Hugging Face's logo

alegendaryfish
/
CodonTranslator

PyTorch
Safetensors
biology
dna
codon-optimization
protein-conditioned-generation
fsdp
Model card Files
xet
 Community
alegendaryfish commited on
Commit
950b7bd
·
verified ·
1 Parent(s): 1dbb59f

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. training_checkpoints/checkpoint-10000/scheduler.pt +3 -0
  2. training_checkpoints/checkpoint-10000/trainer_config.json +17 -0
  3. training_checkpoints/checkpoint-10000/trainer_state.json +4 -0
  4. training_checkpoints/checkpoint-10000/vocab.json +78 -0
  5. training_checkpoints/checkpoint-15000/scheduler.pt +3 -0
  6. training_checkpoints/checkpoint-15000/trainer_config.json +17 -0
  7. training_checkpoints/checkpoint-15000/trainer_state.json +4 -0
  8. training_checkpoints/checkpoint-15000/vocab.json +78 -0
  9. training_checkpoints/checkpoint-20000/scheduler.pt +3 -0
  10. training_checkpoints/checkpoint-20000/trainer_config.json +17 -0
  11. training_checkpoints/checkpoint-20000/trainer_state.json +4 -0
  12. training_checkpoints/checkpoint-20000/vocab.json +78 -0
  13. training_checkpoints/checkpoint-25000/scheduler.pt +3 -0
  14. training_checkpoints/checkpoint-25000/trainer_config.json +17 -0
  15. training_checkpoints/checkpoint-25000/trainer_state.json +4 -0
  16. training_checkpoints/checkpoint-25000/vocab.json +78 -0
  17. training_checkpoints/checkpoint-30000/trainer_config.json +17 -0
  18. training_checkpoints/checkpoint-30000/trainer_state.json +4 -0
  19. training_checkpoints/checkpoint-30000/vocab.json +78 -0
  20. training_checkpoints/checkpoint-35000/trainer_config.json +17 -0
  21. training_checkpoints/checkpoint-35000/trainer_state.json +4 -0
  22. training_checkpoints/checkpoint-35000/vocab.json +78 -0
  23. training_checkpoints/checkpoint-40000/trainer_config.json +17 -0
  24. training_checkpoints/checkpoint-40000/trainer_state.json +4 -0
  25. training_checkpoints/checkpoint-40000/vocab.json +78 -0
  26. training_checkpoints/checkpoint-45000/trainer_config.json +17 -0
  27. training_checkpoints/checkpoint-45000/trainer_state.json +4 -0
  28. training_checkpoints/checkpoint-45000/vocab.json +78 -0
  29. training_checkpoints/checkpoint-5000/trainer_config.json +17 -0
  30. training_checkpoints/checkpoint-5000/trainer_state.json +4 -0
  31. training_checkpoints/checkpoint-5000/vocab.json +78 -0
  32. training_checkpoints/checkpoint-50000/optimizer.pt +3 -0
  33. training_checkpoints/checkpoint-50000/trainer_config.json +17 -0
  34. training_checkpoints/checkpoint-50000/trainer_state.json +4 -0
  35. training_checkpoints/checkpoint-50000/vocab.json +78 -0
  36. training_checkpoints/checkpoint-55000/trainer_config.json +17 -0
  37. training_checkpoints/checkpoint-55000/trainer_state.json +4 -0
  38. training_checkpoints/checkpoint-55000/vocab.json +78 -0
  39. training_checkpoints/checkpoint-60000/optimizer.pt +3 -0
  40. training_checkpoints/checkpoint-60000/trainer_config.json +17 -0
  41. training_checkpoints/checkpoint-60000/trainer_state.json +4 -0
  42. training_checkpoints/checkpoint-60000/vocab.json +78 -0
  43. training_checkpoints/checkpoint-65000/optimizer.pt +3 -0
  44. training_checkpoints/checkpoint-65000/trainer_config.json +17 -0
  45. training_checkpoints/checkpoint-65000/trainer_state.json +4 -0
  46. training_checkpoints/checkpoint-65000/vocab.json +78 -0
  47. training_checkpoints/checkpoint-70000/optimizer.pt +3 -0
  48. training_checkpoints/checkpoint-70000/trainer_config.json +17 -0
  49. training_checkpoints/checkpoint-70000/trainer_state.json +4 -0
  50. training_checkpoints/checkpoint-70000/vocab.json +78 -0
training_checkpoints/checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5823671ed3b2bc675facedd77f22ad8483ff92e91fd3c718219687507cdf4c0
3
+ size 1465
training_checkpoints/checkpoint-10000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 0,
3
+ "global_step": 10000
4
+ }
training_checkpoints/checkpoint-10000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-15000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de62c70093d4935c1964c4ad211b0aebc926c8bd2f29cc09e917906ecba7f53
3
+ size 1465
training_checkpoints/checkpoint-15000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-15000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 0,
3
+ "global_step": 15000
4
+ }
training_checkpoints/checkpoint-15000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477c0b4b118e155de3b3e6948133bdde7b504978d0ea45ddea8c8b2bd9db684c
3
+ size 1465
training_checkpoints/checkpoint-20000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-20000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 0,
3
+ "global_step": 20000
4
+ }
training_checkpoints/checkpoint-20000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-25000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b72fbb8e4f4f60881f28c8afc2275790fe5cc94af4898d509e453957929b4cce
3
+ size 1465
training_checkpoints/checkpoint-25000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-25000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 1,
3
+ "global_step": 25000
4
+ }
training_checkpoints/checkpoint-25000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-30000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-30000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 1,
3
+ "global_step": 30000
4
+ }
training_checkpoints/checkpoint-30000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-35000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-35000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 1,
3
+ "global_step": 35000
4
+ }
training_checkpoints/checkpoint-35000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-40000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-40000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 1,
3
+ "global_step": 40000
4
+ }
training_checkpoints/checkpoint-40000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-45000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-45000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 1,
3
+ "global_step": 45000
4
+ }
training_checkpoints/checkpoint-45000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-5000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 0,
3
+ "global_step": 5000
4
+ }
training_checkpoints/checkpoint-5000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-50000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4713f6f2b96b5c1835d83677851797d82a59fe15b7654bd70b106e73c105e3bb
3
+ size 1237115851
training_checkpoints/checkpoint-50000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-50000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 2,
3
+ "global_step": 50000
4
+ }
training_checkpoints/checkpoint-50000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-55000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-55000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 2,
3
+ "global_step": 55000
4
+ }
training_checkpoints/checkpoint-55000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-60000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255c4293630a42d81f4921a32d3c042ba93b1f54afa52b942acfe9f988c8ff1c
3
+ size 1237115851
training_checkpoints/checkpoint-60000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-60000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 2,
3
+ "global_step": 60000
4
+ }
training_checkpoints/checkpoint-60000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-65000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2049a6b4d0270b1d72cce3973bd6940697cc3e95ef3e0dc922eeaae2e36cbcc
3
+ size 1237115851
training_checkpoints/checkpoint-65000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-65000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 2,
3
+ "global_step": 65000
4
+ }
training_checkpoints/checkpoint-65000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }
training_checkpoints/checkpoint-70000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c4d54ea41cabec318a0452f21880c6e655b814aaccaa5fd7d4a5e756012c71
3
+ size 1237115851
training_checkpoints/checkpoint-70000/trainer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": 2048,
3
+ "max_species_prefix": 0,
4
+ "max_protein_prefix": 1024,
5
+ "hidden_size": 750,
6
+ "num_hidden_layers": 20,
7
+ "num_attention_heads": 15,
8
+ "mlp_ratio": 3.2,
9
+ "prepend_species": true,
10
+ "prepend_protein": true,
11
+ "species_embedding_dim": 1024,
12
+ "esm_model_name": "esmc_300m",
13
+ "esm_device": "cuda:0",
14
+ "esm_dtype": "bf16",
15
+ "attn_impl": "mha",
16
+ "num_kv_groups": 5
17
+ }
training_checkpoints/checkpoint-70000/trainer_state.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "epoch": 2,
3
+ "global_step": 70000
4
+ }
training_checkpoints/checkpoint-70000/vocab.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_token_str": {
3
+ "bos": "<bos>",
4
+ "eos": "<stop>",
5
+ "pad": "<pad>",
6
+ "unk": "<unk>"
7
+ },
8
+ "vocab": {
9
+ "<bos>": 2,
10
+ "<pad>": 0,
11
+ "<stop>": 3,
12
+ "<unk>": 1,
13
+ "AAA": 4,
14
+ "AAC": 5,
15
+ "AAG": 6,
16
+ "AAT": 7,
17
+ "ACA": 8,
18
+ "ACC": 9,
19
+ "ACG": 10,
20
+ "ACT": 11,
21
+ "AGA": 12,
22
+ "AGC": 13,
23
+ "AGG": 14,
24
+ "AGT": 15,
25
+ "ATA": 16,
26
+ "ATC": 17,
27
+ "ATG": 18,
28
+ "ATT": 19,
29
+ "CAA": 20,
30
+ "CAC": 21,
31
+ "CAG": 22,
32
+ "CAT": 23,
33
+ "CCA": 24,
34
+ "CCC": 25,
35
+ "CCG": 26,
36
+ "CCT": 27,
37
+ "CGA": 28,
38
+ "CGC": 29,
39
+ "CGG": 30,
40
+ "CGT": 31,
41
+ "CTA": 32,
42
+ "CTC": 33,
43
+ "CTG": 34,
44
+ "CTT": 35,
45
+ "GAA": 36,
46
+ "GAC": 37,
47
+ "GAG": 38,
48
+ "GAT": 39,
49
+ "GCA": 40,
50
+ "GCC": 41,
51
+ "GCG": 42,
52
+ "GCT": 43,
53
+ "GGA": 44,
54
+ "GGC": 45,
55
+ "GGG": 46,
56
+ "GGT": 47,
57
+ "GTA": 48,
58
+ "GTC": 49,
59
+ "GTG": 50,
60
+ "GTT": 51,
61
+ "TAA": 52,
62
+ "TAC": 53,
63
+ "TAG": 54,
64
+ "TAT": 55,
65
+ "TCA": 56,
66
+ "TCC": 57,
67
+ "TCG": 58,
68
+ "TCT": 59,
69
+ "TGA": 60,
70
+ "TGC": 61,
71
+ "TGG": 62,
72
+ "TGT": 63,
73
+ "TTA": 64,
74
+ "TTC": 65,
75
+ "TTG": 66,
76
+ "TTT": 67
77
+ }
78
+ }