farmery commited on
Commit
d3cc4e9
1 Parent(s): 4721e01

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 sha256:8ac63e267abd1f90cb61c2559cec0958fcf396d93f2b83264c8aaaf8a594badb
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8591b8b4b28ae733f252e490b0eb56ef49e73cf282a09a6600acbcd8fbec20a5
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abd6421d601a2722090238067577378f05a3e1d4c6a8b89d9e5f13ba48066591
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:361086acbbf8816321247b8d1e0eb9af72f134f77369c4a1171eac4a3212cf0e
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 sha256:4a7cfa516c115ce0f3047aa8d0bbf22c70a108611872900fde57f1dd7ff9d37c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c712484095bc66a20352f03124d5661d5a25ad463c0ccd4c101baa500cfe6179
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:dad048ec773f819b06cfd71ffbcca28c2282ac18ad00cf6fe02f5f582f69e0e2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56cbe9aa651e07f582d91068a1048b62fc737eda2043baf265bfc3503ffdbd26
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:fa43c8d9239e2f67e833b8c581c4678005b8fa8a55307caaa37967e4e7a521c4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ee6c3400ab276549c0820c1cd6c988b3399c44baabfc082754e5e287bc6d8f
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:c7adee5fa8497dcc8038b8acaf99b486b9f33f5db8fab8e58b8a8b2034ef0fdb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1136fbeed7bfade0a3a406adf32b2372942e017fe6b8758e34c06b9b1948912f
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": 0.6112602949142456,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 0.08,
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": 39.892,
199
  "eval_steps_per_second": 5.001,
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": 2.652642132099072e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5172708034515381,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.16,
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": 39.892,
199
  "eval_steps_per_second": 5.001,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.0832,
204
+ "grad_norm": 1.339646816253662,
205
+ "learning_rate": 5e-05,
206
+ "loss": 0.6826,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.0864,
211
+ "grad_norm": 1.1944141387939453,
212
+ "learning_rate": 4.6729843538492847e-05,
213
+ "loss": 0.6551,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.0896,
218
+ "grad_norm": 1.4156867265701294,
219
+ "learning_rate": 4.347369038899744e-05,
220
+ "loss": 0.6128,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.0928,
225
+ "grad_norm": 0.8293469548225403,
226
+ "learning_rate": 4.0245483899193595e-05,
227
+ "loss": 0.5205,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.096,
232
+ "grad_norm": 1.3624340295791626,
233
+ "learning_rate": 3.705904774487396e-05,
234
+ "loss": 0.6409,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.0992,
239
+ "grad_norm": 1.3279340267181396,
240
+ "learning_rate": 3.392802673484193e-05,
241
+ "loss": 0.5904,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.1024,
246
+ "grad_norm": 1.172986388206482,
247
+ "learning_rate": 3.086582838174551e-05,
248
+ "loss": 0.5735,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.1056,
253
+ "grad_norm": 1.1812784671783447,
254
+ "learning_rate": 2.7885565489049946e-05,
255
+ "loss": 0.6204,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.1088,
260
+ "grad_norm": 1.3767175674438477,
261
+ "learning_rate": 2.500000000000001e-05,
262
+ "loss": 0.5828,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.112,
267
+ "grad_norm": 1.0632436275482178,
268
+ "learning_rate": 2.2221488349019903e-05,
269
+ "loss": 0.57,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.1152,
274
+ "grad_norm": 0.929205596446991,
275
+ "learning_rate": 1.9561928549563968e-05,
276
+ "loss": 0.5006,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.1184,
281
+ "grad_norm": 1.3007352352142334,
282
+ "learning_rate": 1.703270924499656e-05,
283
+ "loss": 0.7047,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.1216,
288
+ "grad_norm": 1.4487941265106201,
289
+ "learning_rate": 1.4644660940672627e-05,
290
+ "loss": 0.7684,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.1248,
295
+ "grad_norm": 1.5427775382995605,
296
+ "learning_rate": 1.2408009626051137e-05,
297
+ "loss": 0.5627,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.128,
302
+ "grad_norm": 1.1064578294754028,
303
+ "learning_rate": 1.0332332985438248e-05,
304
+ "loss": 0.548,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.1312,
309
+ "grad_norm": 1.229816198348999,
310
+ "learning_rate": 8.426519384872733e-06,
311
+ "loss": 0.5352,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.1344,
316
+ "grad_norm": 1.032274842262268,
317
+ "learning_rate": 6.698729810778065e-06,
318
+ "loss": 0.5009,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.1376,
323
+ "grad_norm": 1.0685501098632812,
324
+ "learning_rate": 5.156362923365588e-06,
325
+ "loss": 0.5532,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.1408,
330
+ "grad_norm": 1.0419175624847412,
331
+ "learning_rate": 3.8060233744356633e-06,
332
+ "loss": 0.5462,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.144,
337
+ "grad_norm": 0.9846985936164856,
338
+ "learning_rate": 2.653493525244721e-06,
339
+ "loss": 0.4817,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.1472,
344
+ "grad_norm": 0.847055971622467,
345
+ "learning_rate": 1.70370868554659e-06,
346
+ "loss": 0.5303,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.1504,
351
+ "grad_norm": 1.1482884883880615,
352
+ "learning_rate": 9.607359798384785e-07,
353
+ "loss": 0.6073,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.1536,
358
+ "grad_norm": 1.1206740140914917,
359
+ "learning_rate": 4.277569313094809e-07,
360
+ "loss": 0.5682,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.1568,
365
+ "grad_norm": 1.4303394556045532,
366
+ "learning_rate": 1.0705383806982606e-07,
367
+ "loss": 0.6277,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.16,
372
+ "grad_norm": 1.308823823928833,
373
+ "learning_rate": 0.0,
374
+ "loss": 0.5633,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.16,
379
+ "eval_loss": 0.5172708034515381,
380
+ "eval_runtime": 52.8099,
381
+ "eval_samples_per_second": 39.879,
382
+ "eval_steps_per_second": 4.999,
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": 5.305284264198144e+17,
413
  "train_batch_size": 2,
414
  "trial_name": null,
415
  "trial_params": null