jjoecclark
commited on
Commit
•
28b0a13
1
Parent(s):
dac4824
Upload 10 files
Browse files- config.json +30 -0
- model-001.safetensors +3 -0
- optimizer-002.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +52 -0
- trainer_state.json +69 -0
- training_args.bin +3 -0
- vocab.txt +33 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/esm2_t33_650M_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": 1280,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
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": 33,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"token_dropout": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.41.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_list": null,
|
29 |
+
"vocab_size": 33
|
30 |
+
}
|
model-001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3ab0696837379210cc8bd6b5ad8ffabf59f3d4c396a8a56af1d143f0fec52ad
|
3 |
+
size 2609498088
|
optimizer-002.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23f34777a67925ecfe4d636416141fd0d1578fee873f131bc38b5ba24381dbd6
|
3 |
+
size 5208796146
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f453a350568e764cbd4a160c5cf5d5b16d3c95141ea8311ab4a59ec7c3abef57
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4e5151ddf5cf4e819aa42fa7f700048a4e0fbe3d461a4c55564350194e50938
|
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 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.5653936862945557,
|
3 |
+
"best_model_checkpoint": "./drive/MyDrive/Models/LazBCDEF_ESM/checkpoint-2441",
|
4 |
+
"epoch": 0.999795207864018,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2441,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.2047921359819783,
|
13 |
+
"grad_norm": 0.6799923181533813,
|
14 |
+
"learning_rate": 2.385497746825072e-06,
|
15 |
+
"loss": 2.6195,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4095842719639566,
|
20 |
+
"grad_norm": 0.6685395240783691,
|
21 |
+
"learning_rate": 1.7709954936501437e-06,
|
22 |
+
"loss": 2.5826,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6143764079459348,
|
27 |
+
"grad_norm": 0.8171830177307129,
|
28 |
+
"learning_rate": 1.1564932404752152e-06,
|
29 |
+
"loss": 2.5739,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8191685439279132,
|
34 |
+
"grad_norm": 0.809063196182251,
|
35 |
+
"learning_rate": 5.419909873002868e-07,
|
36 |
+
"loss": 2.5691,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.999795207864018,
|
41 |
+
"eval_loss": 2.5653936862945557,
|
42 |
+
"eval_runtime": 46.3243,
|
43 |
+
"eval_samples_per_second": 1079.347,
|
44 |
+
"eval_steps_per_second": 4.231,
|
45 |
+
"step": 2441
|
46 |
+
}
|
47 |
+
],
|
48 |
+
"logging_steps": 500,
|
49 |
+
"max_steps": 2441,
|
50 |
+
"num_input_tokens_seen": 0,
|
51 |
+
"num_train_epochs": 1,
|
52 |
+
"save_steps": 500,
|
53 |
+
"stateful_callbacks": {
|
54 |
+
"TrainerControl": {
|
55 |
+
"args": {
|
56 |
+
"should_epoch_stop": false,
|
57 |
+
"should_evaluate": false,
|
58 |
+
"should_log": false,
|
59 |
+
"should_save": true,
|
60 |
+
"should_training_stop": true
|
61 |
+
},
|
62 |
+
"attributes": {}
|
63 |
+
}
|
64 |
+
},
|
65 |
+
"total_flos": 6.346203702454886e+16,
|
66 |
+
"train_batch_size": 256,
|
67 |
+
"trial_name": null,
|
68 |
+
"trial_params": null
|
69 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f703c5fabe5cb9a412c389424fc495379531503bb590137c13ec410f627e14a
|
3 |
+
size 5176
|
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>
|