Upload folder using huggingface_hub
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- trainer_state.json +32 -32
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"up_proj",
|
23 |
-
"
|
24 |
-
"o_proj",
|
25 |
"gate_proj",
|
26 |
-
"
|
|
|
27 |
"v_proj",
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"up_proj",
|
23 |
+
"q_proj",
|
|
|
24 |
"gate_proj",
|
25 |
+
"o_proj",
|
26 |
+
"down_proj",
|
27 |
"v_proj",
|
28 |
+
"k_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242266152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc805562df8d1ecadb0c7ceffd216b6ce1fc1b37b12c12a52bb95c28b1936981
|
3 |
size 242266152
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484650042
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc845a86ea49fcb13768bd2e1dffa9c405dc1c7d0f7bd8eff6b9a03d0a4e377
|
3 |
size 484650042
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97c1c57b943500bdd422828e26395d31b84f5a9794fe4c32c901ecbc4e90724e
|
3 |
size 14244
|
trainer_state.json
CHANGED
@@ -11,187 +11,187 @@
|
|
11 |
{
|
12 |
"epoch": 0.03,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 1.
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.06,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 1.
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.1,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 1.
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.13,
|
31 |
"learning_rate": 0.0002,
|
32 |
-
"loss": 1.
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.16,
|
37 |
"learning_rate": 0.0002,
|
38 |
-
"loss": 1.
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.19,
|
43 |
"learning_rate": 0.0002,
|
44 |
-
"loss": 1.
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.22,
|
49 |
"learning_rate": 0.0002,
|
50 |
-
"loss": 2.
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.26,
|
55 |
"learning_rate": 0.0002,
|
56 |
-
"loss":
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.29,
|
61 |
"learning_rate": 0.0002,
|
62 |
-
"loss": 1.
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.32,
|
67 |
"learning_rate": 0.0002,
|
68 |
-
"loss": 1.
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.35,
|
73 |
"learning_rate": 0.0002,
|
74 |
-
"loss": 1.
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.38,
|
79 |
"learning_rate": 0.0002,
|
80 |
-
"loss": 1.
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.42,
|
85 |
"learning_rate": 0.0002,
|
86 |
-
"loss": 1.
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.45,
|
91 |
"learning_rate": 0.0002,
|
92 |
-
"loss": 1.
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.48,
|
97 |
"learning_rate": 0.0002,
|
98 |
-
"loss":
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.51,
|
103 |
"learning_rate": 0.0002,
|
104 |
-
"loss": 1.
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.54,
|
109 |
"learning_rate": 0.0002,
|
110 |
-
"loss": 1.
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.58,
|
115 |
"learning_rate": 0.0002,
|
116 |
-
"loss": 1.
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.61,
|
121 |
"learning_rate": 0.0002,
|
122 |
-
"loss":
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.64,
|
127 |
"learning_rate": 0.0002,
|
128 |
-
"loss": 1.
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.67,
|
133 |
"learning_rate": 0.0002,
|
134 |
-
"loss": 1.
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.7,
|
139 |
"learning_rate": 0.0002,
|
140 |
-
"loss": 1.
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.74,
|
145 |
"learning_rate": 0.0002,
|
146 |
-
"loss":
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.77,
|
151 |
"learning_rate": 0.0002,
|
152 |
-
"loss": 1.
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.8,
|
157 |
"learning_rate": 0.0002,
|
158 |
-
"loss": 1.
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.83,
|
163 |
"learning_rate": 0.0002,
|
164 |
-
"loss":
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.86,
|
169 |
"learning_rate": 0.0002,
|
170 |
-
"loss":
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.9,
|
175 |
"learning_rate": 0.0002,
|
176 |
-
"loss": 1.
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.93,
|
181 |
"learning_rate": 0.0002,
|
182 |
-
"loss": 1.
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.96,
|
187 |
"learning_rate": 0.0002,
|
188 |
-
"loss": 1.
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.99,
|
193 |
"learning_rate": 0.0002,
|
194 |
-
"loss": 1.
|
195 |
"step": 62
|
196 |
}
|
197 |
],
|
@@ -200,7 +200,7 @@
|
|
200 |
"num_input_tokens_seen": 0,
|
201 |
"num_train_epochs": 1,
|
202 |
"save_steps": 500,
|
203 |
-
"total_flos":
|
204 |
"train_batch_size": 1,
|
205 |
"trial_name": null,
|
206 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 0.03,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 1.6044,
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.06,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.5881,
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.1,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 1.5893,
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.13,
|
31 |
"learning_rate": 0.0002,
|
32 |
+
"loss": 1.6713,
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.16,
|
37 |
"learning_rate": 0.0002,
|
38 |
+
"loss": 1.6675,
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.19,
|
43 |
"learning_rate": 0.0002,
|
44 |
+
"loss": 1.728,
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.22,
|
49 |
"learning_rate": 0.0002,
|
50 |
+
"loss": 2.0484,
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.26,
|
55 |
"learning_rate": 0.0002,
|
56 |
+
"loss": 1.6691,
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.29,
|
61 |
"learning_rate": 0.0002,
|
62 |
+
"loss": 1.2777,
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.32,
|
67 |
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.3286,
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.35,
|
73 |
"learning_rate": 0.0002,
|
74 |
+
"loss": 1.2907,
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.38,
|
79 |
"learning_rate": 0.0002,
|
80 |
+
"loss": 1.2286,
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.42,
|
85 |
"learning_rate": 0.0002,
|
86 |
+
"loss": 1.3034,
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.45,
|
91 |
"learning_rate": 0.0002,
|
92 |
+
"loss": 1.2253,
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.48,
|
97 |
"learning_rate": 0.0002,
|
98 |
+
"loss": 1.398,
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.51,
|
103 |
"learning_rate": 0.0002,
|
104 |
+
"loss": 1.1233,
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.54,
|
109 |
"learning_rate": 0.0002,
|
110 |
+
"loss": 1.181,
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.58,
|
115 |
"learning_rate": 0.0002,
|
116 |
+
"loss": 1.1303,
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.61,
|
121 |
"learning_rate": 0.0002,
|
122 |
+
"loss": 1.12,
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.64,
|
127 |
"learning_rate": 0.0002,
|
128 |
+
"loss": 1.191,
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.67,
|
133 |
"learning_rate": 0.0002,
|
134 |
+
"loss": 1.1562,
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.7,
|
139 |
"learning_rate": 0.0002,
|
140 |
+
"loss": 1.1221,
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.74,
|
145 |
"learning_rate": 0.0002,
|
146 |
+
"loss": 1.2625,
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.77,
|
151 |
"learning_rate": 0.0002,
|
152 |
+
"loss": 1.0936,
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.8,
|
157 |
"learning_rate": 0.0002,
|
158 |
+
"loss": 1.048,
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.83,
|
163 |
"learning_rate": 0.0002,
|
164 |
+
"loss": 0.9645,
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.86,
|
169 |
"learning_rate": 0.0002,
|
170 |
+
"loss": 1.0299,
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.9,
|
175 |
"learning_rate": 0.0002,
|
176 |
+
"loss": 1.0774,
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.93,
|
181 |
"learning_rate": 0.0002,
|
182 |
+
"loss": 1.1457,
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.96,
|
187 |
"learning_rate": 0.0002,
|
188 |
+
"loss": 1.1011,
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.99,
|
193 |
"learning_rate": 0.0002,
|
194 |
+
"loss": 1.0221,
|
195 |
"step": 62
|
196 |
}
|
197 |
],
|
|
|
200 |
"num_input_tokens_seen": 0,
|
201 |
"num_train_epochs": 1,
|
202 |
"save_steps": 500,
|
203 |
+
"total_flos": 2179055645245440.0,
|
204 |
"train_batch_size": 1,
|
205 |
"trial_name": null,
|
206 |
"trial_params": null
|
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 sha256:085df06261844d8e43666229030657ce5dd5cc1aac22d14d759f080cd507fb4e
|
3 |
size 4728
|