Hugging Face's logo

toomax
/
distilBert-BASE-model

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
distilbert
Model card Files
xet
 Metrics Community
toomax commited on
Commit
1909820
·
verified ·
1 Parent(s): 52e3f03

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. checkpoint-15/config.json +35 -0
  2. checkpoint-15/model.safetensors +3 -0
  3. checkpoint-15/optimizer.pt +3 -0
  4. checkpoint-15/rng_state.pth +3 -0
  5. checkpoint-15/scheduler.pt +3 -0
  6. checkpoint-15/trainer_state.json +51 -0
  7. checkpoint-15/training_args.bin +3 -0
  8. checkpoint-54/config.json +35 -0
  9. checkpoint-54/model.safetensors +3 -0
  10. checkpoint-54/optimizer.pt +3 -0
  11. checkpoint-54/rng_state.pth +3 -0
  12. checkpoint-54/scheduler.pt +3 -0
  13. checkpoint-54/trainer_state.json +58 -0
  14. checkpoint-54/training_args.bin +3 -0
  15. config.json +35 -34
  16. model.safetensors +1 -1
  17. runs/Jul09_13-12-28_COMPU-HP/events.out.tfevents.1720552356.COMPU-HP.33856.0 +3 -0
  18. runs/Jul09_13-12-28_COMPU-HP/events.out.tfevents.1720562819.COMPU-HP.33856.1 +3 -0
  19. runs/Jul09_13-12-28_COMPU-HP/events.out.tfevents.1720564771.COMPU-HP.33856.2 +3 -0
checkpoint-15/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "NEGATIVE": 0,
19
+ "POSITIVE": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.42.3",
34
+ "vocab_size": 30522
35
+ }
checkpoint-15/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ab2c222e1356aa1bcbd62450f4222cd09018b864973797c7ed3d16b430e9e0
3
+ size 267832560
checkpoint-15/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2633b579918039b7609928b5807e75246c993fce36b093dc0e5309718b26f034
3
+ size 535724410
checkpoint-15/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bf17d298b1285280aed26227b302cc4078075b26fab14318284b088e51902f
3
+ size 13990
checkpoint-15/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875feb028a53be13a52b9cf27233b0992bdcbaab887da939320bb6bea96ff58c
3
+ size 1064
checkpoint-15/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 15,
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": 0.6,
14
+ "eval_loss": 0.9962844848632812,
15
+ "eval_runtime": 9.462,
16
+ "eval_samples_per_second": 1.057,
17
+ "eval_steps_per_second": 0.211,
18
+ "step": 5
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6,
23
+ "eval_loss": 1.5473401546478271,
24
+ "eval_runtime": 9.6188,
25
+ "eval_samples_per_second": 1.04,
26
+ "eval_steps_per_second": 0.208,
27
+ "step": 10
28
+ }
29
+ ],
30
+ "logging_steps": 30,
31
+ "max_steps": 15,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": true
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 15896087838720.0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
checkpoint-15/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b3299a0e8cdaa395b2abf6e4596ef14b2f27b8508b49b906657138af6491a3
3
+ size 5176
checkpoint-54/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "NEGATIVE": 0,
19
+ "POSITIVE": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.42.3",
34
+ "vocab_size": 30522
35
+ }
checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad036736be69d5c7234b15807037c9f9ad58aa565f06b490ebb2524aed435d6
3
+ size 267832560
checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ed35669dbcffc172215ae4243775dcee082518fb228a4c37fad8d1cf2a1744
3
+ size 535724410
checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6bde596f4d8d1a1e67c074bc918d5efc14185e35431426ac55b00b72f66af9
3
+ size 13990
checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385b15a0b0d2f8986c8e3d1f331b3d654e8f89e31cf4c9730d1f4a8fea2b6457
3
+ size 1064
checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.6,
14
+ "eval_loss": 0.7259632349014282,
15
+ "eval_runtime": 7.5322,
16
+ "eval_samples_per_second": 1.328,
17
+ "eval_steps_per_second": 0.266,
18
+ "step": 18
19
+ },
20
+ {
21
+ "epoch": 1.6666666666666665,
22
+ "grad_norm": 3.253922462463379,
23
+ "learning_rate": 2.2222222222222223e-05,
24
+ "loss": 0.6521,
25
+ "step": 30
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7,
30
+ "eval_loss": 0.6539602279663086,
31
+ "eval_runtime": 7.4252,
32
+ "eval_samples_per_second": 1.347,
33
+ "eval_steps_per_second": 0.269,
34
+ "step": 36
35
+ }
36
+ ],
37
+ "logging_steps": 30,
38
+ "max_steps": 54,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 3,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": true
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 56033709631488.0,
55
+ "train_batch_size": 8,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b3299a0e8cdaa395b2abf6e4596ef14b2f27b8508b49b906657138af6491a3
3
+ size 5176
config.json CHANGED
@@ -1,34 +1,35 @@
1
- {
2
- "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
- "activation": "gelu",
4
- "architectures": [
5
- "DistilBertForSequenceClassification"
6
- ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "finetuning_task": "sst-2",
11
- "hidden_dim": 3072,
12
- "id2label": {
13
- "0": "NEGATIVE",
14
- "1": "POSITIVE"
15
- },
16
- "initializer_range": 0.02,
17
- "label2id": {
18
- "NEGATIVE": 0,
19
- "POSITIVE": 1
20
- },
21
- "max_position_embeddings": 512,
22
- "model_type": "distilbert",
23
- "n_heads": 12,
24
- "n_layers": 6,
25
- "output_past": true,
26
- "pad_token_id": 0,
27
- "qa_dropout": 0.1,
28
- "seq_classif_dropout": 0.2,
29
- "sinusoidal_pos_embds": false,
30
- "tie_weights_": true,
31
- "torch_dtype": "float32",
32
- "transformers_version": "4.41.2",
33
- "vocab_size": 30522
34
- }
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "NEGATIVE": 0,
19
+ "POSITIVE": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.42.3",
34
+ "vocab_size": 30522
35
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61afb985df6fbe77fd84138129481f0a4444c02893782984e330f874f43cee4b
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad036736be69d5c7234b15807037c9f9ad58aa565f06b490ebb2524aed435d6
3
  size 267832560
runs/Jul09_13-12-28_COMPU-HP/events.out.tfevents.1720552356.COMPU-HP.33856.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e06a52da2d1fe4d5c6901d7a85d181c37e15da3976d5c2b22598b24f02af499
3
+ size 6297
runs/Jul09_13-12-28_COMPU-HP/events.out.tfevents.1720562819.COMPU-HP.33856.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68db44471546eda5becd1a2e50acdbea36b051ff4bba1c9d2d9f6f51614c327b
3
+ size 6504
runs/Jul09_13-12-28_COMPU-HP/events.out.tfevents.1720564771.COMPU-HP.33856.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf34aa866cc4f2989ba84c9e722d7aa25af6eb53e06ad682836e68c3ef38ead
3
+ size 405