Hugging Face's logo

AmelieSchreiber
/
PepMLM_v0

Safetensors
Model card Files Community
3
AmelieSchreiber commited on
Commit
14b33ff
•
1 Parent(s): d4058ef

Upload 7 files

Browse files
Files changed (7) hide show
  1. config (6).json +30 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +209 -0
  7. training_args.bin +3 -0
config (6).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": "4.35.0",
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:cff46e1da5c1e5a91e23a930eb941ebaf1a2d03b8c6684eab643c2f370eafe44
3
+ size 2609498088
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ddb74dc8e1b13312662f1c4cee3090907d63ad5144a050192e0d001d5b8c802
3
+ size 5208793186
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5328f04f222a66b45931d6bc246721e0747decf9d78d167903d0547a248f78f0
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7285d7d8fe8880f24cd094fa29c5abf28099fb78efa6b50fd823e41c213d4f5
3
+ size 1000
trainer_state.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.852426052093506,
3
+ "best_model_checkpoint": "./output/checkpoint-102",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 255,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 1.5936680271799274e-05,
14
+ "loss": 3.0929,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.39,
19
+ "learning_rate": 3.187336054359855e-05,
20
+ "loss": 3.1544,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.59,
25
+ "learning_rate": 4.781004081539782e-05,
26
+ "loss": 3.002,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.78,
31
+ "learning_rate": 6.37467210871971e-05,
32
+ "loss": 2.952,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.98,
37
+ "learning_rate": 7.968340135899636e-05,
38
+ "loss": 2.8375,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 1.0,
43
+ "eval_loss": 2.8777899742126465,
44
+ "eval_runtime": 18.561,
45
+ "eval_samples_per_second": 10.937,
46
+ "eval_steps_per_second": 0.7,
47
+ "step": 51
48
+ },
49
+ {
50
+ "epoch": 1.18,
51
+ "learning_rate": 9.562008163079564e-05,
52
+ "loss": 2.7301,
53
+ "step": 60
54
+ },
55
+ {
56
+ "epoch": 1.37,
57
+ "learning_rate": 0.00011155676190259492,
58
+ "loss": 2.6083,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 1.57,
63
+ "learning_rate": 0.0001274934421743942,
64
+ "loss": 2.5973,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.76,
69
+ "learning_rate": 0.00014343012244619346,
70
+ "loss": 2.7028,
71
+ "step": 90
72
+ },
73
+ {
74
+ "epoch": 1.96,
75
+ "learning_rate": 0.00015936680271799272,
76
+ "loss": 2.6389,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 2.0,
81
+ "eval_loss": 2.852426052093506,
82
+ "eval_runtime": 18.9267,
83
+ "eval_samples_per_second": 10.726,
84
+ "eval_steps_per_second": 0.687,
85
+ "step": 102
86
+ },
87
+ {
88
+ "epoch": 2.16,
89
+ "learning_rate": 0.000175303482989792,
90
+ "loss": 2.3737,
91
+ "step": 110
92
+ },
93
+ {
94
+ "epoch": 2.35,
95
+ "learning_rate": 0.00019124016326159128,
96
+ "loss": 2.4245,
97
+ "step": 120
98
+ },
99
+ {
100
+ "epoch": 2.55,
101
+ "learning_rate": 0.00020717684353339054,
102
+ "loss": 2.522,
103
+ "step": 130
104
+ },
105
+ {
106
+ "epoch": 2.75,
107
+ "learning_rate": 0.00022311352380518983,
108
+ "loss": 2.4049,
109
+ "step": 140
110
+ },
111
+ {
112
+ "epoch": 2.94,
113
+ "learning_rate": 0.00023905020407698907,
114
+ "loss": 2.4488,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 3.0,
119
+ "eval_loss": 2.864370346069336,
120
+ "eval_runtime": 19.1132,
121
+ "eval_samples_per_second": 10.621,
122
+ "eval_steps_per_second": 0.68,
123
+ "step": 153
124
+ },
125
+ {
126
+ "epoch": 3.14,
127
+ "learning_rate": 0.0002549868843487884,
128
+ "loss": 2.3544,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 3.33,
133
+ "learning_rate": 0.0002709235646205876,
134
+ "loss": 2.1872,
135
+ "step": 170
136
+ },
137
+ {
138
+ "epoch": 3.53,
139
+ "learning_rate": 0.0002868602448923869,
140
+ "loss": 2.221,
141
+ "step": 180
142
+ },
143
+ {
144
+ "epoch": 3.73,
145
+ "learning_rate": 0.0003027969251641862,
146
+ "loss": 2.4036,
147
+ "step": 190
148
+ },
149
+ {
150
+ "epoch": 3.92,
151
+ "learning_rate": 0.00031873360543598544,
152
+ "loss": 2.4628,
153
+ "step": 200
154
+ },
155
+ {
156
+ "epoch": 4.0,
157
+ "eval_loss": 3.105098247528076,
158
+ "eval_runtime": 19.2038,
159
+ "eval_samples_per_second": 10.571,
160
+ "eval_steps_per_second": 0.677,
161
+ "step": 204
162
+ },
163
+ {
164
+ "epoch": 4.12,
165
+ "learning_rate": 0.0003346702857077847,
166
+ "loss": 2.2478,
167
+ "step": 210
168
+ },
169
+ {
170
+ "epoch": 4.31,
171
+ "learning_rate": 0.000350606965979584,
172
+ "loss": 2.261,
173
+ "step": 220
174
+ },
175
+ {
176
+ "epoch": 4.51,
177
+ "learning_rate": 0.00036654364625138324,
178
+ "loss": 2.3157,
179
+ "step": 230
180
+ },
181
+ {
182
+ "epoch": 4.71,
183
+ "learning_rate": 0.00038248032652318255,
184
+ "loss": 2.1135,
185
+ "step": 240
186
+ },
187
+ {
188
+ "epoch": 4.9,
189
+ "learning_rate": 0.0003984170067949818,
190
+ "loss": 2.2104,
191
+ "step": 250
192
+ },
193
+ {
194
+ "epoch": 5.0,
195
+ "eval_loss": 3.1024045944213867,
196
+ "eval_runtime": 19.1911,
197
+ "eval_samples_per_second": 10.578,
198
+ "eval_steps_per_second": 0.677,
199
+ "step": 255
200
+ }
201
+ ],
202
+ "logging_steps": 10,
203
+ "max_steps": 255,
204
+ "num_train_epochs": 5,
205
+ "save_steps": 500,
206
+ "total_flos": 2188457088743520.0,
207
+ "trial_name": null,
208
+ "trial_params": null
209
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d8fe639bc6c7c7962a8d08ae8a0c4efa2f0384d5101df263bb2617c6750218
3
+ size 4536