leixa commited on
Commit
d1cf2cb
·
verified ·
1 Parent(s): d5c0428

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:b8ec174a29997514b607263f6b7b6faae059037a7e545970a5370171c8219e72
3
  size 119597408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a80e815e8006872b6705256059ab3575083a4642efbd7b75808599c89809d6
3
  size 119597408
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39656aeca7ec5da27240bd78564116ee37961de0e34c39717d1caab25e52b260
3
  size 61226900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9b81fcb300fabe5e7d8a80a50c12fcae5c3cce17a598f17b7483448b5deccf
3
  size 61226900
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa7305ef81d477a716ee7b92a2e1bdb608cdabf40f7a3155ceb9953f57dd2e40
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5894326b8b30bb7eed77b2c54f307fdf693afdf7e1b5dba13bb6cf561bb5feb3
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": 0.8421052631578947,
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": 10.474,
248
  "eval_steps_per_second": 1.309,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.0623806154473472e+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": 0.9473684210526315,
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": 10.474,
248
  "eval_steps_per_second": 1.309,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.8771929824561403,
253
+ "grad_norm": 0.4592737555503845,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 5.4021,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.9122807017543859,
260
+ "grad_norm": 0.46895694732666016,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 5.2216,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.9473684210526315,
267
+ "grad_norm": 0.49175575375556946,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 5.1936,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.9473684210526315,
274
+ "eval_loss": 1.3289103507995605,
275
+ "eval_runtime": 13.7459,
276
+ "eval_samples_per_second": 10.476,
277
+ "eval_steps_per_second": 1.309,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.1951781923782656e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null