jssky commited on
Commit
fd648fb
·
verified ·
1 Parent(s): cba8c5e

Training in progress, step 41, 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:b83a8610d844807472cba0d093ec51553c8680c164843e192ec9bda89e7cb4db
3
  size 147770496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c438ed52924cf620e9aea48351c73788af0f3874931f9e86db2ac77e175bc18
3
  size 147770496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b22613a054d8711045be38129625026aab1eed2981edf56fb21e08dcb96876f
3
  size 295765866
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6c5ccd3097a9b42c66302108b42e97076cee4892de82ba10f2c22c5032ceda
3
  size 295765866
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1722fe481033848fe7c9ad32623357b0fa72eb2a21025076a06e90bd4165050b
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68802e6dc89a02aec3b78de505ed35ef2d5fe141ee8b8443f28141eec2b699ef
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 sha256:684bd91b0266a7884daeddc87473261706198ca980cd79d84fa8000fc3593b2e
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e79ce2d4b65fd05ce485aa114bba872dab9bd9c49570aefa4351f181dced624
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:fa1d71cdb7998ac684d58333abc45676af4bfaacfb83f6422144de367685a831
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633560a61cf4ec100692b47ba2169fd4dac09ee92d8498a792586fd4303b110b
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 sha256:3a17c369e6a7dbd54bfbfa3e91a865ebeb4348aa81cb68214972e8ad87d0501c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7f7788e57929f6becc309fe7f4af5839fada3c6c65cd0a24ae97086c3cbc53
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc6b77c0cbcc35c1c43ee60e2766b6027d2e111edae589e45f75af1b1040b32d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84fc982e8229d2121603832a24f4c07bbdbf63985ed1d38e11762164a04dad3b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 6.001819610595703,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 1.8691588785046729,
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 +198,118 @@
198
  "eval_samples_per_second": 55.318,
199
  "eval_steps_per_second": 7.376,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +333,12 @@
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": 5.645342084798874e+16,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": 6.001819610595703,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 3.0654205607476634,
5
  "eval_steps": 25,
6
+ "global_step": 41,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 55.318,
199
  "eval_steps_per_second": 7.376,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 1.9439252336448598,
204
+ "grad_norm": 1.1970505714416504,
205
+ "learning_rate": 3.226975564787322e-05,
206
+ "loss": 6.4239,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 2.0186915887850465,
211
+ "grad_norm": 1.1707515716552734,
212
+ "learning_rate": 2.8565371929847284e-05,
213
+ "loss": 8.9556,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 2.0934579439252334,
218
+ "grad_norm": 0.7799269556999207,
219
+ "learning_rate": 2.500000000000001e-05,
220
+ "loss": 6.6629,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 2.1682242990654204,
225
+ "grad_norm": 0.8445941209793091,
226
+ "learning_rate": 2.1596762663442218e-05,
227
+ "loss": 5.9799,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 2.2429906542056073,
232
+ "grad_norm": 0.649803102016449,
233
+ "learning_rate": 1.837773122023114e-05,
234
+ "loss": 4.6584,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 2.317757009345794,
239
+ "grad_norm": 0.8148556351661682,
240
+ "learning_rate": 1.536378232452003e-05,
241
+ "loss": 7.5261,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 2.392523364485981,
246
+ "grad_norm": 0.844731867313385,
247
+ "learning_rate": 1.257446259144494e-05,
248
+ "loss": 5.9557,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 2.467289719626168,
253
+ "grad_norm": 0.6243622899055481,
254
+ "learning_rate": 1.0027861829824952e-05,
255
+ "loss": 4.8558,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 2.542056074766355,
260
+ "grad_norm": 0.8896576762199402,
261
+ "learning_rate": 7.740495722810271e-06,
262
+ "loss": 7.3544,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 2.616822429906542,
267
+ "grad_norm": 0.7065213918685913,
268
+ "learning_rate": 5.727198717339511e-06,
269
+ "loss": 5.966,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 2.691588785046729,
274
+ "grad_norm": 0.7317398190498352,
275
+ "learning_rate": 4.001027817058789e-06,
276
+ "loss": 5.3642,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 2.7663551401869158,
281
+ "grad_norm": 0.757183849811554,
282
+ "learning_rate": 2.573177902642726e-06,
283
+ "loss": 6.2839,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 2.8411214953271027,
288
+ "grad_norm": 0.7204071879386902,
289
+ "learning_rate": 1.4529091286973995e-06,
290
+ "loss": 6.29,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 2.9158878504672896,
295
+ "grad_norm": 1.0202537775039673,
296
+ "learning_rate": 6.474868681043578e-07,
297
+ "loss": 6.5971,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 2.9906542056074765,
302
+ "grad_norm": 1.3982231616973877,
303
+ "learning_rate": 1.6213459328950352e-07,
304
+ "loss": 8.418,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 3.0654205607476634,
309
+ "grad_norm": 0.9841596484184265,
310
+ "learning_rate": 0.0,
311
+ "loss": 6.5826,
312
+ "step": 41
313
  }
314
  ],
315
  "logging_steps": 1,
 
333
  "should_evaluate": false,
334
  "should_log": false,
335
  "should_save": true,
336
+ "should_training_stop": true
337
  },
338
  "attributes": {}
339
  }
340
  },
341
+ "total_flos": 9.264320894468096e+16,
342
  "train_batch_size": 2,
343
  "trial_name": null,
344
  "trial_params": null