Hugging Face's logo

salmannyu
/
model-checkpoints

Model card Files
xet
 Community
salmannyu commited on
Commit
1e9049f
·
verified ·
1 Parent(s): 122bac4

Upload rl/qwen3_4b_agent_prm_exact_match/rollouts

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 +90 -0
  2. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/1.jsonl +3 -0
  3. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/10.jsonl +3 -0
  4. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/11.jsonl +3 -0
  5. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/12.jsonl +3 -0
  6. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/13.jsonl +3 -0
  7. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/14.jsonl +3 -0
  8. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/15.jsonl +3 -0
  9. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/16.jsonl +3 -0
  10. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/17.jsonl +3 -0
  11. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/18.jsonl +3 -0
  12. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/19.jsonl +3 -0
  13. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/2.jsonl +3 -0
  14. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/20.jsonl +3 -0
  15. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/21.jsonl +3 -0
  16. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/22.jsonl +3 -0
  17. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/23.jsonl +3 -0
  18. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/24.jsonl +3 -0
  19. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/25.jsonl +3 -0
  20. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/26.jsonl +3 -0
  21. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/27.jsonl +3 -0
  22. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/28.jsonl +3 -0
  23. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/29.jsonl +3 -0
  24. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/3.jsonl +3 -0
  25. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/30.jsonl +3 -0
  26. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/31.jsonl +3 -0
  27. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/32.jsonl +3 -0
  28. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/33.jsonl +3 -0
  29. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/34.jsonl +3 -0
  30. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/35.jsonl +3 -0
  31. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/36.jsonl +3 -0
  32. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/37.jsonl +3 -0
  33. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/38.jsonl +3 -0
  34. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/39.jsonl +3 -0
  35. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/4.jsonl +3 -0
  36. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/40.jsonl +3 -0
  37. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/41.jsonl +3 -0
  38. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/42.jsonl +3 -0
  39. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/43.jsonl +3 -0
  40. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/44.jsonl +3 -0
  41. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/45.jsonl +3 -0
  42. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/46.jsonl +3 -0
  43. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/47.jsonl +3 -0
  44. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/48.jsonl +3 -0
  45. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/49.jsonl +3 -0
  46. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/5.jsonl +3 -0
  47. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/50.jsonl +3 -0
  48. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/51.jsonl +3 -0
  49. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/52.jsonl +3 -0
  50. rl/qwen3_4b_agent_prm_exact_match/rollouts/training/53.jsonl +3 -0
.gitattributes CHANGED
@@ -133,3 +133,93 @@ rl/qwen3_4b_agent_prm/rollouts/training/91.jsonl filter=lfs diff=lfs merge=lfs -
133
  rl/qwen3_4b_agent_prm/rollouts/training/92.jsonl filter=lfs diff=lfs merge=lfs -text
134
  rl/qwen3_4b_agent_prm/rollouts/training/95.jsonl filter=lfs diff=lfs merge=lfs -text
135
  rl/qwen3_4b_agent_prm_exact_match/checkpoints/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
133
  rl/qwen3_4b_agent_prm/rollouts/training/92.jsonl filter=lfs diff=lfs merge=lfs -text
134
  rl/qwen3_4b_agent_prm/rollouts/training/95.jsonl filter=lfs diff=lfs merge=lfs -text
135
  rl/qwen3_4b_agent_prm_exact_match/checkpoints/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
136
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/1.jsonl filter=lfs diff=lfs merge=lfs -text
137
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/10.jsonl filter=lfs diff=lfs merge=lfs -text
138
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/11.jsonl filter=lfs diff=lfs merge=lfs -text
139
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/12.jsonl filter=lfs diff=lfs merge=lfs -text
140
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/13.jsonl filter=lfs diff=lfs merge=lfs -text
141
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/14.jsonl filter=lfs diff=lfs merge=lfs -text
142
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/15.jsonl filter=lfs diff=lfs merge=lfs -text
143
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/16.jsonl filter=lfs diff=lfs merge=lfs -text
144
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/17.jsonl filter=lfs diff=lfs merge=lfs -text
145
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/18.jsonl filter=lfs diff=lfs merge=lfs -text
146
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/19.jsonl filter=lfs diff=lfs merge=lfs -text
147
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/2.jsonl filter=lfs diff=lfs merge=lfs -text
148
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/20.jsonl filter=lfs diff=lfs merge=lfs -text
149
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/21.jsonl filter=lfs diff=lfs merge=lfs -text
150
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/22.jsonl filter=lfs diff=lfs merge=lfs -text
151
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/23.jsonl filter=lfs diff=lfs merge=lfs -text
152
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/24.jsonl filter=lfs diff=lfs merge=lfs -text
153
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/25.jsonl filter=lfs diff=lfs merge=lfs -text
154
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/26.jsonl filter=lfs diff=lfs merge=lfs -text
155
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/27.jsonl filter=lfs diff=lfs merge=lfs -text
156
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/28.jsonl filter=lfs diff=lfs merge=lfs -text
157
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/29.jsonl filter=lfs diff=lfs merge=lfs -text
158
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/3.jsonl filter=lfs diff=lfs merge=lfs -text
159
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/30.jsonl filter=lfs diff=lfs merge=lfs -text
160
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/31.jsonl filter=lfs diff=lfs merge=lfs -text
161
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/32.jsonl filter=lfs diff=lfs merge=lfs -text
162
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/33.jsonl filter=lfs diff=lfs merge=lfs -text
163
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/34.jsonl filter=lfs diff=lfs merge=lfs -text
164
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/35.jsonl filter=lfs diff=lfs merge=lfs -text
165
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/36.jsonl filter=lfs diff=lfs merge=lfs -text
166
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/37.jsonl filter=lfs diff=lfs merge=lfs -text
167
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/38.jsonl filter=lfs diff=lfs merge=lfs -text
168
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/39.jsonl filter=lfs diff=lfs merge=lfs -text
169
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/4.jsonl filter=lfs diff=lfs merge=lfs -text
170
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/40.jsonl filter=lfs diff=lfs merge=lfs -text
171
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/41.jsonl filter=lfs diff=lfs merge=lfs -text
172
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/42.jsonl filter=lfs diff=lfs merge=lfs -text
173
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/43.jsonl filter=lfs diff=lfs merge=lfs -text
174
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/44.jsonl filter=lfs diff=lfs merge=lfs -text
175
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/45.jsonl filter=lfs diff=lfs merge=lfs -text
176
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/46.jsonl filter=lfs diff=lfs merge=lfs -text
177
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/47.jsonl filter=lfs diff=lfs merge=lfs -text
178
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/48.jsonl filter=lfs diff=lfs merge=lfs -text
179
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/49.jsonl filter=lfs diff=lfs merge=lfs -text
180
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/5.jsonl filter=lfs diff=lfs merge=lfs -text
181
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/50.jsonl filter=lfs diff=lfs merge=lfs -text
182
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/51.jsonl filter=lfs diff=lfs merge=lfs -text
183
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/52.jsonl filter=lfs diff=lfs merge=lfs -text
184
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/53.jsonl filter=lfs diff=lfs merge=lfs -text
185
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/54.jsonl filter=lfs diff=lfs merge=lfs -text
186
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/55.jsonl filter=lfs diff=lfs merge=lfs -text
187
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/56.jsonl filter=lfs diff=lfs merge=lfs -text
188
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/57.jsonl filter=lfs diff=lfs merge=lfs -text
189
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/58.jsonl filter=lfs diff=lfs merge=lfs -text
190
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/59.jsonl filter=lfs diff=lfs merge=lfs -text
191
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/6.jsonl filter=lfs diff=lfs merge=lfs -text
192
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/60.jsonl filter=lfs diff=lfs merge=lfs -text
193
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/61.jsonl filter=lfs diff=lfs merge=lfs -text
194
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/62.jsonl filter=lfs diff=lfs merge=lfs -text
195
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/63.jsonl filter=lfs diff=lfs merge=lfs -text
196
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/64.jsonl filter=lfs diff=lfs merge=lfs -text
197
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/65.jsonl filter=lfs diff=lfs merge=lfs -text
198
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/66.jsonl filter=lfs diff=lfs merge=lfs -text
199
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/67.jsonl filter=lfs diff=lfs merge=lfs -text
200
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/68.jsonl filter=lfs diff=lfs merge=lfs -text
201
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/69.jsonl filter=lfs diff=lfs merge=lfs -text
202
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/7.jsonl filter=lfs diff=lfs merge=lfs -text
203
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/70.jsonl filter=lfs diff=lfs merge=lfs -text
204
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/71.jsonl filter=lfs diff=lfs merge=lfs -text
205
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/72.jsonl filter=lfs diff=lfs merge=lfs -text
206
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/73.jsonl filter=lfs diff=lfs merge=lfs -text
207
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/74.jsonl filter=lfs diff=lfs merge=lfs -text
208
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/75.jsonl filter=lfs diff=lfs merge=lfs -text
209
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/76.jsonl filter=lfs diff=lfs merge=lfs -text
210
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/77.jsonl filter=lfs diff=lfs merge=lfs -text
211
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/78.jsonl filter=lfs diff=lfs merge=lfs -text
212
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/79.jsonl filter=lfs diff=lfs merge=lfs -text
213
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/8.jsonl filter=lfs diff=lfs merge=lfs -text
214
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/81.jsonl filter=lfs diff=lfs merge=lfs -text
215
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/82.jsonl filter=lfs diff=lfs merge=lfs -text
216
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/84.jsonl filter=lfs diff=lfs merge=lfs -text
217
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/85.jsonl filter=lfs diff=lfs merge=lfs -text
218
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/86.jsonl filter=lfs diff=lfs merge=lfs -text
219
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/87.jsonl filter=lfs diff=lfs merge=lfs -text
220
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/88.jsonl filter=lfs diff=lfs merge=lfs -text
221
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/89.jsonl filter=lfs diff=lfs merge=lfs -text
222
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/9.jsonl filter=lfs diff=lfs merge=lfs -text
223
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/90.jsonl filter=lfs diff=lfs merge=lfs -text
224
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/91.jsonl filter=lfs diff=lfs merge=lfs -text
225
+ rl/qwen3_4b_agent_prm_exact_match/rollouts/training/92.jsonl filter=lfs diff=lfs merge=lfs -text
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/1.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5a59cc978feccb445366b1ececa3a0d20dee773d9d35711ef7b78b449f7540
3
+ size 13101109
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/10.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6ab244546496365986d6ff2ac8defbdb39ba10b93f26601eb6b136f2157abc
3
+ size 14135136
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/11.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b78cec22e5957c509b7c0eaa38cf32602895d38e61b31e190412c45b134ea977
3
+ size 12318323
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/12.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3b089f9ec7acf621444c27e88cc221bb07e6a5b3b8c73fd032b232fdf03da1
3
+ size 13433768
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/13.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681c4d66a5e5fe4a342528e3101a4186e36485f7e7fb8484b398fe9ce353a2b1
3
+ size 13832713
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/14.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30b1ef9440cbfd7e16f182cd2e8ed959811f28be7b8a89f693bacd8c97482ee
3
+ size 14700344
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/15.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ef693f4cb19e350e0b102025ce1e9574ae216c6c2aeb79298b4f61faf12473
3
+ size 12559649
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/16.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35cd190a98c63bbf7714ae790925ea1e03add09620cdf7df435901874c529ac4
3
+ size 14427747
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/17.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b4a6d27951084ae443ea6412b63ebad8eb58380f5cb43fca70a9c3b82caef0
3
+ size 13918451
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/18.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac43633b2bc3371f9a134d1c6c4b9478edb2824471a08fa5f3a2eddfef7d2ed
3
+ size 11925552
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/19.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfafcc602582b5478490b4117cafad3f3cc1d77a6a133ba6533b135c60a7e167
3
+ size 14040167
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/2.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d3ba44ed61cd6f1076ed6c217e259dde54ec608e298c0bfeeefde3f921d2bd
3
+ size 12381806
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/20.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a873aa389de43116217cafe1b71a58ff9e3bf1a61abad03c17a360e9d17dca5
3
+ size 12819978
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/21.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f90a3aa1cd8016c2247d1ea81a5f7890c4d1176e4be51d76f05cd876fc02b3e
3
+ size 11720027
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/22.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2e5775e048eb1f032c3c031d1ff06504b7d1729a54619e3c904068f557cfdc
3
+ size 14886244
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/23.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df09cc3ff0b48500c7e4a21cf7ee17aebf1ad3672c1740c281de170eacbd0803
3
+ size 12864209
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/24.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790f440bf465c8f3d07c807de00f5c0b54ebc66cfe6552e81b81a206734fece5
3
+ size 13510315
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/25.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53a4a4906c6d3a7262323d97185bfe6d6941d68a944297c6f6ac65fb5363722
3
+ size 15078452
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/26.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e338f0adb44e24ff2fa6ce9e46c634fb77ee1f71241d5ac6d7b06c22e148abc6
3
+ size 10693572
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/27.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e922869928ce56a4eaeb2fcbe22d1b097de2c0634c79a279139c354c2d2250a4
3
+ size 12036723
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/28.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e90af88fb702533b1aefba2f6587e4ecda38f6f4096e34da59961a3ff86ce1b9
3
+ size 12678042
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/29.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cafd98532be9c2c7f1729d9ca30f469e3b90f3abb806485b9a99d261363994df
3
+ size 11595126
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/3.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb8c170f54adcff4607489898e62895360c73900e2d13e3e9c415de103c402b
3
+ size 12932506
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/30.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9915b86e2bbd9c4e4c21f957e6c39ce331f0f43921a13d5508efc2ec22c3dade
3
+ size 12025239
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/31.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5468a35e44409ce0e3cbe0dfc878e845495eb830a1ea73b2a2eb16c6c842d42
3
+ size 13285316
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/32.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4d6b9da730ec8d079020d3868e2c18b7835a6a9afa444e1daa3e80c5942284
3
+ size 14873596
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/33.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9696d23088af7f647a6730df6773a301bf8df689575543e7bd13ac973c5a071a
3
+ size 11561621
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/34.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec300748e040dac5fb6c706b71686d9cafb783a87a610ad4e261daef16604ca0
3
+ size 12153506
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/35.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ac7cd265b7583705e7f633f0550e2aaa2f39615a073fe47ddddcd9eee3fb25
3
+ size 11556542
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/36.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b80de42222b2fde4d49cca6d1efd495502d2629609db7f054e9d3bbd6fe22ae5
3
+ size 14141686
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/37.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c950f485767c439c7b7ea19d2dad16dbca21c10dd2a7730379bd96a6ad9eae08
3
+ size 11868283
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/38.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92a3f89bbdf888f0a5e714fb16ffe6a7805da6921984352724d811f1685de22
3
+ size 14024476
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/39.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e930a1a182eff54569d1ff5673c85d04db9f77473bb1a15e7a8b8003aa8ab95b
3
+ size 11876034
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/4.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798bdf9342ce1f3cab0daecc520cdcce372a1d29ec3ad71475dc5afda452556b
3
+ size 13649806
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/40.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2dd8808c506a67e978b0b480d4fed9d2dab752ecd38f829d1c12916ddd90e77
3
+ size 14899427
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/41.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1c2a244398908a1e15a2b26a57ba6efe7a552ff00074110cf49570ec494ac4
3
+ size 14286030
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/42.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8e7a6c6d8d5cdea4d7e9a480c8867d61fda34ce9f7a7e3475ae506af6b8532
3
+ size 12793442
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/43.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5791a2c84fd4e615b9b3e58b4ba8837d33d6548a2f988d0a99b44f835b60c218
3
+ size 13911855
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/44.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47f66d439308ce96968d2034d111054aede67bf98495bcce23ed5153645d0cd
3
+ size 14614306
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/45.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a20f4693f20d9c74881e1ce7ddab17208e09a146e7389b598c4467a2980cd0f
3
+ size 11767502
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/46.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e858f8c53b2909fcc2fb76287918518b7655fdbf57c5657cba3ac6cdc3e328
3
+ size 11842642
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/47.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bdc51db8374f79753d030e93c65f95785372229d20c30f8fd2a1125705105b
3
+ size 11877796
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/48.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b08da9afcd4e789fb7198736668b930400002bd61cb61b48c21a891bf2e857
3
+ size 12612739
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/49.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e78a2f9363bf71d9bcdfba29174c47d9470a631bd4b088eec444ccf23ee9b3
3
+ size 14134979
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/5.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb952831d0d7ac7ded984ef5812736f71790cb88b1ec0a73982f896fbb034eb
3
+ size 14146728
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/50.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0540377ebc317f49f251db749f2cdc80fa5d1193770cc2aa7d6a057a25cad88f
3
+ size 14463399
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/51.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3905b137bbfdf04a444a381a428eb63567fe02905404d0ecb4a429047fa644
3
+ size 12940329
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/52.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56241b6b6e66889ac64e3b70dc7b6086a153d871fe1adc7270a6bf2754aa5f3c
3
+ size 13932744
rl/qwen3_4b_agent_prm_exact_match/rollouts/training/53.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d22df5cc4efe740d1d024ae496cd7597c2c9ef345b46339a5345aca1ffa1e9b
3
+ size 13110347