vdos commited on
Commit
056a30c
1 Parent(s): 7960156

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 sha256:4894b09bb43b4fa30f095db8c915e80f4229bdb69afbf7728c2df68094446674
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749fdffb34573343d6adc7fadcf6dbe89e178a16d997d4e296c5b8357c6dd36e
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f50b17dfa4b73411cdbca5018e822b963a923353c98903c4795b9c558b270d8a
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1f427c085afbc008b8d0d3846351e4e974181ee2f1c9cae3203c6d719dead2
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 sha256:1cc3135dce65065978699c9a136d91acb0197a1be5047533426027b5fa846185
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7874f5b50553407db50256d23e2cc28d658d542479d1dc8fa987a78448928a95
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 sha256:0ae3d20573a6811f855b751f779997eebbaacf399eb557c85a6a5081fb32017a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b18da50fb8cfc74c59806316e017a84bcdb948bab8c147900df2f2de770d86
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:dcc5b679335e7b06e2793cf789cd8d6bdcab2ad372c93ae55534d0d081ef25a9
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2374628fc44f2339115e7b3d06544f42f3e1403c50c9677ce0c4345e1717cf02
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 sha256:576a908b7c6efc3258fe636101e79861daea259b3dddf7e483fe50c126c8e02f
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6f1b2a6551be5043cc29896e59b8f58f812ba4521985d3fff6474f6e96eb00
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": 2.122105836868286,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.05777841976021956,
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": 32.977,
199
  "eval_steps_per_second": 4.129,
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": 2.984041808658432e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.0190470218658447,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.11555683952043912,
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": 32.977,
199
  "eval_steps_per_second": 4.129,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.06008955655062834,
204
+ "grad_norm": 2.3176376819610596,
205
+ "learning_rate": 5e-05,
206
+ "loss": 1.7672,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.06240069334103712,
211
+ "grad_norm": 1.6695570945739746,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 1.7331,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.06471183013144591,
218
+ "grad_norm": 1.470428705215454,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 1.8564,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.0670229669218547,
225
+ "grad_norm": 1.9413001537322998,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 2.0338,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.06933410371226346,
232
+ "grad_norm": 1.4334675073623657,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 1.9684,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.07164524050267225,
239
+ "grad_norm": 1.4908390045166016,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 1.7507,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.07395637729308104,
246
+ "grad_norm": 1.3455537557601929,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 1.818,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.07626751408348982,
253
+ "grad_norm": 1.1437408924102783,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 1.7837,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.07857865087389859,
260
+ "grad_norm": 1.5162749290466309,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 1.8623,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.08088978766430738,
267
+ "grad_norm": 1.4613982439041138,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 2.086,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.08320092445471616,
274
+ "grad_norm": 0.9104688763618469,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 2.151,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.08551206124512495,
281
+ "grad_norm": 1.7871757745742798,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 2.235,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.08782319803553373,
288
+ "grad_norm": 1.5214916467666626,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 1.9367,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.0901343348259425,
295
+ "grad_norm": 2.2295875549316406,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 1.7298,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.09244547161635129,
302
+ "grad_norm": 1.6196082830429077,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 1.7052,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.09475660840676008,
309
+ "grad_norm": 1.135953664779663,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 1.8029,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.09706774519716886,
316
+ "grad_norm": 0.9740651845932007,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 1.9533,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.09937888198757763,
323
+ "grad_norm": 1.0038777589797974,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 1.7188,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.10169001877798642,
330
+ "grad_norm": 1.0359888076782227,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 1.746,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.1040011555683952,
337
+ "grad_norm": 1.179372787475586,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 1.8965,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.10631229235880399,
344
+ "grad_norm": 1.2560983896255493,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 1.8588,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.10862342914921277,
351
+ "grad_norm": 1.3571735620498657,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 1.9218,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.11093456593962155,
358
+ "grad_norm": 1.9261860847473145,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 2.1027,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.11324570273003033,
365
+ "grad_norm": 1.3769975900650024,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 2.0781,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.11555683952043912,
372
+ "grad_norm": 1.6940319538116455,
373
+ "learning_rate": 0.0,
374
+ "loss": 2.5252,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.11555683952043912,
379
+ "eval_loss": 2.0190470218658447,
380
+ "eval_runtime": 88.4389,
381
+ "eval_samples_per_second": 32.961,
382
+ "eval_steps_per_second": 4.127,
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": 5.968083617316864e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null