Mason72 commited on
Commit
659213f
·
verified ·
1 Parent(s): 6435605

End of training

Browse files
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: distilbert/distilbert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: test_trainer
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # test_trainer
16
+
17
+ This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3.0
43
+
44
+ ### Framework versions
45
+
46
+ - Transformers 4.50.3
47
+ - Pytorch 2.6.0+cu124
48
+ - Datasets 3.5.0
49
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 512,
12
+ "model_type": "distilbert",
13
+ "n_heads": 12,
14
+ "n_layers": 6,
15
+ "pad_token_id": 0,
16
+ "problem_type": "single_label_classification",
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": "4.50.3",
23
+ "vocab_size": 30522
24
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f879db06e139b14ae78640db0da000cf0b79eebc52722c05c976d9175520d3
3
+ size 267832560
runs/Apr04_00-58-20_7b5845568615/events.out.tfevents.1743728332.7b5845568615.717.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1fffea1fb7a4bc0a71991e30d06ee09dc28610830c88335cafeb20c9c3902a
3
+ size 5041
runs/Apr04_00-58-20_7b5845568615/events.out.tfevents.1743728820.7b5845568615.717.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5fa78ae0705b9873b66d655de1bfc45809504c7ac61dfb5cf9a8b9c55ef08b
3
+ size 5041
runs/Apr04_01-07-23_7b5845568615/events.out.tfevents.1743728849.7b5845568615.717.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8199d207bb843e4c75674b39117b80575bea985bb77da7b029bd9778cef45b50
3
+ size 5041
runs/Apr04_01-07-23_7b5845568615/events.out.tfevents.1743728940.7b5845568615.717.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252d6aca70c879c8b79e66c350d2455b85ba501c1612637c3e51a09d18810ce8
3
+ size 5041
runs/Apr04_01-30-06_7b5845568615/events.out.tfevents.1743730215.7b5845568615.717.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525b303d78504a606b2a4a4d6b7688fce7e873f069c5e19b0dcbede273dcd4e4
3
+ size 5041
runs/Apr04_01-30-06_7b5845568615/events.out.tfevents.1743730700.7b5845568615.717.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d002a12b95a496d182702526fa8096d9b7296ca9ccb0e1da126ab1cc826504e4
3
+ size 5041
runs/Apr04_01-48-01_7b5845568615/events.out.tfevents.1743731329.7b5845568615.717.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea6ea6f3fd802fcf81e8b36c4aba8fa5e914458a0315b949b2d27ffe6256fa7
3
+ size 4923
runs/Apr04_01-48-01_7b5845568615/events.out.tfevents.1743731422.7b5845568615.717.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9a39b4278aac521b5a5eab22859c8e2b41b0a6aeddd341eaa1e5fadfbf6d74
3
+ size 6240
runs/Apr04_01-48-01_7b5845568615/events.out.tfevents.1743744447.7b5845568615.717.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7238712a4cba64061c483062e4d1f8252741d1836ed391016720eb304c4f7f73
3
+ size 4946
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf891e6a29af307821489171fec51fb2c0048f2ec4f5180e6c3484c8943e9e7
3
+ size 5368