Shresthadev403 commited on
Commit
338528a
·
1 Parent(s): 5043a3d

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: 4.4177
17
- - eval_runtime: 0.0311
18
- - eval_samples_per_second: 64.258
19
- - eval_steps_per_second: 32.129
20
- - epoch: 2.0
21
- - step: 2
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: 4.4389
17
+ - eval_runtime: 0.03
18
+ - eval_samples_per_second: 66.75
19
+ - eval_steps_per_second: 33.375
20
+ - epoch: 3.0
21
+ - step: 3
22
 
23
  ## Model description
24
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d954126db84566a06f71865f4401052d8d5ed994c28674879ee52bcc5dc2c96d
3
  size 435820636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a8c976af2ce497cc177ad5637552212b541c7429801f42b80b6c2151a37ca8
3
  size 435820636
runs/Jan05_08-15-17_414819e23027/events.out.tfevents.1704442521.414819e23027.9579.19 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae825871995c0206f34146cb1010bc619c3a65e67ec4ea3b48a9c1ea9ce2b72a
3
- size 8266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249bbbd4afebe7c23b2510ca5d0f1ecc7cb669509e30e3bcbb913330da954f6e
3
+ size 8686
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
  "eval_steps": 1,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -35,13 +35,27 @@
35
  "eval_samples_per_second": 64.258,
36
  "eval_steps_per_second": 32.129,
37
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
39
  ],
40
  "logging_steps": 1,
41
  "max_steps": 50,
42
  "num_train_epochs": 50,
43
  "save_steps": 20,
44
- "total_flos": 1152098704800.0,
45
  "trial_name": null,
46
  "trial_params": null
47
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 1,
6
+ "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
35
  "eval_samples_per_second": 64.258,
36
  "eval_steps_per_second": 32.129,
37
  "step": 2
38
+ },
39
+ {
40
+ "epoch": 3.0,
41
+ "learning_rate": 4.7e-05,
42
+ "loss": 1.8305,
43
+ "step": 3
44
+ },
45
+ {
46
+ "epoch": 3.0,
47
+ "eval_loss": 4.438927173614502,
48
+ "eval_runtime": 0.03,
49
+ "eval_samples_per_second": 66.75,
50
+ "eval_steps_per_second": 33.375,
51
+ "step": 3
52
  }
53
  ],
54
  "logging_steps": 1,
55
  "max_steps": 50,
56
  "num_train_epochs": 50,
57
  "save_steps": 20,
58
+ "total_flos": 1728148057200.0,
59
  "trial_name": null,
60
  "trial_params": null
61
  }