Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- trainer_state.json +53 -53
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -19,12 +19,12 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"v_proj",
|
23 |
-
"k_proj",
|
24 |
"q_proj",
|
|
|
25 |
"o_proj",
|
26 |
"gate_proj",
|
27 |
"up_proj",
|
|
|
28 |
"down_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"q_proj",
|
23 |
+
"v_proj",
|
24 |
"o_proj",
|
25 |
"gate_proj",
|
26 |
"up_proj",
|
27 |
+
"k_proj",
|
28 |
"down_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
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 sha256:68ffb7728699344b9838f9afb7975fd02b29fe06bb1fbe0bc66591eed483fa3f
|
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 sha256:4e9a94707bb17ef5829b78f0d9c5987210c0c274f9b4c94292c5857bcb6a7ba5
|
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 sha256:224bead7fd043b72a8e81bd036d7d5df846f092c760212f12210c387735e21a3
|
3 |
size 14244
|
trainer_state.json
CHANGED
@@ -11,310 +11,310 @@
|
|
11 |
{
|
12 |
"epoch": 0.02,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 2.
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.04,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 2.
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.06,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 2.
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.08,
|
31 |
"learning_rate": 0.0002,
|
32 |
-
"loss": 2.
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.1,
|
37 |
"learning_rate": 0.0002,
|
38 |
-
"loss": 2.
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.12,
|
43 |
"learning_rate": 0.0002,
|
44 |
-
"loss": 2.
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.14,
|
49 |
"learning_rate": 0.0002,
|
50 |
-
"loss": 2.
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.16,
|
55 |
"learning_rate": 0.0002,
|
56 |
-
"loss": 2.
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.18,
|
61 |
"learning_rate": 0.0002,
|
62 |
-
"loss": 1.
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.2,
|
67 |
"learning_rate": 0.0002,
|
68 |
-
"loss":
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.22,
|
73 |
"learning_rate": 0.0002,
|
74 |
-
"loss":
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.24,
|
79 |
"learning_rate": 0.0002,
|
80 |
-
"loss": 1.
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.26,
|
85 |
"learning_rate": 0.0002,
|
86 |
-
"loss":
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.28,
|
91 |
"learning_rate": 0.0002,
|
92 |
-
"loss": 2.
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.3,
|
97 |
"learning_rate": 0.0002,
|
98 |
-
"loss":
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.32,
|
103 |
"learning_rate": 0.0002,
|
104 |
-
"loss":
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.34,
|
109 |
"learning_rate": 0.0002,
|
110 |
-
"loss": 2.
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.36,
|
115 |
"learning_rate": 0.0002,
|
116 |
-
"loss": 2.
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.38,
|
121 |
"learning_rate": 0.0002,
|
122 |
-
"loss": 1.
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.4,
|
127 |
"learning_rate": 0.0002,
|
128 |
-
"loss": 1.
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.42,
|
133 |
"learning_rate": 0.0002,
|
134 |
-
"loss": 1.
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.44,
|
139 |
"learning_rate": 0.0002,
|
140 |
-
"loss": 1.
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.46,
|
145 |
"learning_rate": 0.0002,
|
146 |
-
"loss": 1.
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.48,
|
151 |
"learning_rate": 0.0002,
|
152 |
-
"loss": 1.
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.5,
|
157 |
"learning_rate": 0.0002,
|
158 |
-
"loss": 1.
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.52,
|
163 |
"learning_rate": 0.0002,
|
164 |
-
"loss": 1.
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.54,
|
169 |
"learning_rate": 0.0002,
|
170 |
-
"loss": 1.
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.56,
|
175 |
"learning_rate": 0.0002,
|
176 |
-
"loss":
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.58,
|
181 |
"learning_rate": 0.0002,
|
182 |
-
"loss":
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.6,
|
187 |
"learning_rate": 0.0002,
|
188 |
-
"loss": 2.
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.62,
|
193 |
"learning_rate": 0.0002,
|
194 |
-
"loss":
|
195 |
"step": 62
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.64,
|
199 |
"learning_rate": 0.0002,
|
200 |
-
"loss": 1.
|
201 |
"step": 64
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.66,
|
205 |
"learning_rate": 0.0002,
|
206 |
-
"loss":
|
207 |
"step": 66
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.68,
|
211 |
"learning_rate": 0.0002,
|
212 |
-
"loss": 1.
|
213 |
"step": 68
|
214 |
},
|
215 |
{
|
216 |
"epoch": 0.7,
|
217 |
"learning_rate": 0.0002,
|
218 |
-
"loss": 1.
|
219 |
"step": 70
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.72,
|
223 |
"learning_rate": 0.0002,
|
224 |
-
"loss": 1.
|
225 |
"step": 72
|
226 |
},
|
227 |
{
|
228 |
"epoch": 0.74,
|
229 |
"learning_rate": 0.0002,
|
230 |
-
"loss": 1.
|
231 |
"step": 74
|
232 |
},
|
233 |
{
|
234 |
"epoch": 0.76,
|
235 |
"learning_rate": 0.0002,
|
236 |
-
"loss": 1.
|
237 |
"step": 76
|
238 |
},
|
239 |
{
|
240 |
"epoch": 0.78,
|
241 |
"learning_rate": 0.0002,
|
242 |
-
"loss": 1.
|
243 |
"step": 78
|
244 |
},
|
245 |
{
|
246 |
"epoch": 0.8,
|
247 |
"learning_rate": 0.0002,
|
248 |
-
"loss":
|
249 |
"step": 80
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.82,
|
253 |
"learning_rate": 0.0002,
|
254 |
-
"loss":
|
255 |
"step": 82
|
256 |
},
|
257 |
{
|
258 |
"epoch": 0.84,
|
259 |
"learning_rate": 0.0002,
|
260 |
-
"loss":
|
261 |
"step": 84
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.86,
|
265 |
"learning_rate": 0.0002,
|
266 |
-
"loss":
|
267 |
"step": 86
|
268 |
},
|
269 |
{
|
270 |
"epoch": 0.88,
|
271 |
"learning_rate": 0.0002,
|
272 |
-
"loss":
|
273 |
"step": 88
|
274 |
},
|
275 |
{
|
276 |
"epoch": 0.89,
|
277 |
"learning_rate": 0.0002,
|
278 |
-
"loss": 1.
|
279 |
"step": 90
|
280 |
},
|
281 |
{
|
282 |
"epoch": 0.91,
|
283 |
"learning_rate": 0.0002,
|
284 |
-
"loss": 1.
|
285 |
"step": 92
|
286 |
},
|
287 |
{
|
288 |
"epoch": 0.93,
|
289 |
"learning_rate": 0.0002,
|
290 |
-
"loss": 1.
|
291 |
"step": 94
|
292 |
},
|
293 |
{
|
294 |
"epoch": 0.95,
|
295 |
"learning_rate": 0.0002,
|
296 |
-
"loss": 1.
|
297 |
"step": 96
|
298 |
},
|
299 |
{
|
300 |
"epoch": 0.97,
|
301 |
"learning_rate": 0.0002,
|
302 |
-
"loss": 1.
|
303 |
"step": 98
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.99,
|
307 |
"learning_rate": 0.0002,
|
308 |
-
"loss": 1.
|
309 |
"step": 100
|
310 |
}
|
311 |
],
|
312 |
"logging_steps": 2,
|
313 |
-
"max_steps":
|
314 |
"num_input_tokens_seen": 0,
|
315 |
-
"num_train_epochs":
|
316 |
"save_steps": 500,
|
317 |
-
"total_flos": 1.
|
318 |
"train_batch_size": 1,
|
319 |
"trial_name": null,
|
320 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 0.02,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 2.3211,
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.04,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 2.1994,
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.06,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 2.1871,
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.08,
|
31 |
"learning_rate": 0.0002,
|
32 |
+
"loss": 2.1569,
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.1,
|
37 |
"learning_rate": 0.0002,
|
38 |
+
"loss": 2.1101,
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.12,
|
43 |
"learning_rate": 0.0002,
|
44 |
+
"loss": 2.1361,
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.14,
|
49 |
"learning_rate": 0.0002,
|
50 |
+
"loss": 2.002,
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.16,
|
55 |
"learning_rate": 0.0002,
|
56 |
+
"loss": 2.1144,
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.18,
|
61 |
"learning_rate": 0.0002,
|
62 |
+
"loss": 1.9981,
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.2,
|
67 |
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.8518,
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.22,
|
73 |
"learning_rate": 0.0002,
|
74 |
+
"loss": 2.0797,
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.24,
|
79 |
"learning_rate": 0.0002,
|
80 |
+
"loss": 1.9593,
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.26,
|
85 |
"learning_rate": 0.0002,
|
86 |
+
"loss": 2.1172,
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.28,
|
91 |
"learning_rate": 0.0002,
|
92 |
+
"loss": 2.056,
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.3,
|
97 |
"learning_rate": 0.0002,
|
98 |
+
"loss": 1.9752,
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.32,
|
103 |
"learning_rate": 0.0002,
|
104 |
+
"loss": 2.0642,
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.34,
|
109 |
"learning_rate": 0.0002,
|
110 |
+
"loss": 2.082,
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.36,
|
115 |
"learning_rate": 0.0002,
|
116 |
+
"loss": 2.0809,
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.38,
|
121 |
"learning_rate": 0.0002,
|
122 |
+
"loss": 1.9503,
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.4,
|
127 |
"learning_rate": 0.0002,
|
128 |
+
"loss": 1.9841,
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.42,
|
133 |
"learning_rate": 0.0002,
|
134 |
+
"loss": 1.954,
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.44,
|
139 |
"learning_rate": 0.0002,
|
140 |
+
"loss": 1.8861,
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.46,
|
145 |
"learning_rate": 0.0002,
|
146 |
+
"loss": 1.9725,
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.48,
|
151 |
"learning_rate": 0.0002,
|
152 |
+
"loss": 1.8173,
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.5,
|
157 |
"learning_rate": 0.0002,
|
158 |
+
"loss": 1.9095,
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.52,
|
163 |
"learning_rate": 0.0002,
|
164 |
+
"loss": 1.9165,
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.54,
|
169 |
"learning_rate": 0.0002,
|
170 |
+
"loss": 1.954,
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.56,
|
175 |
"learning_rate": 0.0002,
|
176 |
+
"loss": 2.0812,
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.58,
|
181 |
"learning_rate": 0.0002,
|
182 |
+
"loss": 1.9473,
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.6,
|
187 |
"learning_rate": 0.0002,
|
188 |
+
"loss": 2.0644,
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.62,
|
193 |
"learning_rate": 0.0002,
|
194 |
+
"loss": 2.0597,
|
195 |
"step": 62
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.64,
|
199 |
"learning_rate": 0.0002,
|
200 |
+
"loss": 1.9422,
|
201 |
"step": 64
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.66,
|
205 |
"learning_rate": 0.0002,
|
206 |
+
"loss": 1.8022,
|
207 |
"step": 66
|
208 |
},
|
209 |
{
|
210 |
"epoch": 0.68,
|
211 |
"learning_rate": 0.0002,
|
212 |
+
"loss": 1.9411,
|
213 |
"step": 68
|
214 |
},
|
215 |
{
|
216 |
"epoch": 0.7,
|
217 |
"learning_rate": 0.0002,
|
218 |
+
"loss": 1.8742,
|
219 |
"step": 70
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.72,
|
223 |
"learning_rate": 0.0002,
|
224 |
+
"loss": 1.8078,
|
225 |
"step": 72
|
226 |
},
|
227 |
{
|
228 |
"epoch": 0.74,
|
229 |
"learning_rate": 0.0002,
|
230 |
+
"loss": 1.9996,
|
231 |
"step": 74
|
232 |
},
|
233 |
{
|
234 |
"epoch": 0.76,
|
235 |
"learning_rate": 0.0002,
|
236 |
+
"loss": 1.7464,
|
237 |
"step": 76
|
238 |
},
|
239 |
{
|
240 |
"epoch": 0.78,
|
241 |
"learning_rate": 0.0002,
|
242 |
+
"loss": 1.8637,
|
243 |
"step": 78
|
244 |
},
|
245 |
{
|
246 |
"epoch": 0.8,
|
247 |
"learning_rate": 0.0002,
|
248 |
+
"loss": 1.9297,
|
249 |
"step": 80
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.82,
|
253 |
"learning_rate": 0.0002,
|
254 |
+
"loss": 1.9462,
|
255 |
"step": 82
|
256 |
},
|
257 |
{
|
258 |
"epoch": 0.84,
|
259 |
"learning_rate": 0.0002,
|
260 |
+
"loss": 1.9367,
|
261 |
"step": 84
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.86,
|
265 |
"learning_rate": 0.0002,
|
266 |
+
"loss": 1.9843,
|
267 |
"step": 86
|
268 |
},
|
269 |
{
|
270 |
"epoch": 0.88,
|
271 |
"learning_rate": 0.0002,
|
272 |
+
"loss": 2.0611,
|
273 |
"step": 88
|
274 |
},
|
275 |
{
|
276 |
"epoch": 0.89,
|
277 |
"learning_rate": 0.0002,
|
278 |
+
"loss": 1.8584,
|
279 |
"step": 90
|
280 |
},
|
281 |
{
|
282 |
"epoch": 0.91,
|
283 |
"learning_rate": 0.0002,
|
284 |
+
"loss": 1.8235,
|
285 |
"step": 92
|
286 |
},
|
287 |
{
|
288 |
"epoch": 0.93,
|
289 |
"learning_rate": 0.0002,
|
290 |
+
"loss": 1.9358,
|
291 |
"step": 94
|
292 |
},
|
293 |
{
|
294 |
"epoch": 0.95,
|
295 |
"learning_rate": 0.0002,
|
296 |
+
"loss": 1.854,
|
297 |
"step": 96
|
298 |
},
|
299 |
{
|
300 |
"epoch": 0.97,
|
301 |
"learning_rate": 0.0002,
|
302 |
+
"loss": 1.8953,
|
303 |
"step": 98
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.99,
|
307 |
"learning_rate": 0.0002,
|
308 |
+
"loss": 1.7185,
|
309 |
"step": 100
|
310 |
}
|
311 |
],
|
312 |
"logging_steps": 2,
|
313 |
+
"max_steps": 300,
|
314 |
"num_input_tokens_seen": 0,
|
315 |
+
"num_train_epochs": 3,
|
316 |
"save_steps": 500,
|
317 |
+
"total_flos": 1.3484808608858112e+16,
|
318 |
"train_batch_size": 1,
|
319 |
"trial_name": null,
|
320 |
"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 sha256:11b52a2201929623074064b5575a45c1dca7a2d9070772a0ae7e2dd1e5c1225d
|
3 |
size 4728
|