Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ tags:
|
|
7 |
- full
|
8 |
- generated_from_trainer
|
9 |
metrics:
|
10 |
-
- accuracy
|
11 |
model-index:
|
12 |
- name: reward
|
13 |
results: []
|
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# reward
|
20 |
|
21 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the gsm8k_llama3.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.2467
|
24 |
-
- Accuracy: 0.8810
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -56,19 +56,19 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
### Training results
|
58 |
|
59 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
60 |
-
|
61 |
-
| 0.609 | 0.0856 | 5 | 0.4890 | 0.8135
|
62 |
-
| 0.3044 | 0.1711 | 10 | 0.2622 | 0.9204
|
63 |
-
| 0.3091 | 0.2567 | 15 | 0.1574 | 0.9060
|
64 |
-
| 0.2377 | 0.3422 | 20 | 0.2161 | 0.9090
|
65 |
-
| 0.2227 | 0.4278 | 25 | 0.2810 | 0.8696
|
66 |
-
| 0.3034 | 0.5134 | 30 | 0.2796 | 0.8832
|
67 |
-
| 0.2101 | 0.5989 | 35 | 0.2074 | 0.9022
|
68 |
-
| 0.2027 | 0.6845 | 40 | 0.1866 | 0.9075
|
69 |
-
| 0.2683 | 0.7701 | 45 | 0.2167 | 0.8976
|
70 |
-
| 0.1873 | 0.8556 | 50 | 0.2340 | 0.8878
|
71 |
-
| 0.2984 | 0.9412 | 55 | 0.2451 | 0.8825
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
7 |
- full
|
8 |
- generated_from_trainer
|
9 |
metrics:
|
10 |
+
- val accuracy
|
11 |
model-index:
|
12 |
- name: reward
|
13 |
results: []
|
|
|
18 |
|
19 |
# reward
|
20 |
|
21 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the gsm8k_llama3.1-8B_128_1ep dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 0.2467
|
24 |
+
- val Accuracy: 0.8810
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
56 |
|
57 |
### Training results
|
58 |
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | val Accuracy |
|
60 |
+
|:-------------:|:------:|:----:|:---------------:|:------------:|
|
61 |
+
| 0.609 | 0.0856 | 5 | 0.4890 | 0.8135 |
|
62 |
+
| 0.3044 | 0.1711 | 10 | 0.2622 | 0.9204 |
|
63 |
+
| 0.3091 | 0.2567 | 15 | 0.1574 | 0.9060 |
|
64 |
+
| 0.2377 | 0.3422 | 20 | 0.2161 | 0.9090 |
|
65 |
+
| 0.2227 | 0.4278 | 25 | 0.2810 | 0.8696 |
|
66 |
+
| 0.3034 | 0.5134 | 30 | 0.2796 | 0.8832 |
|
67 |
+
| 0.2101 | 0.5989 | 35 | 0.2074 | 0.9022 |
|
68 |
+
| 0.2027 | 0.6845 | 40 | 0.1866 | 0.9075 |
|
69 |
+
| 0.2683 | 0.7701 | 45 | 0.2167 | 0.8976 |
|
70 |
+
| 0.1873 | 0.8556 | 50 | 0.2340 | 0.8878 |
|
71 |
+
| 0.2984 | 0.9412 | 55 | 0.2451 | 0.8825 |
|
72 |
|
73 |
|
74 |
### Framework versions
|