brixeus commited on
Commit
afaee77
·
verified ·
1 Parent(s): 5ad869c

Training in progress, step 81, 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:ea4084f05edcfee38d7da7b0761cf1447b642717d90849273550df2441a28aa8
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514624e8caa7138b89314ee0f940cd757882c866b8affecbb6b0c7ea3f8b1da4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbb9c1eaf20ba6b9ab238b92b711c656020f3981e257668c19bc86321d6b185f
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f27a7441303a26dbf11c4d29cfdb0c36a996dee976afa4496f431272a5a2d6
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0830929024812464,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 13.971,
248
  "eval_steps_per_second": 1.751,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.00953895634731e+17,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0934795152914022,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 13.971,
248
  "eval_steps_per_second": 1.751,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.08655510675129832,
253
+ "grad_norm": 3.645982027053833,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 7.5561,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.09001731102135026,
260
+ "grad_norm": 4.192688941955566,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 7.7532,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.0934795152914022,
267
+ "grad_norm": 4.39183235168457,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 7.7928,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.0934795152914022,
274
+ "eval_loss": 1.9180028438568115,
275
+ "eval_runtime": 104.5172,
276
+ "eval_samples_per_second": 13.969,
277
+ "eval_steps_per_second": 1.751,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.1357313258907238e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null