Hugging Face's logo

julien-c
/
distilbert-sagemaker-1609802168

Text Classification
Transformers
PyTorch
distilbert
sagemaker
Inference Endpoints
Model card Files Community
2
sagemaker commited on
Commit
ccdb63f
•
1 Parent(s): b706502

commit model from SageMaker

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. README.md +22 -0
  3. checkpoint-500/config.json +22 -0
  4. checkpoint-500/optimizer.pt +3 -0
  5. checkpoint-500/pytorch_model.bin +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/trainer_state.json +22 -0
  8. checkpoint-500/training_args.bin +3 -0
  9. config.json +22 -0
  10. eval_results.txt +6 -0
  11. pytorch_model.bin +3 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -6,3 +6,4 @@
6
  *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
  *.ot filter=lfs diff=lfs merge=lfs -text
8
  *.onnx filter=lfs diff=lfs merge=lfs -text
 
 
6
  *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
  *.ot filter=lfs diff=lfs merge=lfs -text
8
  *.onnx filter=lfs diff=lfs merge=lfs -text
9
+ *.pt filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - sagemaker
5
+ datasets:
6
+ - imdb
7
+ ---
8
+
9
+ ## distilbert-sagemaker-1609802168
10
+
11
+ Trained from SageMaker HuggingFace extension.
12
+
13
+ #### Eval
14
+
15
+ | key | value |
16
+ | --- | ----- |
17
+ | eval_loss | 0.19187863171100616 |
18
+ | eval_accuracy | 0.9259 |
19
+ | eval_f1 | 0.9272173656811707 |
20
+ | eval_precision | 0.9147286821705426 |
21
+ | eval_recall | 0.9400517825134436 |
22
+ | epoch | 1.0 |
checkpoint-500/config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "vocab_size": 30522
22
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7e15c38d718f7905016fc002143d3c45bc54a46298067e449f7b658c83d0b4
3
+ size 535705407
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0afe657365814f9efd068c8336d9834b6fcdebb99269c31a6f0d20d7e3977ecd
3
+ size 267863191
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33c224e097cae2496cbff5b97adf82e72607747b4f37635cac15ec223484cf8e
3
+ size 559
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.639386189258312,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.639386189258312,
12
+ "learning_rate": 5e-05,
13
+ "loss": 0.36648394775390625,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 782,
18
+ "num_train_epochs": 1,
19
+ "total_flos": 3290972651520000,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f244a3cc12a77ba8bef12bd3f384fd1a8817271993a03d5fd7bbfc7e9a7b7b98
3
+ size 1839
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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
+ "vocab_size": 30522
22
+ }
eval_results.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch = 1.0
2
+ eval_accuracy = 0.9259
3
+ eval_f1 = 0.9272173656811707
4
+ eval_loss = 0.19187863171100616
5
+ eval_precision = 0.9147286821705426
6
+ eval_recall = 0.9400517825134436
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cabc2a8c9cc480dc918d02de1f660f81df78a701935534b49c8bfe58f1a3ea
3
+ size 267863191
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f244a3cc12a77ba8bef12bd3f384fd1a8817271993a03d5fd7bbfc7e9a7b7b98
3
+ size 1839