second model
Browse files- README.md +8 -4
- adapter_config.json +225 -5
- adapter_model.safetensors +2 -2
- runs/Feb02_11-13-39_e38b76366d3e/events.out.tfevents.1706872425.e38b76366d3e.1538.0 +3 -0
- runs/Feb02_11-20-57_e38b76366d3e/events.out.tfevents.1706872861.e38b76366d3e.4468.0 +3 -0
- runs/Feb02_11-25-49_e38b76366d3e/events.out.tfevents.1706873152.e38b76366d3e.5910.0 +3 -0
- tokenizer.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -7,18 +7,18 @@ tags:
|
|
7 |
- generated_from_trainer
|
8 |
base_model: stabilityai/stablelm-3b-4e1t
|
9 |
model-index:
|
10 |
-
- name:
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
#
|
18 |
|
19 |
This model is a fine-tuned version of [stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -49,7 +49,11 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
| 4.
|
|
|
|
|
|
|
|
|
53 |
|
54 |
|
55 |
### Framework versions
|
|
|
7 |
- generated_from_trainer
|
8 |
base_model: stabilityai/stablelm-3b-4e1t
|
9 |
model-index:
|
10 |
+
- name: persian-stablelm
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# persian-stablelm
|
18 |
|
19 |
This model is a fine-tuned version of [stabilityai/stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 4.2700
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 4.7338 | 0.18 | 100 | 4.5703 |
|
53 |
+
| 4.6391 | 0.36 | 200 | 4.4094 |
|
54 |
+
| 4.8127 | 0.54 | 300 | 4.3277 |
|
55 |
+
| 4.5393 | 0.72 | 400 | 4.2797 |
|
56 |
+
| 4.29 | 0.9 | 500 | 4.2700 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -15,15 +15,235 @@
|
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"embed_tokens",
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_rslora": false
|
|
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"layers.13.self_attn.o_proj",
|
23 |
+
"layers.27.mlp.up_proj",
|
24 |
+
"layers.31.self_attn.q_proj",
|
25 |
+
"layers.24.self_attn.q_proj",
|
26 |
+
"layers.10.self_attn.v_proj",
|
27 |
+
"layers.24.mlp.down_proj",
|
28 |
+
"layers.22.mlp.down_proj",
|
29 |
+
"layers.4.self_attn.q_proj",
|
30 |
+
"layers.25.mlp.down_proj",
|
31 |
+
"layers.1.mlp.up_proj",
|
32 |
+
"layers.10.mlp.gate_proj",
|
33 |
+
"layers.0.self_attn.v_proj",
|
34 |
+
"layers.18.mlp.gate_proj",
|
35 |
+
"layers.22.mlp.gate_proj",
|
36 |
+
"layers.3.self_attn.q_proj",
|
37 |
+
"layers.11.mlp.gate_proj",
|
38 |
+
"layers.21.self_attn.q_proj",
|
39 |
+
"layers.8.mlp.gate_proj",
|
40 |
+
"layers.14.self_attn.q_proj",
|
41 |
+
"layers.28.mlp.gate_proj",
|
42 |
+
"layers.1.self_attn.v_proj",
|
43 |
+
"layers.15.mlp.up_proj",
|
44 |
+
"layers.25.self_attn.v_proj",
|
45 |
+
"layers.23.self_attn.o_proj",
|
46 |
+
"layers.19.mlp.gate_proj",
|
47 |
+
"layers.1.self_attn.k_proj",
|
48 |
+
"layers.1.mlp.down_proj",
|
49 |
+
"layers.13.mlp.down_proj",
|
50 |
+
"layers.23.mlp.up_proj",
|
51 |
+
"layers.6.self_attn.o_proj",
|
52 |
+
"layers.27.self_attn.v_proj",
|
53 |
+
"layers.13.self_attn.k_proj",
|
54 |
+
"layers.11.mlp.up_proj",
|
55 |
+
"layers.5.mlp.up_proj",
|
56 |
+
"layers.29.mlp.down_proj",
|
57 |
+
"layers.30.self_attn.v_proj",
|
58 |
+
"layers.9.self_attn.o_proj",
|
59 |
+
"layers.15.self_attn.q_proj",
|
60 |
+
"layers.25.self_attn.k_proj",
|
61 |
+
"layers.17.self_attn.v_proj",
|
62 |
+
"layers.23.self_attn.v_proj",
|
63 |
+
"layers.12.self_attn.k_proj",
|
64 |
+
"layers.31.self_attn.o_proj",
|
65 |
+
"layers.21.mlp.gate_proj",
|
66 |
+
"layers.2.mlp.up_proj",
|
67 |
+
"layers.9.mlp.up_proj",
|
68 |
+
"layers.10.self_attn.o_proj",
|
69 |
+
"layers.0.mlp.down_proj",
|
70 |
+
"layers.3.mlp.gate_proj",
|
71 |
+
"layers.5.mlp.down_proj",
|
72 |
+
"layers.9.mlp.down_proj",
|
73 |
+
"layers.12.mlp.up_proj",
|
74 |
+
"layers.0.self_attn.k_proj",
|
75 |
+
"layers.25.self_attn.o_proj",
|
76 |
+
"layers.24.mlp.up_proj",
|
77 |
+
"layers.26.mlp.up_proj",
|
78 |
+
"layers.20.self_attn.v_proj",
|
79 |
+
"layers.31.self_attn.v_proj",
|
80 |
+
"layers.0.self_attn.q_proj",
|
81 |
+
"layers.30.mlp.gate_proj",
|
82 |
+
"layers.14.self_attn.o_proj",
|
83 |
+
"layers.8.self_attn.v_proj",
|
84 |
+
"layers.29.mlp.gate_proj",
|
85 |
+
"layers.6.mlp.down_proj",
|
86 |
+
"layers.16.mlp.down_proj",
|
87 |
+
"layers.22.self_attn.q_proj",
|
88 |
+
"layers.28.self_attn.v_proj",
|
89 |
+
"layers.31.mlp.gate_proj",
|
90 |
+
"layers.4.self_attn.k_proj",
|
91 |
+
"layers.12.self_attn.o_proj",
|
92 |
+
"layers.10.mlp.up_proj",
|
93 |
+
"layers.19.self_attn.q_proj",
|
94 |
+
"layers.8.self_attn.o_proj",
|
95 |
+
"layers.16.self_attn.o_proj",
|
96 |
+
"layers.3.mlp.down_proj",
|
97 |
+
"layers.26.self_attn.k_proj",
|
98 |
+
"layers.7.mlp.down_proj",
|
99 |
+
"layers.10.self_attn.k_proj",
|
100 |
+
"layers.23.self_attn.k_proj",
|
101 |
+
"layers.21.self_attn.o_proj",
|
102 |
+
"layers.18.self_attn.k_proj",
|
103 |
+
"layers.27.mlp.down_proj",
|
104 |
+
"layers.17.self_attn.o_proj",
|
105 |
+
"layers.21.self_attn.k_proj",
|
106 |
+
"layers.30.mlp.down_proj",
|
107 |
+
"layers.3.self_attn.k_proj",
|
108 |
+
"layers.25.mlp.gate_proj",
|
109 |
+
"layers.16.mlp.gate_proj",
|
110 |
+
"layers.31.mlp.down_proj",
|
111 |
+
"layers.22.self_attn.o_proj",
|
112 |
+
"layers.6.mlp.gate_proj",
|
113 |
+
"layers.11.mlp.down_proj",
|
114 |
+
"layers.23.self_attn.q_proj",
|
115 |
+
"layers.7.mlp.up_proj",
|
116 |
+
"layers.22.self_attn.k_proj",
|
117 |
+
"layers.12.self_attn.q_proj",
|
118 |
+
"layers.19.self_attn.v_proj",
|
119 |
+
"layers.22.self_attn.v_proj",
|
120 |
+
"layers.24.mlp.gate_proj",
|
121 |
+
"layers.2.self_attn.q_proj",
|
122 |
+
"layers.2.mlp.gate_proj",
|
123 |
+
"layers.30.self_attn.q_proj",
|
124 |
+
"layers.14.self_attn.v_proj",
|
125 |
+
"layers.26.self_attn.v_proj",
|
126 |
+
"layers.28.self_attn.q_proj",
|
127 |
+
"layers.30.mlp.up_proj",
|
128 |
+
"layers.10.mlp.down_proj",
|
129 |
+
"layers.5.self_attn.q_proj",
|
130 |
+
"layers.21.self_attn.v_proj",
|
131 |
+
"layers.15.self_attn.k_proj",
|
132 |
+
"layers.1.self_attn.o_proj",
|
133 |
+
"layers.20.self_attn.k_proj",
|
134 |
+
"layers.4.self_attn.o_proj",
|
135 |
+
"layers.7.self_attn.k_proj",
|
136 |
+
"layers.14.self_attn.k_proj",
|
137 |
+
"layers.12.self_attn.v_proj",
|
138 |
+
"layers.16.self_attn.q_proj",
|
139 |
+
"layers.28.self_attn.o_proj",
|
140 |
+
"layers.29.mlp.up_proj",
|
141 |
+
"layers.18.self_attn.o_proj",
|
142 |
+
"layers.8.mlp.down_proj",
|
143 |
+
"layers.9.self_attn.q_proj",
|
144 |
+
"layers.25.mlp.up_proj",
|
145 |
+
"layers.14.mlp.gate_proj",
|
146 |
+
"layers.11.self_attn.v_proj",
|
147 |
+
"layers.18.mlp.up_proj",
|
148 |
+
"layers.15.self_attn.o_proj",
|
149 |
"embed_tokens",
|
150 |
+
"layers.5.mlp.gate_proj",
|
151 |
+
"layers.29.self_attn.o_proj",
|
152 |
+
"layers.16.mlp.up_proj",
|
153 |
+
"layers.27.self_attn.k_proj",
|
154 |
+
"layers.26.self_attn.q_proj",
|
155 |
+
"layers.20.mlp.down_proj",
|
156 |
+
"layers.4.mlp.up_proj",
|
157 |
+
"layers.19.mlp.up_proj",
|
158 |
+
"layers.18.mlp.down_proj",
|
159 |
+
"layers.3.self_attn.o_proj",
|
160 |
+
"layers.8.mlp.up_proj",
|
161 |
+
"layers.8.self_attn.k_proj",
|
162 |
+
"layers.30.self_attn.k_proj",
|
163 |
+
"layers.15.mlp.down_proj",
|
164 |
+
"layers.10.self_attn.q_proj",
|
165 |
+
"layers.16.self_attn.v_proj",
|
166 |
+
"layers.12.mlp.gate_proj",
|
167 |
+
"layers.6.mlp.up_proj",
|
168 |
+
"layers.0.mlp.up_proj",
|
169 |
+
"layers.9.self_attn.k_proj",
|
170 |
+
"layers.31.self_attn.k_proj",
|
171 |
+
"layers.20.mlp.up_proj",
|
172 |
+
"layers.28.mlp.down_proj",
|
173 |
+
"layers.0.self_attn.o_proj",
|
174 |
+
"layers.4.mlp.gate_proj",
|
175 |
+
"layers.21.mlp.up_proj",
|
176 |
+
"layers.13.self_attn.q_proj",
|
177 |
+
"layers.5.self_attn.k_proj",
|
178 |
+
"layers.21.mlp.down_proj",
|
179 |
+
"layers.17.mlp.down_proj",
|
180 |
+
"layers.30.self_attn.o_proj",
|
181 |
+
"layers.19.mlp.down_proj",
|
182 |
+
"layers.1.mlp.gate_proj",
|
183 |
+
"layers.9.mlp.gate_proj",
|
184 |
+
"layers.13.mlp.gate_proj",
|
185 |
+
"layers.19.self_attn.k_proj",
|
186 |
+
"layers.3.self_attn.v_proj",
|
187 |
+
"layers.20.mlp.gate_proj",
|
188 |
+
"layers.7.self_attn.v_proj",
|
189 |
+
"layers.19.self_attn.o_proj",
|
190 |
+
"layers.22.mlp.up_proj",
|
191 |
+
"layers.17.self_attn.k_proj",
|
192 |
+
"layers.6.self_attn.q_proj",
|
193 |
+
"layers.24.self_attn.o_proj",
|
194 |
+
"layers.16.self_attn.k_proj",
|
195 |
+
"layers.13.mlp.up_proj",
|
196 |
+
"layers.8.self_attn.q_proj",
|
197 |
+
"layers.29.self_attn.k_proj",
|
198 |
+
"layers.28.self_attn.k_proj",
|
199 |
+
"layers.27.mlp.gate_proj",
|
200 |
+
"layers.2.self_attn.o_proj",
|
201 |
+
"layers.28.mlp.up_proj",
|
202 |
+
"layers.25.self_attn.q_proj",
|
203 |
+
"layers.23.mlp.gate_proj",
|
204 |
+
"layers.9.self_attn.v_proj",
|
205 |
+
"layers.7.mlp.gate_proj",
|
206 |
+
"layers.17.mlp.up_proj",
|
207 |
+
"layers.5.self_attn.v_proj",
|
208 |
+
"layers.7.self_attn.o_proj",
|
209 |
+
"layers.13.self_attn.v_proj",
|
210 |
+
"layers.27.self_attn.q_proj",
|
211 |
+
"layers.18.self_attn.q_proj",
|
212 |
+
"layers.2.self_attn.v_proj",
|
213 |
+
"layers.23.mlp.down_proj",
|
214 |
+
"layers.14.mlp.down_proj",
|
215 |
+
"layers.2.self_attn.k_proj",
|
216 |
+
"layers.4.self_attn.v_proj",
|
217 |
+
"layers.26.self_attn.o_proj",
|
218 |
+
"layers.12.mlp.down_proj",
|
219 |
+
"layers.7.self_attn.q_proj",
|
220 |
+
"layers.11.self_attn.k_proj",
|
221 |
+
"layers.27.self_attn.o_proj",
|
222 |
+
"layers.26.mlp.down_proj",
|
223 |
+
"layers.6.self_attn.v_proj",
|
224 |
+
"layers.4.mlp.down_proj",
|
225 |
+
"layers.11.self_attn.o_proj",
|
226 |
+
"layers.29.self_attn.q_proj",
|
227 |
+
"layers.24.self_attn.k_proj",
|
228 |
+
"layers.18.self_attn.v_proj",
|
229 |
+
"layers.20.self_attn.o_proj",
|
230 |
+
"layers.2.mlp.down_proj",
|
231 |
+
"layers.11.self_attn.q_proj",
|
232 |
+
"layers.0.mlp.gate_proj",
|
233 |
+
"layers.3.mlp.up_proj",
|
234 |
+
"layers.6.self_attn.k_proj",
|
235 |
+
"layers.14.mlp.up_proj",
|
236 |
+
"layers.17.mlp.gate_proj",
|
237 |
+
"layers.1.self_attn.q_proj",
|
238 |
+
"layers.24.self_attn.v_proj",
|
239 |
+
"layers.17.self_attn.q_proj",
|
240 |
+
"layers.20.self_attn.q_proj",
|
241 |
+
"layers.29.self_attn.v_proj",
|
242 |
+
"layers.5.self_attn.o_proj",
|
243 |
+
"layers.15.self_attn.v_proj",
|
244 |
+
"layers.15.mlp.gate_proj",
|
245 |
+
"layers.31.mlp.up_proj",
|
246 |
+
"layers.26.mlp.gate_proj"
|
247 |
],
|
248 |
"task_type": "CAUSAL_LM",
|
249 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d716d04cda12d4d345b4c8b1c4e801a7682742bc807c90e463aa91a4f2925fcc
|
3 |
+
size 421083096
|
runs/Feb02_11-13-39_e38b76366d3e/events.out.tfevents.1706872425.e38b76366d3e.1538.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4edae16f0bd9fef1f153c9afd9400f124dee410f98320aeeaf79389a5eaa3ffc
|
3 |
+
size 8022
|
runs/Feb02_11-20-57_e38b76366d3e/events.out.tfevents.1706872861.e38b76366d3e.4468.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55b24b4e329b95d0f5731a65ef5a7bde5f1cb4626ffaab512dcd891e135ff12a
|
3 |
+
size 7559
|
runs/Feb02_11-25-49_e38b76366d3e/events.out.tfevents.1706873152.e38b76366d3e.5910.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7d3338b51ceb4787e5e93c236ace8ca661085f32afdbfbe1366d119d905a831
|
3 |
+
size 92777
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 48,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
training_args.bin
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 sha256:1268c71a97ae93de424ebbbb07d10c6d8a2ff3ac001b287b75b1a9aed450f25f
|
3 |
+
size 4728
|