Hanzalwi commited on
Commit
1a493a0
1 Parent(s): 77706d0

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:df6497b7be986e3959a3bb61600f9c868a5176d599b5978403300eea8a1f1bb0
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:623d44964634679f51782f72fac725504f858e11b7f80b1c785a61821398f079
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f967d6c2e0720085918146fc8b6abd1d0dd6b28f4e9e67250cb1c8f2d57c1b89
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5562da6f932a56bb017624b76dc514bba7d25edd54a00c07bc21e710d5f72a
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e54cd928882c59a21f0f9d6da59404bb91fe271db4a26152a1f7f27631b55a7
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2363b82feb180cfc02981d477371f95eb564639100a05b6f0935a6e396371e
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": 1.3063220977783203,
3
- "best_model_checkpoint": "./outputs/checkpoint-1500",
4
- "epoch": 2.0,
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,
@@ -217,6 +217,20 @@
217
  "eval_samples_per_second": 12.894,
218
  "eval_steps_per_second": 1.617,
219
  "step": 1500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
220
  }
221
  ],
222
  "logging_steps": 100,
@@ -224,7 +238,7 @@
224
  "num_input_tokens_seen": 0,
225
  "num_train_epochs": 3,
226
  "save_steps": 100,
227
- "total_flos": 9.54245491347456e+16,
228
  "trial_name": null,
229
  "trial_params": null
230
  }
 
1
  {
2
+ "best_metric": 1.3022856712341309,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1600",
4
+ "epoch": 2.1333333333333333,
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": 12.894,
218
  "eval_steps_per_second": 1.617,
219
  "step": 1500
220
+ },
221
+ {
222
+ "epoch": 2.13,
223
+ "learning_rate": 0.0002,
224
+ "loss": 1.0584,
225
+ "step": 1600
226
+ },
227
+ {
228
+ "epoch": 2.13,
229
+ "eval_loss": 1.3022856712341309,
230
+ "eval_runtime": 112.433,
231
+ "eval_samples_per_second": 12.905,
232
+ "eval_steps_per_second": 1.619,
233
+ "step": 1600
234
  }
235
  ],
236
  "logging_steps": 100,
 
238
  "num_input_tokens_seen": 0,
239
  "num_train_epochs": 3,
240
  "save_steps": 100,
241
+ "total_flos": 1.0180857681985536e+17,
242
  "trial_name": null,
243
  "trial_params": null
244
  }