Rodo-Sami commited on
Commit
a19a0e2
·
verified ·
1 Parent(s): 19d259a

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c8ae53ca7a447bea5a97ea9117493cac174e9387f655c8b5cc55f61a449379e
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e217e69c74543151fdd06a0b25b701831c0587f803ee1e31cf04c2d69e2c1d
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5161cb8b7b4840e1d91808cde10876919076c75a6abc44d775d1980a30266508
3
  size 202110330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68dd14f6edf5c6d44efdf99bfdda2781bc7833a5efaeadf956d35036324213d2
3
  size 202110330
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c6a08c5c936c8e11a05f5117ed1885068d11e799cfd9b82129998d489348b53
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85ea57ffdd9c8f2a0fb123a9393c169e8cb77a32d11f78582074f240f291e66
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 sha256:7a862bb7907cc174874ec0e28b7eb340600a504c47497cfdd44d1f0ad6f0aee3
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31bed533487fa342bed00d1d139cc3cf815303d29c43c0f19d4de1e13d4a19d
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 sha256:167005b0deb2859eb01411cfea5cb6e4c9361f7b7ea328ea5d8a3266b5b3d38f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1718f9eeafbd9d621d25bc2139bd51ba2148a099a5ac8eae34a332121a49c403
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:a3510c0d3a99c50c0822d37af8a2086568e4d1346ae3743e8f659f88b89906ef
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6e11bc9aa45901e2a717e5df4cd02f5db312deb1034fde63f17e5fad2ad2ba
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.23052285611629486,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.024333860566978952,
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,
@@ -198,6 +198,189 @@
198
  "eval_samples_per_second": 109.539,
199
  "eval_steps_per_second": 13.706,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +404,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 4.16708196040704e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.160928413271904,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.048667721133957904,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 109.539,
199
  "eval_steps_per_second": 13.706,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.02530721498965811,
204
+ "grad_norm": 0.10166118294000626,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.0027,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.02628056941233727,
211
+ "grad_norm": 0.193026602268219,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.0059,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.027253923835016427,
218
+ "grad_norm": 0.27356114983558655,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.009,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.028227278257695585,
225
+ "grad_norm": 0.3083343505859375,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.0108,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.02920063268037474,
232
+ "grad_norm": 0.2875608503818512,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.0106,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.030173987103053898,
239
+ "grad_norm": 0.24416722357273102,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.0095,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.031147341525733056,
246
+ "grad_norm": 0.193377286195755,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.0079,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.032120695948412215,
253
+ "grad_norm": 0.14682887494564056,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.0063,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.03309405037109137,
260
+ "grad_norm": 0.11604669690132141,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.0052,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.03406740479377053,
267
+ "grad_norm": 0.09484685212373734,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.0043,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.03504075921644969,
274
+ "grad_norm": 5.945147514343262,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.9259,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.03601411363912885,
281
+ "grad_norm": 5.888754367828369,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.9055,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.036987468061808006,
288
+ "grad_norm": 1.4646563529968262,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.2314,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.037960822484487164,
295
+ "grad_norm": 0.12405002862215042,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.0059,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.03893417690716632,
302
+ "grad_norm": 0.14476650953292847,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.007,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.03990753132984548,
309
+ "grad_norm": 0.16240093111991882,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.0078,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.04088088575252464,
316
+ "grad_norm": 0.17413407564163208,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.0084,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.0418542401752038,
323
+ "grad_norm": 0.18335355818271637,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.0089,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.042827594597882955,
330
+ "grad_norm": 0.18472228944301605,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.009,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.04380094902056211,
337
+ "grad_norm": 0.1897263079881668,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.0092,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.04477430344324127,
344
+ "grad_norm": 0.1893337368965149,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.0091,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.04574765786592043,
351
+ "grad_norm": 0.18881848454475403,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.0091,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.04672101228859959,
358
+ "grad_norm": 1.1086373329162598,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.1602,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.047694366711278746,
365
+ "grad_norm": 5.398890972137451,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.6574,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.048667721133957904,
372
+ "grad_norm": 5.379086017608643,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.6569,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.048667721133957904,
379
+ "eval_loss": 0.160928413271904,
380
+ "eval_runtime": 62.7866,
381
+ "eval_samples_per_second": 110.231,
382
+ "eval_steps_per_second": 13.793,
383
+ "step": 50
384
  }
385
  ],
386
  "logging_steps": 1,
 
404
  "should_evaluate": false,
405
  "should_log": false,
406
  "should_save": true,
407
+ "should_training_stop": true
408
  },
409
  "attributes": {}
410
  }
411
  },
412
+ "total_flos": 8.33416392081408e+16,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null