avsolatorio commited on
Commit
8395c59
1 Parent(s): cb8988c

Training in progress, step 9000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5e579fef1b7fd0038c9762b3c4fbb2d4563a550ba39f4cad986867eee7d3381
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef874c4e583779c091a7b359ad98755608a67b4a354ff62aa6f203206efed04
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:165717be452493be82c0e50980d64b28838a8e1ad86c8ce5d28ffc1cf050c018
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7eac815d45bb4fd23791a7a83f0d2a076666ede14350634daa752c963c1e370
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.04098295420408249,
3
- "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-8000",
4
- "epoch": 3.9447731755424065,
5
  "eval_steps": 1000,
6
- "global_step": 8000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -215,6 +215,32 @@
215
  "eval_samples_per_second": 560.87,
216
  "eval_steps_per_second": 2.213,
217
  "step": 8000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
218
  }
219
  ],
220
  "logging_steps": 500,
@@ -243,7 +269,7 @@
243
  "attributes": {}
244
  }
245
  },
246
- "total_flos": 181076248886436.0,
247
  "train_batch_size": 4,
248
  "trial_name": null,
249
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.03965826332569122,
3
+ "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-9000",
4
+ "epoch": 4.437869822485207,
5
  "eval_steps": 1000,
6
+ "global_step": 9000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
215
  "eval_samples_per_second": 560.87,
216
  "eval_steps_per_second": 2.213,
217
  "step": 8000
218
+ },
219
+ {
220
+ "epoch": 4.191321499013807,
221
+ "grad_norm": 0.41485270857810974,
222
+ "learning_rate": 1.916173570019724e-05,
223
+ "loss": 0.0361,
224
+ "step": 8500
225
+ },
226
+ {
227
+ "epoch": 4.437869822485207,
228
+ "grad_norm": 0.4282112717628479,
229
+ "learning_rate": 1.911242603550296e-05,
230
+ "loss": 0.0349,
231
+ "step": 9000
232
+ },
233
+ {
234
+ "epoch": 4.437869822485207,
235
+ "eval_accuracy": 0.9867851524299502,
236
+ "eval_f1": 0.5692506698697218,
237
+ "eval_loss": 0.03965826332569122,
238
+ "eval_precision": 0.7205847953216374,
239
+ "eval_recall": 0.4704489920586439,
240
+ "eval_runtime": 14.5109,
241
+ "eval_samples_per_second": 558.891,
242
+ "eval_steps_per_second": 2.205,
243
+ "step": 9000
244
  }
245
  ],
246
  "logging_steps": 500,
 
269
  "attributes": {}
270
  }
271
  },
272
+ "total_flos": 203593330777860.0,
273
  "train_batch_size": 4,
274
  "trial_name": null,
275
  "trial_params": null