limernyou commited on
Commit
c901f39
·
verified ·
1 Parent(s): d953f2e

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +360 -0
  2. README.md +202 -0
  3. adapter_config.json +36 -0
  4. adapter_model.safetensors +3 -0
  5. checkpoint-100/optimizer_0/.metadata +3 -0
  6. checkpoint-100/optimizer_0/__0_0.distcp +3 -0
  7. checkpoint-100/optimizer_0/__1_0.distcp +3 -0
  8. checkpoint-100/optimizer_0/__2_0.distcp +3 -0
  9. checkpoint-100/optimizer_0/__3_0.distcp +3 -0
  10. checkpoint-100/optimizer_0/__4_0.distcp +3 -0
  11. checkpoint-100/optimizer_0/__5_0.distcp +3 -0
  12. checkpoint-100/optimizer_0/__6_0.distcp +3 -0
  13. checkpoint-100/optimizer_0/__7_0.distcp +3 -0
  14. checkpoint-100/pytorch_model_fsdp_0/.metadata +3 -0
  15. checkpoint-100/pytorch_model_fsdp_0/__0_0.distcp +3 -0
  16. checkpoint-100/pytorch_model_fsdp_0/__1_0.distcp +3 -0
  17. checkpoint-100/pytorch_model_fsdp_0/__2_0.distcp +3 -0
  18. checkpoint-100/pytorch_model_fsdp_0/__3_0.distcp +3 -0
  19. checkpoint-100/pytorch_model_fsdp_0/__4_0.distcp +3 -0
  20. checkpoint-100/pytorch_model_fsdp_0/__5_0.distcp +3 -0
  21. checkpoint-100/pytorch_model_fsdp_0/__6_0.distcp +3 -0
  22. checkpoint-100/pytorch_model_fsdp_0/__7_0.distcp +3 -0
  23. checkpoint-100/rng_state_0.pth +3 -0
  24. checkpoint-100/rng_state_1.pth +3 -0
  25. checkpoint-100/rng_state_2.pth +3 -0
  26. checkpoint-100/rng_state_3.pth +3 -0
  27. checkpoint-100/rng_state_4.pth +3 -0
  28. checkpoint-100/rng_state_5.pth +3 -0
  29. checkpoint-100/rng_state_6.pth +3 -0
  30. checkpoint-100/rng_state_7.pth +3 -0
  31. checkpoint-100/scheduler.pt +3 -0
  32. checkpoint-100/trainer_state.json +70 -0
  33. checkpoint-1000/optimizer_0/.metadata +3 -0
  34. checkpoint-1000/optimizer_0/__0_0.distcp +3 -0
  35. checkpoint-1000/optimizer_0/__1_0.distcp +3 -0
  36. checkpoint-1000/optimizer_0/__2_0.distcp +3 -0
  37. checkpoint-1000/optimizer_0/__3_0.distcp +3 -0
  38. checkpoint-1000/optimizer_0/__4_0.distcp +3 -0
  39. checkpoint-1000/optimizer_0/__5_0.distcp +3 -0
  40. checkpoint-1000/optimizer_0/__6_0.distcp +3 -0
  41. checkpoint-1000/optimizer_0/__7_0.distcp +3 -0
  42. checkpoint-1000/pytorch_model_fsdp_0/.metadata +3 -0
  43. checkpoint-1000/pytorch_model_fsdp_0/__0_0.distcp +3 -0
  44. checkpoint-1000/pytorch_model_fsdp_0/__1_0.distcp +3 -0
  45. checkpoint-1000/pytorch_model_fsdp_0/__2_0.distcp +3 -0
  46. checkpoint-1000/pytorch_model_fsdp_0/__3_0.distcp +3 -0
  47. checkpoint-1000/pytorch_model_fsdp_0/__4_0.distcp +3 -0
  48. checkpoint-1000/pytorch_model_fsdp_0/__5_0.distcp +3 -0
  49. checkpoint-1000/pytorch_model_fsdp_0/__6_0.distcp +3 -0
  50. checkpoint-1000/pytorch_model_fsdp_0/__7_0.distcp +3 -0
.gitattributes CHANGED
@@ -33,3 +33,363 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-100/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-100/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-100/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-100/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-100/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-100/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
42
+ checkpoint-100/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
43
+ checkpoint-100/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
44
+ checkpoint-100/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
45
+ checkpoint-100/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
46
+ checkpoint-100/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
47
+ checkpoint-100/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
48
+ checkpoint-100/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
49
+ checkpoint-100/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
50
+ checkpoint-100/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
51
+ checkpoint-100/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
52
+ checkpoint-100/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
53
+ checkpoint-100/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
54
+ checkpoint-1000/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
55
+ checkpoint-1000/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
56
+ checkpoint-1000/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
57
+ checkpoint-1000/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
58
+ checkpoint-1000/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
59
+ checkpoint-1000/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
60
+ checkpoint-1000/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
61
+ checkpoint-1000/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
62
+ checkpoint-1000/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
63
+ checkpoint-1000/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
64
+ checkpoint-1000/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
65
+ checkpoint-1000/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
66
+ checkpoint-1000/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
67
+ checkpoint-1000/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
68
+ checkpoint-1000/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
69
+ checkpoint-1000/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
70
+ checkpoint-1000/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
71
+ checkpoint-1000/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
72
+ checkpoint-1100/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
73
+ checkpoint-1100/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
74
+ checkpoint-1100/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
75
+ checkpoint-1100/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
76
+ checkpoint-1100/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
77
+ checkpoint-1100/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
78
+ checkpoint-1100/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
79
+ checkpoint-1100/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
80
+ checkpoint-1100/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
81
+ checkpoint-1100/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
82
+ checkpoint-1100/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
83
+ checkpoint-1100/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
84
+ checkpoint-1100/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
85
+ checkpoint-1100/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
86
+ checkpoint-1100/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
87
+ checkpoint-1100/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
88
+ checkpoint-1100/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
89
+ checkpoint-1100/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
90
+ checkpoint-1200/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
91
+ checkpoint-1200/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
92
+ checkpoint-1200/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
93
+ checkpoint-1200/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
94
+ checkpoint-1200/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
95
+ checkpoint-1200/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
96
+ checkpoint-1200/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
97
+ checkpoint-1200/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
98
+ checkpoint-1200/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
99
+ checkpoint-1200/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
100
+ checkpoint-1200/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
101
+ checkpoint-1200/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
102
+ checkpoint-1200/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
103
+ checkpoint-1200/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
104
+ checkpoint-1200/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
105
+ checkpoint-1200/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
106
+ checkpoint-1200/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
107
+ checkpoint-1200/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
108
+ checkpoint-1300/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
109
+ checkpoint-1300/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
110
+ checkpoint-1300/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
111
+ checkpoint-1300/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
112
+ checkpoint-1300/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
113
+ checkpoint-1300/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
114
+ checkpoint-1300/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
115
+ checkpoint-1300/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
116
+ checkpoint-1300/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
117
+ checkpoint-1300/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
118
+ checkpoint-1300/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
119
+ checkpoint-1300/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
120
+ checkpoint-1300/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
121
+ checkpoint-1300/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
122
+ checkpoint-1300/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
123
+ checkpoint-1300/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
124
+ checkpoint-1300/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
125
+ checkpoint-1300/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
126
+ checkpoint-1400/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
127
+ checkpoint-1400/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
128
+ checkpoint-1400/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
129
+ checkpoint-1400/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
130
+ checkpoint-1400/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
131
+ checkpoint-1400/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
132
+ checkpoint-1400/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
133
+ checkpoint-1400/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
134
+ checkpoint-1400/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
135
+ checkpoint-1400/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
136
+ checkpoint-1400/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
137
+ checkpoint-1400/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
138
+ checkpoint-1400/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
139
+ checkpoint-1400/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
140
+ checkpoint-1400/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
141
+ checkpoint-1400/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
142
+ checkpoint-1400/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
143
+ checkpoint-1400/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
144
+ checkpoint-1500/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
145
+ checkpoint-1500/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
146
+ checkpoint-1500/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
147
+ checkpoint-1500/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
148
+ checkpoint-1500/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
149
+ checkpoint-1500/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
150
+ checkpoint-1500/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
151
+ checkpoint-1500/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
152
+ checkpoint-1500/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
153
+ checkpoint-1500/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
154
+ checkpoint-1500/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
155
+ checkpoint-1500/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
156
+ checkpoint-1500/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
157
+ checkpoint-1500/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
158
+ checkpoint-1500/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
159
+ checkpoint-1500/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
160
+ checkpoint-1500/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
161
+ checkpoint-1500/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
162
+ checkpoint-1600/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
163
+ checkpoint-1600/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
164
+ checkpoint-1600/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
165
+ checkpoint-1600/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
166
+ checkpoint-1600/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
167
+ checkpoint-1600/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
168
+ checkpoint-1600/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
169
+ checkpoint-1600/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
170
+ checkpoint-1600/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
171
+ checkpoint-1600/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
172
+ checkpoint-1600/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
173
+ checkpoint-1600/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
174
+ checkpoint-1600/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
175
+ checkpoint-1600/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
176
+ checkpoint-1600/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
177
+ checkpoint-1600/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
178
+ checkpoint-1600/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
179
+ checkpoint-1600/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
180
+ checkpoint-1700/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
181
+ checkpoint-1700/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
182
+ checkpoint-1700/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
183
+ checkpoint-1700/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
184
+ checkpoint-1700/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
185
+ checkpoint-1700/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
186
+ checkpoint-1700/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
187
+ checkpoint-1700/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
188
+ checkpoint-1700/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
189
+ checkpoint-1700/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
190
+ checkpoint-1700/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
191
+ checkpoint-1700/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
192
+ checkpoint-1700/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
193
+ checkpoint-1700/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
194
+ checkpoint-1700/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
195
+ checkpoint-1700/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
196
+ checkpoint-1700/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
197
+ checkpoint-1700/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
198
+ checkpoint-1800/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
199
+ checkpoint-1800/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
200
+ checkpoint-1800/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
201
+ checkpoint-1800/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
202
+ checkpoint-1800/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
203
+ checkpoint-1800/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
204
+ checkpoint-1800/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
205
+ checkpoint-1800/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
206
+ checkpoint-1800/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
207
+ checkpoint-1800/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
208
+ checkpoint-1800/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
209
+ checkpoint-1800/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
210
+ checkpoint-1800/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
211
+ checkpoint-1800/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
212
+ checkpoint-1800/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
213
+ checkpoint-1800/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
214
+ checkpoint-1800/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
215
+ checkpoint-1800/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
216
+ checkpoint-1900/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
217
+ checkpoint-1900/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
218
+ checkpoint-1900/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
219
+ checkpoint-1900/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
220
+ checkpoint-1900/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
221
+ checkpoint-1900/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
222
+ checkpoint-1900/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
223
+ checkpoint-1900/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
224
+ checkpoint-1900/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
225
+ checkpoint-1900/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
226
+ checkpoint-1900/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
227
+ checkpoint-1900/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
228
+ checkpoint-1900/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
229
+ checkpoint-1900/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
230
+ checkpoint-1900/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
231
+ checkpoint-1900/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
232
+ checkpoint-1900/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
233
+ checkpoint-1900/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
234
+ checkpoint-200/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
235
+ checkpoint-200/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
236
+ checkpoint-200/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
237
+ checkpoint-200/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
238
+ checkpoint-200/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
239
+ checkpoint-200/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
240
+ checkpoint-200/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
241
+ checkpoint-200/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
242
+ checkpoint-200/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
243
+ checkpoint-200/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
244
+ checkpoint-200/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
245
+ checkpoint-200/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
246
+ checkpoint-200/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
247
+ checkpoint-200/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
248
+ checkpoint-200/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
249
+ checkpoint-200/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
250
+ checkpoint-200/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
251
+ checkpoint-200/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
252
+ checkpoint-2000/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
253
+ checkpoint-2000/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
254
+ checkpoint-2000/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
255
+ checkpoint-2000/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
256
+ checkpoint-2000/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
257
+ checkpoint-2000/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
258
+ checkpoint-2000/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
259
+ checkpoint-2000/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
260
+ checkpoint-2000/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
261
+ checkpoint-2000/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
262
+ checkpoint-2000/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
263
+ checkpoint-2000/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
264
+ checkpoint-2000/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
265
+ checkpoint-2000/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
266
+ checkpoint-2000/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
267
+ checkpoint-2000/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
268
+ checkpoint-2000/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
269
+ checkpoint-2000/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
270
+ checkpoint-300/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
271
+ checkpoint-300/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
272
+ checkpoint-300/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
273
+ checkpoint-300/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
274
+ checkpoint-300/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
275
+ checkpoint-300/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
276
+ checkpoint-300/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
277
+ checkpoint-300/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
278
+ checkpoint-300/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
279
+ checkpoint-300/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
280
+ checkpoint-300/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
281
+ checkpoint-300/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
282
+ checkpoint-300/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
283
+ checkpoint-300/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
284
+ checkpoint-300/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
285
+ checkpoint-300/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
286
+ checkpoint-300/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
287
+ checkpoint-300/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
288
+ checkpoint-400/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
289
+ checkpoint-400/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
290
+ checkpoint-400/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
291
+ checkpoint-400/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
292
+ checkpoint-400/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
293
+ checkpoint-400/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
294
+ checkpoint-400/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
295
+ checkpoint-400/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
296
+ checkpoint-400/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
297
+ checkpoint-400/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
298
+ checkpoint-400/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
299
+ checkpoint-400/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
300
+ checkpoint-400/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
301
+ checkpoint-400/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
302
+ checkpoint-400/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
303
+ checkpoint-400/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
304
+ checkpoint-400/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
305
+ checkpoint-400/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
306
+ checkpoint-500/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
307
+ checkpoint-500/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
308
+ checkpoint-500/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
309
+ checkpoint-500/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
310
+ checkpoint-500/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
311
+ checkpoint-500/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
312
+ checkpoint-500/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
313
+ checkpoint-500/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
314
+ checkpoint-500/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
315
+ checkpoint-500/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
316
+ checkpoint-500/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
317
+ checkpoint-500/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
318
+ checkpoint-500/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
319
+ checkpoint-500/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
320
+ checkpoint-500/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
321
+ checkpoint-500/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
322
+ checkpoint-500/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
323
+ checkpoint-500/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
324
+ checkpoint-600/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
325
+ checkpoint-600/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
326
+ checkpoint-600/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
327
+ checkpoint-600/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
328
+ checkpoint-600/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
329
+ checkpoint-600/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
330
+ checkpoint-600/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
331
+ checkpoint-600/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
332
+ checkpoint-600/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
333
+ checkpoint-600/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
334
+ checkpoint-600/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
335
+ checkpoint-600/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
336
+ checkpoint-600/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
337
+ checkpoint-600/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
338
+ checkpoint-600/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
339
+ checkpoint-600/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
340
+ checkpoint-600/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
341
+ checkpoint-600/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
342
+ checkpoint-700/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
343
+ checkpoint-700/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
344
+ checkpoint-700/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
345
+ checkpoint-700/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
346
+ checkpoint-700/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
347
+ checkpoint-700/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
348
+ checkpoint-700/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
349
+ checkpoint-700/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
350
+ checkpoint-700/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
351
+ checkpoint-700/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
352
+ checkpoint-700/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
353
+ checkpoint-700/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
354
+ checkpoint-700/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
355
+ checkpoint-700/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
356
+ checkpoint-700/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
357
+ checkpoint-700/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
358
+ checkpoint-700/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
359
+ checkpoint-700/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
360
+ checkpoint-800/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
361
+ checkpoint-800/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
362
+ checkpoint-800/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
363
+ checkpoint-800/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
364
+ checkpoint-800/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
365
+ checkpoint-800/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
366
+ checkpoint-800/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
367
+ checkpoint-800/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
368
+ checkpoint-800/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
369
+ checkpoint-800/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
370
+ checkpoint-800/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
371
+ checkpoint-800/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
372
+ checkpoint-800/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
373
+ checkpoint-800/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
374
+ checkpoint-800/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
375
+ checkpoint-800/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
376
+ checkpoint-800/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
377
+ checkpoint-800/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
378
+ checkpoint-900/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
379
+ checkpoint-900/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
380
+ checkpoint-900/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
381
+ checkpoint-900/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
382
+ checkpoint-900/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
383
+ checkpoint-900/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
384
+ checkpoint-900/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
385
+ checkpoint-900/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
386
+ checkpoint-900/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
387
+ checkpoint-900/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
388
+ checkpoint-900/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
389
+ checkpoint-900/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
390
+ checkpoint-900/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
391
+ checkpoint-900/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
392
+ checkpoint-900/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
393
+ checkpoint-900/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
394
+ checkpoint-900/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
395
+ checkpoint-900/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: bigcode/starcoderbase-1b
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigcode/starcoderbase-1b",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_attn",
28
+ "c_proj",
29
+ "c_fc",
30
+ "c_attn"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619eeb3ce00fa2451a888fc83ce28ba50cbbb9c0ebe24b76bb88b36565ea632c
3
+ size 22241240
checkpoint-100/optimizer_0/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64dae846ba7fb20e07cd1d076660c586147ab0156c74645966a8b65ae2664a1b
3
+ size 869361
checkpoint-100/optimizer_0/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c5105cc1702bf3c00aeba22dd04785e56b18c1e4c226b520ec2c885c9a89e0
3
+ size 6008476
checkpoint-100/optimizer_0/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad7704459dd20c3600510d2a3f3e2262b9cf201f9b39c8bbb56594e8323105a
3
+ size 6041200
checkpoint-100/optimizer_0/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf91022a5990365e63959c3c8d31090ec6de97e0e40f785028cd2edf5e8ebb11
3
+ size 6041200
checkpoint-100/optimizer_0/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e379152275e4774566323e2ec970af7cfa502bdfd8a90da768f8367aa78e3563
3
+ size 6043476
checkpoint-100/optimizer_0/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f37e30aec02a02c27e7289c98513c01bc510ffc57bf74982f835c5b1c0f683
3
+ size 6057364
checkpoint-100/optimizer_0/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11729525c054a51a5107225a7d60b0313aae518730d08b2749238c346a1e906c
3
+ size 6042612
checkpoint-100/optimizer_0/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9842cd8b1a5ec425a6a9e6050a067d2c5b08db5f487a4f91e6f3c238af6431
3
+ size 6042612
checkpoint-100/optimizer_0/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0aba0269721eae1aec05e75b68b171e11b144f469cd6adfb1e19a2824b3791
3
+ size 6042612
checkpoint-100/pytorch_model_fsdp_0/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b95e896afde034e76a7b5fdba70015f5e507f24fb23d13a2eb125b6af6b822e
3
+ size 339851
checkpoint-100/pytorch_model_fsdp_0/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276c6102d25252a3058a7c14b3c6e037e6f40aad1e997e057bbd43c56bbcc029
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0f5b8a430b58a8377337a11a1118be38e4e4065799f22312df73e9539edfb5
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920db2946d599036845a8d8e58570c0a129df18a251ccf6054c13cd055056f35
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f62dad52a118474a5ac8feb1156d2bfde1a14979703f1ff312fcbfd30d8a3c1
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3c1a0848cd7291dad379b68801f2e8a9d845989ada5fd42d00e5a23da6597ad
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819bba510acfcb80bf63bce4c0a35be2f0af56ae2e49a72a05af94128b05fb5a
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c591981b57d09088dd5dd3c2c4990f922ffe7df92389509d8b2703137ea6085
3
+ size 3003648
checkpoint-100/pytorch_model_fsdp_0/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b5f0504de2c99266a04deca823b3673b779578680f0e82ddd604156fde6ffc
3
+ size 3003648
checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67ac3c4038beb665d2cc4bd735b6f05977897a2757187e8c7c8e6b89fa4ad3d
3
+ size 15920
checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219fc23b677e769ae4d4806c12e3df4ff2b78c28b311847bec2ecb99a35a51e6
3
+ size 15984
checkpoint-100/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a352b51cb68b5d8818a7a28f74f32dffb1095d7e281ff4022f0e365fe98a8ee0
3
+ size 15984
checkpoint-100/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9e8f9785d0d17d62f1ba8a141384aa7a6438a53ecad5f21d877594c31b45d0
3
+ size 15984
checkpoint-100/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a770deea02d60eea9348a15bd08ac4f95c99d6b5b113eb31bc2fa7631dba1988
3
+ size 15984
checkpoint-100/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b60fb34596e1922ede5c5a2479b5b98033b4b988dc300df633c12f5e255755
3
+ size 15984
checkpoint-100/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84274411027a8eb72ed1179f8209a875b6f4101ac7c2790eaef04102df49af52
3
+ size 15984
checkpoint-100/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbc89ce90c5e7e9f362eb48f3be0a6f39aee82e598c876d2d126ef971bbbfdc
3
+ size 15984
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b84ab1237abc7bd4d31945126355c5b6d9e26cb338d88dae9fd60030b2e1fb3
3
+ size 1064
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.05,
6
+ "eval_steps": 100,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0125,
14
+ "grad_norm": 0.14176353812217712,
15
+ "learning_rate": 0.0004,
16
+ "loss": 1.1525,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.025,
21
+ "grad_norm": 0.1460508555173874,
22
+ "learning_rate": 0.0004998852503731983,
23
+ "loss": 1.047,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.0375,
28
+ "grad_norm": 0.2368021011352539,
29
+ "learning_rate": 0.0004993848168027977,
30
+ "loss": 0.8529,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.05,
35
+ "grad_norm": 0.14488168060779572,
36
+ "learning_rate": 0.0004984880506341147,
37
+ "loss": 0.9756,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.05,
42
+ "eval_loss": 0.9470569491386414,
43
+ "eval_runtime": 845.9115,
44
+ "eval_samples_per_second": 1.297,
45
+ "eval_steps_per_second": 0.021,
46
+ "step": 100
47
+ }
48
+ ],
49
+ "logging_steps": 25,
50
+ "max_steps": 2000,
51
+ "num_input_tokens_seen": 0,
52
+ "num_train_epochs": 9223372036854775807,
53
+ "save_steps": 100,
54
+ "stateful_callbacks": {
55
+ "TrainerControl": {
56
+ "args": {
57
+ "should_epoch_stop": false,
58
+ "should_evaluate": false,
59
+ "should_log": false,
60
+ "should_save": true,
61
+ "should_training_stop": false
62
+ },
63
+ "attributes": {}
64
+ }
65
+ },
66
+ "total_flos": 1.0079315433619456e+16,
67
+ "train_batch_size": 8,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
checkpoint-1000/optimizer_0/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c4b3e6e77e6c4fe0e4ec5ffe86cd9420b22487406f98c30d94993a7cae6335
3
+ size 869362
checkpoint-1000/optimizer_0/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc4f6f9dc852ef0f917b009518f39d10d68a4536c1f51998cea4a5b83e892da
3
+ size 6008476
checkpoint-1000/optimizer_0/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7312e1c4e946ab65367b2525624545d48b44d074f9e0ecba0290412be956f5e3
3
+ size 6041200
checkpoint-1000/optimizer_0/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f002da732a464fc63c29885772852f44b142bb93c15442eb20c54fd05c05b90
3
+ size 6041200
checkpoint-1000/optimizer_0/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f041b71230e388a6e048350c575718e2117303df15582bbd21841c79a30563f1
3
+ size 6043476
checkpoint-1000/optimizer_0/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abff4649eea683c30203f7c7d0079317bf744e54003c8ae8d366f67c1bf3881a
3
+ size 6057364
checkpoint-1000/optimizer_0/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488ddea956a0925e88414a20672caa84392b5dfdf67f9d99a1286fa6236f6112
3
+ size 6042612
checkpoint-1000/optimizer_0/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cebd75cf3f08edef15e48523d99f60d10d2e3d2fe33216bfde563ad390ca8b8
3
+ size 6042612
checkpoint-1000/optimizer_0/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00fe62b7cdadb932c335a2a670e603f0ca4b8cad10a1a11c6af8f89b71c9e4d0
3
+ size 6042612
checkpoint-1000/pytorch_model_fsdp_0/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83582bb2c3364686161e3eda0fc44aa67a4e2029e1fc9605e333669c6f4a3215
3
+ size 339852
checkpoint-1000/pytorch_model_fsdp_0/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa89fe800d11e2d111c108ff934abffb09954deec83c8c403892b023df67f064
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf772693a9e7e6e2205ed5f483cfd7c3c577459292281ccac91680f3f19e64a
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f05dae3a3b9c4ac6c5ebed01990323e5f0321ea9b2a52e83653840798f0ceb7
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a8d4367facec4482692297aeaae3e91fc2dbc7f4924caa4d2f84d174cc6c98
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e6479ff28ace5eeada37360c30b3d17db987b8c05d0ca6046bdcd2b40a65fc
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0861299d5e24a80f99564ac77a2acd79f83f89c1ebe9124cdd6bdbd80b3d505
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fed1b4f6d88ffc7b06186d89144870b25154a95fd66b9323e44bd46a3131737
3
+ size 3003648
checkpoint-1000/pytorch_model_fsdp_0/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c38c7c6f67489e926a46c26ad5fd48cee00118acf74bc9665f6b1793aa4910ea
3
+ size 3003648