Shresthadev403 commited on
Commit
70742b2
·
verified ·
1 Parent(s): d12a08a

End of training

Browse files
README.md CHANGED
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - eval_loss: 0.9071
17
- - eval_runtime: 1376.6401
18
- - eval_samples_per_second: 108.961
19
- - eval_steps_per_second: 1.703
20
- - epoch: 20.15
21
- - step: 850000
22
 
23
  ## Model description
24
 
 
13
 
14
  This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - eval_loss: 0.9067
17
+ - eval_runtime: 1378.1375
18
+ - eval_samples_per_second: 108.843
19
+ - eval_steps_per_second: 1.701
20
+ - epoch: 21.33
21
+ - step: 900000
22
 
23
  ## Model description
24
 
logs/events.out.tfevents.1709538402.34d8bbd0f97b.26.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2e2ab14339aa47825765627f5db692d6145b68ab9a117b6da268fe73d3666d
3
+ size 5142
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d3193ae0f4607a11d15b4d3fdc2406f7bf17648fafc46cd1c042c0e9b981345
3
  size 497918592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2cdec83bd9e62ade6c7b1d79f75a934bf7aa79979795b153b6a0c2744e6142
3
  size 497918592
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 20.14790935811131,
5
  "eval_steps": 50000,
6
- "global_step": 850000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -245,6 +245,20 @@
245
  "eval_samples_per_second": 108.961,
246
  "eval_steps_per_second": 1.703,
247
  "step": 850000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248
  }
249
  ],
250
  "logging_steps": 50000,
@@ -252,7 +266,7 @@
252
  "num_input_tokens_seen": 0,
253
  "num_train_epochs": 100,
254
  "save_steps": 50000,
255
- "total_flos": 1.77676491423744e+18,
256
  "train_batch_size": 32,
257
  "trial_name": null,
258
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 21.33308049682374,
5
  "eval_steps": 50000,
6
+ "global_step": 900000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
245
  "eval_samples_per_second": 108.961,
246
  "eval_steps_per_second": 1.703,
247
  "step": 850000
248
+ },
249
+ {
250
+ "epoch": 21.33,
251
+ "learning_rate": 4.940761590973737e-05,
252
+ "loss": 0.8407,
253
+ "step": 900000
254
+ },
255
+ {
256
+ "epoch": 21.33,
257
+ "eval_loss": 0.906717836856842,
258
+ "eval_runtime": 1378.1375,
259
+ "eval_samples_per_second": 108.843,
260
+ "eval_steps_per_second": 1.701,
261
+ "step": 900000
262
  }
263
  ],
264
  "logging_steps": 50000,
 
266
  "num_input_tokens_seen": 0,
267
  "num_train_epochs": 100,
268
  "save_steps": 50000,
269
+ "total_flos": 1.881280681869312e+18,
270
  "train_batch_size": 32,
271
  "trial_name": null,
272
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
3
  size 4728