SystemAdmin123 commited on
Commit
ac61542
·
verified ·
1 Parent(s): d73e07e

Training in progress, step 300, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b574796a04bdd5ba75f557b1e3a82835e37b6cbdc5653fbe0523f7ca548452fd
3
  size 2066752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae2287b45658d1cae69b4bfe25e777f022036e8d980148fa7635d454487588a9
3
  size 2066752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e060cb2727f49ca568161340577be6a7238338c1d2ddeb535174896912bad9a8
3
  size 2162798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45076cd7d7f407afe1d46ae5fb6859b5620dc1fca8a858a0851ce56bd11f8878
3
  size 2162798
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e165ab94e4c39d599db6d95416fe6b20ee12e2262e929ee099151db7ce619380
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4faa065a55913b65f4b0549e4d93d87e8865c0f6ec216f40a3de4d251a15322a
3
  size 15984
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9cbc25705f026b6aace4fa255cf880974da196014e31a032948b334d2ca7867
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ae8864af9d168bc9a94e5c5625da874d35a133304d7d7414b10c80148467d4
3
  size 15984
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80e9bf66df8c1928f5af3bf47317ecd1b0184ef7e9f158d6f951cc904ae9cbf3
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece1ed46b8aa193251efdc1d8393b3bb872b53f6ba93c31cc3efc627b34d74be
3
  size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcd1ed78c2e5a24c53b901fdcd13d9f77e900b35f51f226710a851a3df6e162f
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3018d94a8b9b3b95a3578032d80b8d3f31c01fab9a615c48039128422aba13ef
3
  size 15984
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea83adac914f4574ef740ff11ec2d9bdb09c46e3947a15a096778da1586b49ee
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53200af24bc9fb65fd10ddaa327aeda1804119510e1de3d0cbe9297bfbcade4
3
  size 15984
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b13ecf7497db0407aadb3d8df50c07202876652d5684788d8266bbef04783351
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c1416ffb6786e15b9550c111cad94cc2bc7bb18dea5ef0cdef3475e2015ab2
3
  size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a48ddde4793935f0588ab76c54160e3cba7ef48fcd34c2871252358b28649d52
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47857ef45555e1fc8f192b42aa88a26a9f993ff97303b3c590fa1e726221a814
3
  size 15984
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99eb96a4a039cb5447a1119d95efed52c77ed0a4b17aaf96b194ac2390ed4870
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1912f7357d97d0c536c21d15f5ae8d134b73c487be1987df761ea730336d8216
3
  size 15984
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0985d0257c892696fb7285dad69becde2a1197c31dbd94a987186cfae751de11
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74485e67705dc36efbfb69b1e54f842e1ff07894d01bb0e36d6d2526a318b300
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": 93.33333333333333,
5
  "eval_steps": 200,
6
- "global_step": 280,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -219,6 +219,20 @@
219
  "learning_rate": 2.1852399266194314e-06,
220
  "loss": 9.6595,
221
  "step": 280
 
 
 
 
 
 
 
 
 
 
 
 
 
 
222
  }
223
  ],
224
  "logging_steps": 10,
@@ -233,12 +247,12 @@
233
  "should_evaluate": false,
234
  "should_log": false,
235
  "should_save": true,
236
- "should_training_stop": false
237
  },
238
  "attributes": {}
239
  }
240
  },
241
- "total_flos": 458257575444480.0,
242
  "train_batch_size": 32,
243
  "trial_name": null,
244
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 100.0,
5
  "eval_steps": 200,
6
+ "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
219
  "learning_rate": 2.1852399266194314e-06,
220
  "loss": 9.6595,
221
  "step": 280
222
+ },
223
+ {
224
+ "epoch": 96.66666666666667,
225
+ "grad_norm": 0.3671875,
226
+ "learning_rate": 5.478104631726711e-07,
227
+ "loss": 9.659,
228
+ "step": 290
229
+ },
230
+ {
231
+ "epoch": 100.0,
232
+ "grad_norm": 0.36328125,
233
+ "learning_rate": 0.0,
234
+ "loss": 9.6596,
235
+ "step": 300
236
  }
237
  ],
238
  "logging_steps": 10,
 
247
  "should_evaluate": false,
248
  "should_log": false,
249
  "should_save": true,
250
+ "should_training_stop": true
251
  },
252
  "attributes": {}
253
  }
254
  },
255
+ "total_flos": 490990259404800.0,
256
  "train_batch_size": 32,
257
  "trial_name": null,
258
  "trial_params": null