Evan-Lin/dpo-llama-chat
Browse files- README.md +19 -19
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Rewards/chosen:
|
22 |
-
- Rewards/rejected:
|
23 |
-
- Rewards/accuracies: 0.
|
24 |
-
- Rewards/margins:
|
25 |
-
- Logps/rejected: -
|
26 |
-
- Logps/chosen: -
|
27 |
-
- Logits/rejected: -0.
|
28 |
-
- Logits/chosen: -0.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -62,16 +62,16 @@ The following hyperparameters were used during training:
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 4.9481
|
21 |
+
- Rewards/chosen: 4.6795
|
22 |
+
- Rewards/rejected: 2.8189
|
23 |
+
- Rewards/accuracies: 0.8547
|
24 |
+
- Rewards/margins: 1.8606
|
25 |
+
- Logps/rejected: -60.8495
|
26 |
+
- Logps/chosen: -50.0326
|
27 |
+
- Logits/rejected: -0.2216
|
28 |
+
- Logits/chosen: -0.2323
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
64 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
65 |
+
| 6.3 | 0.24 | 100 | 6.1290 | 3.4767 | 3.2110 | 0.5920 | 0.2657 | -56.9286 | -62.0606 | -0.2723 | -0.2654 |
|
66 |
+
| 5.5843 | 0.48 | 200 | 5.8936 | 3.6904 | 3.2305 | 0.6520 | 0.4599 | -56.7330 | -59.9230 | 0.2517 | 0.2475 |
|
67 |
+
| 5.757 | 0.72 | 300 | 5.6694 | 3.9164 | 3.1893 | 0.7253 | 0.7271 | -57.1450 | -57.6631 | 0.3505 | 0.3418 |
|
68 |
+
| 5.5385 | 0.96 | 400 | 5.4629 | 4.1466 | 3.1351 | 0.7600 | 1.0115 | -57.6871 | -55.3611 | 0.2059 | 0.1970 |
|
69 |
+
| 5.2301 | 1.2 | 500 | 5.2891 | 4.3324 | 3.0305 | 0.7880 | 1.3020 | -58.7338 | -53.5027 | 0.1063 | 0.0968 |
|
70 |
+
| 5.0115 | 1.44 | 600 | 5.1601 | 4.4582 | 2.9458 | 0.8213 | 1.5124 | -59.5800 | -52.2452 | -0.1082 | -0.1154 |
|
71 |
+
| 4.9893 | 1.68 | 700 | 5.0431 | 4.5787 | 2.9142 | 0.8413 | 1.6645 | -59.8968 | -51.0404 | -0.1716 | -0.1829 |
|
72 |
+
| 5.0292 | 1.92 | 800 | 4.9770 | 4.6501 | 2.8827 | 0.8427 | 1.7673 | -60.2111 | -50.3266 | -0.1929 | -0.2042 |
|
73 |
+
| 4.331 | 2.16 | 900 | 4.9577 | 4.6724 | 2.8191 | 0.8480 | 1.8534 | -60.8478 | -50.1027 | -0.2005 | -0.2121 |
|
74 |
+
| 4.5481 | 2.4 | 1000 | 4.9481 | 4.6795 | 2.8189 | 0.8547 | 1.8606 | -60.8495 | -50.0326 | -0.2216 | -0.2323 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -21,10 +21,10 @@
|
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
"v_proj",
|
24 |
-
"out_proj",
|
25 |
-
"fc_in",
|
26 |
"fc_out",
|
27 |
"wte",
|
|
|
|
|
28 |
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
|
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
"v_proj",
|
|
|
|
|
24 |
"fc_out",
|
25 |
"wte",
|
26 |
+
"fc_in",
|
27 |
+
"out_proj",
|
28 |
"q_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25191360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93108e6c28525ffb8d87b05696eb8b31bd08294e5d33015dc93951b035400c55
|
3 |
size 25191360
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:630e45561e688294a8f14eb6f70d7fa318ee9bc7202832df13997d33d58e0344
|
3 |
size 4728
|