ramdhanfirdaus commited on
Commit
1010048
1 Parent(s): 31a4a9a

Training in progress, step 1600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3386eeaf777fa8ee04d3eb6a698d8c64d05a1a27e4b7b072d3c1e502d66f21c5
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8c69a22c4024e6d6f615d58e2c795cd699118f945dcb1c8aee1912f18478f9
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d91e11143c5aca4dfc98c64510c889f61e481c7b4c113e3d924b2a79f08349ba
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9a796192f42eeebc4da2a1e5fe69a123bf78d995f0b205e0d2d8ed980cf541
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab823abb115c32fa0673f758e0b0199bf6d5f3e43f5557dbadcc612729790b53
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd0e92abf050d4ab2ae03dc05823099af1cb99bab8778b951d8b18b05768e217
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5351721048355103,
3
- "best_model_checkpoint": "./outputs/checkpoint-1500",
4
- "epoch": 1.092896174863388,
5
  "eval_steps": 100,
6
- "global_step": 1500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -217,13 +217,27 @@
217
  "eval_samples_per_second": 43.634,
218
  "eval_steps_per_second": 5.46,
219
  "step": 1500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
220
  }
221
  ],
222
  "logging_steps": 100,
223
  "max_steps": 4116,
224
  "num_train_epochs": 3,
225
  "save_steps": 100,
226
- "total_flos": 8.943146869488845e+16,
227
  "trial_name": null,
228
  "trial_params": null
229
  }
 
1
  {
2
+ "best_metric": 1.5172873735427856,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1600",
4
+ "epoch": 1.1657559198542806,
5
  "eval_steps": 100,
6
+ "global_step": 1600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
217
  "eval_samples_per_second": 43.634,
218
  "eval_steps_per_second": 5.46,
219
  "step": 1500
220
+ },
221
+ {
222
+ "epoch": 1.17,
223
+ "learning_rate": 0.0002,
224
+ "loss": 1.5063,
225
+ "step": 1600
226
+ },
227
+ {
228
+ "epoch": 1.17,
229
+ "eval_loss": 1.5172873735427856,
230
+ "eval_runtime": 143.6475,
231
+ "eval_samples_per_second": 43.676,
232
+ "eval_steps_per_second": 5.465,
233
+ "step": 1600
234
  }
235
  ],
236
  "logging_steps": 100,
237
  "max_steps": 4116,
238
  "num_train_epochs": 3,
239
  "save_steps": 100,
240
+ "total_flos": 9.539236838063309e+16,
241
  "trial_name": null,
242
  "trial_params": null
243
  }