howard
commited on
Commit
•
162b431
1
Parent(s):
7454159
for the west coast gas price only
Browse files- README.md +42 -42
- adapter_config.json +3 -3
- adapter_model.bin +1 -1
- checkpoint-3178/adapter_config.json +3 -3
- checkpoint-3178/adapter_model.safetensors +1 -1
- checkpoint-3178/optimizer.pt +1 -1
- checkpoint-3178/trainer_state.json +0 -0
- checkpoint-3178/training_args.bin +1 -1
- checkpoint-3632/adapter_config.json +3 -3
- checkpoint-3632/adapter_model.safetensors +1 -1
- checkpoint-3632/optimizer.pt +1 -1
- checkpoint-3632/trainer_state.json +0 -0
- checkpoint-3632/training_args.bin +1 -1
- checkpoint-4086/adapter_config.json +3 -3
- checkpoint-4086/adapter_model.safetensors +1 -1
- checkpoint-4086/optimizer.pt +1 -1
- checkpoint-4086/trainer_state.json +0 -0
- checkpoint-4086/training_args.bin +1 -1
- checkpoint-4540/adapter_config.json +3 -3
- checkpoint-4540/adapter_model.safetensors +1 -1
- checkpoint-4540/optimizer.pt +1 -1
- checkpoint-4540/trainer_state.json +0 -0
- checkpoint-4540/training_args.bin +1 -1
README.md
CHANGED
@@ -92,12 +92,12 @@ seed: 42
|
|
92 |
|
93 |
</details><br>
|
94 |
|
95 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://rosewandb.ucsd.edu/cht028/finetune/runs/
|
96 |
# finetune/outputs/gas-west
|
97 |
|
98 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
99 |
It achieves the following results on the evaluation set:
|
100 |
-
- Loss: 0.
|
101 |
|
102 |
## Model description
|
103 |
|
@@ -134,46 +134,46 @@ The following hyperparameters were used during training:
|
|
134 |
|
135 |
| Training Loss | Epoch | Step | Validation Loss |
|
136 |
|:-------------:|:------:|:----:|:---------------:|
|
137 |
-
| 1.
|
138 |
-
| 0.
|
139 |
-
| 0.
|
140 |
-
| 0.
|
141 |
-
| 0.
|
142 |
-
| 0.
|
143 |
-
| 0.
|
144 |
-
| 0.
|
145 |
-
| 0.
|
146 |
-
| 0.
|
147 |
-
| 0.
|
148 |
-
| 0.
|
149 |
-
| 0.
|
150 |
-
| 0.
|
151 |
-
| 0.
|
152 |
-
| 0.
|
153 |
-
| 0.
|
154 |
-
| 0.
|
155 |
-
| 0.
|
156 |
-
| 0.
|
157 |
-
| 0.
|
158 |
-
| 0.
|
159 |
-
| 0.
|
160 |
-
| 0.0001 | 5.7690 | 2622 | 0.
|
161 |
-
| 0.0001 | 6.0198 | 2736 | 0.
|
162 |
-
| 0.0001 | 6.2706 | 2850 | 0.
|
163 |
-
| 0.0001 | 6.5215 | 2964 | 0.
|
164 |
-
| 0.0001 | 6.7723 | 3078 | 0.
|
165 |
-
| 0.0001 | 7.0231 | 3192 | 0.
|
166 |
-
| 0.0001 | 7.2739 | 3306 | 0.
|
167 |
-
| 0.0001 | 7.5248 | 3420 | 0.
|
168 |
-
| 0.0001 | 7.7756 | 3534 | 0.
|
169 |
-
| 0.0002 | 8.0264 | 3648 | 0.
|
170 |
-
| 0.0002 | 8.2772 | 3762 | 0.
|
171 |
-
| 0.0001 | 8.5281 | 3876 | 0.
|
172 |
-
| 0.0001 | 8.7789 | 3990 | 0.
|
173 |
-
| 0.
|
174 |
-
| 0.0001 | 9.2805 | 4218 | 0.
|
175 |
-
| 0.0001 | 9.5314 | 4332 | 0.
|
176 |
-
| 0.0001 | 9.7822 | 4446 | 0.
|
177 |
|
178 |
|
179 |
### Framework versions
|
|
|
92 |
|
93 |
</details><br>
|
94 |
|
95 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://rosewandb.ucsd.edu/cht028/finetune/runs/5y7pxhrx)
|
96 |
# finetune/outputs/gas-west
|
97 |
|
98 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
|
99 |
It achieves the following results on the evaluation set:
|
100 |
+
- Loss: 0.0003
|
101 |
|
102 |
## Model description
|
103 |
|
|
|
134 |
|
135 |
| Training Loss | Epoch | Step | Validation Loss |
|
136 |
|:-------------:|:------:|:----:|:---------------:|
|
137 |
+
| 1.4517 | 0.0022 | 1 | 1.3369 |
|
138 |
+
| 0.6431 | 0.2508 | 114 | 0.6256 |
|
139 |
+
| 0.3998 | 0.5017 | 228 | 0.4131 |
|
140 |
+
| 0.1741 | 0.7525 | 342 | 0.2322 |
|
141 |
+
| 0.0913 | 1.0033 | 456 | 0.1268 |
|
142 |
+
| 0.0679 | 1.2541 | 570 | 0.0809 |
|
143 |
+
| 0.0503 | 1.5050 | 684 | 0.0605 |
|
144 |
+
| 0.0476 | 1.7558 | 798 | 0.0484 |
|
145 |
+
| 0.0084 | 2.0066 | 912 | 0.0417 |
|
146 |
+
| 0.0273 | 2.2574 | 1026 | 0.0410 |
|
147 |
+
| 0.0296 | 2.5083 | 1140 | 0.0384 |
|
148 |
+
| 0.0317 | 2.7591 | 1254 | 0.0344 |
|
149 |
+
| 0.0086 | 3.0099 | 1368 | 0.0268 |
|
150 |
+
| 0.0076 | 3.2607 | 1482 | 0.0224 |
|
151 |
+
| 0.0043 | 3.5116 | 1596 | 0.0206 |
|
152 |
+
| 0.0085 | 3.7624 | 1710 | 0.0127 |
|
153 |
+
| 0.0071 | 4.0132 | 1824 | 0.0081 |
|
154 |
+
| 0.002 | 4.2640 | 1938 | 0.0053 |
|
155 |
+
| 0.0028 | 4.5149 | 2052 | 0.0034 |
|
156 |
+
| 0.0007 | 4.7657 | 2166 | 0.0016 |
|
157 |
+
| 0.0003 | 5.0165 | 2280 | 0.0008 |
|
158 |
+
| 0.0002 | 5.2673 | 2394 | 0.0005 |
|
159 |
+
| 0.0002 | 5.5182 | 2508 | 0.0004 |
|
160 |
+
| 0.0001 | 5.7690 | 2622 | 0.0004 |
|
161 |
+
| 0.0001 | 6.0198 | 2736 | 0.0004 |
|
162 |
+
| 0.0001 | 6.2706 | 2850 | 0.0004 |
|
163 |
+
| 0.0001 | 6.5215 | 2964 | 0.0004 |
|
164 |
+
| 0.0001 | 6.7723 | 3078 | 0.0004 |
|
165 |
+
| 0.0001 | 7.0231 | 3192 | 0.0004 |
|
166 |
+
| 0.0001 | 7.2739 | 3306 | 0.0004 |
|
167 |
+
| 0.0001 | 7.5248 | 3420 | 0.0004 |
|
168 |
+
| 0.0001 | 7.7756 | 3534 | 0.0004 |
|
169 |
+
| 0.0002 | 8.0264 | 3648 | 0.0004 |
|
170 |
+
| 0.0002 | 8.2772 | 3762 | 0.0003 |
|
171 |
+
| 0.0001 | 8.5281 | 3876 | 0.0004 |
|
172 |
+
| 0.0001 | 8.7789 | 3990 | 0.0003 |
|
173 |
+
| 0.0002 | 9.0297 | 4104 | 0.0003 |
|
174 |
+
| 0.0001 | 9.2805 | 4218 | 0.0003 |
|
175 |
+
| 0.0001 | 9.5314 | 4332 | 0.0004 |
|
176 |
+
| 0.0001 | 9.7822 | 4446 | 0.0003 |
|
177 |
|
178 |
|
179 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
|
|
26 |
"o_proj",
|
27 |
-
"up_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"gate_proj",
|
24 |
+
"q_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
"o_proj",
|
|
|
28 |
"v_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167934026
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33193aaced75889415645d62a2c9663cd760864ab10f4304a831ddbacb7be301
|
3 |
size 167934026
|
checkpoint-3178/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
|
|
26 |
"o_proj",
|
27 |
-
"up_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"gate_proj",
|
24 |
+
"q_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
"o_proj",
|
|
|
28 |
"v_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
checkpoint-3178/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af75d09941aa410e75084a4d0cb9c274d2efa9f9af4e1a36750ec7a5fe555e97
|
3 |
size 167832688
|
checkpoint-3178/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671364538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7f4f8a3ba9b2ee8e28e4a65b9ed1770adb2675aeeb07b3408ee90efd2b22b3d
|
3 |
size 671364538
|
checkpoint-3178/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3178/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78459f829b6083e305e5286ac1c78edf160f2077290cd2a1eff77d1b67cfdd8b
|
3 |
size 6072
|
checkpoint-3632/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
|
|
26 |
"o_proj",
|
27 |
-
"up_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"gate_proj",
|
24 |
+
"q_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
"o_proj",
|
|
|
28 |
"v_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
checkpoint-3632/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:862575a4ae141e75178da53f4627bbf333b20fa678f68303fc8b7aa65a67fd69
|
3 |
size 167832688
|
checkpoint-3632/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671364538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac3ba5f37738dd78aab031f633dd27f9914f627f0590934c40e44b69cbac3489
|
3 |
size 671364538
|
checkpoint-3632/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3632/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78459f829b6083e305e5286ac1c78edf160f2077290cd2a1eff77d1b67cfdd8b
|
3 |
size 6072
|
checkpoint-4086/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
|
|
26 |
"o_proj",
|
27 |
-
"up_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"gate_proj",
|
24 |
+
"q_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
"o_proj",
|
|
|
28 |
"v_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
checkpoint-4086/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca5b3e2e9a14b122bb2c1fc8481d93134aecdadeed4ba9db53b1701047fd3c52
|
3 |
size 167832688
|
checkpoint-4086/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671364538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c570406e4674f603d2de0715526d0238b3647f3bd60cfd8b2b87025fb745a912
|
3 |
size 671364538
|
checkpoint-4086/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4086/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78459f829b6083e305e5286ac1c78edf160f2077290cd2a1eff77d1b67cfdd8b
|
3 |
size 6072
|
checkpoint-4540/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
|
|
26 |
"o_proj",
|
27 |
-
"up_proj",
|
28 |
"v_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"gate_proj",
|
24 |
+
"q_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
"o_proj",
|
|
|
28 |
"v_proj",
|
29 |
+
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
checkpoint-4540/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1740f20c0c776740397134d55ced0551825a25f672959e3bf584b998d7b78eb
|
3 |
size 167832688
|
checkpoint-4540/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671364538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68615d058768db922830868658dc8092a1a3b57a8dec3af33eb1240695fed591
|
3 |
size 671364538
|
checkpoint-4540/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4540/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78459f829b6083e305e5286ac1c78edf160f2077290cd2a1eff77d1b67cfdd8b
|
3 |
size 6072
|