Shresthadev403 commited on
Commit
30a01e1
1 Parent(s): f63b342

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: 0.9052
17
- - eval_runtime: 1372.6886
18
- - eval_samples_per_second: 109.275
19
- - eval_steps_per_second: 1.708
20
- - epoch: 17.78
21
- - step: 750000
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: 0.9034
17
+ - eval_runtime: 1376.7168
18
+ - eval_samples_per_second: 108.955
19
+ - eval_steps_per_second: 1.703
20
+ - epoch: 18.96
21
+ - step: 800000
22
 
23
  ## Model description
24
 
logs/events.out.tfevents.1709140136.1603750d14c2.25.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739a6fc016aab02b7ce054e6e14a8c9a4bff35d40bed122d2e04dca553a4e4a2
3
+ size 5154
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d29d6d99a53aea865a135433fe708f41fc80200781badae74d7b36925f8b4142
3
  size 497918592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a347c18c530d4f57e7d1f7191e6060cd0df8e867924acb29724727579ae0277b
3
  size 497918592
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 17.777567080686453,
5
  "eval_steps": 50000,
6
- "global_step": 750000,
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": 109.275,
218
  "eval_steps_per_second": 1.708,
219
  "step": 750000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
220
  }
221
  ],
222
  "logging_steps": 50000,
@@ -224,7 +238,7 @@
224
  "num_input_tokens_seen": 0,
225
  "num_train_epochs": 100,
226
  "save_steps": 50000,
227
- "total_flos": 1.567734424141824e+18,
228
  "train_batch_size": 32,
229
  "trial_name": null,
230
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 18.96273821939888,
5
  "eval_steps": 50000,
6
+ "global_step": 800000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
217
  "eval_samples_per_second": 109.275,
218
  "eval_steps_per_second": 1.708,
219
  "step": 750000
220
+ },
221
+ {
222
+ "epoch": 18.96,
223
+ "learning_rate": 4.940762776144876e-05,
224
+ "loss": 0.8528,
225
+ "step": 800000
226
+ },
227
+ {
228
+ "epoch": 18.96,
229
+ "eval_loss": 0.9034462571144104,
230
+ "eval_runtime": 1376.7168,
231
+ "eval_samples_per_second": 108.955,
232
+ "eval_steps_per_second": 1.703,
233
+ "step": 800000
234
  }
235
  ],
236
  "logging_steps": 50000,
 
238
  "num_input_tokens_seen": 0,
239
  "num_train_epochs": 100,
240
  "save_steps": 50000,
241
+ "total_flos": 1.672250191773696e+18,
242
  "train_batch_size": 32,
243
  "trial_name": null,
244
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
3
  size 4728