catperson1208 commited on
Commit
4230841
1 Parent(s): f70d42c

Yelp review classification

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: results
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
+ # results
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: 1.3648
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: 2e-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
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 3
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.36.2
53
+ - Pytorch 2.3.0+cpu
54
+ - Datasets 2.16.1
55
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3,
24
+ "LABEL_4": 4
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "pad_token_id": 0,
31
+ "problem_type": "single_label_classification",
32
+ "qa_dropout": 0.1,
33
+ "seq_classif_dropout": 0.2,
34
+ "sinusoidal_pos_embds": false,
35
+ "tie_weights_": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.36.2",
38
+ "vocab_size": 30522
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5ce77735fd8907c73886414789c9e1f957095c5d87488628ac1ff41f7cf312
3
+ size 267841796
tmp-checkpoint-190/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2,
23
+ "LABEL_3": 3,
24
+ "LABEL_4": 4
25
+ },
26
+ "max_position_embeddings": 512,
27
+ "model_type": "distilbert",
28
+ "n_heads": 12,
29
+ "n_layers": 6,
30
+ "pad_token_id": 0,
31
+ "problem_type": "single_label_classification",
32
+ "qa_dropout": 0.1,
33
+ "seq_classif_dropout": 0.2,
34
+ "sinusoidal_pos_embds": false,
35
+ "tie_weights_": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.36.2",
38
+ "vocab_size": 30522
39
+ }
tmp-checkpoint-190/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfe752e14d624b3c9b01f5e73ec913df4cb95ed9de0b596baf29ddcf36938fd
3
+ size 267841796
tmp-checkpoint-190/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f198d4cb632ab36792c0cc1b88e310ad49a548837cbd746e55a2bfebf6c06a78
3
+ size 535742842
tmp-checkpoint-190/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152fa5092883c03114268a4e9caf7c9f29dd031192949d7cf1b9e176f997efcf
3
+ size 13990
tmp-checkpoint-190/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9575d955bd5f968932ac2b47259411bbf7b6544377a4a31744d8aec8953911df
3
+ size 1064
tmp-checkpoint-190/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.0,
5
+ "eval_steps": 500,
6
+ "global_step": 190,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 200,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 20,
15
+ "save_steps": 500,
16
+ "total_flos": 201361218355200.0,
17
+ "train_batch_size": 8,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
tmp-checkpoint-190/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ce5f541b46d33aa8546b965dddd4949f2c8d95d667a6064bbaf9db2b6cee111
3
+ size 4664
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee02e5494ca385bc1353b121d0cb41615933860717cb5e4fdd320371d5c2813
3
+ size 4664