Harikishanth commited on
Commit
d990486
·
1 Parent(s): 6d3689c

results: training evidence

Browse files
Files changed (2) hide show
  1. sft_loss_curve.png +3 -0
  2. training_rewards.json +252 -0
sft_loss_curve.png ADDED

Git LFS Details

  • SHA256: b4734887d96f9405fee95223c8aff5af05be5f140b23fb431130daca9f58e462
  • Pointer size: 130 Bytes
  • Size of remote file: 59.8 kB
training_rewards.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "episode": 1,
4
+ "reward": -6.545,
5
+ "resolved": false
6
+ },
7
+ {
8
+ "episode": 2,
9
+ "reward": -6.545,
10
+ "resolved": false
11
+ },
12
+ {
13
+ "episode": 3,
14
+ "reward": -6.585,
15
+ "resolved": false
16
+ },
17
+ {
18
+ "episode": 4,
19
+ "reward": -6.545,
20
+ "resolved": false
21
+ },
22
+ {
23
+ "episode": 5,
24
+ "reward": -6.545,
25
+ "resolved": false
26
+ },
27
+ {
28
+ "episode": 6,
29
+ "reward": -6.585,
30
+ "resolved": false
31
+ },
32
+ {
33
+ "episode": 7,
34
+ "reward": -6.585,
35
+ "resolved": false
36
+ },
37
+ {
38
+ "episode": 8,
39
+ "reward": -6.545,
40
+ "resolved": false
41
+ },
42
+ {
43
+ "episode": 9,
44
+ "reward": -6.545,
45
+ "resolved": false
46
+ },
47
+ {
48
+ "episode": 10,
49
+ "reward": -6.545,
50
+ "resolved": false
51
+ },
52
+ {
53
+ "episode": 11,
54
+ "reward": -6.545,
55
+ "resolved": false
56
+ },
57
+ {
58
+ "episode": 12,
59
+ "reward": -6.585,
60
+ "resolved": false
61
+ },
62
+ {
63
+ "episode": 13,
64
+ "reward": -6.545,
65
+ "resolved": false
66
+ },
67
+ {
68
+ "episode": 14,
69
+ "reward": -6.545,
70
+ "resolved": false
71
+ },
72
+ {
73
+ "episode": 15,
74
+ "reward": -6.545,
75
+ "resolved": false
76
+ },
77
+ {
78
+ "episode": 16,
79
+ "reward": -5.945,
80
+ "resolved": false
81
+ },
82
+ {
83
+ "episode": 17,
84
+ "reward": -6.545,
85
+ "resolved": false
86
+ },
87
+ {
88
+ "episode": 18,
89
+ "reward": -6.545,
90
+ "resolved": false
91
+ },
92
+ {
93
+ "episode": 19,
94
+ "reward": -6.545,
95
+ "resolved": false
96
+ },
97
+ {
98
+ "episode": 20,
99
+ "reward": -6.585,
100
+ "resolved": false
101
+ },
102
+ {
103
+ "episode": 21,
104
+ "reward": -6.545,
105
+ "resolved": false
106
+ },
107
+ {
108
+ "episode": 22,
109
+ "reward": -6.545,
110
+ "resolved": false
111
+ },
112
+ {
113
+ "episode": 23,
114
+ "reward": -5.925,
115
+ "resolved": false
116
+ },
117
+ {
118
+ "episode": 24,
119
+ "reward": -6.585,
120
+ "resolved": false
121
+ },
122
+ {
123
+ "episode": 25,
124
+ "reward": -6.545,
125
+ "resolved": false
126
+ },
127
+ {
128
+ "episode": 26,
129
+ "reward": -6.545,
130
+ "resolved": false
131
+ },
132
+ {
133
+ "episode": 27,
134
+ "reward": -6.545,
135
+ "resolved": false
136
+ },
137
+ {
138
+ "episode": 28,
139
+ "reward": -6.545,
140
+ "resolved": false
141
+ },
142
+ {
143
+ "episode": 29,
144
+ "reward": -6.545,
145
+ "resolved": false
146
+ },
147
+ {
148
+ "episode": 30,
149
+ "reward": -6.545,
150
+ "resolved": false
151
+ },
152
+ {
153
+ "episode": 31,
154
+ "reward": -6.545,
155
+ "resolved": false
156
+ },
157
+ {
158
+ "episode": 32,
159
+ "reward": -5.925,
160
+ "resolved": false
161
+ },
162
+ {
163
+ "episode": 33,
164
+ "reward": -6.545,
165
+ "resolved": false
166
+ },
167
+ {
168
+ "episode": 34,
169
+ "reward": -6.585,
170
+ "resolved": false
171
+ },
172
+ {
173
+ "episode": 35,
174
+ "reward": -6.545,
175
+ "resolved": false
176
+ },
177
+ {
178
+ "episode": 36,
179
+ "reward": -6.545,
180
+ "resolved": false
181
+ },
182
+ {
183
+ "episode": 37,
184
+ "reward": -6.545,
185
+ "resolved": false
186
+ },
187
+ {
188
+ "episode": 38,
189
+ "reward": -6.585,
190
+ "resolved": false
191
+ },
192
+ {
193
+ "episode": 39,
194
+ "reward": -6.545,
195
+ "resolved": false
196
+ },
197
+ {
198
+ "episode": 40,
199
+ "reward": -6.545,
200
+ "resolved": false
201
+ },
202
+ {
203
+ "episode": 41,
204
+ "reward": -6.545,
205
+ "resolved": false
206
+ },
207
+ {
208
+ "episode": 42,
209
+ "reward": -6.585,
210
+ "resolved": false
211
+ },
212
+ {
213
+ "episode": 43,
214
+ "reward": -6.585,
215
+ "resolved": false
216
+ },
217
+ {
218
+ "episode": 44,
219
+ "reward": -6.545,
220
+ "resolved": false
221
+ },
222
+ {
223
+ "episode": 45,
224
+ "reward": -6.545,
225
+ "resolved": false
226
+ },
227
+ {
228
+ "episode": 46,
229
+ "reward": -6.585,
230
+ "resolved": false
231
+ },
232
+ {
233
+ "episode": 47,
234
+ "reward": -6.585,
235
+ "resolved": false
236
+ },
237
+ {
238
+ "episode": 48,
239
+ "reward": -6.545,
240
+ "resolved": false
241
+ },
242
+ {
243
+ "episode": 49,
244
+ "reward": -6.545,
245
+ "resolved": false
246
+ },
247
+ {
248
+ "episode": 50,
249
+ "reward": -6.585,
250
+ "resolved": false
251
+ }
252
+ ]