Hugging Face's logo

zfan3
/
Genesis_Quant_8k_attention_pooling

Safetensors
Model card Files
xet
 Community
zfan3 commited on
Commit
9304fdd
·
verified ·
1 Parent(s): 6bfb333

Upload 9 files

Browse files
Files changed (9) hide show
  1. model.safetensors +3 -0
  2. optimizer.pt +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer_config.json +52 -0
  7. trainer_state.json +99 -0
  8. training_args.bin +3 -0
  9. vocab.txt +33 -0
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11594e3d4a40bd632e6fe5836f1f6a0aae01f98d67b72e5df1aed7781d9900fa
3
+ size 136002512
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adbfb95c457ffd422960bd4b81e156236e4919cdf02bd6b580c082743e35f4ce
3
+ size 266328378
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0461cec498e3d67c6d8179f9a198ad9ae60c60ae04a6fe4c7a8b70ffa87cbe
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": 1024,
49
+ "pad_token": "<pad>",
50
+ "tokenizer_class": "EsmTokenizer",
51
+ "unk_token": "<unk>"
52
+ }
trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.08365064859390259,
3
+ "best_model_checkpoint": "./Genesis_quant_v18_8k_linear_padding_head_benchmarking/checkpoint-3614",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3614,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.28,
13
+ "learning_rate": 2.8339789706696182e-05,
14
+ "loss": 0.0439,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.55,
19
+ "learning_rate": 2.6679579413392364e-05,
20
+ "loss": 0.0339,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.83,
25
+ "learning_rate": 2.5019369120088545e-05,
26
+ "loss": 0.0219,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_epoch": 1.0,
32
+ "eval_head_type": "linear",
33
+ "eval_loss": 0.03443923220038414,
34
+ "eval_mae2": 0.23664554953575134,
35
+ "eval_mse1": 0.02161429077386856,
36
+ "eval_mse2": 0.13640384376049042,
37
+ "eval_n_valid": 904,
38
+ "eval_pearson2": 0.757525353160554,
39
+ "eval_r2_2": 0.38493316923911924,
40
+ "eval_rmse2": 0.36932891607284546,
41
+ "eval_runtime": 8.9423,
42
+ "eval_samples_per_second": 101.092,
43
+ "eval_spearman2": 0.7637428902304154,
44
+ "eval_steps_per_second": 25.273,
45
+ "step": 1807
46
+ },
47
+ {
48
+ "epoch": 1.11,
49
+ "learning_rate": 2.3359158826784726e-05,
50
+ "loss": 0.0189,
51
+ "step": 2000
52
+ },
53
+ {
54
+ "epoch": 1.38,
55
+ "learning_rate": 2.1698948533480908e-05,
56
+ "loss": 0.0147,
57
+ "step": 2500
58
+ },
59
+ {
60
+ "epoch": 1.66,
61
+ "learning_rate": 2.003873824017709e-05,
62
+ "loss": 0.0123,
63
+ "step": 3000
64
+ },
65
+ {
66
+ "epoch": 1.94,
67
+ "learning_rate": 1.837852794687327e-05,
68
+ "loss": 0.0139,
69
+ "step": 3500
70
+ },
71
+ {
72
+ "epoch": 2.0,
73
+ "eval_epoch": 2.0,
74
+ "eval_head_type": "linear",
75
+ "eval_loss": 0.02601287141442299,
76
+ "eval_mae2": 0.18473036587238312,
77
+ "eval_mse1": 0.018763288855552673,
78
+ "eval_mse2": 0.08365064859390259,
79
+ "eval_n_valid": 904,
80
+ "eval_pearson2": 0.8231394464607437,
81
+ "eval_r2_2": 0.6228058801891168,
82
+ "eval_rmse2": 0.28922420740127563,
83
+ "eval_runtime": 8.9375,
84
+ "eval_samples_per_second": 101.147,
85
+ "eval_spearman2": 0.7646683676720165,
86
+ "eval_steps_per_second": 25.287,
87
+ "step": 3614
88
+ }
89
+ ],
90
+ "logging_steps": 500,
91
+ "max_steps": 9035,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 5,
94
+ "save_steps": 500,
95
+ "total_flos": 0.0,
96
+ "train_batch_size": 4,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e87820050e860973b5022ae16e2eeded9aad42db2a77815ec4222da5e9316e
3
+ size 4792
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>