Hugging Face's logo

Devishetty100
/
redmoon-gibberishdetective

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
 Metrics Community
Devishetty100 commited on
Commit
c2f2683
·
verified ·
1 Parent(s): ae44f06

Training in progress, epoch 1, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-95/config.json +33 -0
  2. checkpoint-95/model.safetensors +3 -0
  3. checkpoint-95/optimizer.pt +3 -0
  4. checkpoint-95/rng_state.pth +3 -0
  5. checkpoint-95/scaler.pt +3 -0
  6. checkpoint-95/scheduler.pt +3 -0
  7. checkpoint-95/trainer_state.json +42 -0
  8. checkpoint-95/training_args.bin +3 -0
checkpoint-95/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "clean",
13
+ "1": "gibberish"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "clean": 0,
18
+ "gibberish": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.49.0",
32
+ "vocab_size": 30522
33
+ }
checkpoint-95/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6676c1b143c8ccfa558a4f96868afc7e7e66d73c99b29d43caa266b664196fb9
3
+ size 267832560
checkpoint-95/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f29472fc6644fb96b1063de90afb4e5f97b20e9eff487ff33d06dec5ddae0a89
3
+ size 535727290
checkpoint-95/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c16bad3a5ef45420da273943dddc8a1b9c2e918783152a7d6935d6230b34394
3
+ size 14244
checkpoint-95/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f0f97954656f2b0c7f56b333a088e49015b6c56bfff5b7573a96773c36fbff
3
+ size 988
checkpoint-95/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5095e5fe129a9d18f44ea66bb15daa2478dbd199dc88ddbbce7a15cb2882ddf
3
+ size 1064
checkpoint-95/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.6642088414519094e-05,
3
+ "best_model_checkpoint": "redmoon-gibberishdetective/checkpoint-95",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 95,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 1.0,
14
+ "eval_loss": 2.6642088414519094e-05,
15
+ "eval_runtime": 0.6769,
16
+ "eval_samples_per_second": 1112.483,
17
+ "eval_steps_per_second": 35.458,
18
+ "step": 95
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 285,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": false
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 99747951187968.0,
39
+ "train_batch_size": 32,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
checkpoint-95/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60997ebe145d3815febdbc269a01a0a4faca685b7dcdcdc18ab6f0d2908ff18a
3
+ size 5368