Hugging Face's logo

GleghornLab
/
CAMP_nat

Transformers
Safetensors
CAMP
Inference Endpoints
Model card Files Community
lhallee commited on
Commit
910d2d6
·
verified ·
1 Parent(s): 4cc2777

Training in progress, step 2000, checkpoint

Browse files
Files changed (4) hide show
  1. checkpoint-2000/config.json +25 -0
  2. checkpoint-2000/model.safetensors +3 -0
  3. checkpoint-2000/trainer_state.json +195 -0
  4. checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "annotation_transformer": false,
3
+ "architectures": [
4
+ "CAMP"
5
+ ],
6
+ "diff": false,
7
+ "dropout": 0.05,
8
+ "hidden_dim": 640,
9
+ "input_dim": 384,
10
+ "intermediate_dim": 2560,
11
+ "kernel_size": 11,
12
+ "latent": false,
13
+ "mlm": false,
14
+ "mnr": false,
15
+ "model_type": "CAMP",
16
+ "nhead": 8,
17
+ "nlp_path": "allenai/scibert_scivocab_uncased",
18
+ "num_hidden_layers": 1,
19
+ "out_dim": 512,
20
+ "plm_path": "facebook/esm2_t33_650m_UR50D",
21
+ "pooling": "avg",
22
+ "token": null,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.41.2"
25
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ef05b1a66abe8d896f5634ed7d96b8b0c43d6cc17bfd7a3ee1214ab64759a5
3
+ size 1570427506
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.04479684630202034,
5
+ "eval_steps": 1000,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002239842315101017,
13
+ "grad_norm": 71.10852813720703,
14
+ "learning_rate": 0.0001,
15
+ "loss": 3.5057,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.004479684630202034,
20
+ "grad_norm": 57.756534576416016,
21
+ "learning_rate": 9.9998756572327e-05,
22
+ "loss": 0.8254,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.006719526945303051,
27
+ "grad_norm": 44.61080551147461,
28
+ "learning_rate": 9.999502635115246e-05,
29
+ "loss": 0.6935,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.008959369260404068,
34
+ "grad_norm": 50.82619094848633,
35
+ "learning_rate": 9.998880952200681e-05,
36
+ "loss": 0.5972,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.011199211575505085,
41
+ "grad_norm": 44.26677703857422,
42
+ "learning_rate": 9.998010639409713e-05,
43
+ "loss": 0.5408,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.013439053890606102,
48
+ "grad_norm": 42.8045654296875,
49
+ "learning_rate": 9.996891740029186e-05,
50
+ "loss": 0.5509,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.01567889620570712,
55
+ "grad_norm": 30.989139556884766,
56
+ "learning_rate": 9.995524309709913e-05,
57
+ "loss": 0.4823,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.017918738520808136,
62
+ "grad_norm": 34.01952362060547,
63
+ "learning_rate": 9.993908416463927e-05,
64
+ "loss": 0.5111,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.020158580835909153,
69
+ "grad_norm": 34.079307556152344,
70
+ "learning_rate": 9.992044140661079e-05,
71
+ "loss": 0.4635,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.02239842315101017,
76
+ "grad_norm": 26.16071128845215,
77
+ "learning_rate": 9.989931575025056e-05,
78
+ "loss": 0.4883,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.02239842315101017,
83
+ "eval_avg_non_pair_similarity": 0.0020343252948339737,
84
+ "eval_avg_pair_similarity": 0.008852629057131708,
85
+ "eval_loss": 0.5431402921676636,
86
+ "eval_runtime": 19.6178,
87
+ "eval_samples_per_second": 25.487,
88
+ "eval_similarity_ratio": 4.35162905343228,
89
+ "eval_steps_per_second": 0.816,
90
+ "step": 1000
91
+ },
92
+ {
93
+ "epoch": 0.024638265466111187,
94
+ "grad_norm": 35.38695526123047,
95
+ "learning_rate": 9.987570824628759e-05,
96
+ "loss": 0.4655,
97
+ "step": 1100
98
+ },
99
+ {
100
+ "epoch": 0.026878107781212204,
101
+ "grad_norm": 32.071346282958984,
102
+ "learning_rate": 9.984962006889084e-05,
103
+ "loss": 0.4342,
104
+ "step": 1200
105
+ },
106
+ {
107
+ "epoch": 0.029117950096313218,
108
+ "grad_norm": 39.6610221862793,
109
+ "learning_rate": 9.982105251561082e-05,
110
+ "loss": 0.458,
111
+ "step": 1300
112
+ },
113
+ {
114
+ "epoch": 0.03135779241141424,
115
+ "grad_norm": 31.493322372436523,
116
+ "learning_rate": 9.979000700731491e-05,
117
+ "loss": 0.4525,
118
+ "step": 1400
119
+ },
120
+ {
121
+ "epoch": 0.03359763472651525,
122
+ "grad_norm": 34.453399658203125,
123
+ "learning_rate": 9.975648508811693e-05,
124
+ "loss": 0.41,
125
+ "step": 1500
126
+ },
127
+ {
128
+ "epoch": 0.03583747704161627,
129
+ "grad_norm": 33.990074157714844,
130
+ "learning_rate": 9.972048842530012e-05,
131
+ "loss": 0.4097,
132
+ "step": 1600
133
+ },
134
+ {
135
+ "epoch": 0.038077319356717286,
136
+ "grad_norm": 30.44228172302246,
137
+ "learning_rate": 9.968201880923439e-05,
138
+ "loss": 0.4257,
139
+ "step": 1700
140
+ },
141
+ {
142
+ "epoch": 0.040317161671818307,
143
+ "grad_norm": 31.427162170410156,
144
+ "learning_rate": 9.964107815328711e-05,
145
+ "loss": 0.3821,
146
+ "step": 1800
147
+ },
148
+ {
149
+ "epoch": 0.04255700398691932,
150
+ "grad_norm": 25.877887725830078,
151
+ "learning_rate": 9.959766849372808e-05,
152
+ "loss": 0.3788,
153
+ "step": 1900
154
+ },
155
+ {
156
+ "epoch": 0.04479684630202034,
157
+ "grad_norm": 25.36798095703125,
158
+ "learning_rate": 9.955179198962817e-05,
159
+ "loss": 0.3854,
160
+ "step": 2000
161
+ },
162
+ {
163
+ "epoch": 0.04479684630202034,
164
+ "eval_avg_non_pair_similarity": 0.0016289287904792565,
165
+ "eval_avg_pair_similarity": 0.0032495629731565715,
166
+ "eval_loss": 0.4394480586051941,
167
+ "eval_runtime": 19.5064,
168
+ "eval_samples_per_second": 25.633,
169
+ "eval_similarity_ratio": 1.9949079371360972,
170
+ "eval_steps_per_second": 0.82,
171
+ "step": 2000
172
+ }
173
+ ],
174
+ "logging_steps": 100,
175
+ "max_steps": 44646,
176
+ "num_input_tokens_seen": 0,
177
+ "num_train_epochs": 1,
178
+ "save_steps": 1000,
179
+ "stateful_callbacks": {
180
+ "TrainerControl": {
181
+ "args": {
182
+ "should_epoch_stop": false,
183
+ "should_evaluate": false,
184
+ "should_log": false,
185
+ "should_save": true,
186
+ "should_training_stop": false
187
+ },
188
+ "attributes": {}
189
+ }
190
+ },
191
+ "total_flos": 0.0,
192
+ "train_batch_size": 32,
193
+ "trial_name": null,
194
+ "trial_params": null
195
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6bbe0930b5977d5ef83c9c6a2872aea787e9f64c3d133a00319e43c833ad34
3
+ size 5112