DONE
Browse files- README.md +101 -101
- adapter_model.safetensors +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
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.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,106 +47,106 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
|
|
51 |
-
|
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
-
|
|
81 |
-
|
|
82 |
-
|
|
83 |
-
|
|
84 |
-
|
|
85 |
-
|
|
86 |
-
|
|
87 |
-
|
|
88 |
-
|
|
89 |
-
|
|
90 |
-
|
|
91 |
-
|
|
92 |
-
|
|
93 |
-
|
|
94 |
-
|
|
95 |
-
|
|
96 |
-
|
|
97 |
-
|
|
98 |
-
|
|
99 |
-
|
|
100 |
-
|
|
101 |
-
|
|
102 |
-
|
|
103 |
-
|
|
104 |
-
|
|
105 |
-
|
|
106 |
-
|
|
107 |
-
|
|
108 |
-
|
|
109 |
-
|
|
110 |
-
|
|
111 |
-
|
|
112 |
-
|
|
113 |
-
|
|
114 |
-
|
|
115 |
-
|
|
116 |
-
|
|
117 |
-
|
|
118 |
-
|
|
119 |
-
|
|
120 |
-
|
|
121 |
-
|
|
122 |
-
|
|
123 |
-
|
|
124 |
-
|
|
125 |
-
|
|
126 |
-
|
|
127 |
-
|
|
128 |
-
|
|
129 |
-
|
|
130 |
-
|
|
131 |
-
|
|
132 |
-
|
|
133 |
-
|
|
134 |
-
|
|
135 |
-
|
|
136 |
-
|
|
137 |
-
|
|
138 |
-
|
|
139 |
-
|
|
140 |
-
|
|
141 |
-
|
|
142 |
-
|
|
143 |
-
|
|
144 |
-
|
|
145 |
-
|
|
146 |
-
|
|
147 |
-
|
|
148 |
-
|
|
149 |
-
|
|
150 |
|
151 |
|
152 |
### Framework versions
|
|
|
16 |
|
17 |
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.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0122
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 2.663 | 1.0 | 1 | 2.6473 |
|
51 |
+
| 2.663 | 2.0 | 2 | 2.6284 |
|
52 |
+
| 2.663 | 3.0 | 3 | 2.6095 |
|
53 |
+
| 2.663 | 4.0 | 4 | 2.5898 |
|
54 |
+
| 2.663 | 5.0 | 5 | 2.5701 |
|
55 |
+
| 2.663 | 6.0 | 6 | 2.5508 |
|
56 |
+
| 2.663 | 7.0 | 7 | 2.5316 |
|
57 |
+
| 2.663 | 8.0 | 8 | 2.5124 |
|
58 |
+
| 2.663 | 9.0 | 9 | 2.4934 |
|
59 |
+
| 2.663 | 10.0 | 10 | 2.4744 |
|
60 |
+
| 2.663 | 11.0 | 11 | 2.4557 |
|
61 |
+
| 2.663 | 12.0 | 12 | 2.4364 |
|
62 |
+
| 2.663 | 13.0 | 13 | 2.4178 |
|
63 |
+
| 2.663 | 14.0 | 14 | 2.3992 |
|
64 |
+
| 2.663 | 15.0 | 15 | 2.3805 |
|
65 |
+
| 2.663 | 16.0 | 16 | 2.3617 |
|
66 |
+
| 2.663 | 17.0 | 17 | 2.3427 |
|
67 |
+
| 2.663 | 18.0 | 18 | 2.3242 |
|
68 |
+
| 2.663 | 19.0 | 19 | 2.3051 |
|
69 |
+
| 2.663 | 20.0 | 20 | 2.2862 |
|
70 |
+
| 2.663 | 21.0 | 21 | 2.2672 |
|
71 |
+
| 2.663 | 22.0 | 22 | 2.2477 |
|
72 |
+
| 2.663 | 23.0 | 23 | 2.2290 |
|
73 |
+
| 2.663 | 24.0 | 24 | 2.2094 |
|
74 |
+
| 2.663 | 25.0 | 25 | 2.1900 |
|
75 |
+
| 2.663 | 26.0 | 26 | 2.1703 |
|
76 |
+
| 2.663 | 27.0 | 27 | 2.1507 |
|
77 |
+
| 2.663 | 28.0 | 28 | 2.1307 |
|
78 |
+
| 2.663 | 29.0 | 29 | 2.1109 |
|
79 |
+
| 2.663 | 30.0 | 30 | 2.0904 |
|
80 |
+
| 2.663 | 31.0 | 31 | 2.0707 |
|
81 |
+
| 2.663 | 32.0 | 32 | 2.0505 |
|
82 |
+
| 2.663 | 33.0 | 33 | 2.0301 |
|
83 |
+
| 2.663 | 34.0 | 34 | 2.0093 |
|
84 |
+
| 2.663 | 35.0 | 35 | 1.9888 |
|
85 |
+
| 2.663 | 36.0 | 36 | 1.9680 |
|
86 |
+
| 2.663 | 37.0 | 37 | 1.9474 |
|
87 |
+
| 2.663 | 38.0 | 38 | 1.9263 |
|
88 |
+
| 2.663 | 39.0 | 39 | 1.9056 |
|
89 |
+
| 2.663 | 40.0 | 40 | 1.8845 |
|
90 |
+
| 2.663 | 41.0 | 41 | 1.8634 |
|
91 |
+
| 2.663 | 42.0 | 42 | 1.8422 |
|
92 |
+
| 2.663 | 43.0 | 43 | 1.8211 |
|
93 |
+
| 2.663 | 44.0 | 44 | 1.7998 |
|
94 |
+
| 2.663 | 45.0 | 45 | 1.7781 |
|
95 |
+
| 2.663 | 46.0 | 46 | 1.7571 |
|
96 |
+
| 2.663 | 47.0 | 47 | 1.7359 |
|
97 |
+
| 2.663 | 48.0 | 48 | 1.7143 |
|
98 |
+
| 2.663 | 49.0 | 49 | 1.6924 |
|
99 |
+
| 2.663 | 50.0 | 50 | 1.6712 |
|
100 |
+
| 2.663 | 51.0 | 51 | 1.6498 |
|
101 |
+
| 2.663 | 52.0 | 52 | 1.6280 |
|
102 |
+
| 2.663 | 53.0 | 53 | 1.6064 |
|
103 |
+
| 2.663 | 54.0 | 54 | 1.5849 |
|
104 |
+
| 2.663 | 55.0 | 55 | 1.5633 |
|
105 |
+
| 2.663 | 56.0 | 56 | 1.5415 |
|
106 |
+
| 2.663 | 57.0 | 57 | 1.5203 |
|
107 |
+
| 2.663 | 58.0 | 58 | 1.4995 |
|
108 |
+
| 2.663 | 59.0 | 59 | 1.4784 |
|
109 |
+
| 2.663 | 60.0 | 60 | 1.4582 |
|
110 |
+
| 2.663 | 61.0 | 61 | 1.4383 |
|
111 |
+
| 2.663 | 62.0 | 62 | 1.4182 |
|
112 |
+
| 2.663 | 63.0 | 63 | 1.3990 |
|
113 |
+
| 2.663 | 64.0 | 64 | 1.3797 |
|
114 |
+
| 2.663 | 65.0 | 65 | 1.3604 |
|
115 |
+
| 2.663 | 66.0 | 66 | 1.3420 |
|
116 |
+
| 2.663 | 67.0 | 67 | 1.3234 |
|
117 |
+
| 2.663 | 68.0 | 68 | 1.3057 |
|
118 |
+
| 2.663 | 69.0 | 69 | 1.2877 |
|
119 |
+
| 2.663 | 70.0 | 70 | 1.2709 |
|
120 |
+
| 2.663 | 71.0 | 71 | 1.2545 |
|
121 |
+
| 2.663 | 72.0 | 72 | 1.2383 |
|
122 |
+
| 2.663 | 73.0 | 73 | 1.2223 |
|
123 |
+
| 2.663 | 74.0 | 74 | 1.2075 |
|
124 |
+
| 2.663 | 75.0 | 75 | 1.1930 |
|
125 |
+
| 2.663 | 76.0 | 76 | 1.1782 |
|
126 |
+
| 2.663 | 77.0 | 77 | 1.1645 |
|
127 |
+
| 2.663 | 78.0 | 78 | 1.1511 |
|
128 |
+
| 2.663 | 79.0 | 79 | 1.1386 |
|
129 |
+
| 2.663 | 80.0 | 80 | 1.1269 |
|
130 |
+
| 2.663 | 81.0 | 81 | 1.1160 |
|
131 |
+
| 2.663 | 82.0 | 82 | 1.1056 |
|
132 |
+
| 2.663 | 83.0 | 83 | 1.0966 |
|
133 |
+
| 2.663 | 84.0 | 84 | 1.0882 |
|
134 |
+
| 2.663 | 85.0 | 85 | 1.0798 |
|
135 |
+
| 2.663 | 86.0 | 86 | 1.0715 |
|
136 |
+
| 2.663 | 87.0 | 87 | 1.0632 |
|
137 |
+
| 2.663 | 88.0 | 88 | 1.0557 |
|
138 |
+
| 2.663 | 89.0 | 89 | 1.0486 |
|
139 |
+
| 2.663 | 90.0 | 90 | 1.0418 |
|
140 |
+
| 2.663 | 91.0 | 91 | 1.0366 |
|
141 |
+
| 2.663 | 92.0 | 92 | 1.0314 |
|
142 |
+
| 2.663 | 93.0 | 93 | 1.0269 |
|
143 |
+
| 2.663 | 94.0 | 94 | 1.0230 |
|
144 |
+
| 2.663 | 95.0 | 95 | 1.0201 |
|
145 |
+
| 2.663 | 96.0 | 96 | 1.0176 |
|
146 |
+
| 2.663 | 97.0 | 97 | 1.0154 |
|
147 |
+
| 2.663 | 98.0 | 98 | 1.0138 |
|
148 |
+
| 2.663 | 99.0 | 99 | 1.0125 |
|
149 |
+
| 1.7168 | 100.0 | 100 | 1.0122 |
|
150 |
|
151 |
|
152 |
### Framework versions
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9229de89713968ce128b1df581a5c67709e347e9644d826eab6b58c713b1110a
|
3 |
+
size 18906384
|