End of training
Browse files- README.md +10 -10
- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- metrics.jsonl +2 -0
- metrics_epoch_0.96_fold_0_lr_0.0001_seed_5678_weight_2.0.json +1 -0
- metrics_epoch_2.0_fold_0_lr_0.0001_seed_5678_weight_2.0.json +1 -0
- results_epoch_0.96_fold_0_lr_0.0001_seed_5678_weight_2.0.json +0 -0
- results_epoch_2.0_fold_0_lr_0.0001_seed_5678_weight_2.0.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Eval/rewards/chosen:
|
23 |
-
- Eval/logps/chosen: -
|
24 |
-
- Eval/rewards/rejected:
|
25 |
-
- Eval/logps/rejected: -
|
26 |
-
- Eval/rewards/margins:
|
27 |
-
- Eval/kl:
|
28 |
|
29 |
## Model description
|
30 |
|
@@ -43,7 +43,7 @@ More information needed
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
-
- learning_rate: 0.
|
47 |
- train_batch_size: 1
|
48 |
- eval_batch_size: 2
|
49 |
- seed: 5678
|
@@ -58,8 +58,8 @@ The following hyperparameters were used during training:
|
|
58 |
|
59 |
| Training Loss | Epoch | Step | Validation Loss | |
|
60 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6719
|
22 |
+
- Eval/rewards/chosen: 3.3033
|
23 |
+
- Eval/logps/chosen: -167.4968
|
24 |
+
- Eval/rewards/rejected: 2.5694
|
25 |
+
- Eval/logps/rejected: -214.6203
|
26 |
+
- Eval/rewards/margins: 0.7339
|
27 |
+
- Eval/kl: 27.9394
|
28 |
|
29 |
## Model description
|
30 |
|
|
|
43 |
### Training hyperparameters
|
44 |
|
45 |
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 0.0001
|
47 |
- train_batch_size: 1
|
48 |
- eval_batch_size: 2
|
49 |
- seed: 5678
|
|
|
58 |
|
59 |
| Training Loss | Epoch | Step | Validation Loss | |
|
60 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
61 |
+
| 0.5643 | 0.96 | 12 | 0.6616 | 20.6058 |
|
62 |
+
| 0.5188 | 2.0 | 25 | 0.6719 | 27.9394 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
"v_proj",
|
|
|
25 |
"k_proj",
|
26 |
"o_proj"
|
27 |
],
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
"k_proj",
|
26 |
"o_proj"
|
27 |
],
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27297544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4527ca7d2c9e75f611647772f1c417097f415a07ebe3f41a2599123982f932f
|
3 |
size 27297544
|
metrics.jsonl
CHANGED
@@ -12,3 +12,5 @@
|
|
12 |
{"epoch": 2.0, "precision": 0.5686274498654363, "recall": 0.9666666634444444, "fold": 0}
|
13 |
{"epoch": 0.96, "precision": 0.3582089546892404, "recall": 0.7999999973333333, "fold": 0}
|
14 |
{"epoch": 2.0, "precision": 0.624999998046875, "recall": 0.6666666644444444, "fold": 0}
|
|
|
|
|
|
12 |
{"epoch": 2.0, "precision": 0.5686274498654363, "recall": 0.9666666634444444, "fold": 0}
|
13 |
{"epoch": 0.96, "precision": 0.3582089546892404, "recall": 0.7999999973333333, "fold": 0}
|
14 |
{"epoch": 2.0, "precision": 0.624999998046875, "recall": 0.6666666644444444, "fold": 0}
|
15 |
+
{"epoch": 0.96, "precision": 0.3749999994791667, "recall": 0.899999997, "fold": 0}
|
16 |
+
{"epoch": 2.0, "precision": 0.9090909049586776, "recall": 0.6666666644444444, "fold": 0}
|
metrics_epoch_0.96_fold_0_lr_0.0001_seed_5678_weight_2.0.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"epoch": 0.96, "precision": 0.3749999994791667, "recall": 0.899999997, "fold": 0}
|
metrics_epoch_2.0_fold_0_lr_0.0001_seed_5678_weight_2.0.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"epoch": 2.0, "precision": 0.9090909049586776, "recall": 0.6666666644444444, "fold": 0}
|
results_epoch_0.96_fold_0_lr_0.0001_seed_5678_weight_2.0.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
results_epoch_2.0_fold_0_lr_0.0001_seed_5678_weight_2.0.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:424b754ebd47e29ce17ae5e53d89c6ab439b604a77dbde60473874ff30be8777
|
3 |
size 5688
|