Model save
Browse files- README.md +4 -9
- all_results.json +4 -9
- config.json +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- runs/Aug01_17-23-33_ale-distillm-8-0-0/events.out.tfevents.1722529424.ale-distillm-8-0-0.201606.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +116 -116
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,15 +1,10 @@
|
|
1 |
---
|
2 |
-
base_model: data/gemma-2b
|
3 |
tags:
|
4 |
-
- alignment-handbook
|
5 |
-
- trl
|
6 |
-
- sft
|
7 |
-
- generated_from_trainer
|
8 |
- trl
|
9 |
- sft
|
10 |
- generated_from_trainer
|
11 |
datasets:
|
12 |
-
-
|
13 |
model-index:
|
14 |
- name: zephyr-2b-gemma-dft-debug
|
15 |
results: []
|
@@ -20,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
# zephyr-2b-gemma-dft-debug
|
22 |
|
23 |
-
This model
|
24 |
It achieves the following results on the evaluation set:
|
25 |
-
- Loss:
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -56,7 +51,7 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
|:-------------:|:------:|:----:|:---------------:|
|
59 |
-
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
tags:
|
|
|
|
|
|
|
|
|
3 |
- trl
|
4 |
- sft
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- generator
|
8 |
model-index:
|
9 |
- name: zephyr-2b-gemma-dft-debug
|
10 |
results: []
|
|
|
15 |
|
16 |
# zephyr-2b-gemma-dft-debug
|
17 |
|
18 |
+
This model was trained from scratch on the generator dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 5.7530
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 5.7909 | 0.9982 | 270 | 5.7530 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,14 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 0.9981515711645101,
|
3 |
-
"eval_loss": 2957.430908203125,
|
4 |
-
"eval_runtime": 422.6685,
|
5 |
-
"eval_samples": 750,
|
6 |
-
"eval_samples_per_second": 2.297,
|
7 |
-
"eval_steps_per_second": 0.289,
|
8 |
"total_flos": 5.260333472022528e+16,
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 6750,
|
12 |
-
"train_samples_per_second": 3.
|
13 |
-
"train_steps_per_second": 0.
|
14 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.9981515711645101,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 5.260333472022528e+16,
|
4 |
+
"train_loss": 7.3803352285314485,
|
5 |
+
"train_runtime": 2516.7229,
|
6 |
"train_samples": 6750,
|
7 |
+
"train_samples_per_second": 3.438,
|
8 |
+
"train_steps_per_second": 0.107
|
9 |
}
|
config.json
CHANGED
@@ -24,6 +24,6 @@
|
|
24 |
"rope_theta": 10000.0,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.43.3",
|
27 |
-
"use_cache":
|
28 |
"vocab_size": 256000
|
29 |
}
|
|
|
24 |
"rope_theta": 10000.0,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
"transformers_version": "4.43.3",
|
27 |
+
"use_cache": false,
|
28 |
"vocab_size": 256000
|
29 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4945242264
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cc245fefab97d950d4759fe13ab557dd93524fd58102bb040e57fbe13709f50
|
3 |
size 4945242264
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 67121608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c9ca3299801e9176ca770f65c661ccc72a5b519bf063d407a2606c996c2efcd
|
3 |
size 67121608
|
runs/Aug01_17-23-33_ale-distillm-8-0-0/events.out.tfevents.1722529424.ale-distillm-8-0-0.201606.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:428c3dea3b10f73a541d7a5192b95a7c3b285974d5e707d4805a0fb9f5756639
|
3 |
+
size 17099
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 0.9981515711645101,
|
3 |
"total_flos": 5.260333472022528e+16,
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 6750,
|
7 |
-
"train_samples_per_second": 3.
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.9981515711645101,
|
3 |
"total_flos": 5.260333472022528e+16,
|
4 |
+
"train_loss": 7.3803352285314485,
|
5 |
+
"train_runtime": 2516.7229,
|
6 |
"train_samples": 6750,
|
7 |
+
"train_samples_per_second": 3.438,
|
8 |
+
"train_steps_per_second": 0.107
|
9 |
}
|
trainer_state.json
CHANGED
@@ -10,398 +10,398 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.018484288354898338,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 3.7037037037037037e-06,
|
15 |
-
"loss":
|
16 |
"step": 5
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.036968576709796676,
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 7.4074074074074075e-06,
|
22 |
-
"loss":
|
23 |
"step": 10
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.05545286506469501,
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 1.1111111111111113e-05,
|
29 |
-
"loss":
|
30 |
"step": 15
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.07393715341959335,
|
34 |
-
"grad_norm":
|
35 |
"learning_rate": 1.4814814814814815e-05,
|
36 |
-
"loss":
|
37 |
"step": 20
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.09242144177449169,
|
41 |
-
"grad_norm":
|
42 |
"learning_rate": 1.851851851851852e-05,
|
43 |
-
"loss":
|
44 |
"step": 25
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.11090573012939002,
|
48 |
-
"grad_norm":
|
49 |
"learning_rate": 1.9992479525042305e-05,
|
50 |
-
"loss":
|
51 |
"step": 30
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.12939001848428835,
|
55 |
-
"grad_norm":
|
56 |
"learning_rate": 1.9946562024066018e-05,
|
57 |
-
"loss":
|
58 |
"step": 35
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.1478743068391867,
|
62 |
-
"grad_norm":
|
63 |
"learning_rate": 1.9859096633447965e-05,
|
64 |
-
"loss":
|
65 |
"step": 40
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.16635859519408502,
|
69 |
-
"grad_norm":
|
70 |
"learning_rate": 1.973044870579824e-05,
|
71 |
-
"loss":
|
72 |
"step": 45
|
73 |
},
|
74 |
{
|
75 |
"epoch": 0.18484288354898337,
|
76 |
-
"grad_norm":
|
77 |
"learning_rate": 1.95611556177388e-05,
|
78 |
-
"loss":
|
79 |
"step": 50
|
80 |
},
|
81 |
{
|
82 |
"epoch": 0.2033271719038817,
|
83 |
-
"grad_norm":
|
84 |
"learning_rate": 1.93519245252219e-05,
|
85 |
-
"loss":
|
86 |
"step": 55
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.22181146025878004,
|
90 |
-
"grad_norm":
|
91 |
"learning_rate": 1.9103629409661468e-05,
|
92 |
-
"loss":
|
93 |
"step": 60
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.24029574861367836,
|
97 |
-
"grad_norm":
|
98 |
"learning_rate": 1.881730742721608e-05,
|
99 |
-
"loss":
|
100 |
"step": 65
|
101 |
},
|
102 |
{
|
103 |
"epoch": 0.2587800369685767,
|
104 |
-
"grad_norm":
|
105 |
"learning_rate": 1.8494154576472976e-05,
|
106 |
-
"loss":
|
107 |
"step": 70
|
108 |
},
|
109 |
{
|
110 |
"epoch": 0.27726432532347506,
|
111 |
-
"grad_norm":
|
112 |
"learning_rate": 1.8135520702629677e-05,
|
113 |
-
"loss":
|
114 |
"step": 75
|
115 |
},
|
116 |
{
|
117 |
"epoch": 0.2957486136783734,
|
118 |
-
"grad_norm":
|
119 |
"learning_rate": 1.7742903859041324e-05,
|
120 |
-
"loss":
|
121 |
"step": 80
|
122 |
},
|
123 |
{
|
124 |
"epoch": 0.3142329020332717,
|
125 |
-
"grad_norm":
|
126 |
"learning_rate": 1.7317944049686125e-05,
|
127 |
-
"loss":
|
128 |
"step": 85
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.33271719038817005,
|
132 |
-
"grad_norm":
|
133 |
"learning_rate": 1.686241637868734e-05,
|
134 |
-
"loss":
|
135 |
"step": 90
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.3512014787430684,
|
139 |
-
"grad_norm":
|
140 |
"learning_rate": 1.637822363550706e-05,
|
141 |
-
"loss":
|
142 |
"step": 95
|
143 |
},
|
144 |
{
|
145 |
"epoch": 0.36968576709796674,
|
146 |
-
"grad_norm":
|
147 |
"learning_rate": 1.586738834678418e-05,
|
148 |
-
"loss":
|
149 |
"step": 100
|
150 |
},
|
151 |
{
|
152 |
"epoch": 0.38817005545286504,
|
153 |
-
"grad_norm":
|
154 |
"learning_rate": 1.5332044328016916e-05,
|
155 |
-
"loss":
|
156 |
"step": 105
|
157 |
},
|
158 |
{
|
159 |
"epoch": 0.4066543438077634,
|
160 |
-
"grad_norm":
|
161 |
"learning_rate": 1.4774427770379492e-05,
|
162 |
-
"loss":
|
163 |
"step": 110
|
164 |
},
|
165 |
{
|
166 |
"epoch": 0.42513863216266173,
|
167 |
-
"grad_norm":
|
168 |
"learning_rate": 1.4196867899904292e-05,
|
169 |
-
"loss":
|
170 |
"step": 115
|
171 |
},
|
172 |
{
|
173 |
"epoch": 0.4436229205175601,
|
174 |
-
"grad_norm":
|
175 |
"learning_rate": 1.3601777248047105e-05,
|
176 |
-
"loss":
|
177 |
"step": 120
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.46210720887245843,
|
181 |
-
"grad_norm":
|
182 |
"learning_rate": 1.2991641574276419e-05,
|
183 |
-
"loss":
|
184 |
"step": 125
|
185 |
},
|
186 |
{
|
187 |
"epoch": 0.4805914972273567,
|
188 |
-
"grad_norm":
|
189 |
"learning_rate": 1.2369009482781191e-05,
|
190 |
-
"loss":
|
191 |
"step": 130
|
192 |
},
|
193 |
{
|
194 |
"epoch": 0.49907578558225507,
|
195 |
-
"grad_norm":
|
196 |
"learning_rate": 1.1736481776669307e-05,
|
197 |
-
"loss":
|
198 |
"step": 135
|
199 |
},
|
200 |
{
|
201 |
"epoch": 0.5175600739371534,
|
202 |
-
"grad_norm":
|
203 |
"learning_rate": 1.1096700594125318e-05,
|
204 |
-
"loss":
|
205 |
"step": 140
|
206 |
},
|
207 |
{
|
208 |
"epoch": 0.5360443622920518,
|
209 |
-
"grad_norm":
|
210 |
"learning_rate": 1.0452338371907065e-05,
|
211 |
-
"loss":
|
212 |
"step": 145
|
213 |
},
|
214 |
{
|
215 |
"epoch": 0.5545286506469501,
|
216 |
-
"grad_norm":
|
217 |
"learning_rate": 9.806086682281759e-06,
|
218 |
-
"loss":
|
219 |
"step": 150
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.5730129390018485,
|
223 |
-
"grad_norm":
|
224 |
"learning_rate": 9.160644990030932e-06,
|
225 |
-
"loss":
|
226 |
"step": 155
|
227 |
},
|
228 |
{
|
229 |
"epoch": 0.5914972273567468,
|
230 |
-
"grad_norm":
|
231 |
"learning_rate": 8.518709376487515e-06,
|
232 |
-
"loss":
|
233 |
"step": 160
|
234 |
},
|
235 |
{
|
236 |
"epoch": 0.609981515711645,
|
237 |
-
"grad_norm":
|
238 |
"learning_rate": 7.882961277705897e-06,
|
239 |
-
"loss":
|
240 |
"step": 165
|
241 |
},
|
242 |
{
|
243 |
"epoch": 0.6284658040665434,
|
244 |
-
"grad_norm":
|
245 |
"learning_rate": 7.256056283806987e-06,
|
246 |
-
"loss":
|
247 |
"step": 170
|
248 |
},
|
249 |
{
|
250 |
"epoch": 0.6469500924214417,
|
251 |
-
"grad_norm":
|
252 |
"learning_rate": 6.640613046284581e-06,
|
253 |
-
"loss":
|
254 |
"step": 175
|
255 |
},
|
256 |
{
|
257 |
"epoch": 0.6654343807763401,
|
258 |
-
"grad_norm":
|
259 |
"learning_rate": 6.039202339608432e-06,
|
260 |
-
"loss":
|
261 |
"step": 180
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.6839186691312384,
|
265 |
-
"grad_norm":
|
266 |
"learning_rate": 5.454336322814995e-06,
|
267 |
-
"loss":
|
268 |
"step": 185
|
269 |
},
|
270 |
{
|
271 |
"epoch": 0.7024029574861368,
|
272 |
-
"grad_norm":
|
273 |
"learning_rate": 4.888458045941269e-06,
|
274 |
-
"loss":
|
275 |
"step": 190
|
276 |
},
|
277 |
{
|
278 |
"epoch": 0.7208872458410351,
|
279 |
-
"grad_norm":
|
280 |
"learning_rate": 4.343931245134616e-06,
|
281 |
-
"loss":
|
282 |
"step": 195
|
283 |
},
|
284 |
{
|
285 |
"epoch": 0.7393715341959335,
|
286 |
-
"grad_norm":
|
287 |
"learning_rate": 3.823030469065431e-06,
|
288 |
-
"loss":
|
289 |
"step": 200
|
290 |
},
|
291 |
{
|
292 |
"epoch": 0.7578558225508318,
|
293 |
-
"grad_norm":
|
294 |
"learning_rate": 3.3279315778858034e-06,
|
295 |
-
"loss":
|
296 |
"step": 205
|
297 |
},
|
298 |
{
|
299 |
"epoch": 0.7763401109057301,
|
300 |
-
"grad_norm":
|
301 |
"learning_rate": 2.8607026544210115e-06,
|
302 |
-
"loss":
|
303 |
"step": 210
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.7948243992606284,
|
307 |
-
"grad_norm":
|
308 |
"learning_rate": 2.423295365558821e-06,
|
309 |
-
"loss":
|
310 |
"step": 215
|
311 |
},
|
312 |
{
|
313 |
"epoch": 0.8133086876155268,
|
314 |
-
"grad_norm":
|
315 |
"learning_rate": 2.01753680992107e-06,
|
316 |
-
"loss":
|
317 |
"step": 220
|
318 |
},
|
319 |
{
|
320 |
"epoch": 0.8317929759704251,
|
321 |
-
"grad_norm":
|
322 |
"learning_rate": 1.6451218858706374e-06,
|
323 |
-
"loss":
|
324 |
"step": 225
|
325 |
},
|
326 |
{
|
327 |
"epoch": 0.8502772643253235,
|
328 |
-
"grad_norm":
|
329 |
"learning_rate": 1.307606211733522e-06,
|
330 |
-
"loss":
|
331 |
"step": 230
|
332 |
},
|
333 |
{
|
334 |
"epoch": 0.8687615526802218,
|
335 |
-
"grad_norm":
|
336 |
"learning_rate": 1.0063996278090704e-06,
|
337 |
-
"loss":
|
338 |
"step": 235
|
339 |
},
|
340 |
{
|
341 |
"epoch": 0.8872458410351202,
|
342 |
-
"grad_norm":
|
343 |
"learning_rate": 7.427603073110967e-07,
|
344 |
-
"loss":
|
345 |
"step": 240
|
346 |
},
|
347 |
{
|
348 |
"epoch": 0.9057301293900185,
|
349 |
-
"grad_norm":
|
350 |
"learning_rate": 5.177895008392353e-07,
|
351 |
-
"loss":
|
352 |
"step": 245
|
353 |
},
|
354 |
{
|
355 |
"epoch": 0.9242144177449169,
|
356 |
-
"grad_norm":
|
357 |
"learning_rate": 3.3242693633337986e-07,
|
358 |
-
"loss":
|
359 |
"step": 250
|
360 |
},
|
361 |
{
|
362 |
"epoch": 0.9426987060998152,
|
363 |
-
"grad_norm":
|
364 |
"learning_rate": 1.874468937261531e-07,
|
365 |
-
"loss":
|
366 |
"step": 255
|
367 |
},
|
368 |
{
|
369 |
"epoch": 0.9611829944547134,
|
370 |
-
"grad_norm":
|
371 |
"learning_rate": 8.345497068998897e-08,
|
372 |
-
"loss":
|
373 |
"step": 260
|
374 |
},
|
375 |
{
|
376 |
"epoch": 0.9796672828096118,
|
377 |
-
"grad_norm":
|
378 |
"learning_rate": 2.088555298867978e-08,
|
379 |
-
"loss":
|
380 |
"step": 265
|
381 |
},
|
382 |
{
|
383 |
"epoch": 0.9981515711645101,
|
384 |
-
"grad_norm":
|
385 |
"learning_rate": 0.0,
|
386 |
-
"loss":
|
387 |
"step": 270
|
388 |
},
|
389 |
{
|
390 |
"epoch": 0.9981515711645101,
|
391 |
-
"eval_loss":
|
392 |
-
"eval_runtime":
|
393 |
-
"eval_samples_per_second": 2.
|
394 |
-
"eval_steps_per_second": 0.
|
395 |
"step": 270
|
396 |
},
|
397 |
{
|
398 |
"epoch": 0.9981515711645101,
|
399 |
"step": 270,
|
400 |
"total_flos": 5.260333472022528e+16,
|
401 |
-
"train_loss":
|
402 |
-
"train_runtime":
|
403 |
-
"train_samples_per_second": 3.
|
404 |
-
"train_steps_per_second": 0.
|
405 |
}
|
406 |
],
|
407 |
"logging_steps": 5,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.018484288354898338,
|
13 |
+
"grad_norm": 422.0,
|
14 |
"learning_rate": 3.7037037037037037e-06,
|
15 |
+
"loss": 20.7086,
|
16 |
"step": 5
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.036968576709796676,
|
20 |
+
"grad_norm": 185.0,
|
21 |
"learning_rate": 7.4074074074074075e-06,
|
22 |
+
"loss": 19.253,
|
23 |
"step": 10
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.05545286506469501,
|
27 |
+
"grad_norm": 147.0,
|
28 |
"learning_rate": 1.1111111111111113e-05,
|
29 |
+
"loss": 16.7138,
|
30 |
"step": 15
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.07393715341959335,
|
34 |
+
"grad_norm": 62.75,
|
35 |
"learning_rate": 1.4814814814814815e-05,
|
36 |
+
"loss": 14.0999,
|
37 |
"step": 20
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.09242144177449169,
|
41 |
+
"grad_norm": 46.25,
|
42 |
"learning_rate": 1.851851851851852e-05,
|
43 |
+
"loss": 11.9456,
|
44 |
"step": 25
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.11090573012939002,
|
48 |
+
"grad_norm": 49.75,
|
49 |
"learning_rate": 1.9992479525042305e-05,
|
50 |
+
"loss": 10.3044,
|
51 |
"step": 30
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.12939001848428835,
|
55 |
+
"grad_norm": 88.5,
|
56 |
"learning_rate": 1.9946562024066018e-05,
|
57 |
+
"loss": 9.602,
|
58 |
"step": 35
|
59 |
},
|
60 |
{
|
61 |
"epoch": 0.1478743068391867,
|
62 |
+
"grad_norm": 49.25,
|
63 |
"learning_rate": 1.9859096633447965e-05,
|
64 |
+
"loss": 9.1612,
|
65 |
"step": 40
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.16635859519408502,
|
69 |
+
"grad_norm": 114.0,
|
70 |
"learning_rate": 1.973044870579824e-05,
|
71 |
+
"loss": 8.5549,
|
72 |
"step": 45
|
73 |
},
|
74 |
{
|
75 |
"epoch": 0.18484288354898337,
|
76 |
+
"grad_norm": 54.75,
|
77 |
"learning_rate": 1.95611556177388e-05,
|
78 |
+
"loss": 8.3168,
|
79 |
"step": 50
|
80 |
},
|
81 |
{
|
82 |
"epoch": 0.2033271719038817,
|
83 |
+
"grad_norm": 16.875,
|
84 |
"learning_rate": 1.93519245252219e-05,
|
85 |
+
"loss": 7.8042,
|
86 |
"step": 55
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.22181146025878004,
|
90 |
+
"grad_norm": 55.75,
|
91 |
"learning_rate": 1.9103629409661468e-05,
|
92 |
+
"loss": 7.4335,
|
93 |
"step": 60
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.24029574861367836,
|
97 |
+
"grad_norm": 17.5,
|
98 |
"learning_rate": 1.881730742721608e-05,
|
99 |
+
"loss": 7.4047,
|
100 |
"step": 65
|
101 |
},
|
102 |
{
|
103 |
"epoch": 0.2587800369685767,
|
104 |
+
"grad_norm": 52.5,
|
105 |
"learning_rate": 1.8494154576472976e-05,
|
106 |
+
"loss": 7.0682,
|
107 |
"step": 70
|
108 |
},
|
109 |
{
|
110 |
"epoch": 0.27726432532347506,
|
111 |
+
"grad_norm": 69.5,
|
112 |
"learning_rate": 1.8135520702629677e-05,
|
113 |
+
"loss": 7.1519,
|
114 |
"step": 75
|
115 |
},
|
116 |
{
|
117 |
"epoch": 0.2957486136783734,
|
118 |
+
"grad_norm": 23.125,
|
119 |
"learning_rate": 1.7742903859041324e-05,
|
120 |
+
"loss": 6.9284,
|
121 |
"step": 80
|
122 |
},
|
123 |
{
|
124 |
"epoch": 0.3142329020332717,
|
125 |
+
"grad_norm": 17.25,
|
126 |
"learning_rate": 1.7317944049686125e-05,
|
127 |
+
"loss": 6.723,
|
128 |
"step": 85
|
129 |
},
|
130 |
{
|
131 |
"epoch": 0.33271719038817005,
|
132 |
+
"grad_norm": 103.5,
|
133 |
"learning_rate": 1.686241637868734e-05,
|
134 |
+
"loss": 6.6468,
|
135 |
"step": 90
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.3512014787430684,
|
139 |
+
"grad_norm": 17.625,
|
140 |
"learning_rate": 1.637822363550706e-05,
|
141 |
+
"loss": 6.5427,
|
142 |
"step": 95
|
143 |
},
|
144 |
{
|
145 |
"epoch": 0.36968576709796674,
|
146 |
+
"grad_norm": 15.6875,
|
147 |
"learning_rate": 1.586738834678418e-05,
|
148 |
+
"loss": 6.3795,
|
149 |
"step": 100
|
150 |
},
|
151 |
{
|
152 |
"epoch": 0.38817005545286504,
|
153 |
+
"grad_norm": 17.875,
|
154 |
"learning_rate": 1.5332044328016916e-05,
|
155 |
+
"loss": 6.4565,
|
156 |
"step": 105
|
157 |
},
|
158 |
{
|
159 |
"epoch": 0.4066543438077634,
|
160 |
+
"grad_norm": 68.0,
|
161 |
"learning_rate": 1.4774427770379492e-05,
|
162 |
+
"loss": 6.416,
|
163 |
"step": 110
|
164 |
},
|
165 |
{
|
166 |
"epoch": 0.42513863216266173,
|
167 |
+
"grad_norm": 71.5,
|
168 |
"learning_rate": 1.4196867899904292e-05,
|
169 |
+
"loss": 6.2522,
|
170 |
"step": 115
|
171 |
},
|
172 |
{
|
173 |
"epoch": 0.4436229205175601,
|
174 |
+
"grad_norm": 28.875,
|
175 |
"learning_rate": 1.3601777248047105e-05,
|
176 |
+
"loss": 6.0918,
|
177 |
"step": 120
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.46210720887245843,
|
181 |
+
"grad_norm": 25.75,
|
182 |
"learning_rate": 1.2991641574276419e-05,
|
183 |
+
"loss": 6.0943,
|
184 |
"step": 125
|
185 |
},
|
186 |
{
|
187 |
"epoch": 0.4805914972273567,
|
188 |
+
"grad_norm": 24.375,
|
189 |
"learning_rate": 1.2369009482781191e-05,
|
190 |
+
"loss": 6.0615,
|
191 |
"step": 130
|
192 |
},
|
193 |
{
|
194 |
"epoch": 0.49907578558225507,
|
195 |
+
"grad_norm": 53.0,
|
196 |
"learning_rate": 1.1736481776669307e-05,
|
197 |
+
"loss": 5.9591,
|
198 |
"step": 135
|
199 |
},
|
200 |
{
|
201 |
"epoch": 0.5175600739371534,
|
202 |
+
"grad_norm": 93.5,
|
203 |
"learning_rate": 1.1096700594125318e-05,
|
204 |
+
"loss": 6.0178,
|
205 |
"step": 140
|
206 |
},
|
207 |
{
|
208 |
"epoch": 0.5360443622920518,
|
209 |
+
"grad_norm": 14.0625,
|
210 |
"learning_rate": 1.0452338371907065e-05,
|
211 |
+
"loss": 5.8597,
|
212 |
"step": 145
|
213 |
},
|
214 |
{
|
215 |
"epoch": 0.5545286506469501,
|
216 |
+
"grad_norm": 102.0,
|
217 |
"learning_rate": 9.806086682281759e-06,
|
218 |
+
"loss": 5.8942,
|
219 |
"step": 150
|
220 |
},
|
221 |
{
|
222 |
"epoch": 0.5730129390018485,
|
223 |
+
"grad_norm": 30.125,
|
224 |
"learning_rate": 9.160644990030932e-06,
|
225 |
+
"loss": 5.9999,
|
226 |
"step": 155
|
227 |
},
|
228 |
{
|
229 |
"epoch": 0.5914972273567468,
|
230 |
+
"grad_norm": 23.25,
|
231 |
"learning_rate": 8.518709376487515e-06,
|
232 |
+
"loss": 5.9019,
|
233 |
"step": 160
|
234 |
},
|
235 |
{
|
236 |
"epoch": 0.609981515711645,
|
237 |
+
"grad_norm": 56.0,
|
238 |
"learning_rate": 7.882961277705897e-06,
|
239 |
+
"loss": 5.8274,
|
240 |
"step": 165
|
241 |
},
|
242 |
{
|
243 |
"epoch": 0.6284658040665434,
|
244 |
+
"grad_norm": 10.1875,
|
245 |
"learning_rate": 7.256056283806987e-06,
|
246 |
+
"loss": 5.9167,
|
247 |
"step": 170
|
248 |
},
|
249 |
{
|
250 |
"epoch": 0.6469500924214417,
|
251 |
+
"grad_norm": 26.75,
|
252 |
"learning_rate": 6.640613046284581e-06,
|
253 |
+
"loss": 5.9097,
|
254 |
"step": 175
|
255 |
},
|
256 |
{
|
257 |
"epoch": 0.6654343807763401,
|
258 |
+
"grad_norm": 11.5625,
|
259 |
"learning_rate": 6.039202339608432e-06,
|
260 |
+
"loss": 5.6327,
|
261 |
"step": 180
|
262 |
},
|
263 |
{
|
264 |
"epoch": 0.6839186691312384,
|
265 |
+
"grad_norm": 26.75,
|
266 |
"learning_rate": 5.454336322814995e-06,
|
267 |
+
"loss": 5.6804,
|
268 |
"step": 185
|
269 |
},
|
270 |
{
|
271 |
"epoch": 0.7024029574861368,
|
272 |
+
"grad_norm": 30.375,
|
273 |
"learning_rate": 4.888458045941269e-06,
|
274 |
+
"loss": 5.7316,
|
275 |
"step": 190
|
276 |
},
|
277 |
{
|
278 |
"epoch": 0.7208872458410351,
|
279 |
+
"grad_norm": 39.5,
|
280 |
"learning_rate": 4.343931245134616e-06,
|
281 |
+
"loss": 5.7299,
|
282 |
"step": 195
|
283 |
},
|
284 |
{
|
285 |
"epoch": 0.7393715341959335,
|
286 |
+
"grad_norm": 11.75,
|
287 |
"learning_rate": 3.823030469065431e-06,
|
288 |
+
"loss": 5.6982,
|
289 |
"step": 200
|
290 |
},
|
291 |
{
|
292 |
"epoch": 0.7578558225508318,
|
293 |
+
"grad_norm": 20.625,
|
294 |
"learning_rate": 3.3279315778858034e-06,
|
295 |
+
"loss": 5.862,
|
296 |
"step": 205
|
297 |
},
|
298 |
{
|
299 |
"epoch": 0.7763401109057301,
|
300 |
+
"grad_norm": 50.75,
|
301 |
"learning_rate": 2.8607026544210115e-06,
|
302 |
+
"loss": 5.7507,
|
303 |
"step": 210
|
304 |
},
|
305 |
{
|
306 |
"epoch": 0.7948243992606284,
|
307 |
+
"grad_norm": 49.75,
|
308 |
"learning_rate": 2.423295365558821e-06,
|
309 |
+
"loss": 5.7101,
|
310 |
"step": 215
|
311 |
},
|
312 |
{
|
313 |
"epoch": 0.8133086876155268,
|
314 |
+
"grad_norm": 14.4375,
|
315 |
"learning_rate": 2.01753680992107e-06,
|
316 |
+
"loss": 5.8428,
|
317 |
"step": 220
|
318 |
},
|
319 |
{
|
320 |
"epoch": 0.8317929759704251,
|
321 |
+
"grad_norm": 34.75,
|
322 |
"learning_rate": 1.6451218858706374e-06,
|
323 |
+
"loss": 5.7162,
|
324 |
"step": 225
|
325 |
},
|
326 |
{
|
327 |
"epoch": 0.8502772643253235,
|
328 |
+
"grad_norm": 47.0,
|
329 |
"learning_rate": 1.307606211733522e-06,
|
330 |
+
"loss": 5.6621,
|
331 |
"step": 230
|
332 |
},
|
333 |
{
|
334 |
"epoch": 0.8687615526802218,
|
335 |
+
"grad_norm": 12.875,
|
336 |
"learning_rate": 1.0063996278090704e-06,
|
337 |
+
"loss": 5.6616,
|
338 |
"step": 235
|
339 |
},
|
340 |
{
|
341 |
"epoch": 0.8872458410351202,
|
342 |
+
"grad_norm": 13.1875,
|
343 |
"learning_rate": 7.427603073110967e-07,
|
344 |
+
"loss": 5.8559,
|
345 |
"step": 240
|
346 |
},
|
347 |
{
|
348 |
"epoch": 0.9057301293900185,
|
349 |
+
"grad_norm": 7.96875,
|
350 |
"learning_rate": 5.177895008392353e-07,
|
351 |
+
"loss": 5.7149,
|
352 |
"step": 245
|
353 |
},
|
354 |
{
|
355 |
"epoch": 0.9242144177449169,
|
356 |
+
"grad_norm": 61.75,
|
357 |
"learning_rate": 3.3242693633337986e-07,
|
358 |
+
"loss": 5.9011,
|
359 |
"step": 250
|
360 |
},
|
361 |
{
|
362 |
"epoch": 0.9426987060998152,
|
363 |
+
"grad_norm": 13.625,
|
364 |
"learning_rate": 1.874468937261531e-07,
|
365 |
+
"loss": 5.685,
|
366 |
"step": 255
|
367 |
},
|
368 |
{
|
369 |
"epoch": 0.9611829944547134,
|
370 |
+
"grad_norm": 15.6875,
|
371 |
"learning_rate": 8.345497068998897e-08,
|
372 |
+
"loss": 5.7765,
|
373 |
"step": 260
|
374 |
},
|
375 |
{
|
376 |
"epoch": 0.9796672828096118,
|
377 |
+
"grad_norm": 18.5,
|
378 |
"learning_rate": 2.088555298867978e-08,
|
379 |
+
"loss": 5.734,
|
380 |
"step": 265
|
381 |
},
|
382 |
{
|
383 |
"epoch": 0.9981515711645101,
|
384 |
+
"grad_norm": 28.25,
|
385 |
"learning_rate": 0.0,
|
386 |
+
"loss": 5.7909,
|
387 |
"step": 270
|
388 |
},
|
389 |
{
|
390 |
"epoch": 0.9981515711645101,
|
391 |
+
"eval_loss": 5.75302791595459,
|
392 |
+
"eval_runtime": 376.2306,
|
393 |
+
"eval_samples_per_second": 2.581,
|
394 |
+
"eval_steps_per_second": 0.324,
|
395 |
"step": 270
|
396 |
},
|
397 |
{
|
398 |
"epoch": 0.9981515711645101,
|
399 |
"step": 270,
|
400 |
"total_flos": 5.260333472022528e+16,
|
401 |
+
"train_loss": 7.3803352285314485,
|
402 |
+
"train_runtime": 2516.7229,
|
403 |
+
"train_samples_per_second": 3.438,
|
404 |
+
"train_steps_per_second": 0.107
|
405 |
}
|
406 |
],
|
407 |
"logging_steps": 5,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa1e4059799b3fd2bc19d9b9bdbb3a0911a6dc0077207bdb4e02f055fcee2618
|
3 |
size 5368
|