Commit
•
a27f778
1
Parent(s):
1117a9a
Model save
Browse files- README.md +7 -8
- adapter_model.safetensors +1 -1
- all_results.json +7 -12
- runs/May25_02-29-05_5c31577a2818/events.out.tfevents.1716604156.5c31577a2818.18685.0 +2 -2
- train_results.json +7 -7
- trainer_state.json +153 -1028
README.md
CHANGED
@@ -2,13 +2,12 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
9 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
10 |
datasets:
|
11 |
-
-
|
12 |
model-index:
|
13 |
- name: zilo-instruct-v2-sft-qlora
|
14 |
results: []
|
@@ -19,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
# zilo-instruct-v2-sft-qlora
|
21 |
|
22 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -40,7 +39,7 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
- learning_rate:
|
44 |
- train_batch_size: 4
|
45 |
- eval_batch_size: 8
|
46 |
- seed: 42
|
@@ -56,9 +55,9 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
|:-------------:|:------:|:----:|:---------------:|
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
9 |
datasets:
|
10 |
+
- generator
|
11 |
model-index:
|
12 |
- name: zilo-instruct-v2-sft-qlora
|
13 |
results: []
|
|
|
18 |
|
19 |
# zilo-instruct-v2-sft-qlora
|
20 |
|
21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.6246
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
- train_batch_size: 4
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:------:|:----:|:---------------:|
|
58 |
+
| 0.7588 | 0.9899 | 49 | 0.7386 |
|
59 |
+
| 0.6201 | 2.0 | 99 | 0.6307 |
|
60 |
+
| 0.6087 | 2.9697 | 147 | 0.6246 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
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:e1a7c5ba3953bb0b3141884f066d930329b6e5947c0a580e0ee9b4f54c973f98
|
3 |
size 83946192
|
all_results.json
CHANGED
@@ -1,14 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch": 2.
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"train_loss": 0.2601610358741651,
|
10 |
-
"train_runtime": 3322.581,
|
11 |
-
"train_samples": 29084,
|
12 |
-
"train_samples_per_second": 1.86,
|
13 |
-
"train_steps_per_second": 0.232
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.9696969696969697,
|
3 |
+
"total_flos": 2.0566538541072384e+17,
|
4 |
+
"train_loss": 0.7671454966473742,
|
5 |
+
"train_runtime": 1686.4021,
|
6 |
+
"train_samples": 12338,
|
7 |
+
"train_samples_per_second": 0.699,
|
8 |
+
"train_steps_per_second": 0.087
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
runs/May25_02-29-05_5c31577a2818/events.out.tfevents.1716604156.5c31577a2818.18685.0
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:a90ad6eb838a4d61c4be30dc0597b702e1f9dad091f28d7f7d628a084861c6a3
|
3 |
+
size 12783
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch": 2.
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples":
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.9696969696969697,
|
3 |
+
"total_flos": 2.0566538541072384e+17,
|
4 |
+
"train_loss": 0.7671454966473742,
|
5 |
+
"train_runtime": 1686.4021,
|
6 |
+
"train_samples": 12338,
|
7 |
+
"train_samples_per_second": 0.699,
|
8 |
+
"train_steps_per_second": 0.087
|
9 |
}
|
trainer_state.json
CHANGED
@@ -1,1134 +1,259 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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.
|
13 |
-
"grad_norm": 2.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 1.
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm": 2.
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 1.
|
23 |
"step": 5
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 2.
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 1.
|
30 |
"step": 10
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0.
|
34 |
-
"grad_norm": 1.
|
35 |
-
"learning_rate":
|
36 |
-
"loss": 1.
|
37 |
"step": 15
|
38 |
},
|
39 |
{
|
40 |
-
"epoch": 0.
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate":
|
43 |
-
"loss": 1.
|
44 |
"step": 20
|
45 |
},
|
46 |
{
|
47 |
-
"epoch": 0.
|
48 |
-
"grad_norm": 0.
|
49 |
-
"learning_rate":
|
50 |
-
"loss":
|
51 |
"step": 25
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 0.
|
55 |
-
"grad_norm": 0.
|
56 |
-
"learning_rate":
|
57 |
-
"loss": 0.
|
58 |
"step": 30
|
59 |
},
|
60 |
{
|
61 |
-
"epoch": 0.
|
62 |
-
"grad_norm": 0.
|
63 |
-
"learning_rate":
|
64 |
-
"loss": 0.
|
65 |
"step": 35
|
66 |
},
|
67 |
{
|
68 |
-
"epoch": 0.
|
69 |
-
"grad_norm": 0.
|
70 |
-
"learning_rate":
|
71 |
-
"loss": 0.
|
72 |
"step": 40
|
73 |
},
|
74 |
{
|
75 |
-
"epoch": 0.
|
76 |
-
"grad_norm": 0.
|
77 |
-
"learning_rate":
|
78 |
-
"loss": 0.
|
79 |
"step": 45
|
80 |
},
|
81 |
{
|
82 |
-
"epoch": 0.
|
83 |
-
"
|
84 |
-
"
|
85 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
"step": 50
|
87 |
},
|
88 |
{
|
89 |
-
"epoch":
|
90 |
-
"grad_norm": 0.
|
91 |
-
"learning_rate":
|
92 |
-
"loss": 0.
|
93 |
"step": 55
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"grad_norm": 0.
|
98 |
-
"learning_rate":
|
99 |
-
"loss": 0.
|
100 |
"step": 60
|
101 |
},
|
102 |
{
|
103 |
-
"epoch":
|
104 |
-
"grad_norm": 0.
|
105 |
-
"learning_rate":
|
106 |
-
"loss": 0.
|
107 |
"step": 65
|
108 |
},
|
109 |
{
|
110 |
-
"epoch":
|
111 |
-
"grad_norm": 0.
|
112 |
-
"learning_rate":
|
113 |
-
"loss": 0.
|
114 |
"step": 70
|
115 |
},
|
116 |
{
|
117 |
-
"epoch":
|
118 |
-
"grad_norm": 0.
|
119 |
-
"learning_rate":
|
120 |
-
"loss": 0.
|
121 |
"step": 75
|
122 |
},
|
123 |
{
|
124 |
-
"epoch":
|
125 |
-
"grad_norm": 0.
|
126 |
-
"learning_rate":
|
127 |
-
"loss": 0.
|
128 |
"step": 80
|
129 |
},
|
130 |
{
|
131 |
-
"epoch":
|
132 |
-
"grad_norm": 0.
|
133 |
-
"learning_rate":
|
134 |
-
"loss": 0.
|
135 |
"step": 85
|
136 |
},
|
137 |
{
|
138 |
-
"epoch":
|
139 |
-
"grad_norm": 0.
|
140 |
-
"learning_rate":
|
141 |
-
"loss": 0.
|
142 |
"step": 90
|
143 |
},
|
144 |
{
|
145 |
-
"epoch":
|
146 |
-
"grad_norm": 0.
|
147 |
-
"learning_rate":
|
148 |
-
"loss": 0.
|
149 |
"step": 95
|
150 |
},
|
151 |
{
|
152 |
-
"epoch": 0
|
153 |
-
"
|
154 |
-
"
|
155 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
156 |
"step": 100
|
157 |
},
|
158 |
{
|
159 |
-
"epoch":
|
160 |
-
"grad_norm": 0.
|
161 |
-
"learning_rate":
|
162 |
-
"loss": 0.
|
163 |
"step": 105
|
164 |
},
|
165 |
{
|
166 |
-
"epoch":
|
167 |
-
"grad_norm": 0.
|
168 |
-
"learning_rate":
|
169 |
-
"loss": 0.
|
170 |
"step": 110
|
171 |
},
|
172 |
{
|
173 |
-
"epoch":
|
174 |
-
"grad_norm": 0.
|
175 |
-
"learning_rate":
|
176 |
-
"loss": 0.
|
177 |
"step": 115
|
178 |
},
|
179 |
{
|
180 |
-
"epoch":
|
181 |
-
"grad_norm": 0.
|
182 |
-
"learning_rate":
|
183 |
-
"loss": 0.
|
184 |
"step": 120
|
185 |
},
|
186 |
{
|
187 |
-
"epoch":
|
188 |
-
"grad_norm": 0.
|
189 |
-
"learning_rate":
|
190 |
-
"loss": 0.
|
191 |
"step": 125
|
192 |
},
|
193 |
{
|
194 |
-
"epoch":
|
195 |
-
"grad_norm": 0.
|
196 |
-
"learning_rate":
|
197 |
-
"loss": 0.
|
198 |
"step": 130
|
199 |
},
|
200 |
{
|
201 |
-
"epoch":
|
202 |
-
"grad_norm": 0.
|
203 |
-
"learning_rate":
|
204 |
-
"loss": 0.
|
205 |
"step": 135
|
206 |
},
|
207 |
{
|
208 |
-
"epoch":
|
209 |
-
"grad_norm": 0.
|
210 |
-
"learning_rate":
|
211 |
-
"loss": 0.
|
212 |
"step": 140
|
213 |
},
|
214 |
{
|
215 |
-
"epoch":
|
216 |
-
"grad_norm": 0.
|
217 |
-
"learning_rate":
|
218 |
-
"loss": 0.
|
219 |
"step": 145
|
220 |
},
|
221 |
{
|
222 |
-
"epoch":
|
223 |
-
"
|
224 |
-
"
|
225 |
-
"
|
226 |
-
"
|
227 |
-
|
228 |
-
{
|
229 |
-
"epoch": 0.6019417475728155,
|
230 |
-
"grad_norm": 0.298828125,
|
231 |
-
"learning_rate": 0.00019396926207859084,
|
232 |
-
"loss": 0.4604,
|
233 |
-
"step": 155
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 0.6213592233009708,
|
237 |
-
"grad_norm": 0.26953125,
|
238 |
-
"learning_rate": 0.00019316994610215116,
|
239 |
-
"loss": 0.4866,
|
240 |
-
"step": 160
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 0.6407766990291263,
|
244 |
-
"grad_norm": 0.271484375,
|
245 |
-
"learning_rate": 0.00019232276375115515,
|
246 |
-
"loss": 0.4898,
|
247 |
-
"step": 165
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"epoch": 0.6601941747572816,
|
251 |
-
"grad_norm": 0.2578125,
|
252 |
-
"learning_rate": 0.00019142815026839755,
|
253 |
-
"loss": 0.4908,
|
254 |
-
"step": 170
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.6796116504854369,
|
258 |
-
"grad_norm": 0.28515625,
|
259 |
-
"learning_rate": 0.0001904865652645773,
|
260 |
-
"loss": 0.4566,
|
261 |
-
"step": 175
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 0.6990291262135923,
|
265 |
-
"grad_norm": 0.27734375,
|
266 |
-
"learning_rate": 0.000189498492482171,
|
267 |
-
"loss": 0.45,
|
268 |
-
"step": 180
|
269 |
-
},
|
270 |
-
{
|
271 |
-
"epoch": 0.7184466019417476,
|
272 |
-
"grad_norm": 0.259765625,
|
273 |
-
"learning_rate": 0.00018846443954690848,
|
274 |
-
"loss": 0.4646,
|
275 |
-
"step": 185
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 0.7378640776699029,
|
279 |
-
"grad_norm": 0.275390625,
|
280 |
-
"learning_rate": 0.00018738493770697852,
|
281 |
-
"loss": 0.4625,
|
282 |
-
"step": 190
|
283 |
-
},
|
284 |
-
{
|
285 |
-
"epoch": 0.7572815533980582,
|
286 |
-
"grad_norm": 0.26171875,
|
287 |
-
"learning_rate": 0.00018626054156009806,
|
288 |
-
"loss": 0.4452,
|
289 |
-
"step": 195
|
290 |
-
},
|
291 |
-
{
|
292 |
-
"epoch": 0.7766990291262136,
|
293 |
-
"grad_norm": 0.29296875,
|
294 |
-
"learning_rate": 0.00018509182876858611,
|
295 |
-
"loss": 0.4535,
|
296 |
-
"step": 200
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.7961165048543689,
|
300 |
-
"grad_norm": 0.25390625,
|
301 |
-
"learning_rate": 0.00018387939976258734,
|
302 |
-
"loss": 0.4393,
|
303 |
-
"step": 205
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 0.8155339805825242,
|
307 |
-
"grad_norm": 0.263671875,
|
308 |
-
"learning_rate": 0.0001826238774315995,
|
309 |
-
"loss": 0.4391,
|
310 |
-
"step": 210
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 0.8349514563106796,
|
314 |
-
"grad_norm": 0.271484375,
|
315 |
-
"learning_rate": 0.00018132590680446147,
|
316 |
-
"loss": 0.443,
|
317 |
-
"step": 215
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 0.8543689320388349,
|
321 |
-
"grad_norm": 0.279296875,
|
322 |
-
"learning_rate": 0.00017998615471796775,
|
323 |
-
"loss": 0.4527,
|
324 |
-
"step": 220
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"epoch": 0.8737864077669902,
|
328 |
-
"grad_norm": 0.265625,
|
329 |
-
"learning_rate": 0.00017860530947427875,
|
330 |
-
"loss": 0.4416,
|
331 |
-
"step": 225
|
332 |
-
},
|
333 |
-
{
|
334 |
-
"epoch": 0.8932038834951457,
|
335 |
-
"grad_norm": 0.2890625,
|
336 |
-
"learning_rate": 0.00017718408048730317,
|
337 |
-
"loss": 0.4506,
|
338 |
-
"step": 230
|
339 |
-
},
|
340 |
-
{
|
341 |
-
"epoch": 0.912621359223301,
|
342 |
-
"grad_norm": 0.298828125,
|
343 |
-
"learning_rate": 0.00017572319791823424,
|
344 |
-
"loss": 0.4538,
|
345 |
-
"step": 235
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 0.9320388349514563,
|
349 |
-
"grad_norm": 0.263671875,
|
350 |
-
"learning_rate": 0.000174223412300427,
|
351 |
-
"loss": 0.4467,
|
352 |
-
"step": 240
|
353 |
-
},
|
354 |
-
{
|
355 |
-
"epoch": 0.9514563106796117,
|
356 |
-
"grad_norm": 0.26953125,
|
357 |
-
"learning_rate": 0.00017268549415380916,
|
358 |
-
"loss": 0.4425,
|
359 |
-
"step": 245
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 0.970873786407767,
|
363 |
-
"grad_norm": 0.267578125,
|
364 |
-
"learning_rate": 0.00017111023358902392,
|
365 |
-
"loss": 0.4389,
|
366 |
-
"step": 250
|
367 |
-
},
|
368 |
-
{
|
369 |
-
"epoch": 0.9902912621359223,
|
370 |
-
"grad_norm": 0.251953125,
|
371 |
-
"learning_rate": 0.00016949843990150796,
|
372 |
-
"loss": 0.4177,
|
373 |
-
"step": 255
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 0.9980582524271845,
|
377 |
-
"eval_loss": 0.4281997084617615,
|
378 |
-
"eval_runtime": 22.0587,
|
379 |
-
"eval_samples_per_second": 4.987,
|
380 |
-
"eval_steps_per_second": 0.635,
|
381 |
-
"step": 257
|
382 |
-
},
|
383 |
-
{
|
384 |
-
"epoch": 1.0097087378640777,
|
385 |
-
"grad_norm": 0.236328125,
|
386 |
-
"learning_rate": 0.00016785094115571322,
|
387 |
-
"loss": 0.4083,
|
388 |
-
"step": 260
|
389 |
-
},
|
390 |
-
{
|
391 |
-
"epoch": 1.029126213592233,
|
392 |
-
"grad_norm": 0.275390625,
|
393 |
-
"learning_rate": 0.00016616858375968595,
|
394 |
-
"loss": 0.4012,
|
395 |
-
"step": 265
|
396 |
-
},
|
397 |
-
{
|
398 |
-
"epoch": 1.0485436893203883,
|
399 |
-
"grad_norm": 0.28515625,
|
400 |
-
"learning_rate": 0.00016445223203022166,
|
401 |
-
"loss": 0.3935,
|
402 |
-
"step": 270
|
403 |
-
},
|
404 |
-
{
|
405 |
-
"epoch": 1.0679611650485437,
|
406 |
-
"grad_norm": 0.279296875,
|
407 |
-
"learning_rate": 0.00016270276774881954,
|
408 |
-
"loss": 0.3972,
|
409 |
-
"step": 275
|
410 |
-
},
|
411 |
-
{
|
412 |
-
"epoch": 1.087378640776699,
|
413 |
-
"grad_norm": 0.267578125,
|
414 |
-
"learning_rate": 0.00016092108970866423,
|
415 |
-
"loss": 0.4004,
|
416 |
-
"step": 280
|
417 |
-
},
|
418 |
-
{
|
419 |
-
"epoch": 1.1067961165048543,
|
420 |
-
"grad_norm": 0.279296875,
|
421 |
-
"learning_rate": 0.00015910811325286768,
|
422 |
-
"loss": 0.3941,
|
423 |
-
"step": 285
|
424 |
-
},
|
425 |
-
{
|
426 |
-
"epoch": 1.1262135922330097,
|
427 |
-
"grad_norm": 0.271484375,
|
428 |
-
"learning_rate": 0.00015726476980420864,
|
429 |
-
"loss": 0.3877,
|
430 |
-
"step": 290
|
431 |
-
},
|
432 |
-
{
|
433 |
-
"epoch": 1.145631067961165,
|
434 |
-
"grad_norm": 0.287109375,
|
435 |
-
"learning_rate": 0.00015539200638661104,
|
436 |
-
"loss": 0.3819,
|
437 |
-
"step": 295
|
438 |
-
},
|
439 |
-
{
|
440 |
-
"epoch": 1.1650485436893203,
|
441 |
-
"grad_norm": 0.291015625,
|
442 |
-
"learning_rate": 0.00015349078513860726,
|
443 |
-
"loss": 0.3816,
|
444 |
-
"step": 300
|
445 |
-
},
|
446 |
-
{
|
447 |
-
"epoch": 1.1844660194174756,
|
448 |
-
"grad_norm": 0.318359375,
|
449 |
-
"learning_rate": 0.00015156208281903613,
|
450 |
-
"loss": 0.3953,
|
451 |
-
"step": 305
|
452 |
-
},
|
453 |
-
{
|
454 |
-
"epoch": 1.203883495145631,
|
455 |
-
"grad_norm": 0.296875,
|
456 |
-
"learning_rate": 0.0001496068903052299,
|
457 |
-
"loss": 0.3905,
|
458 |
-
"step": 310
|
459 |
-
},
|
460 |
-
{
|
461 |
-
"epoch": 1.2233009708737863,
|
462 |
-
"grad_norm": 0.2734375,
|
463 |
-
"learning_rate": 0.0001476262120839475,
|
464 |
-
"loss": 0.3763,
|
465 |
-
"step": 315
|
466 |
-
},
|
467 |
-
{
|
468 |
-
"epoch": 1.2427184466019416,
|
469 |
-
"grad_norm": 0.3125,
|
470 |
-
"learning_rate": 0.0001456210657353163,
|
471 |
-
"loss": 0.3792,
|
472 |
-
"step": 320
|
473 |
-
},
|
474 |
-
{
|
475 |
-
"epoch": 1.262135922330097,
|
476 |
-
"grad_norm": 0.29296875,
|
477 |
-
"learning_rate": 0.00014359248141004668,
|
478 |
-
"loss": 0.3794,
|
479 |
-
"step": 325
|
480 |
-
},
|
481 |
-
{
|
482 |
-
"epoch": 1.2815533980582523,
|
483 |
-
"grad_norm": 0.294921875,
|
484 |
-
"learning_rate": 0.00014154150130018866,
|
485 |
-
"loss": 0.3756,
|
486 |
-
"step": 330
|
487 |
-
},
|
488 |
-
{
|
489 |
-
"epoch": 1.3009708737864076,
|
490 |
-
"grad_norm": 0.287109375,
|
491 |
-
"learning_rate": 0.00013946917910370233,
|
492 |
-
"loss": 0.3876,
|
493 |
-
"step": 335
|
494 |
-
},
|
495 |
-
{
|
496 |
-
"epoch": 1.3203883495145632,
|
497 |
-
"grad_norm": 0.306640625,
|
498 |
-
"learning_rate": 0.00013737657948311683,
|
499 |
-
"loss": 0.3819,
|
500 |
-
"step": 340
|
501 |
-
},
|
502 |
-
{
|
503 |
-
"epoch": 1.3398058252427185,
|
504 |
-
"grad_norm": 0.26171875,
|
505 |
-
"learning_rate": 0.00013526477751855644,
|
506 |
-
"loss": 0.3925,
|
507 |
-
"step": 345
|
508 |
-
},
|
509 |
-
{
|
510 |
-
"epoch": 1.3592233009708738,
|
511 |
-
"grad_norm": 0.287109375,
|
512 |
-
"learning_rate": 0.00013313485815541454,
|
513 |
-
"loss": 0.3915,
|
514 |
-
"step": 350
|
515 |
-
},
|
516 |
-
{
|
517 |
-
"epoch": 1.3786407766990292,
|
518 |
-
"grad_norm": 0.28515625,
|
519 |
-
"learning_rate": 0.00013098791564695927,
|
520 |
-
"loss": 0.3902,
|
521 |
-
"step": 355
|
522 |
-
},
|
523 |
-
{
|
524 |
-
"epoch": 1.3980582524271845,
|
525 |
-
"grad_norm": 0.2890625,
|
526 |
-
"learning_rate": 0.0001288250529921571,
|
527 |
-
"loss": 0.3864,
|
528 |
-
"step": 360
|
529 |
-
},
|
530 |
-
{
|
531 |
-
"epoch": 1.4174757281553398,
|
532 |
-
"grad_norm": 0.27734375,
|
533 |
-
"learning_rate": 0.00012664738136900348,
|
534 |
-
"loss": 0.3778,
|
535 |
-
"step": 365
|
536 |
-
},
|
537 |
-
{
|
538 |
-
"epoch": 1.4368932038834952,
|
539 |
-
"grad_norm": 0.2890625,
|
540 |
-
"learning_rate": 0.0001244560195636515,
|
541 |
-
"loss": 0.3732,
|
542 |
-
"step": 370
|
543 |
-
},
|
544 |
-
{
|
545 |
-
"epoch": 1.4563106796116505,
|
546 |
-
"grad_norm": 0.318359375,
|
547 |
-
"learning_rate": 0.00012225209339563145,
|
548 |
-
"loss": 0.3856,
|
549 |
-
"step": 375
|
550 |
-
},
|
551 |
-
{
|
552 |
-
"epoch": 1.4757281553398058,
|
553 |
-
"grad_norm": 0.265625,
|
554 |
-
"learning_rate": 0.00012003673513945746,
|
555 |
-
"loss": 0.3745,
|
556 |
-
"step": 380
|
557 |
-
},
|
558 |
-
{
|
559 |
-
"epoch": 1.4951456310679612,
|
560 |
-
"grad_norm": 0.306640625,
|
561 |
-
"learning_rate": 0.0001178110829429175,
|
562 |
-
"loss": 0.3657,
|
563 |
-
"step": 385
|
564 |
-
},
|
565 |
-
{
|
566 |
-
"epoch": 1.5145631067961165,
|
567 |
-
"grad_norm": 0.25390625,
|
568 |
-
"learning_rate": 0.0001155762802423463,
|
569 |
-
"loss": 0.3728,
|
570 |
-
"step": 390
|
571 |
-
},
|
572 |
-
{
|
573 |
-
"epoch": 1.5339805825242718,
|
574 |
-
"grad_norm": 0.265625,
|
575 |
-
"learning_rate": 0.0001133334751751809,
|
576 |
-
"loss": 0.3849,
|
577 |
-
"step": 395
|
578 |
-
},
|
579 |
-
{
|
580 |
-
"epoch": 1.5533980582524272,
|
581 |
-
"grad_norm": 0.291015625,
|
582 |
-
"learning_rate": 0.00011108381999010111,
|
583 |
-
"loss": 0.3979,
|
584 |
-
"step": 400
|
585 |
-
},
|
586 |
-
{
|
587 |
-
"epoch": 1.5728155339805825,
|
588 |
-
"grad_norm": 0.26171875,
|
589 |
-
"learning_rate": 0.00010882847045505808,
|
590 |
-
"loss": 0.3819,
|
591 |
-
"step": 405
|
592 |
-
},
|
593 |
-
{
|
594 |
-
"epoch": 1.5922330097087378,
|
595 |
-
"grad_norm": 0.2578125,
|
596 |
-
"learning_rate": 0.00010656858526349449,
|
597 |
-
"loss": 0.3704,
|
598 |
-
"step": 410
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"epoch": 1.6116504854368932,
|
602 |
-
"grad_norm": 0.26171875,
|
603 |
-
"learning_rate": 0.00010430532543906179,
|
604 |
-
"loss": 0.3702,
|
605 |
-
"step": 415
|
606 |
-
},
|
607 |
-
{
|
608 |
-
"epoch": 1.6310679611650487,
|
609 |
-
"grad_norm": 0.283203125,
|
610 |
-
"learning_rate": 0.00010203985373914056,
|
611 |
-
"loss": 0.373,
|
612 |
-
"step": 420
|
613 |
-
},
|
614 |
-
{
|
615 |
-
"epoch": 1.650485436893204,
|
616 |
-
"grad_norm": 0.279296875,
|
617 |
-
"learning_rate": 9.977333405746979e-05,
|
618 |
-
"loss": 0.366,
|
619 |
-
"step": 425
|
620 |
-
},
|
621 |
-
{
|
622 |
-
"epoch": 1.6699029126213594,
|
623 |
-
"grad_norm": 0.30859375,
|
624 |
-
"learning_rate": 9.750693082619273e-05,
|
625 |
-
"loss": 0.3555,
|
626 |
-
"step": 430
|
627 |
-
},
|
628 |
-
{
|
629 |
-
"epoch": 1.6893203883495147,
|
630 |
-
"grad_norm": 0.279296875,
|
631 |
-
"learning_rate": 9.524180841762577e-05,
|
632 |
-
"loss": 0.3793,
|
633 |
-
"step": 435
|
634 |
-
},
|
635 |
-
{
|
636 |
-
"epoch": 1.70873786407767,
|
637 |
-
"grad_norm": 0.25390625,
|
638 |
-
"learning_rate": 9.297913054605838e-05,
|
639 |
-
"loss": 0.3692,
|
640 |
-
"step": 440
|
641 |
-
},
|
642 |
-
{
|
643 |
-
"epoch": 1.7281553398058254,
|
644 |
-
"grad_norm": 0.27734375,
|
645 |
-
"learning_rate": 9.072005966989084e-05,
|
646 |
-
"loss": 0.3655,
|
647 |
-
"step": 445
|
648 |
-
},
|
649 |
-
{
|
650 |
-
"epoch": 1.7475728155339807,
|
651 |
-
"grad_norm": 0.265625,
|
652 |
-
"learning_rate": 8.846575639441732e-05,
|
653 |
-
"loss": 0.3791,
|
654 |
-
"step": 450
|
655 |
-
},
|
656 |
-
{
|
657 |
-
"epoch": 1.766990291262136,
|
658 |
-
"grad_norm": 0.29296875,
|
659 |
-
"learning_rate": 8.621737887556114e-05,
|
660 |
-
"loss": 0.3661,
|
661 |
-
"step": 455
|
662 |
-
},
|
663 |
-
{
|
664 |
-
"epoch": 1.7864077669902914,
|
665 |
-
"grad_norm": 0.2890625,
|
666 |
-
"learning_rate": 8.397608222486805e-05,
|
667 |
-
"loss": 0.3611,
|
668 |
-
"step": 460
|
669 |
-
},
|
670 |
-
{
|
671 |
-
"epoch": 1.8058252427184467,
|
672 |
-
"grad_norm": 0.291015625,
|
673 |
-
"learning_rate": 8.174301791606385e-05,
|
674 |
-
"loss": 0.3611,
|
675 |
-
"step": 465
|
676 |
-
},
|
677 |
-
{
|
678 |
-
"epoch": 1.825242718446602,
|
679 |
-
"grad_norm": 0.279296875,
|
680 |
-
"learning_rate": 7.951933319348095e-05,
|
681 |
-
"loss": 0.3493,
|
682 |
-
"step": 470
|
683 |
-
},
|
684 |
-
{
|
685 |
-
"epoch": 1.8446601941747574,
|
686 |
-
"grad_norm": 0.2578125,
|
687 |
-
"learning_rate": 7.730617048265761e-05,
|
688 |
-
"loss": 0.3655,
|
689 |
-
"step": 475
|
690 |
-
},
|
691 |
-
{
|
692 |
-
"epoch": 1.8640776699029127,
|
693 |
-
"grad_norm": 0.318359375,
|
694 |
-
"learning_rate": 7.510466680341301e-05,
|
695 |
-
"loss": 0.3527,
|
696 |
-
"step": 480
|
697 |
-
},
|
698 |
-
{
|
699 |
-
"epoch": 1.883495145631068,
|
700 |
-
"grad_norm": 0.298828125,
|
701 |
-
"learning_rate": 7.291595318569951e-05,
|
702 |
-
"loss": 0.3528,
|
703 |
-
"step": 485
|
704 |
-
},
|
705 |
-
{
|
706 |
-
"epoch": 1.9029126213592233,
|
707 |
-
"grad_norm": 0.30078125,
|
708 |
-
"learning_rate": 7.074115408853203e-05,
|
709 |
-
"loss": 0.3784,
|
710 |
-
"step": 490
|
711 |
-
},
|
712 |
-
{
|
713 |
-
"epoch": 1.9223300970873787,
|
714 |
-
"grad_norm": 0.27734375,
|
715 |
-
"learning_rate": 6.858138682229376e-05,
|
716 |
-
"loss": 0.3571,
|
717 |
-
"step": 495
|
718 |
-
},
|
719 |
-
{
|
720 |
-
"epoch": 1.941747572815534,
|
721 |
-
"grad_norm": 0.265625,
|
722 |
-
"learning_rate": 6.643776097471377e-05,
|
723 |
-
"loss": 0.3658,
|
724 |
-
"step": 500
|
725 |
-
},
|
726 |
-
{
|
727 |
-
"epoch": 1.9611650485436893,
|
728 |
-
"grad_norm": 0.275390625,
|
729 |
-
"learning_rate": 6.431137784081282e-05,
|
730 |
-
"loss": 0.3567,
|
731 |
-
"step": 505
|
732 |
-
},
|
733 |
-
{
|
734 |
-
"epoch": 1.9805825242718447,
|
735 |
-
"grad_norm": 0.29296875,
|
736 |
-
"learning_rate": 6.220332985710936e-05,
|
737 |
-
"loss": 0.3526,
|
738 |
-
"step": 510
|
739 |
-
},
|
740 |
-
{
|
741 |
-
"epoch": 2.0,
|
742 |
-
"grad_norm": 0.30078125,
|
743 |
-
"learning_rate": 6.011470004037636e-05,
|
744 |
-
"loss": 0.361,
|
745 |
-
"step": 515
|
746 |
-
},
|
747 |
-
{
|
748 |
-
"epoch": 2.0,
|
749 |
-
"eval_loss": 0.38420218229293823,
|
750 |
-
"eval_runtime": 22.0532,
|
751 |
-
"eval_samples_per_second": 4.988,
|
752 |
-
"eval_steps_per_second": 0.635,
|
753 |
-
"step": 515
|
754 |
-
},
|
755 |
-
{
|
756 |
-
"epoch": 2.0194174757281553,
|
757 |
-
"grad_norm": 0.2421875,
|
758 |
-
"learning_rate": 5.804656143123801e-05,
|
759 |
-
"loss": 0.308,
|
760 |
-
"step": 520
|
761 |
-
},
|
762 |
-
{
|
763 |
-
"epoch": 2.0388349514563107,
|
764 |
-
"grad_norm": 0.283203125,
|
765 |
-
"learning_rate": 5.599997654289129e-05,
|
766 |
-
"loss": 0.3136,
|
767 |
-
"step": 525
|
768 |
-
},
|
769 |
-
{
|
770 |
-
"epoch": 2.058252427184466,
|
771 |
-
"grad_norm": 0.3046875,
|
772 |
-
"learning_rate": 5.397599681523643e-05,
|
773 |
-
"loss": 0.3037,
|
774 |
-
"step": 530
|
775 |
-
},
|
776 |
-
{
|
777 |
-
"epoch": 2.0776699029126213,
|
778 |
-
"grad_norm": 0.298828125,
|
779 |
-
"learning_rate": 5.1975662074695865e-05,
|
780 |
-
"loss": 0.3098,
|
781 |
-
"step": 535
|
782 |
-
},
|
783 |
-
{
|
784 |
-
"epoch": 2.0970873786407767,
|
785 |
-
"grad_norm": 0.28125,
|
786 |
-
"learning_rate": 5.000000000000002e-05,
|
787 |
-
"loss": 0.3111,
|
788 |
-
"step": 540
|
789 |
-
},
|
790 |
-
{
|
791 |
-
"epoch": 2.116504854368932,
|
792 |
-
"grad_norm": 0.294921875,
|
793 |
-
"learning_rate": 4.8050025594214e-05,
|
794 |
-
"loss": 0.3083,
|
795 |
-
"step": 545
|
796 |
-
},
|
797 |
-
{
|
798 |
-
"epoch": 2.1359223300970873,
|
799 |
-
"grad_norm": 0.29296875,
|
800 |
-
"learning_rate": 4.6126740663276166e-05,
|
801 |
-
"loss": 0.3133,
|
802 |
-
"step": 550
|
803 |
-
},
|
804 |
-
{
|
805 |
-
"epoch": 2.1553398058252426,
|
806 |
-
"grad_norm": 0.29296875,
|
807 |
-
"learning_rate": 4.423113330131707e-05,
|
808 |
-
"loss": 0.3076,
|
809 |
-
"step": 555
|
810 |
-
},
|
811 |
-
{
|
812 |
-
"epoch": 2.174757281553398,
|
813 |
-
"grad_norm": 0.29296875,
|
814 |
-
"learning_rate": 4.236417738302257e-05,
|
815 |
-
"loss": 0.2981,
|
816 |
-
"step": 560
|
817 |
-
},
|
818 |
-
{
|
819 |
-
"epoch": 2.1941747572815533,
|
820 |
-
"grad_norm": 0.314453125,
|
821 |
-
"learning_rate": 4.052683206330267e-05,
|
822 |
-
"loss": 0.312,
|
823 |
-
"step": 565
|
824 |
-
},
|
825 |
-
{
|
826 |
-
"epoch": 2.2135922330097086,
|
827 |
-
"grad_norm": 0.298828125,
|
828 |
-
"learning_rate": 3.872004128452231e-05,
|
829 |
-
"loss": 0.2942,
|
830 |
-
"step": 570
|
831 |
-
},
|
832 |
-
{
|
833 |
-
"epoch": 2.233009708737864,
|
834 |
-
"grad_norm": 0.314453125,
|
835 |
-
"learning_rate": 3.694473329154778e-05,
|
836 |
-
"loss": 0.3205,
|
837 |
-
"step": 575
|
838 |
-
},
|
839 |
-
{
|
840 |
-
"epoch": 2.2524271844660193,
|
841 |
-
"grad_norm": 0.3359375,
|
842 |
-
"learning_rate": 3.5201820154857755e-05,
|
843 |
-
"loss": 0.322,
|
844 |
-
"step": 580
|
845 |
-
},
|
846 |
-
{
|
847 |
-
"epoch": 2.2718446601941746,
|
848 |
-
"grad_norm": 0.296875,
|
849 |
-
"learning_rate": 3.3492197301964145e-05,
|
850 |
-
"loss": 0.2931,
|
851 |
-
"step": 585
|
852 |
-
},
|
853 |
-
{
|
854 |
-
"epoch": 2.29126213592233,
|
855 |
-
"grad_norm": 0.33203125,
|
856 |
-
"learning_rate": 3.18167430573831e-05,
|
857 |
-
"loss": 0.3107,
|
858 |
-
"step": 590
|
859 |
-
},
|
860 |
-
{
|
861 |
-
"epoch": 2.3106796116504853,
|
862 |
-
"grad_norm": 0.302734375,
|
863 |
-
"learning_rate": 3.0176318191392726e-05,
|
864 |
-
"loss": 0.3065,
|
865 |
-
"step": 595
|
866 |
-
},
|
867 |
-
{
|
868 |
-
"epoch": 2.3300970873786406,
|
869 |
-
"grad_norm": 0.3203125,
|
870 |
-
"learning_rate": 2.8571765477809643e-05,
|
871 |
-
"loss": 0.3031,
|
872 |
-
"step": 600
|
873 |
-
},
|
874 |
-
{
|
875 |
-
"epoch": 2.349514563106796,
|
876 |
-
"grad_norm": 0.3125,
|
877 |
-
"learning_rate": 2.7003909261010928e-05,
|
878 |
-
"loss": 0.2894,
|
879 |
-
"step": 605
|
880 |
-
},
|
881 |
-
{
|
882 |
-
"epoch": 2.3689320388349513,
|
883 |
-
"grad_norm": 0.314453125,
|
884 |
-
"learning_rate": 2.5473555032424533e-05,
|
885 |
-
"loss": 0.3136,
|
886 |
-
"step": 610
|
887 |
-
},
|
888 |
-
{
|
889 |
-
"epoch": 2.3883495145631066,
|
890 |
-
"grad_norm": 0.33984375,
|
891 |
-
"learning_rate": 2.3981489016705205e-05,
|
892 |
-
"loss": 0.3078,
|
893 |
-
"step": 615
|
894 |
-
},
|
895 |
-
{
|
896 |
-
"epoch": 2.407766990291262,
|
897 |
-
"grad_norm": 0.322265625,
|
898 |
-
"learning_rate": 2.2528477767808963e-05,
|
899 |
-
"loss": 0.3094,
|
900 |
-
"step": 620
|
901 |
-
},
|
902 |
-
{
|
903 |
-
"epoch": 2.4271844660194173,
|
904 |
-
"grad_norm": 0.31640625,
|
905 |
-
"learning_rate": 2.1115267775173532e-05,
|
906 |
-
"loss": 0.2985,
|
907 |
-
"step": 625
|
908 |
-
},
|
909 |
-
{
|
910 |
-
"epoch": 2.4466019417475726,
|
911 |
-
"grad_norm": 0.322265625,
|
912 |
-
"learning_rate": 1.9742585080206755e-05,
|
913 |
-
"loss": 0.3191,
|
914 |
-
"step": 630
|
915 |
-
},
|
916 |
-
{
|
917 |
-
"epoch": 2.466019417475728,
|
918 |
-
"grad_norm": 0.3203125,
|
919 |
-
"learning_rate": 1.8411134903280303e-05,
|
920 |
-
"loss": 0.3117,
|
921 |
-
"step": 635
|
922 |
-
},
|
923 |
-
{
|
924 |
-
"epoch": 2.4854368932038833,
|
925 |
-
"grad_norm": 0.306640625,
|
926 |
-
"learning_rate": 1.7121601281420495e-05,
|
927 |
-
"loss": 0.3086,
|
928 |
-
"step": 640
|
929 |
-
},
|
930 |
-
{
|
931 |
-
"epoch": 2.5048543689320386,
|
932 |
-
"grad_norm": 0.33203125,
|
933 |
-
"learning_rate": 1.587464671688187e-05,
|
934 |
-
"loss": 0.3072,
|
935 |
-
"step": 645
|
936 |
-
},
|
937 |
-
{
|
938 |
-
"epoch": 2.524271844660194,
|
939 |
-
"grad_norm": 0.306640625,
|
940 |
-
"learning_rate": 1.467091183678444e-05,
|
941 |
-
"loss": 0.3044,
|
942 |
-
"step": 650
|
943 |
-
},
|
944 |
-
{
|
945 |
-
"epoch": 2.5436893203883493,
|
946 |
-
"grad_norm": 0.298828125,
|
947 |
-
"learning_rate": 1.3511015063989274e-05,
|
948 |
-
"loss": 0.3081,
|
949 |
-
"step": 655
|
950 |
-
},
|
951 |
-
{
|
952 |
-
"epoch": 2.5631067961165046,
|
953 |
-
"grad_norm": 0.275390625,
|
954 |
-
"learning_rate": 1.2395552299381741e-05,
|
955 |
-
"loss": 0.3005,
|
956 |
-
"step": 660
|
957 |
-
},
|
958 |
-
{
|
959 |
-
"epoch": 2.58252427184466,
|
960 |
-
"grad_norm": 0.3125,
|
961 |
-
"learning_rate": 1.1325096615725427e-05,
|
962 |
-
"loss": 0.3034,
|
963 |
-
"step": 665
|
964 |
-
},
|
965 |
-
{
|
966 |
-
"epoch": 2.6019417475728153,
|
967 |
-
"grad_norm": 0.3125,
|
968 |
-
"learning_rate": 1.030019796324404e-05,
|
969 |
-
"loss": 0.3075,
|
970 |
-
"step": 670
|
971 |
-
},
|
972 |
-
{
|
973 |
-
"epoch": 2.6213592233009706,
|
974 |
-
"grad_norm": 0.3125,
|
975 |
-
"learning_rate": 9.321382887082563e-06,
|
976 |
-
"loss": 0.3084,
|
977 |
-
"step": 675
|
978 |
-
},
|
979 |
-
{
|
980 |
-
"epoch": 2.6407766990291264,
|
981 |
-
"grad_norm": 0.3203125,
|
982 |
-
"learning_rate": 8.38915425679304e-06,
|
983 |
-
"loss": 0.3064,
|
984 |
-
"step": 680
|
985 |
-
},
|
986 |
-
{
|
987 |
-
"epoch": 2.6601941747572817,
|
988 |
-
"grad_norm": 0.310546875,
|
989 |
-
"learning_rate": 7.503991007983524e-06,
|
990 |
-
"loss": 0.3087,
|
991 |
-
"step": 685
|
992 |
-
},
|
993 |
-
{
|
994 |
-
"epoch": 2.679611650485437,
|
995 |
-
"grad_norm": 0.3359375,
|
996 |
-
"learning_rate": 6.666347896263325e-06,
|
997 |
-
"loss": 0.3129,
|
998 |
-
"step": 690
|
999 |
-
},
|
1000 |
-
{
|
1001 |
-
"epoch": 2.6990291262135924,
|
1002 |
-
"grad_norm": 0.291015625,
|
1003 |
-
"learning_rate": 5.876655263610842e-06,
|
1004 |
-
"loss": 0.2897,
|
1005 |
-
"step": 695
|
1006 |
-
},
|
1007 |
-
{
|
1008 |
-
"epoch": 2.7184466019417477,
|
1009 |
-
"grad_norm": 0.31640625,
|
1010 |
-
"learning_rate": 5.1353188172838074e-06,
|
1011 |
-
"loss": 0.3033,
|
1012 |
-
"step": 700
|
1013 |
-
},
|
1014 |
-
{
|
1015 |
-
"epoch": 2.737864077669903,
|
1016 |
-
"grad_norm": 0.30859375,
|
1017 |
-
"learning_rate": 4.442719421385922e-06,
|
1018 |
-
"loss": 0.2994,
|
1019 |
-
"step": 705
|
1020 |
-
},
|
1021 |
-
{
|
1022 |
-
"epoch": 2.7572815533980584,
|
1023 |
-
"grad_norm": 0.330078125,
|
1024 |
-
"learning_rate": 3.7992129011965803e-06,
|
1025 |
-
"loss": 0.3152,
|
1026 |
-
"step": 710
|
1027 |
-
},
|
1028 |
-
{
|
1029 |
-
"epoch": 2.7766990291262137,
|
1030 |
-
"grad_norm": 0.314453125,
|
1031 |
-
"learning_rate": 3.2051298603643753e-06,
|
1032 |
-
"loss": 0.3101,
|
1033 |
-
"step": 715
|
1034 |
-
},
|
1035 |
-
{
|
1036 |
-
"epoch": 2.796116504854369,
|
1037 |
-
"grad_norm": 0.30859375,
|
1038 |
-
"learning_rate": 2.6607755110584887e-06,
|
1039 |
-
"loss": 0.3125,
|
1040 |
-
"step": 720
|
1041 |
-
},
|
1042 |
-
{
|
1043 |
-
"epoch": 2.8155339805825244,
|
1044 |
-
"grad_norm": 0.291015625,
|
1045 |
-
"learning_rate": 2.1664295171648364e-06,
|
1046 |
-
"loss": 0.3024,
|
1047 |
-
"step": 725
|
1048 |
-
},
|
1049 |
-
{
|
1050 |
-
"epoch": 2.8349514563106797,
|
1051 |
-
"grad_norm": 0.31640625,
|
1052 |
-
"learning_rate": 1.7223458506077316e-06,
|
1053 |
-
"loss": 0.2913,
|
1054 |
-
"step": 730
|
1055 |
-
},
|
1056 |
-
{
|
1057 |
-
"epoch": 2.854368932038835,
|
1058 |
-
"grad_norm": 0.3046875,
|
1059 |
-
"learning_rate": 1.3287526608711131e-06,
|
1060 |
-
"loss": 0.2968,
|
1061 |
-
"step": 735
|
1062 |
-
},
|
1063 |
-
{
|
1064 |
-
"epoch": 2.8737864077669903,
|
1065 |
-
"grad_norm": 0.3203125,
|
1066 |
-
"learning_rate": 9.85852157785816e-07,
|
1067 |
-
"loss": 0.3033,
|
1068 |
-
"step": 740
|
1069 |
-
},
|
1070 |
-
{
|
1071 |
-
"epoch": 2.8932038834951457,
|
1072 |
-
"grad_norm": 0.310546875,
|
1073 |
-
"learning_rate": 6.938205076436832e-07,
|
1074 |
-
"loss": 0.2991,
|
1075 |
-
"step": 745
|
1076 |
-
},
|
1077 |
-
{
|
1078 |
-
"epoch": 2.912621359223301,
|
1079 |
-
"grad_norm": 0.328125,
|
1080 |
-
"learning_rate": 4.5280774269154115e-07,
|
1081 |
-
"loss": 0.3003,
|
1082 |
-
"step": 750
|
1083 |
-
},
|
1084 |
-
{
|
1085 |
-
"epoch": 2.9320388349514563,
|
1086 |
-
"grad_norm": 0.2890625,
|
1087 |
-
"learning_rate": 2.629376840515452e-07,
|
1088 |
-
"loss": 0.2999,
|
1089 |
-
"step": 755
|
1090 |
-
},
|
1091 |
-
{
|
1092 |
-
"epoch": 2.9514563106796117,
|
1093 |
-
"grad_norm": 0.32421875,
|
1094 |
-
"learning_rate": 1.2430787810776555e-07,
|
1095 |
-
"loss": 0.3023,
|
1096 |
-
"step": 760
|
1097 |
-
},
|
1098 |
-
{
|
1099 |
-
"epoch": 2.970873786407767,
|
1100 |
-
"grad_norm": 0.326171875,
|
1101 |
-
"learning_rate": 3.6989546391297256e-08,
|
1102 |
-
"loss": 0.3106,
|
1103 |
-
"step": 765
|
1104 |
-
},
|
1105 |
-
{
|
1106 |
-
"epoch": 2.9902912621359223,
|
1107 |
-
"grad_norm": 0.318359375,
|
1108 |
-
"learning_rate": 1.0275489900624102e-09,
|
1109 |
-
"loss": 0.3036,
|
1110 |
-
"step": 770
|
1111 |
-
},
|
1112 |
-
{
|
1113 |
-
"epoch": 2.994174757281553,
|
1114 |
-
"eval_loss": 0.38681623339653015,
|
1115 |
-
"eval_runtime": 22.0402,
|
1116 |
-
"eval_samples_per_second": 4.991,
|
1117 |
-
"eval_steps_per_second": 0.635,
|
1118 |
-
"step": 771
|
1119 |
},
|
1120 |
{
|
1121 |
-
"epoch": 2.
|
1122 |
-
"step":
|
1123 |
-
"total_flos":
|
1124 |
-
"train_loss": 0.
|
1125 |
-
"train_runtime":
|
1126 |
-
"train_samples_per_second":
|
1127 |
-
"train_steps_per_second": 0.
|
1128 |
}
|
1129 |
],
|
1130 |
"logging_steps": 5,
|
1131 |
-
"max_steps":
|
1132 |
"num_input_tokens_seen": 0,
|
1133 |
"num_train_epochs": 3,
|
1134 |
"save_steps": 100,
|
@@ -1144,7 +269,7 @@
|
|
1144 |
"attributes": {}
|
1145 |
}
|
1146 |
},
|
1147 |
-
"total_flos":
|
1148 |
"train_batch_size": 4,
|
1149 |
"trial_name": null,
|
1150 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9696969696969697,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 147,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.020202020202020204,
|
13 |
+
"grad_norm": 2.578125,
|
14 |
+
"learning_rate": 1.3333333333333334e-06,
|
15 |
+
"loss": 1.5448,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.10101010101010101,
|
20 |
+
"grad_norm": 2.546875,
|
21 |
+
"learning_rate": 6.666666666666667e-06,
|
22 |
+
"loss": 1.5503,
|
23 |
"step": 5
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.20202020202020202,
|
27 |
+
"grad_norm": 2.390625,
|
28 |
+
"learning_rate": 1.3333333333333333e-05,
|
29 |
+
"loss": 1.469,
|
30 |
"step": 10
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.30303030303030304,
|
34 |
+
"grad_norm": 1.65625,
|
35 |
+
"learning_rate": 2e-05,
|
36 |
+
"loss": 1.2465,
|
37 |
"step": 15
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.40404040404040403,
|
41 |
+
"grad_norm": 1.203125,
|
42 |
+
"learning_rate": 1.9929278846732883e-05,
|
43 |
+
"loss": 1.0305,
|
44 |
"step": 20
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.5050505050505051,
|
48 |
+
"grad_norm": 0.953125,
|
49 |
+
"learning_rate": 1.9718115683235418e-05,
|
50 |
+
"loss": 0.9205,
|
51 |
"step": 25
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.6060606060606061,
|
55 |
+
"grad_norm": 0.609375,
|
56 |
+
"learning_rate": 1.936949724999762e-05,
|
57 |
+
"loss": 0.8521,
|
58 |
"step": 30
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.7070707070707071,
|
62 |
+
"grad_norm": 0.48046875,
|
63 |
+
"learning_rate": 1.8888354486549238e-05,
|
64 |
+
"loss": 0.8354,
|
65 |
"step": 35
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.8080808080808081,
|
69 |
+
"grad_norm": 0.478515625,
|
70 |
+
"learning_rate": 1.8281492787113707e-05,
|
71 |
+
"loss": 0.7916,
|
72 |
"step": 40
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 0.9090909090909091,
|
76 |
+
"grad_norm": 0.46484375,
|
77 |
+
"learning_rate": 1.7557495743542586e-05,
|
78 |
+
"loss": 0.7588,
|
79 |
"step": 45
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.98989898989899,
|
83 |
+
"eval_loss": 0.7386298179626465,
|
84 |
+
"eval_runtime": 17.3037,
|
85 |
+
"eval_samples_per_second": 2.485,
|
86 |
+
"eval_steps_per_second": 0.347,
|
87 |
+
"step": 49
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.0101010101010102,
|
91 |
+
"grad_norm": 0.5390625,
|
92 |
+
"learning_rate": 1.6726603737012527e-05,
|
93 |
+
"loss": 0.7461,
|
94 |
"step": 50
|
95 |
},
|
96 |
{
|
97 |
+
"epoch": 1.1111111111111112,
|
98 |
+
"grad_norm": 0.5078125,
|
99 |
+
"learning_rate": 1.5800569095711983e-05,
|
100 |
+
"loss": 0.715,
|
101 |
"step": 55
|
102 |
},
|
103 |
{
|
104 |
+
"epoch": 1.2121212121212122,
|
105 |
+
"grad_norm": 0.3046875,
|
106 |
+
"learning_rate": 1.479248986720057e-05,
|
107 |
+
"loss": 0.6996,
|
108 |
"step": 60
|
109 |
},
|
110 |
{
|
111 |
+
"epoch": 1.3131313131313131,
|
112 |
+
"grad_norm": 0.28125,
|
113 |
+
"learning_rate": 1.3716624556603275e-05,
|
114 |
+
"loss": 0.6809,
|
115 |
"step": 65
|
116 |
},
|
117 |
{
|
118 |
+
"epoch": 1.4141414141414141,
|
119 |
+
"grad_norm": 0.318359375,
|
120 |
+
"learning_rate": 1.2588190451025209e-05,
|
121 |
+
"loss": 0.6585,
|
122 |
"step": 70
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 1.5151515151515151,
|
126 |
+
"grad_norm": 0.2255859375,
|
127 |
+
"learning_rate": 1.1423148382732854e-05,
|
128 |
+
"loss": 0.6599,
|
129 |
"step": 75
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 1.6161616161616161,
|
133 |
+
"grad_norm": 0.2431640625,
|
134 |
+
"learning_rate": 1.0237976975461074e-05,
|
135 |
+
"loss": 0.646,
|
136 |
"step": 80
|
137 |
},
|
138 |
{
|
139 |
+
"epoch": 1.7171717171717171,
|
140 |
+
"grad_norm": 0.203125,
|
141 |
+
"learning_rate": 9.049439566958176e-06,
|
142 |
+
"loss": 0.6349,
|
143 |
"step": 85
|
144 |
},
|
145 |
{
|
146 |
+
"epoch": 1.8181818181818183,
|
147 |
+
"grad_norm": 0.2392578125,
|
148 |
+
"learning_rate": 7.874347104470234e-06,
|
149 |
+
"loss": 0.6352,
|
150 |
"step": 90
|
151 |
},
|
152 |
{
|
153 |
+
"epoch": 1.9191919191919191,
|
154 |
+
"grad_norm": 0.2060546875,
|
155 |
+
"learning_rate": 6.729320366825785e-06,
|
156 |
+
"loss": 0.6201,
|
157 |
"step": 95
|
158 |
},
|
159 |
{
|
160 |
+
"epoch": 2.0,
|
161 |
+
"eval_loss": 0.6306869983673096,
|
162 |
+
"eval_runtime": 17.31,
|
163 |
+
"eval_samples_per_second": 2.484,
|
164 |
+
"eval_steps_per_second": 0.347,
|
165 |
+
"step": 99
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.0202020202020203,
|
169 |
+
"grad_norm": 0.2001953125,
|
170 |
+
"learning_rate": 5.630554876306407e-06,
|
171 |
+
"loss": 0.6233,
|
172 |
"step": 100
|
173 |
},
|
174 |
{
|
175 |
+
"epoch": 2.121212121212121,
|
176 |
+
"grad_norm": 0.2021484375,
|
177 |
+
"learning_rate": 4.593591825444028e-06,
|
178 |
+
"loss": 0.6138,
|
179 |
"step": 105
|
180 |
},
|
181 |
{
|
182 |
+
"epoch": 2.2222222222222223,
|
183 |
+
"grad_norm": 0.2275390625,
|
184 |
+
"learning_rate": 3.633098258809119e-06,
|
185 |
+
"loss": 0.6218,
|
186 |
"step": 110
|
187 |
},
|
188 |
{
|
189 |
+
"epoch": 2.323232323232323,
|
190 |
+
"grad_norm": 0.2021484375,
|
191 |
+
"learning_rate": 2.7626596189492983e-06,
|
192 |
+
"loss": 0.6201,
|
193 |
"step": 115
|
194 |
},
|
195 |
{
|
196 |
+
"epoch": 2.4242424242424243,
|
197 |
+
"grad_norm": 0.19921875,
|
198 |
+
"learning_rate": 1.994587590756397e-06,
|
199 |
+
"loss": 0.6164,
|
200 |
"step": 120
|
201 |
},
|
202 |
{
|
203 |
+
"epoch": 2.525252525252525,
|
204 |
+
"grad_norm": 0.2041015625,
|
205 |
+
"learning_rate": 1.339745962155613e-06,
|
206 |
+
"loss": 0.6157,
|
207 |
"step": 125
|
208 |
},
|
209 |
{
|
210 |
+
"epoch": 2.6262626262626263,
|
211 |
+
"grad_norm": 0.216796875,
|
212 |
+
"learning_rate": 8.073969641833446e-07,
|
213 |
+
"loss": 0.6151,
|
214 |
"step": 130
|
215 |
},
|
216 |
{
|
217 |
+
"epoch": 2.7272727272727275,
|
218 |
+
"grad_norm": 0.267578125,
|
219 |
+
"learning_rate": 4.0507026385502747e-07,
|
220 |
+
"loss": 0.6097,
|
221 |
"step": 135
|
222 |
},
|
223 |
{
|
224 |
+
"epoch": 2.8282828282828283,
|
225 |
+
"grad_norm": 0.208984375,
|
226 |
+
"learning_rate": 1.3845646281813508e-07,
|
227 |
+
"loss": 0.617,
|
228 |
"step": 140
|
229 |
},
|
230 |
{
|
231 |
+
"epoch": 2.929292929292929,
|
232 |
+
"grad_norm": 0.1943359375,
|
233 |
+
"learning_rate": 1.1326608169920373e-08,
|
234 |
+
"loss": 0.6087,
|
235 |
"step": 145
|
236 |
},
|
237 |
{
|
238 |
+
"epoch": 2.9696969696969697,
|
239 |
+
"eval_loss": 0.6245681643486023,
|
240 |
+
"eval_runtime": 17.3067,
|
241 |
+
"eval_samples_per_second": 2.485,
|
242 |
+
"eval_steps_per_second": 0.347,
|
243 |
+
"step": 147
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
244 |
},
|
245 |
{
|
246 |
+
"epoch": 2.9696969696969697,
|
247 |
+
"step": 147,
|
248 |
+
"total_flos": 2.0566538541072384e+17,
|
249 |
+
"train_loss": 0.7671454966473742,
|
250 |
+
"train_runtime": 1686.4021,
|
251 |
+
"train_samples_per_second": 0.699,
|
252 |
+
"train_steps_per_second": 0.087
|
253 |
}
|
254 |
],
|
255 |
"logging_steps": 5,
|
256 |
+
"max_steps": 147,
|
257 |
"num_input_tokens_seen": 0,
|
258 |
"num_train_epochs": 3,
|
259 |
"save_steps": 100,
|
|
|
269 |
"attributes": {}
|
270 |
}
|
271 |
},
|
272 |
+
"total_flos": 2.0566538541072384e+17,
|
273 |
"train_batch_size": 4,
|
274 |
"trial_name": null,
|
275 |
"trial_params": null
|