npan1990 commited on
Commit
8374d93
verified
1 Parent(s): 4d98623

End of training

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: squad-distil-bert
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
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
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
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
54
+
55
+ - Transformers 4.37.2
56
+ - Pytorch 2.2.0+cu121
57
+ - Tokenizers 0.15.1
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": "float32",
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": "float16",
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 sha256:7a1d0e330d263149334dc80e3a61ac995a981d25afd913d45b1aee61e609d403
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e2e8bebe98a807d5e54a8987f39c2235f27a82a1334de4f178940fbd0a6760
3
+ size 132741084
runs/Feb04_00-29-29_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706999372.nikos-IdeaPad-Gaming-3-16ARH7.21675.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b033c98c4a028eaa1fc51ac2c3135582744c323790e09c0c7a793286e862809b
3
- size 13989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413761d86950891af94500083a4bdf1113bc5cbcb5234cc84f2f93a230c462df
3
+ size 14309
runs/Feb04_10-33-20_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1707035602.nikos-IdeaPad-Gaming-3-16ARH7.6915.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a712ec948a330afa3c3961a6d2f37a98056ff56bfdeb597a65f4ccb4ffed49b0
3
+ size 4240
runs/Feb04_10-34-59_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1707035701.nikos-IdeaPad-Gaming-3-16ARH7.6986.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5a3df0d1bcf08952cb52834b0b2f16cf517bb629eee1cc69ab9169839b1c4fc
3
+ size 11929
tmp-checkpoint-31000/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
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
+ }
tmp-checkpoint-31000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c0fc2ff98853f6d0dcdd0f1fbeaf024d5bdd050c56d1cb76fcf0e2ce87e4ed
3
+ size 265470032
tmp-checkpoint-31000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f6aeecfc0903b94c3d798cdcbf543cad466e15ad358bf7f2baeb20dea94ca8
3
+ size 51515729
tmp-checkpoint-31000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b31626c6a12bb2d16190e00edd2c45229b666383bf8dedc98021f40fb727580
3
+ size 4792
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b31626c6a12bb2d16190e00edd2c45229b666383bf8dedc98021f40fb727580
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7940770d5303f66b9d06a710da92855d0e2debe2445f01d0a4f6be93972e4886
3
  size 4792