npan1990 commited on
Commit
ac7712c
verified
1 Parent(s): 8374d93

End of training

Browse files
README.md CHANGED
@@ -14,8 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
14
  # squad-distil-bert
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
- It achieves the following results on the evaluation set:
18
- - Loss: nan
19
 
20
  ## Model description
21
 
@@ -34,20 +32,19 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 1e-05
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 2
44
 
45
  ### Training results
46
 
47
- | Training Loss | Epoch | Step | Validation Loss |
48
- |:-------------:|:-----:|:-----:|:---------------:|
49
- | 0.0 | 1.0 | 10852 | nan |
50
- | 0.0 | 2.0 | 21704 | nan |
51
 
52
 
53
  ### Framework versions
 
14
  # squad-distil-bert
15
 
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 
 
17
 
18
  ## Model description
19
 
 
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
+ - learning_rate: 0.0001
36
  - train_batch_size: 8
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
  - lr_scheduler_type: linear
41
+ - num_epochs: 1
42
 
43
  ### Training results
44
 
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:----:|:---------------:|
47
+ | No log | 1.0 | 125 | 3.7461 |
 
48
 
49
 
50
  ### Framework versions
config.json CHANGED
@@ -18,7 +18,7 @@
18
  "seq_classif_dropout": 0.2,
19
  "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
- "torch_dtype": "float16",
22
  "transformers_version": "4.37.2",
23
  "vocab_size": 30522
24
  }
 
18
  "seq_classif_dropout": 0.2,
19
  "sinusoidal_pos_embds": false,
20
  "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
  "transformers_version": "4.37.2",
23
  "vocab_size": 30522
24
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89e2e8bebe98a807d5e54a8987f39c2235f27a82a1334de4f178940fbd0a6760
3
- size 132741084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9d3ac954d1edd8205449c374609bc643791a397d714ef53e01bb53d66a9f69d
3
+ size 265470032
runs/Feb04_12-55-21_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1707044123.nikos-IdeaPad-Gaming-3-16ARH7.16506.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95893c38166bf90be158a0908288b94603464674f53e0c14c9c92d4195059764
3
+ size 4237
runs/Feb04_12-56-49_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1707044209.nikos-IdeaPad-Gaming-3-16ARH7.16613.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d651fc30d3eac0fc763fb4b2ad309af594237d1dc123fffb951da64e36494d
3
+ size 4851
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7940770d5303f66b9d06a710da92855d0e2debe2445f01d0a4f6be93972e4886
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe84838c7159f2f12b794848116cf20875764a8d524767534564c10dc7e864d
3
  size 4792