baby-dev commited on
Commit
00cd722
·
verified ·
1 Parent(s): 01a4ee0

End of training

Browse files
Files changed (3) hide show
  1. README.md +26 -29
  2. adapter_model.bin +1 -1
  3. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -113,7 +113,7 @@ xformers_attention: null
113
 
114
  This model is a fine-tuned version of [peft-internal-testing/tiny-dummy-qwen2](https://huggingface.co/peft-internal-testing/tiny-dummy-qwen2) on the None dataset.
115
  It achieves the following results on the evaluation set:
116
- - Loss: 11.8994
117
 
118
  ## Model description
119
 
@@ -148,34 +148,31 @@ The following hyperparameters were used during training:
148
  | Training Loss | Epoch | Step | Validation Loss |
149
  |:-------------:|:-------:|:----:|:---------------:|
150
  | No log | 0.0083 | 1 | 11.9304 |
151
- | 12.1074 | 1.2474 | 150 | 11.9141 |
152
- | 11.917 | 2.4948 | 300 | 11.9077 |
153
- | 11.9081 | 3.7422 | 450 | 11.9052 |
154
- | 11.9026 | 4.9896 | 600 | 11.9038 |
155
- | 12.0859 | 6.2370 | 750 | 11.9026 |
156
- | 11.9028 | 7.4844 | 900 | 11.9019 |
157
- | 11.8998 | 8.7318 | 1050 | 11.9016 |
158
- | 11.9048 | 9.9792 | 1200 | 11.9015 |
159
- | 12.084 | 11.2266 | 1350 | 11.9014 |
160
- | 11.8994 | 12.4740 | 1500 | 11.9011 |
161
- | 11.8969 | 13.7214 | 1650 | 11.9008 |
162
- | 11.8969 | 14.9688 | 1800 | 11.9005 |
163
- | 12.0752 | 16.2162 | 1950 | 11.9004 |
164
- | 11.8995 | 17.4636 | 2100 | 11.9006 |
165
- | 11.9041 | 18.7110 | 2250 | 11.9004 |
166
- | 11.9008 | 19.9584 | 2400 | 11.9004 |
167
- | 12.0829 | 21.2058 | 2550 | 11.9002 |
168
- | 11.9013 | 22.4532 | 2700 | 11.8999 |
169
- | 11.9025 | 23.7006 | 2850 | 11.8999 |
170
- | 11.8988 | 24.9480 | 3000 | 11.8996 |
171
- | 12.0787 | 26.1954 | 3150 | 11.8996 |
172
- | 11.8966 | 27.4428 | 3300 | 11.8996 |
173
- | 11.8997 | 28.6902 | 3450 | 11.8996 |
174
- | 11.9017 | 29.9376 | 3600 | 11.8995 |
175
- | 12.0742 | 31.1850 | 3750 | 11.8995 |
176
- | 11.8992 | 32.4324 | 3900 | 11.8992 |
177
- | 11.9043 | 33.6798 | 4050 | 11.8994 |
178
- | 11.895 | 34.9272 | 4200 | 11.8994 |
179
 
180
 
181
  ### Framework versions
 
113
 
114
  This model is a fine-tuned version of [peft-internal-testing/tiny-dummy-qwen2](https://huggingface.co/peft-internal-testing/tiny-dummy-qwen2) on the None dataset.
115
  It achieves the following results on the evaluation set:
116
+ - Loss: 11.8983
117
 
118
  ## Model description
119
 
 
148
  | Training Loss | Epoch | Step | Validation Loss |
149
  |:-------------:|:-------:|:----:|:---------------:|
150
  | No log | 0.0083 | 1 | 11.9304 |
151
+ | 12.1085 | 1.2474 | 150 | 11.9156 |
152
+ | 11.917 | 2.4948 | 300 | 11.9073 |
153
+ | 11.908 | 3.7422 | 450 | 11.9048 |
154
+ | 11.9016 | 4.9896 | 600 | 11.9026 |
155
+ | 12.0853 | 6.2370 | 750 | 11.9015 |
156
+ | 11.9024 | 7.4844 | 900 | 11.9007 |
157
+ | 11.8993 | 8.7318 | 1050 | 11.9006 |
158
+ | 11.9043 | 9.9792 | 1200 | 11.9003 |
159
+ | 12.0835 | 11.2266 | 1350 | 11.9001 |
160
+ | 11.8991 | 12.4740 | 1500 | 11.9000 |
161
+ | 11.8963 | 13.7214 | 1650 | 11.8995 |
162
+ | 11.8964 | 14.9688 | 1800 | 11.8992 |
163
+ | 12.0746 | 16.2162 | 1950 | 11.8992 |
164
+ | 11.8988 | 17.4636 | 2100 | 11.8993 |
165
+ | 11.9032 | 18.7110 | 2250 | 11.8992 |
166
+ | 11.9002 | 19.9584 | 2400 | 11.8991 |
167
+ | 12.0821 | 21.2058 | 2550 | 11.8989 |
168
+ | 11.9004 | 22.4532 | 2700 | 11.8986 |
169
+ | 11.9018 | 23.7006 | 2850 | 11.8985 |
170
+ | 11.8981 | 24.9480 | 3000 | 11.8982 |
171
+ | 12.0775 | 26.1954 | 3150 | 11.8983 |
172
+ | 11.8959 | 27.4428 | 3300 | 11.8982 |
173
+ | 11.8987 | 28.6902 | 3450 | 11.8982 |
174
+ | 11.901 | 29.9376 | 3600 | 11.8982 |
175
+ | 12.0734 | 31.1850 | 3750 | 11.8983 |
 
 
 
176
 
177
 
178
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4508921f2ccb5fd88d4646b57d46f9749b5d720c519b7e10c595067c7e6ded1
3
  size 55170
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edce383b7f5f48534cae1b2b3d8eb97699453e0acd294eeaf692082a6f18b217
3
  size 55170
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15c45c6e7cae74c7c01cc815be82d11c04abfc37e552bbb2e1edeb577ca83b42
3
  size 48552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7564ca0da7a36af4a49e6efe1b662d7b48552179d9139c4a0001f28fb52be0f7
3
  size 48552