DeepDream2045 commited on
Commit
c3364ab
1 Parent(s): a9528e8

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 sha256:5d300f84a566dc98abdddf796befd91b6ae9db5faf9562d9f5b3ffb1aa9c2cf9
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e23e7223f243908b05fc72804470fda9e9ef9ef82cd8e49ac3b403062b494c0
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d26793f4295f95b2220ef1ee50122cdaa5ae6578f0974291da78a2300d942830
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122ee36ed2feb5bfcb1df0f566f8776f3cbf52c9cf17d91da6898fc0f111e2d5
3
  size 671466706
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1580a1418dd216fbc0a8ceb25d290ef13e3fec209de36826aa4cdc457e604a11
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9bcefaada626fdb19118fa7a9da76f4f5a584a0cd7811dc81eeb46b39ed885e
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 sha256:31a7cb49c1a46eff856118f433a51592488566f30ed55c781b9b6a99f6b927a8
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f162db68806d4bfccb68450582df37b72f68536f2ce2f790f2e29bd56ae0998
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 sha256:02a407488429bfa3515d00c1efe61caf74a20ef86d2165fe2158712dcd671f39
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a0e87f43ca64e739fff7ef9418cbce05bcf80b849972a2c957c6b1dacf3671
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:a30eafbfc76a1cd21544a00e4c55846a51a364198262b65f0d0714d4eb0198f5
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f9cd8660d0f4eff1b6fbdb000fca5ce272cea2319e72be91e4d96668205127
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": 0.03865384683012962,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.29542097488921715,
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": 30.146,
199
  "eval_steps_per_second": 3.808,
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": 3.015747257237504e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.024680091068148613,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.5908419497784343,
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": 30.146,
199
  "eval_steps_per_second": 3.808,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.3072378138847858,
204
+ "grad_norm": 2.0008926391601562,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.3063,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.3190546528803545,
211
+ "grad_norm": 0.007220223546028137,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.0001,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.3308714918759232,
218
+ "grad_norm": 0.0031562913209199905,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.0,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.34268833087149186,
225
+ "grad_norm": 0.01956658624112606,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.0002,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.35450516986706054,
232
+ "grad_norm": 0.01140380185097456,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.0001,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.3663220088626292,
239
+ "grad_norm": 0.0098069803789258,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.0001,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.37813884785819796,
246
+ "grad_norm": 0.0027902915608137846,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.0001,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.38995568685376664,
253
+ "grad_norm": 0.010911458171904087,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.0001,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.4017725258493353,
260
+ "grad_norm": 0.002692491514608264,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.0,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.413589364844904,
267
+ "grad_norm": 0.045907288789749146,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.0003,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.4254062038404727,
274
+ "grad_norm": 0.026951441541314125,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.0001,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.43722304283604135,
281
+ "grad_norm": 0.00568424304947257,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.0001,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.44903988183161003,
288
+ "grad_norm": 1.7761626243591309,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.4578,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.4608567208271787,
295
+ "grad_norm": 0.029375163838267326,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.0002,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.4726735598227474,
302
+ "grad_norm": 0.015356656163930893,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.0002,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.4844903988183161,
309
+ "grad_norm": 0.3691544234752655,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.0008,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.4963072378138848,
316
+ "grad_norm": 0.02166283316910267,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.0002,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.5081240768094535,
323
+ "grad_norm": 0.10131458938121796,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.0004,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.5199409158050221,
330
+ "grad_norm": 0.01139977015554905,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.0001,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.5317577548005908,
337
+ "grad_norm": 0.008314274251461029,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.0001,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.5435745937961596,
344
+ "grad_norm": 0.008410402573645115,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.0001,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.5553914327917282,
351
+ "grad_norm": 0.03753000497817993,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.0003,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.5672082717872969,
358
+ "grad_norm": 0.012496479786932468,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.0001,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.5790251107828656,
365
+ "grad_norm": 0.024329444393515587,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.0002,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.5908419497784343,
372
+ "grad_norm": 0.010945094749331474,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.0001,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.5908419497784343,
379
+ "eval_loss": 0.024680091068148613,
380
+ "eval_runtime": 18.8907,
381
+ "eval_samples_per_second": 30.174,
382
+ "eval_steps_per_second": 3.811,
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": 6.027764453490033e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null