mgh6 commited on
Commit
94eacd8
·
1 Parent(s): 41f2fc2

Training in progress, step 5500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ff721e4a6c56053bf413e1567573ce87ef232b4ccf251a600525759976b1921
3
  size 135998360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebfd0d2508b097460491a16843d7685c50686005f6790680a7d1dddd0edcbed
3
  size 135998360
run-bad69_00000/checkpoint-5500/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mgh6/esm_cluster_35M_linear",
3
+ "architectures": [
4
+ "EsmForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout": 0.18727005942368125,
8
+ "emb_layer_norm_before": false,
9
+ "esmfold_config": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 480,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 1920,
18
+ "is_folding_model": false,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "mask_token_id": 32,
24
+ "max_position_embeddings": 1026,
25
+ "model_type": "esm",
26
+ "num_attention_heads": 20,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "rotary",
30
+ "problem_type": "regression",
31
+ "token_dropout": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.2",
34
+ "use_cache": true,
35
+ "vocab_list": null,
36
+ "vocab_size": 33
37
+ }
run-bad69_00000/checkpoint-5500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebfd0d2508b097460491a16843d7685c50686005f6790680a7d1dddd0edcbed
3
+ size 135998360
run-bad69_00000/checkpoint-5500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85645ccca6b20cd3560f57a8d589fa253eb9409f52189d380ed7c8a376b2923b
3
+ size 268171578
run-bad69_00000/checkpoint-5500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39cc61601df3eaac699ee8bc16c179d3f2418d9e439c33a8780992463dbc4723
3
+ size 14244
run-bad69_00000/checkpoint-5500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b524c288284c9ca2bba99c62d8e93a9de70291f72422b2606980706a12db551
3
+ size 1064
run-bad69_00000/checkpoint-5500/trainer_state.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18187156319618225,
3
+ "best_model_checkpoint": "mgh6/TCS_Pair/run-bad69_00000/checkpoint-2000",
4
+ "epoch": 1.4790910313298373,
5
+ "eval_steps": 500,
6
+ "global_step": 5500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13,
13
+ "learning_rate": 0.00079158678443389,
14
+ "loss": 0.1584,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.13,
19
+ "eval_loss": 0.2451040893793106,
20
+ "eval_runtime": 21.3792,
21
+ "eval_samples_per_second": 224.096,
22
+ "eval_steps_per_second": 28.018,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.27,
27
+ "learning_rate": 0.000786228087003387,
28
+ "loss": 0.1285,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.27,
33
+ "eval_loss": 0.19461262226104736,
34
+ "eval_runtime": 21.0052,
35
+ "eval_samples_per_second": 228.086,
36
+ "eval_steps_per_second": 28.517,
37
+ "step": 1000
38
+ },
39
+ {
40
+ "epoch": 0.4,
41
+ "learning_rate": 0.0007808693895728842,
42
+ "loss": 0.1232,
43
+ "step": 1500
44
+ },
45
+ {
46
+ "epoch": 0.4,
47
+ "eval_loss": 0.268852174282074,
48
+ "eval_runtime": 21.1069,
49
+ "eval_samples_per_second": 226.988,
50
+ "eval_steps_per_second": 28.379,
51
+ "step": 1500
52
+ },
53
+ {
54
+ "epoch": 0.54,
55
+ "learning_rate": 0.0007755106921423813,
56
+ "loss": 0.1182,
57
+ "step": 2000
58
+ },
59
+ {
60
+ "epoch": 0.54,
61
+ "eval_loss": 0.18187156319618225,
62
+ "eval_runtime": 21.0753,
63
+ "eval_samples_per_second": 227.328,
64
+ "eval_steps_per_second": 28.422,
65
+ "step": 2000
66
+ },
67
+ {
68
+ "epoch": 0.67,
69
+ "learning_rate": 0.0007701519947118784,
70
+ "loss": 0.1642,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 0.67,
75
+ "eval_loss": 0.25392478704452515,
76
+ "eval_runtime": 21.48,
77
+ "eval_samples_per_second": 223.045,
78
+ "eval_steps_per_second": 27.886,
79
+ "step": 2500
80
+ },
81
+ {
82
+ "epoch": 0.81,
83
+ "learning_rate": 0.0007647932972813753,
84
+ "loss": 0.1779,
85
+ "step": 3000
86
+ },
87
+ {
88
+ "epoch": 0.81,
89
+ "eval_loss": 0.2446264624595642,
90
+ "eval_runtime": 21.3207,
91
+ "eval_samples_per_second": 224.711,
92
+ "eval_steps_per_second": 28.095,
93
+ "step": 3000
94
+ },
95
+ {
96
+ "epoch": 0.94,
97
+ "learning_rate": 0.0007594345998508726,
98
+ "loss": 0.1776,
99
+ "step": 3500
100
+ },
101
+ {
102
+ "epoch": 0.94,
103
+ "eval_loss": 0.2562008798122406,
104
+ "eval_runtime": 21.0095,
105
+ "eval_samples_per_second": 228.039,
106
+ "eval_steps_per_second": 28.511,
107
+ "step": 3500
108
+ },
109
+ {
110
+ "epoch": 1.08,
111
+ "learning_rate": 0.0007540759024203697,
112
+ "loss": 0.175,
113
+ "step": 4000
114
+ },
115
+ {
116
+ "epoch": 1.08,
117
+ "eval_loss": 0.2355659455060959,
118
+ "eval_runtime": 21.3063,
119
+ "eval_samples_per_second": 224.863,
120
+ "eval_steps_per_second": 28.114,
121
+ "step": 4000
122
+ },
123
+ {
124
+ "epoch": 1.21,
125
+ "learning_rate": 0.0007487172049898666,
126
+ "loss": 0.1362,
127
+ "step": 4500
128
+ },
129
+ {
130
+ "epoch": 1.21,
131
+ "eval_loss": 0.21570900082588196,
132
+ "eval_runtime": 21.316,
133
+ "eval_samples_per_second": 224.761,
134
+ "eval_steps_per_second": 28.101,
135
+ "step": 4500
136
+ },
137
+ {
138
+ "epoch": 1.34,
139
+ "learning_rate": 0.0007433585075593637,
140
+ "loss": 0.1122,
141
+ "step": 5000
142
+ },
143
+ {
144
+ "epoch": 1.34,
145
+ "eval_loss": 0.1876734346151352,
146
+ "eval_runtime": 21.4079,
147
+ "eval_samples_per_second": 223.796,
148
+ "eval_steps_per_second": 27.98,
149
+ "step": 5000
150
+ },
151
+ {
152
+ "epoch": 1.48,
153
+ "learning_rate": 0.0007379998101288608,
154
+ "loss": 0.101,
155
+ "step": 5500
156
+ },
157
+ {
158
+ "epoch": 1.48,
159
+ "eval_loss": 0.18231742084026337,
160
+ "eval_runtime": 21.3418,
161
+ "eval_samples_per_second": 224.489,
162
+ "eval_steps_per_second": 28.067,
163
+ "step": 5500
164
+ }
165
+ ],
166
+ "logging_steps": 500,
167
+ "max_steps": 74360,
168
+ "num_train_epochs": 20,
169
+ "save_steps": 500,
170
+ "total_flos": 5586848799976368.0,
171
+ "trial_name": null,
172
+ "trial_params": {
173
+ "classifier_dropout": 0.18727005942368125,
174
+ "gradient_accumulation_steps": 2,
175
+ "learning_rate": 0.0007969454818643929,
176
+ "weight_decay": 0.029106359131330688
177
+ }
178
+ }
run-bad69_00000/checkpoint-5500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6824f9fe4d5530bdfbcda9b94035c681cade4710ef178c7fb69dcfe7e47c4df
3
+ size 4600