Evan-Lin/dpo-llama-chat
Browse files- README.md +22 -22
- adapter_config.json +6 -6
- 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: 0.
|
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 |
|
@@ -45,13 +45,13 @@ More information needed
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 0.0001
|
48 |
-
- train_batch_size:
|
49 |
- eval_batch_size: 2
|
50 |
- seed: 42
|
51 |
- distributed_type: multi-GPU
|
52 |
- num_devices: 2
|
53 |
-
- gradient_accumulation_steps:
|
54 |
-
- total_train_batch_size:
|
55 |
- total_eval_batch_size: 4
|
56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
- lr_scheduler_type: cosine
|
@@ -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 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
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: 0.1928
|
21 |
+
- Rewards/chosen: -1.3672
|
22 |
+
- Rewards/rejected: -4.3992
|
23 |
+
- Rewards/accuracies: 0.9310
|
24 |
+
- Rewards/margins: 3.0321
|
25 |
+
- Logps/rejected: -133.6114
|
26 |
+
- Logps/chosen: -90.8071
|
27 |
+
- Logits/rejected: -0.8584
|
28 |
+
- Logits/chosen: -0.8277
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 0.0001
|
48 |
+
- train_batch_size: 2
|
49 |
- eval_batch_size: 2
|
50 |
- seed: 42
|
51 |
- distributed_type: multi-GPU
|
52 |
- num_devices: 2
|
53 |
+
- gradient_accumulation_steps: 16
|
54 |
+
- total_train_batch_size: 64
|
55 |
- total_eval_batch_size: 4
|
56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
- lr_scheduler_type: cosine
|
|
|
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 |
+
| 0.5985 | 0.24 | 100 | 0.5908 | -0.0098 | -0.3706 | 0.6857 | 0.3608 | -93.3248 | -77.2335 | -0.7818 | -0.8133 |
|
66 |
+
| 0.5032 | 0.47 | 200 | 0.4768 | -0.1589 | -0.9349 | 0.8037 | 0.7760 | -98.9677 | -78.7246 | -0.8669 | -0.8774 |
|
67 |
+
| 0.4105 | 0.71 | 300 | 0.4056 | -0.3303 | -1.5893 | 0.8316 | 1.2589 | -105.5115 | -80.4384 | -0.8423 | -0.8361 |
|
68 |
+
| 0.3707 | 0.94 | 400 | 0.3501 | -0.2376 | -1.6094 | 0.8760 | 1.3718 | -105.7129 | -79.5110 | -0.7540 | -0.7564 |
|
69 |
+
| 0.2363 | 1.18 | 500 | 0.2939 | -0.8615 | -2.9614 | 0.8932 | 2.0999 | -119.2329 | -85.7499 | -0.8983 | -0.8797 |
|
70 |
+
| 0.1947 | 1.42 | 600 | 0.2463 | -1.0709 | -3.5879 | 0.9085 | 2.5170 | -125.4976 | -87.8440 | -0.8982 | -0.8717 |
|
71 |
+
| 0.1823 | 1.65 | 700 | 0.2242 | -1.2056 | -3.7965 | 0.9158 | 2.5909 | -127.5844 | -89.1917 | -0.8272 | -0.8112 |
|
72 |
+
| 0.1476 | 1.89 | 800 | 0.2042 | -1.1764 | -3.9644 | 0.9271 | 2.7881 | -129.2632 | -88.8989 | -0.8622 | -0.8415 |
|
73 |
+
| 0.112 | 2.13 | 900 | 0.1936 | -1.3373 | -4.3265 | 0.9330 | 2.9891 | -132.8835 | -90.5088 | -0.8608 | -0.8338 |
|
74 |
+
| 0.0949 | 2.36 | 1000 | 0.1928 | -1.3672 | -4.3992 | 0.9310 | 3.0321 | -133.6114 | -90.8071 | -0.8584 | -0.8277 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"wte",
|
23 |
-
"k_proj",
|
24 |
-
"v_proj",
|
25 |
-
"fc_out",
|
26 |
"q_proj",
|
27 |
-
"
|
28 |
-
"
|
|
|
|
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
|
|
|
|
22 |
"q_proj",
|
23 |
+
"fc_out",
|
24 |
+
"v_proj",
|
25 |
+
"fc_in",
|
26 |
+
"k_proj",
|
27 |
+
"wte",
|
28 |
+
"out_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
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:fc3e5eb50b8a8a1cc43ddc29766728a77c67150c862524c353594915cdf705c3
|
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 sha256:97dff2bbaa6fc557cf89b82d24d24aa9d4d70634cde8b9dc8894b5eeee7e0230
|
3 |
size 4728
|