
+ G
8
+ V
9
+ S
10
+ E
11
+ R
12
+ T
13
+ I
14
+ D
15
+ P
16
+ K
17
+ Q
18
+ N
19
+ F
20
+ Y
21
+ M
22
+ H
23
+ W
24
+ C
25
+ X
26
+ B
27
+ U
28
+ Z
29
+ O
30
+ .
31
+ -
32
+ <null_1>
33
+ <mask>