Model save
Browse files- README.md +1 -2
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- all_results.json +4 -9
- runs/Apr08_20-25-52_ip-172-31-69-60.ec2.internal/events.out.tfevents.1712607974.ip-172-31-69-60.ec2.internal.23138.0 +3 -0
- runs/Apr08_22-39-05_ip-172-31-69-60.ec2.internal/events.out.tfevents.1712615965.ip-172-31-69-60.ec2.internal.45971.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +128 -128
- training_args.bin +1 -1
README.md
CHANGED
@@ -4,7 +4,6 @@ library_name: peft
|
|
4 |
tags:
|
5 |
- trl
|
6 |
- sft
|
7 |
-
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
base_model: mistralai/Mistral-7B-v0.1
|
10 |
model-index:
|
@@ -56,7 +55,7 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|
|
59 |
-
| 0.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
4 |
tags:
|
5 |
- trl
|
6 |
- sft
|
|
|
7 |
- generated_from_trainer
|
8 |
base_model: mistralai/Mistral-7B-v0.1
|
9 |
model-index:
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 0.7491 | 1.0 | 325 | 0.7774 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"down_proj",
|
25 |
"gate_proj",
|
26 |
"k_proj",
|
27 |
-
"
|
28 |
-
"
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"up_proj",
|
23 |
+
"o_proj",
|
|
|
24 |
"gate_proj",
|
25 |
"k_proj",
|
26 |
+
"down_proj",
|
27 |
+
"q_proj",
|
28 |
+
"v_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83946192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53af4775901a7163d635d95a3fe57ac3c41ec324e6f8f992e5db1cc53b59f2b4
|
3 |
size 83946192
|
all_results.json
CHANGED
@@ -1,13 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"eval_samples": 231,
|
6 |
-
"eval_samples_per_second": 5.101,
|
7 |
-
"eval_steps_per_second": 0.177,
|
8 |
-
"train_loss": 0.057297961895282454,
|
9 |
-
"train_runtime": 986.3633,
|
10 |
"train_samples": 20787,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.7601131853690514,
|
4 |
+
"train_runtime": 11993.6222,
|
|
|
|
|
|
|
|
|
|
|
5 |
"train_samples": 20787,
|
6 |
+
"train_samples_per_second": 1.733,
|
7 |
+
"train_steps_per_second": 0.027
|
8 |
}
|
runs/Apr08_20-25-52_ip-172-31-69-60.ec2.internal/events.out.tfevents.1712607974.ip-172-31-69-60.ec2.internal.23138.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272707ee25876d39e2d4b937c0d3e81d55db05ff5b99c8bf6800390d0ee51767
|
3 |
+
size 5725
|
runs/Apr08_22-39-05_ip-172-31-69-60.ec2.internal/events.out.tfevents.1712615965.ip-172-31-69-60.ec2.internal.45971.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9858aeaa7e541e20024a4a3996d8551253eb440245d9f61f0bc5738dfa93b4c6
|
3 |
+
size 19137
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 20787,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"train_loss": 0.7601131853690514,
|
4 |
+
"train_runtime": 11993.6222,
|
5 |
"train_samples": 20787,
|
6 |
+
"train_samples_per_second": 1.733,
|
7 |
+
"train_steps_per_second": 0.027
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,482 +10,482 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
-
"grad_norm": 0.
|
14 |
"learning_rate": 6.060606060606061e-06,
|
15 |
"loss": 0.7782,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.02,
|
20 |
-
"grad_norm": 0.
|
21 |
"learning_rate": 3.0303030303030306e-05,
|
22 |
-
"loss": 0.
|
23 |
"step": 5
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.03,
|
27 |
-
"grad_norm": 0.
|
28 |
"learning_rate": 6.060606060606061e-05,
|
29 |
"loss": 0.7851,
|
30 |
"step": 10
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.05,
|
34 |
-
"grad_norm": 0.
|
35 |
"learning_rate": 9.090909090909092e-05,
|
36 |
-
"loss": 0.
|
37 |
"step": 15
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.06,
|
41 |
-
"grad_norm": 0.
|
42 |
"learning_rate": 0.00012121212121212122,
|
43 |
-
"loss": 0.
|
44 |
"step": 20
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.08,
|
48 |
-
"grad_norm": 0.
|
49 |
"learning_rate": 0.00015151515151515152,
|
50 |
-
"loss": 0.
|
51 |
"step": 25
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.09,
|
55 |
-
"grad_norm": 0.
|
56 |
"learning_rate": 0.00018181818181818183,
|
57 |
-
"loss": 0.
|
58 |
"step": 30
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.11,
|
62 |
-
"grad_norm": 0.
|
63 |
"learning_rate": 0.00019997685019798912,
|
64 |
-
"loss": 0.
|
65 |
"step": 35
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.12,
|
69 |
-
"grad_norm": 0.
|
70 |
"learning_rate": 0.0001997165380022878,
|
71 |
"loss": 0.7607,
|
72 |
"step": 40
|
73 |
},
|
74 |
{
|
75 |
"epoch": 0.14,
|
76 |
-
"grad_norm": 0.
|
77 |
"learning_rate": 0.000199167731989929,
|
78 |
-
"loss": 0.
|
79 |
"step": 45
|
80 |
},
|
81 |
{
|
82 |
"epoch": 0.15,
|
83 |
-
"grad_norm": 0.
|
84 |
"learning_rate": 0.0001983320199330545,
|
85 |
-
"loss": 0.
|
86 |
"step": 50
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.17,
|
90 |
-
"grad_norm": 0.
|
91 |
"learning_rate": 0.00019721181966290613,
|
92 |
-
"loss": 0.
|
93 |
"step": 55
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.18,
|
97 |
-
"grad_norm": 0.
|
98 |
"learning_rate": 0.00019581037207470382,
|
99 |
-
"loss": 0.
|
100 |
"step": 60
|
101 |
},
|
102 |
{
|
103 |
"epoch": 0.2,
|
104 |
-
"grad_norm": 0.
|
105 |
"learning_rate": 0.00019413173175128473,
|
106 |
-
"loss": 0.
|
107 |
"step": 65
|
108 |
},
|
109 |
{
|
110 |
"epoch": 0.22,
|
111 |
-
"grad_norm": 0.
|
112 |
"learning_rate": 0.00019218075523263104,
|
113 |
-
"loss": 0.
|
114 |
"step": 70
|
115 |
},
|
116 |
{
|
117 |
"epoch": 0.23,
|
118 |
-
"grad_norm": 0.
|
119 |
"learning_rate": 0.00018996308696522433,
|
120 |
"loss": 0.7617,
|
121 |
"step": 75
|
122 |
},
|
123 |
{
|
124 |
"epoch": 0.25,
|
125 |
-
"grad_norm": 0.
|
126 |
"learning_rate": 0.00018748514297187648,
|
127 |
"loss": 0.7995,
|
128 |
"step": 80
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.26,
|
132 |
-
"grad_norm": 0.
|
133 |
"learning_rate": 0.00018475409228928312,
|
134 |
-
"loss": 0.
|
135 |
"step": 85
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.28,
|
139 |
-
"grad_norm": 0.
|
140 |
"learning_rate": 0.00018177783622700327,
|
141 |
"loss": 0.7754,
|
142 |
"step": 90
|
143 |
},
|
144 |
{
|
145 |
"epoch": 0.29,
|
146 |
-
"grad_norm": 0.
|
147 |
"learning_rate": 0.00017856498550787144,
|
148 |
-
"loss": 0.
|
149 |
"step": 95
|
150 |
},
|
151 |
{
|
152 |
"epoch": 0.31,
|
153 |
-
"grad_norm": 0.
|
154 |
"learning_rate": 0.00017512483535597867,
|
155 |
-
"loss": 0.
|
156 |
"step": 100
|
157 |
},
|
158 |
{
|
159 |
"epoch": 0.32,
|
160 |
-
"grad_norm": 0.
|
161 |
"learning_rate": 0.00017146733860429612,
|
162 |
-
"loss": 0.
|
163 |
"step": 105
|
164 |
},
|
165 |
{
|
166 |
"epoch": 0.34,
|
167 |
-
"grad_norm": 0.
|
168 |
"learning_rate": 0.0001676030768997445,
|
169 |
-
"loss": 0.
|
170 |
"step": 110
|
171 |
},
|
172 |
{
|
173 |
"epoch": 0.35,
|
174 |
-
"grad_norm": 0.
|
175 |
"learning_rate": 0.00016354323008901776,
|
176 |
"loss": 0.7499,
|
177 |
"step": 115
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.37,
|
181 |
-
"grad_norm": 0.
|
182 |
"learning_rate": 0.00015929954387373103,
|
183 |
-
"loss": 0.
|
184 |
"step": 120
|
185 |
},
|
186 |
{
|
187 |
"epoch": 0.38,
|
188 |
-
"grad_norm": 0.
|
189 |
"learning_rate": 0.00015488429582847192,
|
190 |
-
"loss": 0.
|
191 |
"step": 125
|
192 |
},
|
193 |
{
|
194 |
"epoch": 0.4,
|
195 |
-
"grad_norm": 0.
|
196 |
"learning_rate": 0.00015031025988006936,
|
197 |
-
"loss": 0.
|
198 |
"step": 130
|
199 |
},
|
200 |
{
|
201 |
"epoch": 0.42,
|
202 |
-
"grad_norm": 0.
|
203 |
"learning_rate": 0.00014559066935084588,
|
204 |
-
"loss": 0.
|
205 |
"step": 135
|
206 |
},
|
207 |
{
|
208 |
"epoch": 0.43,
|
209 |
-
"grad_norm": 0.
|
210 |
"learning_rate": 0.00014073917867277557,
|
211 |
-
"loss": 0.
|
212 |
"step": 140
|
213 |
},
|
214 |
{
|
215 |
"epoch": 0.45,
|
216 |
-
"grad_norm": 0.
|
217 |
"learning_rate": 0.0001357698238833126,
|
218 |
-
"loss": 0.
|
219 |
"step": 145
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.46,
|
223 |
-
"grad_norm": 0.
|
224 |
"learning_rate": 0.000130696982017182,
|
225 |
"loss": 0.7349,
|
226 |
"step": 150
|
227 |
},
|
228 |
{
|
229 |
"epoch": 0.48,
|
230 |
-
"grad_norm": 0.
|
231 |
"learning_rate": 0.0001255353295116187,
|
232 |
-
"loss": 0.
|
233 |
"step": 155
|
234 |
},
|
235 |
{
|
236 |
"epoch": 0.49,
|
237 |
-
"grad_norm": 0.
|
238 |
"learning_rate": 0.00012029979974539234,
|
239 |
"loss": 0.7428,
|
240 |
"step": 160
|
241 |
},
|
242 |
{
|
243 |
"epoch": 0.51,
|
244 |
-
"grad_norm": 0.
|
245 |
"learning_rate": 0.00011500553983446527,
|
246 |
-
"loss": 0.
|
247 |
"step": 165
|
248 |
},
|
249 |
{
|
250 |
"epoch": 0.52,
|
251 |
-
"grad_norm": 0.
|
252 |
"learning_rate": 0.00010966786680927874,
|
253 |
-
"loss": 0.
|
254 |
"step": 170
|
255 |
},
|
256 |
{
|
257 |
"epoch": 0.54,
|
258 |
-
"grad_norm": 0.
|
259 |
"learning_rate": 0.00010430222330045304,
|
260 |
-
"loss": 0.
|
261 |
"step": 175
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.55,
|
265 |
-
"grad_norm": 0.
|
266 |
"learning_rate": 9.892413286110886e-05,
|
267 |
-
"loss": 0.
|
268 |
"step": 180
|
269 |
},
|
270 |
{
|
271 |
"epoch": 0.57,
|
272 |
-
"grad_norm": 0.
|
273 |
"learning_rate": 9.354915505506839e-05,
|
274 |
-
"loss": 0.
|
275 |
"step": 185
|
276 |
},
|
277 |
{
|
278 |
"epoch": 0.58,
|
279 |
-
"grad_norm": 0.
|
280 |
"learning_rate": 8.81928404408726e-05,
|
281 |
-
"loss": 0.
|
282 |
"step": 190
|
283 |
},
|
284 |
{
|
285 |
"epoch": 0.6,
|
286 |
-
"grad_norm": 0.
|
287 |
"learning_rate": 8.287068558185225e-05,
|
288 |
"loss": 0.785,
|
289 |
"step": 195
|
290 |
},
|
291 |
{
|
292 |
"epoch": 0.62,
|
293 |
-
"grad_norm": 0.
|
294 |
"learning_rate": 7.759808821241406e-05,
|
295 |
-
"loss": 0.
|
296 |
"step": 200
|
297 |
},
|
298 |
{
|
299 |
"epoch": 0.63,
|
300 |
-
"grad_norm": 0.
|
301 |
"learning_rate": 7.239030269025311e-05,
|
302 |
-
"loss": 0.
|
303 |
"step": 205
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.65,
|
307 |
-
"grad_norm": 0.
|
308 |
"learning_rate": 6.726239586337408e-05,
|
309 |
"loss": 0.76,
|
310 |
"step": 210
|
311 |
},
|
312 |
{
|
313 |
"epoch": 0.66,
|
314 |
-
"grad_norm": 0.
|
315 |
"learning_rate": 6.22292034796035e-05,
|
316 |
-
"loss": 0.
|
317 |
"step": 215
|
318 |
},
|
319 |
{
|
320 |
"epoch": 0.68,
|
321 |
-
"grad_norm": 0.
|
322 |
"learning_rate": 5.730528726470792e-05,
|
323 |
-
"loss": 0.
|
324 |
"step": 220
|
325 |
},
|
326 |
{
|
327 |
"epoch": 0.69,
|
328 |
-
"grad_norm": 0.
|
329 |
"learning_rate": 5.2504892793295e-05,
|
330 |
-
"loss": 0.
|
331 |
"step": 225
|
332 |
},
|
333 |
{
|
334 |
"epoch": 0.71,
|
335 |
-
"grad_norm": 0.
|
336 |
"learning_rate": 4.7841908274384616e-05,
|
337 |
-
"loss": 0.
|
338 |
"step": 230
|
339 |
},
|
340 |
{
|
341 |
"epoch": 0.72,
|
342 |
-
"grad_norm": 0.
|
343 |
"learning_rate": 4.332982437088825e-05,
|
344 |
-
"loss": 0.
|
345 |
"step": 235
|
346 |
},
|
347 |
{
|
348 |
"epoch": 0.74,
|
349 |
-
"grad_norm": 0.
|
350 |
"learning_rate": 3.898169516924398e-05,
|
351 |
-
"loss": 0.
|
352 |
"step": 240
|
353 |
},
|
354 |
{
|
355 |
"epoch": 0.75,
|
356 |
-
"grad_norm": 0.
|
357 |
"learning_rate": 3.4810100412128747e-05,
|
358 |
-
"loss": 0.
|
359 |
"step": 245
|
360 |
},
|
361 |
{
|
362 |
"epoch": 0.77,
|
363 |
-
"grad_norm": 0.
|
364 |
"learning_rate": 3.0827109103512643e-05,
|
365 |
"loss": 0.7669,
|
366 |
"step": 250
|
367 |
},
|
368 |
{
|
369 |
"epoch": 0.78,
|
370 |
-
"grad_norm": 0.
|
371 |
"learning_rate": 2.7044244591351232e-05,
|
372 |
-
"loss": 0.
|
373 |
"step": 255
|
374 |
},
|
375 |
{
|
376 |
"epoch": 0.8,
|
377 |
-
"grad_norm": 0.
|
378 |
"learning_rate": 2.3472451228937253e-05,
|
379 |
-
"loss": 0.
|
380 |
"step": 260
|
381 |
},
|
382 |
{
|
383 |
"epoch": 0.82,
|
384 |
-
"grad_norm": 0.
|
385 |
"learning_rate": 2.0122062711363532e-05,
|
386 |
-
"loss": 0.
|
387 |
"step": 265
|
388 |
},
|
389 |
{
|
390 |
"epoch": 0.83,
|
391 |
-
"grad_norm": 0.
|
392 |
"learning_rate": 1.7002772178705716e-05,
|
393 |
-
"loss": 0.
|
394 |
"step": 270
|
395 |
},
|
396 |
{
|
397 |
"epoch": 0.85,
|
398 |
-
"grad_norm": 0.
|
399 |
"learning_rate": 1.4123604172419713e-05,
|
400 |
-
"loss": 0.
|
401 |
"step": 275
|
402 |
},
|
403 |
{
|
404 |
"epoch": 0.86,
|
405 |
-
"grad_norm": 0.
|
406 |
"learning_rate": 1.149288852608743e-05,
|
407 |
"loss": 0.7558,
|
408 |
"step": 280
|
409 |
},
|
410 |
{
|
411 |
"epoch": 0.88,
|
412 |
-
"grad_norm": 0.
|
413 |
"learning_rate": 9.118236266049707e-06,
|
414 |
-
"loss": 0.
|
415 |
"step": 285
|
416 |
},
|
417 |
{
|
418 |
"epoch": 0.89,
|
419 |
-
"grad_norm": 0.
|
420 |
"learning_rate": 7.0065175916482095e-06,
|
421 |
-
"loss": 0.
|
422 |
"step": 290
|
423 |
},
|
424 |
{
|
425 |
"epoch": 0.91,
|
426 |
-
"grad_norm": 0.
|
427 |
"learning_rate": 5.163841998782837e-06,
|
428 |
-
"loss": 0.
|
429 |
"step": 295
|
430 |
},
|
431 |
{
|
432 |
"epoch": 0.92,
|
433 |
-
"grad_norm": 0.
|
434 |
"learning_rate": 3.595540604290437e-06,
|
435 |
-
"loss": 0.
|
436 |
"step": 300
|
437 |
},
|
438 |
{
|
439 |
"epoch": 0.94,
|
440 |
-
"grad_norm": 0.
|
441 |
"learning_rate": 2.30615072228183e-06,
|
442 |
-
"loss": 0.
|
443 |
"step": 305
|
444 |
},
|
445 |
{
|
446 |
"epoch": 0.95,
|
447 |
-
"grad_norm": 0.
|
448 |
"learning_rate": 1.2994027370611173e-06,
|
449 |
-
"loss": 0.
|
450 |
"step": 310
|
451 |
},
|
452 |
{
|
453 |
"epoch": 0.97,
|
454 |
-
"grad_norm": 0.
|
455 |
"learning_rate": 5.782093106048159e-07,
|
456 |
"loss": 0.7366,
|
457 |
"step": 315
|
458 |
},
|
459 |
{
|
460 |
"epoch": 0.98,
|
461 |
-
"grad_norm": 0.
|
462 |
"learning_rate": 1.446569558255395e-07,
|
463 |
-
"loss": 0.
|
464 |
"step": 320
|
465 |
},
|
466 |
{
|
467 |
"epoch": 1.0,
|
468 |
-
"grad_norm": 0.
|
469 |
"learning_rate": 0.0,
|
470 |
-
"loss": 0.
|
471 |
"step": 325
|
472 |
},
|
473 |
{
|
474 |
"epoch": 1.0,
|
475 |
-
"eval_loss": 0.
|
476 |
-
"eval_runtime":
|
477 |
-
"eval_samples_per_second": 4.
|
478 |
-
"eval_steps_per_second": 0.
|
479 |
"step": 325
|
480 |
},
|
481 |
{
|
482 |
"epoch": 1.0,
|
483 |
"step": 325,
|
484 |
-
"total_flos":
|
485 |
-
"train_loss": 0.
|
486 |
-
"train_runtime":
|
487 |
-
"train_samples_per_second":
|
488 |
-
"train_steps_per_second": 0.
|
489 |
}
|
490 |
],
|
491 |
"logging_steps": 5,
|
@@ -493,7 +493,7 @@
|
|
493 |
"num_input_tokens_seen": 0,
|
494 |
"num_train_epochs": 1,
|
495 |
"save_steps": 100,
|
496 |
-
"total_flos":
|
497 |
"train_batch_size": 8,
|
498 |
"trial_name": null,
|
499 |
"trial_params": null
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0,
|
13 |
+
"grad_norm": 0.26868827253641747,
|
14 |
"learning_rate": 6.060606060606061e-06,
|
15 |
"loss": 0.7782,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.02,
|
20 |
+
"grad_norm": 0.21382632169384555,
|
21 |
"learning_rate": 3.0303030303030306e-05,
|
22 |
+
"loss": 0.7798,
|
23 |
"step": 5
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.03,
|
27 |
+
"grad_norm": 0.22445606867737244,
|
28 |
"learning_rate": 6.060606060606061e-05,
|
29 |
"loss": 0.7851,
|
30 |
"step": 10
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.05,
|
34 |
+
"grad_norm": 0.2072105558411773,
|
35 |
"learning_rate": 9.090909090909092e-05,
|
36 |
+
"loss": 0.7855,
|
37 |
"step": 15
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.06,
|
41 |
+
"grad_norm": 0.17995218448427217,
|
42 |
"learning_rate": 0.00012121212121212122,
|
43 |
+
"loss": 0.792,
|
44 |
"step": 20
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.08,
|
48 |
+
"grad_norm": 0.226508952573423,
|
49 |
"learning_rate": 0.00015151515151515152,
|
50 |
+
"loss": 0.7382,
|
51 |
"step": 25
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.09,
|
55 |
+
"grad_norm": 0.18958014075029098,
|
56 |
"learning_rate": 0.00018181818181818183,
|
57 |
+
"loss": 0.7419,
|
58 |
"step": 30
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.11,
|
62 |
+
"grad_norm": 0.19949889749656097,
|
63 |
"learning_rate": 0.00019997685019798912,
|
64 |
+
"loss": 0.7642,
|
65 |
"step": 35
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.12,
|
69 |
+
"grad_norm": 0.19567934772580736,
|
70 |
"learning_rate": 0.0001997165380022878,
|
71 |
"loss": 0.7607,
|
72 |
"step": 40
|
73 |
},
|
74 |
{
|
75 |
"epoch": 0.14,
|
76 |
+
"grad_norm": 0.18969776374927835,
|
77 |
"learning_rate": 0.000199167731989929,
|
78 |
+
"loss": 0.795,
|
79 |
"step": 45
|
80 |
},
|
81 |
{
|
82 |
"epoch": 0.15,
|
83 |
+
"grad_norm": 0.1942706799722158,
|
84 |
"learning_rate": 0.0001983320199330545,
|
85 |
+
"loss": 0.764,
|
86 |
"step": 50
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.17,
|
90 |
+
"grad_norm": 0.19464988909031225,
|
91 |
"learning_rate": 0.00019721181966290613,
|
92 |
+
"loss": 0.7836,
|
93 |
"step": 55
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.18,
|
97 |
+
"grad_norm": 0.1849352970071158,
|
98 |
"learning_rate": 0.00019581037207470382,
|
99 |
+
"loss": 0.757,
|
100 |
"step": 60
|
101 |
},
|
102 |
{
|
103 |
"epoch": 0.2,
|
104 |
+
"grad_norm": 0.17976128059849958,
|
105 |
"learning_rate": 0.00019413173175128473,
|
106 |
+
"loss": 0.7616,
|
107 |
"step": 65
|
108 |
},
|
109 |
{
|
110 |
"epoch": 0.22,
|
111 |
+
"grad_norm": 0.1934718609207969,
|
112 |
"learning_rate": 0.00019218075523263104,
|
113 |
+
"loss": 0.7538,
|
114 |
"step": 70
|
115 |
},
|
116 |
{
|
117 |
"epoch": 0.23,
|
118 |
+
"grad_norm": 0.16955946612078765,
|
119 |
"learning_rate": 0.00018996308696522433,
|
120 |
"loss": 0.7617,
|
121 |
"step": 75
|
122 |
},
|
123 |
{
|
124 |
"epoch": 0.25,
|
125 |
+
"grad_norm": 0.19860710500579018,
|
126 |
"learning_rate": 0.00018748514297187648,
|
127 |
"loss": 0.7995,
|
128 |
"step": 80
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.26,
|
132 |
+
"grad_norm": 0.17834039868116905,
|
133 |
"learning_rate": 0.00018475409228928312,
|
134 |
+
"loss": 0.7539,
|
135 |
"step": 85
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.28,
|
139 |
+
"grad_norm": 0.1889302979453787,
|
140 |
"learning_rate": 0.00018177783622700327,
|
141 |
"loss": 0.7754,
|
142 |
"step": 90
|
143 |
},
|
144 |
{
|
145 |
"epoch": 0.29,
|
146 |
+
"grad_norm": 0.17928302611917235,
|
147 |
"learning_rate": 0.00017856498550787144,
|
148 |
+
"loss": 0.7924,
|
149 |
"step": 95
|
150 |
},
|
151 |
{
|
152 |
"epoch": 0.31,
|
153 |
+
"grad_norm": 0.18965987325021239,
|
154 |
"learning_rate": 0.00017512483535597867,
|
155 |
+
"loss": 0.7547,
|
156 |
"step": 100
|
157 |
},
|
158 |
{
|
159 |
"epoch": 0.32,
|
160 |
+
"grad_norm": 0.16948470382160882,
|
161 |
"learning_rate": 0.00017146733860429612,
|
162 |
+
"loss": 0.7755,
|
163 |
"step": 105
|
164 |
},
|
165 |
{
|
166 |
"epoch": 0.34,
|
167 |
+
"grad_norm": 0.20373009441973453,
|
168 |
"learning_rate": 0.0001676030768997445,
|
169 |
+
"loss": 0.7452,
|
170 |
"step": 110
|
171 |
},
|
172 |
{
|
173 |
"epoch": 0.35,
|
174 |
+
"grad_norm": 0.18030063668475196,
|
175 |
"learning_rate": 0.00016354323008901776,
|
176 |
"loss": 0.7499,
|
177 |
"step": 115
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.37,
|
181 |
+
"grad_norm": 0.16132188005262432,
|
182 |
"learning_rate": 0.00015929954387373103,
|
183 |
+
"loss": 0.7344,
|
184 |
"step": 120
|
185 |
},
|
186 |
{
|
187 |
"epoch": 0.38,
|
188 |
+
"grad_norm": 0.2014655387761585,
|
189 |
"learning_rate": 0.00015488429582847192,
|
190 |
+
"loss": 0.7909,
|
191 |
"step": 125
|
192 |
},
|
193 |
{
|
194 |
"epoch": 0.4,
|
195 |
+
"grad_norm": 0.19701253442033323,
|
196 |
"learning_rate": 0.00015031025988006936,
|
197 |
+
"loss": 0.7846,
|
198 |
"step": 130
|
199 |
},
|
200 |
{
|
201 |
"epoch": 0.42,
|
202 |
+
"grad_norm": 0.18599715688382074,
|
203 |
"learning_rate": 0.00014559066935084588,
|
204 |
+
"loss": 0.7884,
|
205 |
"step": 135
|
206 |
},
|
207 |
{
|
208 |
"epoch": 0.43,
|
209 |
+
"grad_norm": 0.15916898081839567,
|
210 |
"learning_rate": 0.00014073917867277557,
|
211 |
+
"loss": 0.7478,
|
212 |
"step": 140
|
213 |
},
|
214 |
{
|
215 |
"epoch": 0.45,
|
216 |
+
"grad_norm": 0.1693289847957747,
|
217 |
"learning_rate": 0.0001357698238833126,
|
218 |
+
"loss": 0.758,
|
219 |
"step": 145
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.46,
|
223 |
+
"grad_norm": 0.1724296952005482,
|
224 |
"learning_rate": 0.000130696982017182,
|
225 |
"loss": 0.7349,
|
226 |
"step": 150
|
227 |
},
|
228 |
{
|
229 |
"epoch": 0.48,
|
230 |
+
"grad_norm": 0.20365543265357713,
|
231 |
"learning_rate": 0.0001255353295116187,
|
232 |
+
"loss": 0.7581,
|
233 |
"step": 155
|
234 |
},
|
235 |
{
|
236 |
"epoch": 0.49,
|
237 |
+
"grad_norm": 0.17925645984310104,
|
238 |
"learning_rate": 0.00012029979974539234,
|
239 |
"loss": 0.7428,
|
240 |
"step": 160
|
241 |
},
|
242 |
{
|
243 |
"epoch": 0.51,
|
244 |
+
"grad_norm": 0.1849261223570645,
|
245 |
"learning_rate": 0.00011500553983446527,
|
246 |
+
"loss": 0.7915,
|
247 |
"step": 165
|
248 |
},
|
249 |
{
|
250 |
"epoch": 0.52,
|
251 |
+
"grad_norm": 0.17147514694965366,
|
252 |
"learning_rate": 0.00010966786680927874,
|
253 |
+
"loss": 0.7282,
|
254 |
"step": 170
|
255 |
},
|
256 |
{
|
257 |
"epoch": 0.54,
|
258 |
+
"grad_norm": 0.19718678657625408,
|
259 |
"learning_rate": 0.00010430222330045304,
|
260 |
+
"loss": 0.7807,
|
261 |
"step": 175
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.55,
|
265 |
+
"grad_norm": 0.1697756132509757,
|
266 |
"learning_rate": 9.892413286110886e-05,
|
267 |
+
"loss": 0.7522,
|
268 |
"step": 180
|
269 |
},
|
270 |
{
|
271 |
"epoch": 0.57,
|
272 |
+
"grad_norm": 0.1745926097752596,
|
273 |
"learning_rate": 9.354915505506839e-05,
|
274 |
+
"loss": 0.7656,
|
275 |
"step": 185
|
276 |
},
|
277 |
{
|
278 |
"epoch": 0.58,
|
279 |
+
"grad_norm": 0.17991554784663008,
|
280 |
"learning_rate": 8.81928404408726e-05,
|
281 |
+
"loss": 0.7425,
|
282 |
"step": 190
|
283 |
},
|
284 |
{
|
285 |
"epoch": 0.6,
|
286 |
+
"grad_norm": 0.1638975774298517,
|
287 |
"learning_rate": 8.287068558185225e-05,
|
288 |
"loss": 0.785,
|
289 |
"step": 195
|
290 |
},
|
291 |
{
|
292 |
"epoch": 0.62,
|
293 |
+
"grad_norm": 0.1721376274882642,
|
294 |
"learning_rate": 7.759808821241406e-05,
|
295 |
+
"loss": 0.747,
|
296 |
"step": 200
|
297 |
},
|
298 |
{
|
299 |
"epoch": 0.63,
|
300 |
+
"grad_norm": 0.16645909181505114,
|
301 |
"learning_rate": 7.239030269025311e-05,
|
302 |
+
"loss": 0.7436,
|
303 |
"step": 205
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.65,
|
307 |
+
"grad_norm": 0.17668278165163676,
|
308 |
"learning_rate": 6.726239586337408e-05,
|
309 |
"loss": 0.76,
|
310 |
"step": 210
|
311 |
},
|
312 |
{
|
313 |
"epoch": 0.66,
|
314 |
+
"grad_norm": 0.1592821063866204,
|
315 |
"learning_rate": 6.22292034796035e-05,
|
316 |
+
"loss": 0.7532,
|
317 |
"step": 215
|
318 |
},
|
319 |
{
|
320 |
"epoch": 0.68,
|
321 |
+
"grad_norm": 0.18211269157973645,
|
322 |
"learning_rate": 5.730528726470792e-05,
|
323 |
+
"loss": 0.7684,
|
324 |
"step": 220
|
325 |
},
|
326 |
{
|
327 |
"epoch": 0.69,
|
328 |
+
"grad_norm": 0.1611844005218168,
|
329 |
"learning_rate": 5.2504892793295e-05,
|
330 |
+
"loss": 0.7432,
|
331 |
"step": 225
|
332 |
},
|
333 |
{
|
334 |
"epoch": 0.71,
|
335 |
+
"grad_norm": 0.1770721524356504,
|
336 |
"learning_rate": 4.7841908274384616e-05,
|
337 |
+
"loss": 0.7719,
|
338 |
"step": 230
|
339 |
},
|
340 |
{
|
341 |
"epoch": 0.72,
|
342 |
+
"grad_norm": 0.17458138059176753,
|
343 |
"learning_rate": 4.332982437088825e-05,
|
344 |
+
"loss": 0.7153,
|
345 |
"step": 235
|
346 |
},
|
347 |
{
|
348 |
"epoch": 0.74,
|
349 |
+
"grad_norm": 0.1764916869298734,
|
350 |
"learning_rate": 3.898169516924398e-05,
|
351 |
+
"loss": 0.7509,
|
352 |
"step": 240
|
353 |
},
|
354 |
{
|
355 |
"epoch": 0.75,
|
356 |
+
"grad_norm": 0.17474182112370204,
|
357 |
"learning_rate": 3.4810100412128747e-05,
|
358 |
+
"loss": 0.7562,
|
359 |
"step": 245
|
360 |
},
|
361 |
{
|
362 |
"epoch": 0.77,
|
363 |
+
"grad_norm": 0.1741562771880736,
|
364 |
"learning_rate": 3.0827109103512643e-05,
|
365 |
"loss": 0.7669,
|
366 |
"step": 250
|
367 |
},
|
368 |
{
|
369 |
"epoch": 0.78,
|
370 |
+
"grad_norm": 0.17549490206623847,
|
371 |
"learning_rate": 2.7044244591351232e-05,
|
372 |
+
"loss": 0.7592,
|
373 |
"step": 255
|
374 |
},
|
375 |
{
|
376 |
"epoch": 0.8,
|
377 |
+
"grad_norm": 0.16399003172635285,
|
378 |
"learning_rate": 2.3472451228937253e-05,
|
379 |
+
"loss": 0.7396,
|
380 |
"step": 260
|
381 |
},
|
382 |
{
|
383 |
"epoch": 0.82,
|
384 |
+
"grad_norm": 0.1713214529866966,
|
385 |
"learning_rate": 2.0122062711363532e-05,
|
386 |
+
"loss": 0.7766,
|
387 |
"step": 265
|
388 |
},
|
389 |
{
|
390 |
"epoch": 0.83,
|
391 |
+
"grad_norm": 0.17574824064745212,
|
392 |
"learning_rate": 1.7002772178705716e-05,
|
393 |
+
"loss": 0.7329,
|
394 |
"step": 270
|
395 |
},
|
396 |
{
|
397 |
"epoch": 0.85,
|
398 |
+
"grad_norm": 0.16897840325162736,
|
399 |
"learning_rate": 1.4123604172419713e-05,
|
400 |
+
"loss": 0.7723,
|
401 |
"step": 275
|
402 |
},
|
403 |
{
|
404 |
"epoch": 0.86,
|
405 |
+
"grad_norm": 0.18239238197655358,
|
406 |
"learning_rate": 1.149288852608743e-05,
|
407 |
"loss": 0.7558,
|
408 |
"step": 280
|
409 |
},
|
410 |
{
|
411 |
"epoch": 0.88,
|
412 |
+
"grad_norm": 0.16446806582557563,
|
413 |
"learning_rate": 9.118236266049707e-06,
|
414 |
+
"loss": 0.731,
|
415 |
"step": 285
|
416 |
},
|
417 |
{
|
418 |
"epoch": 0.89,
|
419 |
+
"grad_norm": 0.17024389183471494,
|
420 |
"learning_rate": 7.0065175916482095e-06,
|
421 |
+
"loss": 0.7599,
|
422 |
"step": 290
|
423 |
},
|
424 |
{
|
425 |
"epoch": 0.91,
|
426 |
+
"grad_norm": 0.15264356146830035,
|
427 |
"learning_rate": 5.163841998782837e-06,
|
428 |
+
"loss": 0.7644,
|
429 |
"step": 295
|
430 |
},
|
431 |
{
|
432 |
"epoch": 0.92,
|
433 |
+
"grad_norm": 0.16324609453084554,
|
434 |
"learning_rate": 3.595540604290437e-06,
|
435 |
+
"loss": 0.7581,
|
436 |
"step": 300
|
437 |
},
|
438 |
{
|
439 |
"epoch": 0.94,
|
440 |
+
"grad_norm": 0.1710138375738759,
|
441 |
"learning_rate": 2.30615072228183e-06,
|
442 |
+
"loss": 0.7332,
|
443 |
"step": 305
|
444 |
},
|
445 |
{
|
446 |
"epoch": 0.95,
|
447 |
+
"grad_norm": 0.1611044475082952,
|
448 |
"learning_rate": 1.2994027370611173e-06,
|
449 |
+
"loss": 0.7627,
|
450 |
"step": 310
|
451 |
},
|
452 |
{
|
453 |
"epoch": 0.97,
|
454 |
+
"grad_norm": 0.1514646487097857,
|
455 |
"learning_rate": 5.782093106048159e-07,
|
456 |
"loss": 0.7366,
|
457 |
"step": 315
|
458 |
},
|
459 |
{
|
460 |
"epoch": 0.98,
|
461 |
+
"grad_norm": 0.17261842858442877,
|
462 |
"learning_rate": 1.446569558255395e-07,
|
463 |
+
"loss": 0.7436,
|
464 |
"step": 320
|
465 |
},
|
466 |
{
|
467 |
"epoch": 1.0,
|
468 |
+
"grad_norm": 0.16882560969081586,
|
469 |
"learning_rate": 0.0,
|
470 |
+
"loss": 0.7491,
|
471 |
"step": 325
|
472 |
},
|
473 |
{
|
474 |
"epoch": 1.0,
|
475 |
+
"eval_loss": 0.7773829698562622,
|
476 |
+
"eval_runtime": 46.5077,
|
477 |
+
"eval_samples_per_second": 4.967,
|
478 |
+
"eval_steps_per_second": 0.172,
|
479 |
"step": 325
|
480 |
},
|
481 |
{
|
482 |
"epoch": 1.0,
|
483 |
"step": 325,
|
484 |
+
"total_flos": 4962652747988992.0,
|
485 |
+
"train_loss": 0.7601131853690514,
|
486 |
+
"train_runtime": 11993.6222,
|
487 |
+
"train_samples_per_second": 1.733,
|
488 |
+
"train_steps_per_second": 0.027
|
489 |
}
|
490 |
],
|
491 |
"logging_steps": 5,
|
|
|
493 |
"num_input_tokens_seen": 0,
|
494 |
"num_train_epochs": 1,
|
495 |
"save_steps": 100,
|
496 |
+
"total_flos": 4962652747988992.0,
|
497 |
"train_batch_size": 8,
|
498 |
"trial_name": null,
|
499 |
"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 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:971a709049ccad23c89c4e6cee01ec3eb6463ee0f5a631966b03929525be0f01
|
3 |
size 6072
|