Upload 7 files
Browse files- adapter_config.json +19 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +359 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "daryl149/llama-2-7b-chat-hf",
|
3 |
+
"bias": "none",
|
4 |
+
"enable_lora": null,
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"lora_alpha": 16,
|
9 |
+
"lora_dropout": 0.05,
|
10 |
+
"merge_weights": false,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 8,
|
14 |
+
"target_modules": [
|
15 |
+
"q_proj",
|
16 |
+
"v_proj"
|
17 |
+
],
|
18 |
+
"task_type": "CAUSAL_LM"
|
19 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fb852814e5b5732532e100f3c83c98c861dc9016a53e69ec7c2df6fcdc31f1d
|
3 |
+
size 16823434
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68b8183c44ef7bb1b180aec7dcc5f540e1c2c072404b256e621c8baeff730849
|
3 |
+
size 33662074
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a69e29f7fb427ad10a49a3b4f10efbf0031814e170f5d92de555468e9105b36
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e218532adb96c5c297ad4a44b4d0ab3e8c0f451fb19877122c6a6558e70ebb59
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,359 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9167455434799194,
|
3 |
+
"best_model_checkpoint": "lora/checkpoint-50",
|
4 |
+
"epoch": 3.7209302325581395,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07,
|
13 |
+
"learning_rate": 1.0000000000000002e-06,
|
14 |
+
"loss": 2.6945,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.15,
|
19 |
+
"learning_rate": 2.0000000000000003e-06,
|
20 |
+
"loss": 2.821,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.22,
|
25 |
+
"learning_rate": 3e-06,
|
26 |
+
"loss": 2.951,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.3,
|
31 |
+
"learning_rate": 4.000000000000001e-06,
|
32 |
+
"loss": 2.6822,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.37,
|
37 |
+
"learning_rate": 5e-06,
|
38 |
+
"loss": 2.7875,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.45,
|
43 |
+
"learning_rate": 6e-06,
|
44 |
+
"loss": 2.9668,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.52,
|
49 |
+
"learning_rate": 7.000000000000001e-06,
|
50 |
+
"loss": 2.6852,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.6,
|
55 |
+
"learning_rate": 8.000000000000001e-06,
|
56 |
+
"loss": 2.791,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.67,
|
61 |
+
"learning_rate": 9e-06,
|
62 |
+
"loss": 2.9174,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.74,
|
67 |
+
"learning_rate": 1e-05,
|
68 |
+
"loss": 2.6653,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.74,
|
73 |
+
"eval_loss": 2.7832038402557373,
|
74 |
+
"eval_runtime": 6.0415,
|
75 |
+
"eval_samples_per_second": 31.615,
|
76 |
+
"eval_steps_per_second": 3.973,
|
77 |
+
"step": 10
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.82,
|
81 |
+
"learning_rate": 1.1000000000000001e-05,
|
82 |
+
"loss": 2.79,
|
83 |
+
"step": 11
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.89,
|
87 |
+
"learning_rate": 1.2e-05,
|
88 |
+
"loss": 2.9187,
|
89 |
+
"step": 12
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.97,
|
93 |
+
"learning_rate": 1.3000000000000001e-05,
|
94 |
+
"loss": 2.7263,
|
95 |
+
"step": 13
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.04,
|
99 |
+
"learning_rate": 1.4000000000000001e-05,
|
100 |
+
"loss": 2.7614,
|
101 |
+
"step": 14
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.12,
|
105 |
+
"learning_rate": 1.5e-05,
|
106 |
+
"loss": 2.7264,
|
107 |
+
"step": 15
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.19,
|
111 |
+
"learning_rate": 1.6000000000000003e-05,
|
112 |
+
"loss": 2.817,
|
113 |
+
"step": 16
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.27,
|
117 |
+
"learning_rate": 1.7000000000000003e-05,
|
118 |
+
"loss": 2.7676,
|
119 |
+
"step": 17
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 1.34,
|
123 |
+
"learning_rate": 1.8e-05,
|
124 |
+
"loss": 2.6791,
|
125 |
+
"step": 18
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 1.41,
|
129 |
+
"learning_rate": 1.9e-05,
|
130 |
+
"loss": 2.7726,
|
131 |
+
"step": 19
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 1.49,
|
135 |
+
"learning_rate": 2e-05,
|
136 |
+
"loss": 2.7456,
|
137 |
+
"step": 20
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.49,
|
141 |
+
"eval_loss": 2.711270809173584,
|
142 |
+
"eval_runtime": 5.8906,
|
143 |
+
"eval_samples_per_second": 32.425,
|
144 |
+
"eval_steps_per_second": 4.074,
|
145 |
+
"step": 20
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.56,
|
149 |
+
"learning_rate": 2.1e-05,
|
150 |
+
"loss": 2.6796,
|
151 |
+
"step": 21
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 1.64,
|
155 |
+
"learning_rate": 2.2000000000000003e-05,
|
156 |
+
"loss": 2.8011,
|
157 |
+
"step": 22
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 1.71,
|
161 |
+
"learning_rate": 2.3000000000000003e-05,
|
162 |
+
"loss": 2.723,
|
163 |
+
"step": 23
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.79,
|
167 |
+
"learning_rate": 2.4e-05,
|
168 |
+
"loss": 2.6006,
|
169 |
+
"step": 24
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.86,
|
173 |
+
"learning_rate": 2.5e-05,
|
174 |
+
"loss": 2.7069,
|
175 |
+
"step": 25
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 1.93,
|
179 |
+
"learning_rate": 2.6000000000000002e-05,
|
180 |
+
"loss": 2.65,
|
181 |
+
"step": 26
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 2.01,
|
185 |
+
"learning_rate": 2.7000000000000002e-05,
|
186 |
+
"loss": 2.6998,
|
187 |
+
"step": 27
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"epoch": 2.08,
|
191 |
+
"learning_rate": 2.8000000000000003e-05,
|
192 |
+
"loss": 2.4935,
|
193 |
+
"step": 28
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 2.16,
|
197 |
+
"learning_rate": 2.9e-05,
|
198 |
+
"loss": 2.6282,
|
199 |
+
"step": 29
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 2.23,
|
203 |
+
"learning_rate": 3e-05,
|
204 |
+
"loss": 2.6905,
|
205 |
+
"step": 30
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.23,
|
209 |
+
"eval_loss": 2.5354292392730713,
|
210 |
+
"eval_runtime": 5.7422,
|
211 |
+
"eval_samples_per_second": 33.262,
|
212 |
+
"eval_steps_per_second": 4.18,
|
213 |
+
"step": 30
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 2.31,
|
217 |
+
"learning_rate": 3.1e-05,
|
218 |
+
"loss": 2.4446,
|
219 |
+
"step": 31
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.38,
|
223 |
+
"learning_rate": 3.2000000000000005e-05,
|
224 |
+
"loss": 2.5132,
|
225 |
+
"step": 32
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 2.46,
|
229 |
+
"learning_rate": 3.3e-05,
|
230 |
+
"loss": 2.5779,
|
231 |
+
"step": 33
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 2.53,
|
235 |
+
"learning_rate": 3.4000000000000007e-05,
|
236 |
+
"loss": 2.3595,
|
237 |
+
"step": 34
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 2.6,
|
241 |
+
"learning_rate": 3.5e-05,
|
242 |
+
"loss": 2.4434,
|
243 |
+
"step": 35
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 2.68,
|
247 |
+
"learning_rate": 3.6e-05,
|
248 |
+
"loss": 2.4813,
|
249 |
+
"step": 36
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.75,
|
253 |
+
"learning_rate": 3.7e-05,
|
254 |
+
"loss": 2.2946,
|
255 |
+
"step": 37
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 2.83,
|
259 |
+
"learning_rate": 3.8e-05,
|
260 |
+
"loss": 2.3288,
|
261 |
+
"step": 38
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.9,
|
265 |
+
"learning_rate": 3.9000000000000006e-05,
|
266 |
+
"loss": 2.3864,
|
267 |
+
"step": 39
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 2.98,
|
271 |
+
"learning_rate": 4e-05,
|
272 |
+
"loss": 2.243,
|
273 |
+
"step": 40
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 2.98,
|
277 |
+
"eval_loss": 2.237229347229004,
|
278 |
+
"eval_runtime": 5.7266,
|
279 |
+
"eval_samples_per_second": 33.353,
|
280 |
+
"eval_steps_per_second": 4.191,
|
281 |
+
"step": 40
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 3.05,
|
285 |
+
"learning_rate": 4.1e-05,
|
286 |
+
"loss": 2.2389,
|
287 |
+
"step": 41
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 3.13,
|
291 |
+
"learning_rate": 4.2e-05,
|
292 |
+
"loss": 2.1705,
|
293 |
+
"step": 42
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 3.2,
|
297 |
+
"learning_rate": 4.3e-05,
|
298 |
+
"loss": 2.2266,
|
299 |
+
"step": 43
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 3.27,
|
303 |
+
"learning_rate": 4.4000000000000006e-05,
|
304 |
+
"loss": 2.1714,
|
305 |
+
"step": 44
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 3.35,
|
309 |
+
"learning_rate": 4.5e-05,
|
310 |
+
"loss": 2.0949,
|
311 |
+
"step": 45
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 3.42,
|
315 |
+
"learning_rate": 4.600000000000001e-05,
|
316 |
+
"loss": 2.1432,
|
317 |
+
"step": 46
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 3.5,
|
321 |
+
"learning_rate": 4.7e-05,
|
322 |
+
"loss": 2.0676,
|
323 |
+
"step": 47
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 3.57,
|
327 |
+
"learning_rate": 4.8e-05,
|
328 |
+
"loss": 2.0115,
|
329 |
+
"step": 48
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 3.65,
|
333 |
+
"learning_rate": 4.9e-05,
|
334 |
+
"loss": 2.0231,
|
335 |
+
"step": 49
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 3.72,
|
339 |
+
"learning_rate": 5e-05,
|
340 |
+
"loss": 1.9708,
|
341 |
+
"step": 50
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 3.72,
|
345 |
+
"eval_loss": 1.9167455434799194,
|
346 |
+
"eval_runtime": 5.7354,
|
347 |
+
"eval_samples_per_second": 33.302,
|
348 |
+
"eval_steps_per_second": 4.185,
|
349 |
+
"step": 50
|
350 |
+
}
|
351 |
+
],
|
352 |
+
"logging_steps": 1,
|
353 |
+
"max_steps": 52,
|
354 |
+
"num_train_epochs": 4,
|
355 |
+
"save_steps": 10,
|
356 |
+
"total_flos": 4.32902346080256e+16,
|
357 |
+
"trial_name": null,
|
358 |
+
"trial_params": null
|
359 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58f3139df7e1b4f6d33a3906ca570463a2a86c68e0f166a3245fcb6198950b60
|
3 |
+
size 4536
|