Shresthadev403 commited on
Commit
71f3957
1 Parent(s): 7ddf80d

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: 0.9121
17
- - eval_runtime: 1374.6065
18
- - eval_samples_per_second: 109.122
19
- - eval_steps_per_second: 1.705
20
- - epoch: 13.04
21
- - step: 550000
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: 0.9102
17
+ - eval_runtime: 1370.4302
18
+ - eval_samples_per_second: 109.455
19
+ - eval_steps_per_second: 1.71
20
+ - epoch: 14.22
21
+ - step: 600000
22
 
23
  ## Model description
24
 
logs/events.out.tfevents.1708534313.ef069b1332b9.26.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec13d99b79a44c4a0f2c21aeec46b3361a26e8f77ebe1b4f68bc8fa672281dfc
3
+ size 5142
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc26b7156c94261538c66d6f1c986a9445a4c87876cad57acc8a240d957d2680
3
  size 497918592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b47e220e2f1f3ca73055393677e5e1c953e35d8d65d8603755f5e1e048690c
3
  size 497918592
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 13.036882525836731,
5
  "eval_steps": 50000,
6
- "global_step": 550000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -161,6 +161,20 @@
161
  "eval_samples_per_second": 109.122,
162
  "eval_steps_per_second": 1.705,
163
  "step": 550000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
164
  }
165
  ],
166
  "logging_steps": 50000,
@@ -168,7 +182,7 @@
168
  "num_input_tokens_seen": 0,
169
  "num_train_epochs": 100,
170
  "save_steps": 50000,
171
- "total_flos": 1.149671353614336e+18,
172
  "train_batch_size": 32,
173
  "trial_name": null,
174
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 14.222053664549161,
5
  "eval_steps": 50000,
6
+ "global_step": 600000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
161
  "eval_samples_per_second": 109.122,
162
  "eval_steps_per_second": 1.705,
163
  "step": 550000
164
+ },
165
+ {
166
+ "epoch": 14.22,
167
+ "learning_rate": 4.940762776144876e-05,
168
+ "loss": 0.8727,
169
+ "step": 600000
170
+ },
171
+ {
172
+ "epoch": 14.22,
173
+ "eval_loss": 0.9102199077606201,
174
+ "eval_runtime": 1370.4302,
175
+ "eval_samples_per_second": 109.455,
176
+ "eval_steps_per_second": 1.71,
177
+ "step": 600000
178
  }
179
  ],
180
  "logging_steps": 50000,
 
182
  "num_input_tokens_seen": 0,
183
  "num_train_epochs": 100,
184
  "save_steps": 50000,
185
+ "total_flos": 1.254187121246208e+18,
186
  "train_batch_size": 32,
187
  "trial_name": null,
188
  "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