Training in progress, step 25, checkpoint
Browse files- last-checkpoint/adapter_config.json +5 -5
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +59 -242
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"v_proj",
|
24 |
-
"up_proj",
|
25 |
-
"down_proj",
|
26 |
-
"k_proj",
|
27 |
"o_proj",
|
|
|
|
|
28 |
"q_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
23 |
"o_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_proj",
|
26 |
"q_proj",
|
27 |
+
"v_proj",
|
28 |
+
"up_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f99bc2c659cbdb0992e1a6091af6809085d19bc2edf14ae50e83db113fa5fcb4
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a69589c53894362eff20f58966ceb7c4fe896fd6b42431e73043324550d40fb
|
3 |
size 640009682
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:080926b6fad49ee6b44ff32b6c88dcf1a54560ba5269dd472628f349a0e91734
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97e6f18cc73c49e1b8ffd8c02656630b4c1ab425d84004ddab33c7d1ac32ba3f
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a884ce65b2106c5faada4bc542ca8806b383884d40a67a36a96d4d9a59de34ad
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1601b0f6af9e056067f5465ae47446902063858add4122d3355cea2b50d7a490
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 25,
|
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": 0.00026683788764457196,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 5e-05,
|
15 |
"loss": 99.4744,
|
16 |
"step": 1
|
@@ -18,369 +18,186 @@
|
|
18 |
{
|
19 |
"epoch": 0.00026683788764457196,
|
20 |
"eval_loss": 3.534377336502075,
|
21 |
-
"eval_runtime": 2.
|
22 |
-
"eval_samples_per_second": 17.
|
23 |
-
"eval_steps_per_second": 4.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0005336757752891439,
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 0.0001,
|
30 |
"loss": 103.3411,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0008005136629337158,
|
35 |
-
"grad_norm":
|
36 |
"learning_rate": 9.990365154573717e-05,
|
37 |
-
"loss": 101.
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0010673515505782878,
|
42 |
-
"grad_norm":
|
43 |
"learning_rate": 9.961501876182148e-05,
|
44 |
-
"loss": 102.
|
45 |
"step": 4
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.0013341894382228596,
|
49 |
-
"grad_norm":
|
50 |
"learning_rate": 9.913533761814537e-05,
|
51 |
-
"loss": 98.
|
52 |
"step": 5
|
53 |
},
|
54 |
{
|
55 |
"epoch": 0.0016010273258674317,
|
56 |
-
"grad_norm":
|
57 |
"learning_rate": 9.846666218300807e-05,
|
58 |
-
"loss": 96.
|
59 |
"step": 6
|
60 |
},
|
61 |
{
|
62 |
"epoch": 0.0018678652135120035,
|
63 |
-
"grad_norm":
|
64 |
"learning_rate": 9.761185582727977e-05,
|
65 |
-
"loss": 94.
|
66 |
"step": 7
|
67 |
},
|
68 |
{
|
69 |
"epoch": 0.0021347031011565757,
|
70 |
-
"grad_norm":
|
71 |
"learning_rate": 9.657457896300791e-05,
|
72 |
-
"loss": 93.
|
73 |
"step": 8
|
74 |
},
|
75 |
{
|
76 |
"epoch": 0.0024015409888011475,
|
77 |
-
"grad_norm":
|
78 |
"learning_rate": 9.535927336897098e-05,
|
79 |
-
"loss": 91.
|
80 |
"step": 9
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.0026683788764457193,
|
84 |
-
"grad_norm":
|
85 |
"learning_rate": 9.397114317029975e-05,
|
86 |
-
"loss": 93.
|
87 |
"step": 10
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.002935216764090291,
|
91 |
-
"grad_norm":
|
92 |
"learning_rate": 9.241613255361455e-05,
|
93 |
-
"loss": 93.
|
94 |
"step": 11
|
95 |
},
|
96 |
{
|
97 |
"epoch": 0.0032020546517348633,
|
98 |
-
"grad_norm":
|
99 |
"learning_rate": 9.070090031310558e-05,
|
100 |
-
"loss": 100.
|
101 |
"step": 12
|
102 |
},
|
103 |
{
|
104 |
"epoch": 0.003468892539379435,
|
105 |
-
"grad_norm":
|
106 |
"learning_rate": 8.883279133655399e-05,
|
107 |
-
"loss": 103.
|
108 |
"step": 13
|
109 |
},
|
110 |
{
|
111 |
"epoch": 0.003735730427024007,
|
112 |
-
"grad_norm":
|
113 |
"learning_rate": 8.681980515339464e-05,
|
114 |
-
"loss": 90.
|
115 |
"step": 14
|
116 |
},
|
117 |
{
|
118 |
"epoch": 0.004002568314668579,
|
119 |
-
"grad_norm":
|
120 |
"learning_rate": 8.467056167950311e-05,
|
121 |
-
"loss":
|
122 |
"step": 15
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.004269406202313151,
|
126 |
-
"grad_norm":
|
127 |
"learning_rate": 8.239426430539243e-05,
|
128 |
-
"loss": 86.
|
129 |
"step": 16
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.004536244089957723,
|
133 |
-
"grad_norm":
|
134 |
"learning_rate": 8.000066048588211e-05,
|
135 |
-
"loss": 87.
|
136 |
"step": 17
|
137 |
},
|
138 |
{
|
139 |
"epoch": 0.004803081977602295,
|
140 |
-
"grad_norm":
|
141 |
"learning_rate": 7.75e-05,
|
142 |
-
"loss": 87.
|
143 |
"step": 18
|
144 |
},
|
145 |
{
|
146 |
"epoch": 0.005069919865246866,
|
147 |
-
"grad_norm":
|
148 |
"learning_rate": 7.490299105985507e-05,
|
149 |
-
"loss": 87.
|
150 |
"step": 19
|
151 |
},
|
152 |
{
|
153 |
"epoch": 0.0053367577528914386,
|
154 |
-
"grad_norm":
|
155 |
"learning_rate": 7.222075445642904e-05,
|
156 |
-
"loss": 87.
|
157 |
"step": 20
|
158 |
},
|
159 |
{
|
160 |
"epoch": 0.005603595640536011,
|
161 |
-
"grad_norm": 13.
|
162 |
"learning_rate": 6.946477593864228e-05,
|
163 |
-
"loss": 87.
|
164 |
"step": 21
|
165 |
},
|
166 |
{
|
167 |
"epoch": 0.005870433528180582,
|
168 |
-
"grad_norm":
|
169 |
"learning_rate": 6.664685702961344e-05,
|
170 |
-
"loss": 86.
|
171 |
"step": 22
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.006137271415825154,
|
175 |
-
"grad_norm":
|
176 |
"learning_rate": 6.377906449072578e-05,
|
177 |
-
"loss": 88.
|
178 |
"step": 23
|
179 |
},
|
180 |
{
|
181 |
"epoch": 0.006404109303469727,
|
182 |
-
"grad_norm":
|
183 |
"learning_rate": 6.087367864990233e-05,
|
184 |
-
"loss": 89.
|
185 |
"step": 24
|
186 |
},
|
187 |
{
|
188 |
"epoch": 0.006670947191114298,
|
189 |
-
"grad_norm":
|
190 |
"learning_rate": 5.794314081535644e-05,
|
191 |
-
"loss":
|
192 |
"step": 25
|
193 |
},
|
194 |
{
|
195 |
"epoch": 0.006670947191114298,
|
196 |
-
"eval_loss": 2.
|
197 |
-
"eval_runtime": 2.
|
198 |
-
"eval_samples_per_second": 16.
|
199 |
-
"eval_steps_per_second": 4.
|
200 |
"step": 25
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 0.00693778507875887,
|
204 |
-
"grad_norm": 11.069785118103027,
|
205 |
-
"learning_rate": 5.500000000000001e-05,
|
206 |
-
"loss": 85.2464,
|
207 |
-
"step": 26
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"epoch": 0.0072046229664034424,
|
211 |
-
"grad_norm": 11.894067764282227,
|
212 |
-
"learning_rate": 5.205685918464356e-05,
|
213 |
-
"loss": 86.4133,
|
214 |
-
"step": 27
|
215 |
-
},
|
216 |
-
{
|
217 |
-
"epoch": 0.007471460854048014,
|
218 |
-
"grad_norm": 11.504545211791992,
|
219 |
-
"learning_rate": 4.912632135009769e-05,
|
220 |
-
"loss": 85.9424,
|
221 |
-
"step": 28
|
222 |
-
},
|
223 |
-
{
|
224 |
-
"epoch": 0.007738298741692586,
|
225 |
-
"grad_norm": 9.52103042602539,
|
226 |
-
"learning_rate": 4.6220935509274235e-05,
|
227 |
-
"loss": 85.5899,
|
228 |
-
"step": 29
|
229 |
-
},
|
230 |
-
{
|
231 |
-
"epoch": 0.008005136629337158,
|
232 |
-
"grad_norm": 8.053053855895996,
|
233 |
-
"learning_rate": 4.3353142970386564e-05,
|
234 |
-
"loss": 86.4908,
|
235 |
-
"step": 30
|
236 |
-
},
|
237 |
-
{
|
238 |
-
"epoch": 0.00827197451698173,
|
239 |
-
"grad_norm": 6.596405982971191,
|
240 |
-
"learning_rate": 4.053522406135775e-05,
|
241 |
-
"loss": 84.509,
|
242 |
-
"step": 31
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 0.008538812404626303,
|
246 |
-
"grad_norm": 12.154988288879395,
|
247 |
-
"learning_rate": 3.777924554357096e-05,
|
248 |
-
"loss": 85.5146,
|
249 |
-
"step": 32
|
250 |
-
},
|
251 |
-
{
|
252 |
-
"epoch": 0.008805650292270874,
|
253 |
-
"grad_norm": 12.631579399108887,
|
254 |
-
"learning_rate": 3.509700894014496e-05,
|
255 |
-
"loss": 84.0384,
|
256 |
-
"step": 33
|
257 |
-
},
|
258 |
-
{
|
259 |
-
"epoch": 0.009072488179915445,
|
260 |
-
"grad_norm": 14.187871932983398,
|
261 |
-
"learning_rate": 3.250000000000001e-05,
|
262 |
-
"loss": 85.3073,
|
263 |
-
"step": 34
|
264 |
-
},
|
265 |
-
{
|
266 |
-
"epoch": 0.009339326067560017,
|
267 |
-
"grad_norm": 17.819459915161133,
|
268 |
-
"learning_rate": 2.9999339514117912e-05,
|
269 |
-
"loss": 83.8787,
|
270 |
-
"step": 35
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"epoch": 0.00960616395520459,
|
274 |
-
"grad_norm": 20.426162719726562,
|
275 |
-
"learning_rate": 2.760573569460757e-05,
|
276 |
-
"loss": 87.1894,
|
277 |
-
"step": 36
|
278 |
-
},
|
279 |
-
{
|
280 |
-
"epoch": 0.009873001842849161,
|
281 |
-
"grad_norm": 31.33350944519043,
|
282 |
-
"learning_rate": 2.53294383204969e-05,
|
283 |
-
"loss": 89.3437,
|
284 |
-
"step": 37
|
285 |
-
},
|
286 |
-
{
|
287 |
-
"epoch": 0.010139839730493733,
|
288 |
-
"grad_norm": 47.56151580810547,
|
289 |
-
"learning_rate": 2.3180194846605367e-05,
|
290 |
-
"loss": 100.6103,
|
291 |
-
"step": 38
|
292 |
-
},
|
293 |
-
{
|
294 |
-
"epoch": 0.010406677618138306,
|
295 |
-
"grad_norm": 6.464964866638184,
|
296 |
-
"learning_rate": 2.1167208663446025e-05,
|
297 |
-
"loss": 83.3005,
|
298 |
-
"step": 39
|
299 |
-
},
|
300 |
-
{
|
301 |
-
"epoch": 0.010673515505782877,
|
302 |
-
"grad_norm": 6.612872123718262,
|
303 |
-
"learning_rate": 1.9299099686894423e-05,
|
304 |
-
"loss": 84.2439,
|
305 |
-
"step": 40
|
306 |
-
},
|
307 |
-
{
|
308 |
-
"epoch": 0.010940353393427448,
|
309 |
-
"grad_norm": 6.869765758514404,
|
310 |
-
"learning_rate": 1.758386744638546e-05,
|
311 |
-
"loss": 84.894,
|
312 |
-
"step": 41
|
313 |
-
},
|
314 |
-
{
|
315 |
-
"epoch": 0.011207191281072022,
|
316 |
-
"grad_norm": 5.677627086639404,
|
317 |
-
"learning_rate": 1.602885682970026e-05,
|
318 |
-
"loss": 84.2743,
|
319 |
-
"step": 42
|
320 |
-
},
|
321 |
-
{
|
322 |
-
"epoch": 0.011474029168716593,
|
323 |
-
"grad_norm": 6.212136745452881,
|
324 |
-
"learning_rate": 1.464072663102903e-05,
|
325 |
-
"loss": 85.6072,
|
326 |
-
"step": 43
|
327 |
-
},
|
328 |
-
{
|
329 |
-
"epoch": 0.011740867056361164,
|
330 |
-
"grad_norm": 6.752817153930664,
|
331 |
-
"learning_rate": 1.3425421036992098e-05,
|
332 |
-
"loss": 84.6236,
|
333 |
-
"step": 44
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"epoch": 0.012007704944005737,
|
337 |
-
"grad_norm": 7.166438102722168,
|
338 |
-
"learning_rate": 1.2388144172720251e-05,
|
339 |
-
"loss": 83.1906,
|
340 |
-
"step": 45
|
341 |
-
},
|
342 |
-
{
|
343 |
-
"epoch": 0.012274542831650309,
|
344 |
-
"grad_norm": 7.727652549743652,
|
345 |
-
"learning_rate": 1.1533337816991932e-05,
|
346 |
-
"loss": 83.4727,
|
347 |
-
"step": 46
|
348 |
-
},
|
349 |
-
{
|
350 |
-
"epoch": 0.01254138071929488,
|
351 |
-
"grad_norm": 8.032402038574219,
|
352 |
-
"learning_rate": 1.0864662381854632e-05,
|
353 |
-
"loss": 84.3546,
|
354 |
-
"step": 47
|
355 |
-
},
|
356 |
-
{
|
357 |
-
"epoch": 0.012808218606939453,
|
358 |
-
"grad_norm": 10.028108596801758,
|
359 |
-
"learning_rate": 1.0384981238178534e-05,
|
360 |
-
"loss": 84.996,
|
361 |
-
"step": 48
|
362 |
-
},
|
363 |
-
{
|
364 |
-
"epoch": 0.013075056494584025,
|
365 |
-
"grad_norm": 15.79798698425293,
|
366 |
-
"learning_rate": 1.0096348454262845e-05,
|
367 |
-
"loss": 87.5037,
|
368 |
-
"step": 49
|
369 |
-
},
|
370 |
-
{
|
371 |
-
"epoch": 0.013341894382228596,
|
372 |
-
"grad_norm": 68.88801574707031,
|
373 |
-
"learning_rate": 1e-05,
|
374 |
-
"loss": 99.1348,
|
375 |
-
"step": 50
|
376 |
-
},
|
377 |
-
{
|
378 |
-
"epoch": 0.013341894382228596,
|
379 |
-
"eval_loss": 2.6576178073883057,
|
380 |
-
"eval_runtime": 2.9174,
|
381 |
-
"eval_samples_per_second": 17.139,
|
382 |
-
"eval_steps_per_second": 4.456,
|
383 |
-
"step": 50
|
384 |
}
|
385 |
],
|
386 |
"logging_steps": 1,
|
@@ -395,12 +212,12 @@
|
|
395 |
"should_evaluate": false,
|
396 |
"should_log": false,
|
397 |
"should_save": true,
|
398 |
-
"should_training_stop":
|
399 |
},
|
400 |
"attributes": {}
|
401 |
}
|
402 |
},
|
403 |
-
"total_flos":
|
404 |
"train_batch_size": 1,
|
405 |
"trial_name": null,
|
406 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006670947191114298,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.00026683788764457196,
|
13 |
+
"grad_norm": 22.89421844482422,
|
14 |
"learning_rate": 5e-05,
|
15 |
"loss": 99.4744,
|
16 |
"step": 1
|
|
|
18 |
{
|
19 |
"epoch": 0.00026683788764457196,
|
20 |
"eval_loss": 3.534377336502075,
|
21 |
+
"eval_runtime": 2.9106,
|
22 |
+
"eval_samples_per_second": 17.179,
|
23 |
+
"eval_steps_per_second": 4.466,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0005336757752891439,
|
28 |
+
"grad_norm": 23.7343692779541,
|
29 |
"learning_rate": 0.0001,
|
30 |
"loss": 103.3411,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0008005136629337158,
|
35 |
+
"grad_norm": 48.079044342041016,
|
36 |
"learning_rate": 9.990365154573717e-05,
|
37 |
+
"loss": 101.9827,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0010673515505782878,
|
42 |
+
"grad_norm": 38.11738967895508,
|
43 |
"learning_rate": 9.961501876182148e-05,
|
44 |
+
"loss": 102.6331,
|
45 |
"step": 4
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.0013341894382228596,
|
49 |
+
"grad_norm": 32.43550109863281,
|
50 |
"learning_rate": 9.913533761814537e-05,
|
51 |
+
"loss": 98.8496,
|
52 |
"step": 5
|
53 |
},
|
54 |
{
|
55 |
"epoch": 0.0016010273258674317,
|
56 |
+
"grad_norm": 36.24091339111328,
|
57 |
"learning_rate": 9.846666218300807e-05,
|
58 |
+
"loss": 96.6713,
|
59 |
"step": 6
|
60 |
},
|
61 |
{
|
62 |
"epoch": 0.0018678652135120035,
|
63 |
+
"grad_norm": 37.49607467651367,
|
64 |
"learning_rate": 9.761185582727977e-05,
|
65 |
+
"loss": 94.9006,
|
66 |
"step": 7
|
67 |
},
|
68 |
{
|
69 |
"epoch": 0.0021347031011565757,
|
70 |
+
"grad_norm": 34.56901931762695,
|
71 |
"learning_rate": 9.657457896300791e-05,
|
72 |
+
"loss": 93.4301,
|
73 |
"step": 8
|
74 |
},
|
75 |
{
|
76 |
"epoch": 0.0024015409888011475,
|
77 |
+
"grad_norm": 31.850221633911133,
|
78 |
"learning_rate": 9.535927336897098e-05,
|
79 |
+
"loss": 91.105,
|
80 |
"step": 9
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.0026683788764457193,
|
84 |
+
"grad_norm": 43.924991607666016,
|
85 |
"learning_rate": 9.397114317029975e-05,
|
86 |
+
"loss": 93.5747,
|
87 |
"step": 10
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.002935216764090291,
|
91 |
+
"grad_norm": 33.07682800292969,
|
92 |
"learning_rate": 9.241613255361455e-05,
|
93 |
+
"loss": 93.5264,
|
94 |
"step": 11
|
95 |
},
|
96 |
{
|
97 |
"epoch": 0.0032020546517348633,
|
98 |
+
"grad_norm": 52.70429992675781,
|
99 |
"learning_rate": 9.070090031310558e-05,
|
100 |
+
"loss": 100.4311,
|
101 |
"step": 12
|
102 |
},
|
103 |
{
|
104 |
"epoch": 0.003468892539379435,
|
105 |
+
"grad_norm": 91.30162048339844,
|
106 |
"learning_rate": 8.883279133655399e-05,
|
107 |
+
"loss": 103.5051,
|
108 |
"step": 13
|
109 |
},
|
110 |
{
|
111 |
"epoch": 0.003735730427024007,
|
112 |
+
"grad_norm": 48.74945068359375,
|
113 |
"learning_rate": 8.681980515339464e-05,
|
114 |
+
"loss": 90.932,
|
115 |
"step": 14
|
116 |
},
|
117 |
{
|
118 |
"epoch": 0.004002568314668579,
|
119 |
+
"grad_norm": 38.04246139526367,
|
120 |
"learning_rate": 8.467056167950311e-05,
|
121 |
+
"loss": 91.092,
|
122 |
"step": 15
|
123 |
},
|
124 |
{
|
125 |
"epoch": 0.004269406202313151,
|
126 |
+
"grad_norm": 32.99767303466797,
|
127 |
"learning_rate": 8.239426430539243e-05,
|
128 |
+
"loss": 86.978,
|
129 |
"step": 16
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.004536244089957723,
|
133 |
+
"grad_norm": 25.959495544433594,
|
134 |
"learning_rate": 8.000066048588211e-05,
|
135 |
+
"loss": 87.323,
|
136 |
"step": 17
|
137 |
},
|
138 |
{
|
139 |
"epoch": 0.004803081977602295,
|
140 |
+
"grad_norm": 22.552183151245117,
|
141 |
"learning_rate": 7.75e-05,
|
142 |
+
"loss": 87.7695,
|
143 |
"step": 18
|
144 |
},
|
145 |
{
|
146 |
"epoch": 0.005069919865246866,
|
147 |
+
"grad_norm": 17.352420806884766,
|
148 |
"learning_rate": 7.490299105985507e-05,
|
149 |
+
"loss": 87.1552,
|
150 |
"step": 19
|
151 |
},
|
152 |
{
|
153 |
"epoch": 0.0053367577528914386,
|
154 |
+
"grad_norm": 14.216341018676758,
|
155 |
"learning_rate": 7.222075445642904e-05,
|
156 |
+
"loss": 87.1521,
|
157 |
"step": 20
|
158 |
},
|
159 |
{
|
160 |
"epoch": 0.005603595640536011,
|
161 |
+
"grad_norm": 13.55358600616455,
|
162 |
"learning_rate": 6.946477593864228e-05,
|
163 |
+
"loss": 87.6133,
|
164 |
"step": 21
|
165 |
},
|
166 |
{
|
167 |
"epoch": 0.005870433528180582,
|
168 |
+
"grad_norm": 18.19391441345215,
|
169 |
"learning_rate": 6.664685702961344e-05,
|
170 |
+
"loss": 86.9043,
|
171 |
"step": 22
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.006137271415825154,
|
175 |
+
"grad_norm": 20.173397064208984,
|
176 |
"learning_rate": 6.377906449072578e-05,
|
177 |
+
"loss": 88.4352,
|
178 |
"step": 23
|
179 |
},
|
180 |
{
|
181 |
"epoch": 0.006404109303469727,
|
182 |
+
"grad_norm": 27.15044403076172,
|
183 |
"learning_rate": 6.087367864990233e-05,
|
184 |
+
"loss": 89.5455,
|
185 |
"step": 24
|
186 |
},
|
187 |
{
|
188 |
"epoch": 0.006670947191114298,
|
189 |
+
"grad_norm": 77.1603012084961,
|
190 |
"learning_rate": 5.794314081535644e-05,
|
191 |
+
"loss": 105.756,
|
192 |
"step": 25
|
193 |
},
|
194 |
{
|
195 |
"epoch": 0.006670947191114298,
|
196 |
+
"eval_loss": 2.6978037357330322,
|
197 |
+
"eval_runtime": 2.9516,
|
198 |
+
"eval_samples_per_second": 16.94,
|
199 |
+
"eval_steps_per_second": 4.404,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
|
|
212 |
"should_evaluate": false,
|
213 |
"should_log": false,
|
214 |
"should_save": true,
|
215 |
+
"should_training_stop": false
|
216 |
},
|
217 |
"attributes": {}
|
218 |
}
|
219 |
},
|
220 |
+
"total_flos": 2.629578157719552e+17,
|
221 |
"train_batch_size": 1,
|
222 |
"trial_name": null,
|
223 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daa6781a2b3f71155ea06bbf181fb9d6e5488ae8ac1598f881bc93f1a056095c
|
3 |
size 6840
|