Upload folder using huggingface_hub
Browse files- README.md +3 -2
- adapter_config.json +4 -4
- adapter_model.bin +1 -1
- optimizer.pt +1 -1
- trainer_state.json +16 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,6 +18,7 @@ base_model: Qwen/Qwen-14B
|
|
18 |
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
|
|
21 |
- **Shared by [optional]:** [More Information Needed]
|
22 |
- **Model type:** [More Information Needed]
|
23 |
- **Language(s) (NLP):** [More Information Needed]
|
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
|
|
76 |
|
77 |
### Training Data
|
78 |
|
79 |
-
<!-- This should link to a
|
80 |
|
81 |
[More Information Needed]
|
82 |
|
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
|
|
107 |
|
108 |
#### Testing Data
|
109 |
|
110 |
-
<!-- This should link to a
|
111 |
|
112 |
[More Information Needed]
|
113 |
|
|
|
18 |
|
19 |
|
20 |
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
- **Shared by [optional]:** [More Information Needed]
|
23 |
- **Model type:** [More Information Needed]
|
24 |
- **Language(s) (NLP):** [More Information Needed]
|
|
|
77 |
|
78 |
### Training Data
|
79 |
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
|
82 |
[More Information Needed]
|
83 |
|
|
|
108 |
|
109 |
#### Testing Data
|
110 |
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
|
113 |
[More Information Needed]
|
114 |
|
adapter_config.json
CHANGED
@@ -16,14 +16,14 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"k_proj",
|
20 |
"v_proj",
|
21 |
"q_proj",
|
22 |
-
"lm_head",
|
23 |
-
"o_proj",
|
24 |
"down_proj",
|
|
|
|
|
25 |
"up_proj",
|
26 |
-
"gate_proj"
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
"q_proj",
|
|
|
|
|
21 |
"down_proj",
|
22 |
+
"o_proj",
|
23 |
+
"lm_head",
|
24 |
"up_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"k_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM"
|
29 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5031484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba8207e6ad6bb7847a4549593b5f444cee0c1ffb6757548360c16050433e4be0
|
3 |
size 5031484
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2525844
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc3bd2d24b27e0c5e5ecd76d11c058563be58130d9ad347aa2e3e1ec6f663181
|
3 |
size 2525844
|
trainer_state.json
CHANGED
@@ -17,7 +17,7 @@
|
|
17 |
{
|
18 |
"epoch": 0.1,
|
19 |
"learning_rate": 1.8426966292134835e-05,
|
20 |
-
"loss": 1.
|
21 |
"step": 40
|
22 |
},
|
23 |
{
|
@@ -41,91 +41,91 @@
|
|
41 |
{
|
42 |
"epoch": 0.29,
|
43 |
"learning_rate": 1.4831460674157305e-05,
|
44 |
-
"loss": 1.
|
45 |
"step": 120
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.34,
|
49 |
"learning_rate": 1.3932584269662923e-05,
|
50 |
-
"loss": 1.
|
51 |
"step": 140
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.39,
|
55 |
"learning_rate": 1.303370786516854e-05,
|
56 |
-
"loss": 1.
|
57 |
"step": 160
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.43,
|
61 |
"learning_rate": 1.213483146067416e-05,
|
62 |
-
"loss": 1.
|
63 |
"step": 180
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.48,
|
67 |
"learning_rate": 1.1235955056179778e-05,
|
68 |
-
"loss": 1.
|
69 |
"step": 200
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.53,
|
73 |
"learning_rate": 1.0337078651685396e-05,
|
74 |
-
"loss": 1.
|
75 |
"step": 220
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.58,
|
79 |
"learning_rate": 9.438202247191012e-06,
|
80 |
-
"loss": 1.
|
81 |
"step": 240
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.63,
|
85 |
"learning_rate": 8.53932584269663e-06,
|
86 |
-
"loss": 1.
|
87 |
"step": 260
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.68,
|
91 |
"learning_rate": 7.640449438202247e-06,
|
92 |
-
"loss": 1.
|
93 |
"step": 280
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.72,
|
97 |
"learning_rate": 6.741573033707865e-06,
|
98 |
-
"loss": 1.
|
99 |
"step": 300
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.77,
|
103 |
"learning_rate": 5.842696629213483e-06,
|
104 |
-
"loss": 1.
|
105 |
"step": 320
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.82,
|
109 |
"learning_rate": 4.943820224719101e-06,
|
110 |
-
"loss": 1.
|
111 |
"step": 340
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.87,
|
115 |
"learning_rate": 4.04494382022472e-06,
|
116 |
-
"loss": 1.
|
117 |
"step": 360
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.92,
|
121 |
"learning_rate": 3.146067415730337e-06,
|
122 |
-
"loss": 1.
|
123 |
"step": 380
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.97,
|
127 |
"learning_rate": 2.2471910112359554e-06,
|
128 |
-
"loss": 1.
|
129 |
"step": 400
|
130 |
}
|
131 |
],
|
|
|
17 |
{
|
18 |
"epoch": 0.1,
|
19 |
"learning_rate": 1.8426966292134835e-05,
|
20 |
+
"loss": 1.9281,
|
21 |
"step": 40
|
22 |
},
|
23 |
{
|
|
|
41 |
{
|
42 |
"epoch": 0.29,
|
43 |
"learning_rate": 1.4831460674157305e-05,
|
44 |
+
"loss": 1.8235,
|
45 |
"step": 120
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.34,
|
49 |
"learning_rate": 1.3932584269662923e-05,
|
50 |
+
"loss": 1.9047,
|
51 |
"step": 140
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.39,
|
55 |
"learning_rate": 1.303370786516854e-05,
|
56 |
+
"loss": 1.8508,
|
57 |
"step": 160
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.43,
|
61 |
"learning_rate": 1.213483146067416e-05,
|
62 |
+
"loss": 1.8613,
|
63 |
"step": 180
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.48,
|
67 |
"learning_rate": 1.1235955056179778e-05,
|
68 |
+
"loss": 1.7997,
|
69 |
"step": 200
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.53,
|
73 |
"learning_rate": 1.0337078651685396e-05,
|
74 |
+
"loss": 1.8873,
|
75 |
"step": 220
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.58,
|
79 |
"learning_rate": 9.438202247191012e-06,
|
80 |
+
"loss": 1.8394,
|
81 |
"step": 240
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.63,
|
85 |
"learning_rate": 8.53932584269663e-06,
|
86 |
+
"loss": 1.8793,
|
87 |
"step": 260
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.68,
|
91 |
"learning_rate": 7.640449438202247e-06,
|
92 |
+
"loss": 1.883,
|
93 |
"step": 280
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.72,
|
97 |
"learning_rate": 6.741573033707865e-06,
|
98 |
+
"loss": 1.8483,
|
99 |
"step": 300
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.77,
|
103 |
"learning_rate": 5.842696629213483e-06,
|
104 |
+
"loss": 1.9065,
|
105 |
"step": 320
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.82,
|
109 |
"learning_rate": 4.943820224719101e-06,
|
110 |
+
"loss": 1.8699,
|
111 |
"step": 340
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.87,
|
115 |
"learning_rate": 4.04494382022472e-06,
|
116 |
+
"loss": 1.8274,
|
117 |
"step": 360
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.92,
|
121 |
"learning_rate": 3.146067415730337e-06,
|
122 |
+
"loss": 1.8264,
|
123 |
"step": 380
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.97,
|
127 |
"learning_rate": 2.2471910112359554e-06,
|
128 |
+
"loss": 1.8423,
|
129 |
"step": 400
|
130 |
}
|
131 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4472
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e57641cf92861a0f39416c240625455232fda32e4298c91afe2b2d5e77c9e9b1
|
3 |
size 4472
|