Hugging Face's logo

Spaces:
Sunirmala
/
MedPhi-2
Runtime error

App Files Community
Sunirmala commited on
Commit
60c4fd9
·
1 Parent(s): 8ff3715

Upload 2 files

Browse files
Files changed (2) hide show
  1. Med360/optimizer.pt +3 -0
  2. Med360/trainer_state.json +237 -0
Med360/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ecd9f08c6dc9df7f075a8ec7a080e702883e8653731e427e104f4589357bfd
3
+ size 671247290
Med360/trainer_state.json ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7331975560081466,
5
+ "eval_steps": 500,
6
+ "global_step": 360,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 0.0002,
14
+ "loss": 1.6532,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.04,
19
+ "learning_rate": 0.0002,
20
+ "loss": 1.4479,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.06,
25
+ "learning_rate": 0.0002,
26
+ "loss": 1.5807,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.08,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.8864,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.1,
37
+ "learning_rate": 0.0002,
38
+ "loss": 1.9486,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.12,
43
+ "learning_rate": 0.0002,
44
+ "loss": 1.4537,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.14,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.4056,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.16,
55
+ "learning_rate": 0.0002,
56
+ "loss": 1.4739,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.18,
61
+ "learning_rate": 0.0002,
62
+ "loss": 1.878,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.2,
67
+ "learning_rate": 0.0002,
68
+ "loss": 1.9504,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.22,
73
+ "learning_rate": 0.0002,
74
+ "loss": 1.465,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 0.24,
79
+ "learning_rate": 0.0002,
80
+ "loss": 1.4416,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 0.26,
85
+ "learning_rate": 0.0002,
86
+ "loss": 1.5208,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 0.29,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.8197,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 0.31,
97
+ "learning_rate": 0.0002,
98
+ "loss": 1.9127,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 0.33,
103
+ "learning_rate": 0.0002,
104
+ "loss": 1.4908,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 0.35,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.3915,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 0.37,
115
+ "learning_rate": 0.0002,
116
+ "loss": 1.5791,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 0.39,
121
+ "learning_rate": 0.0002,
122
+ "loss": 2.0458,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 0.41,
127
+ "learning_rate": 0.0002,
128
+ "loss": 1.9205,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 0.43,
133
+ "learning_rate": 0.0002,
134
+ "loss": 1.4595,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 0.45,
139
+ "learning_rate": 0.0002,
140
+ "loss": 1.4085,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 0.47,
145
+ "learning_rate": 0.0002,
146
+ "loss": 1.4964,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 0.49,
151
+ "learning_rate": 0.0002,
152
+ "loss": 1.8586,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 0.51,
157
+ "learning_rate": 0.0002,
158
+ "loss": 1.8511,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 0.53,
163
+ "learning_rate": 0.0002,
164
+ "loss": 1.3773,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 0.55,
169
+ "learning_rate": 0.0002,
170
+ "loss": 1.3869,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 0.57,
175
+ "learning_rate": 0.0002,
176
+ "loss": 1.6083,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 0.59,
181
+ "learning_rate": 0.0002,
182
+ "loss": 1.8549,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 0.61,
187
+ "learning_rate": 0.0002,
188
+ "loss": 1.8714,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 0.63,
193
+ "learning_rate": 0.0002,
194
+ "loss": 1.3614,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 0.65,
199
+ "learning_rate": 0.0002,
200
+ "loss": 1.4,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 0.67,
205
+ "learning_rate": 0.0002,
206
+ "loss": 1.5435,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 0.69,
211
+ "learning_rate": 0.0002,
212
+ "loss": 1.8155,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 0.71,
217
+ "learning_rate": 0.0002,
218
+ "loss": 1.9587,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 0.73,
223
+ "learning_rate": 0.0002,
224
+ "loss": 1.3705,
225
+ "step": 360
226
+ }
227
+ ],
228
+ "logging_steps": 10,
229
+ "max_steps": 500,
230
+ "num_input_tokens_seen": 0,
231
+ "num_train_epochs": 2,
232
+ "save_steps": 20,
233
+ "total_flos": 1.757604963096576e+16,
234
+ "train_batch_size": 2,
235
+ "trial_name": null,
236
+ "trial_params": null
237
+ }