kooff11 commited on
Commit
904dba3
·
verified ·
1 Parent(s): 40d22db

Training in progress, step 29, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1af7c68dddd4c07b21d5d7ebfe7305d018c2f79fb8f3e923f9992c4dc5028113
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313a3009e689b5574f84990c440e35c40810ab6729fd26a7dee2d22263fc1d0c
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:777463137d179646b3dcdc335fc1e392a657cbbd1967b01b54cea0bbabe08d2f
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e094587a906d8d1b12e67ad3410b00c1fd2f5824dc209d50a177ab91b8e44810
3
  size 85723284
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5631bbf02b26fe187968a013bbddf8fd4c860685f275c830320a8cd4afa18d26
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2d25e57315b0b164773fae5bd86b1ebdcc832531c49dc2f68546d41b7f8fc4
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c05db228c582523f2484f96646741880104bd1f199b26c4fb4dad8d90c7b8232
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f60184ae469aa0d38f3263176cfb7ad5d5538cabd5c8505b2bfdbac07e1472
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac599fff4b26ed2f8aaa3f64038b795f8035d5e4d74e62f4a3c0c4e718607220
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b1cd5ec232ad7fc4a8bf29290c170002b5e29b256da7fe912039052d43ab0b
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": 0.8523862375138734,
5
  "eval_steps": 8,
6
- "global_step": 24,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -207,6 +207,41 @@
207
  "eval_samples_per_second": 10.779,
208
  "eval_steps_per_second": 2.723,
209
  "step": 24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
210
  }
211
  ],
212
  "logging_steps": 1,
@@ -221,12 +256,12 @@
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": 5.6976943377442406e+17,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.029966703662597,
5
  "eval_steps": 8,
6
+ "global_step": 29,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
207
  "eval_samples_per_second": 10.779,
208
  "eval_steps_per_second": 2.723,
209
  "step": 24
210
+ },
211
+ {
212
+ "epoch": 0.8879023307436182,
213
+ "grad_norm": 0.209746316075325,
214
+ "learning_rate": 5.318367983829392e-06,
215
+ "loss": 0.8696,
216
+ "step": 25
217
+ },
218
+ {
219
+ "epoch": 0.9234184239733629,
220
+ "grad_norm": 0.21727362275123596,
221
+ "learning_rate": 3.0153689607045845e-06,
222
+ "loss": 0.886,
223
+ "step": 26
224
+ },
225
+ {
226
+ "epoch": 0.9589345172031076,
227
+ "grad_norm": 0.21419359743595123,
228
+ "learning_rate": 1.3477564710088098e-06,
229
+ "loss": 0.8859,
230
+ "step": 27
231
+ },
232
+ {
233
+ "epoch": 0.9944506104328524,
234
+ "grad_norm": 0.22184455394744873,
235
+ "learning_rate": 3.380821129028489e-07,
236
+ "loss": 0.8763,
237
+ "step": 28
238
+ },
239
+ {
240
+ "epoch": 1.029966703662597,
241
+ "grad_norm": 0.48768743872642517,
242
+ "learning_rate": 0.0,
243
+ "loss": 1.5605,
244
+ "step": 29
245
  }
246
  ],
247
  "logging_steps": 1,
 
256
  "should_evaluate": false,
257
  "should_log": false,
258
  "should_save": true,
259
+ "should_training_stop": true
260
  },
261
  "attributes": {}
262
  }
263
  },
264
+ "total_flos": 6.884713991440957e+17,
265
  "train_batch_size": 2,
266
  "trial_name": null,
267
  "trial_params": null