Hugging Face's logo

gerbejon
/
digilog-eform-classifier

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
gerbejon commited on
Commit
8bc19f9
·
verified ·
1 Parent(s): 0e7e972

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-500/config.json +50 -0
  2. checkpoint-500/model.safetensors +3 -0
  3. checkpoint-500/optimizer.pt +3 -0
  4. checkpoint-500/rng_state.pth +3 -0
  5. checkpoint-500/scheduler.pt +3 -0
  6. checkpoint-500/trainer_state.json +40 -0
  7. checkpoint-500/training_args.bin +3 -0
  8. checkpoint-681/config.json +50 -0
  9. checkpoint-681/model.safetensors +3 -0
  10. checkpoint-681/optimizer.pt +3 -0
  11. checkpoint-681/rng_state.pth +3 -0
  12. checkpoint-681/scheduler.pt +3 -0
  13. checkpoint-681/trainer_state.json +40 -0
  14. checkpoint-681/training_args.bin +3 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
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
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8,
34
+ "LABEL_9": 9
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "problem_type": "single_label_classification",
43
+ "qa_dropout": 0.1,
44
+ "seq_classif_dropout": 0.2,
45
+ "sinusoidal_pos_embds": false,
46
+ "tie_weights_": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.49.0",
49
+ "vocab_size": 119547
50
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad825797b0d29fc081f31a8ba9d6e1a5cc2543857e953e521d88b3d5c904de3
3
+ size 541341984
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc9be92a8640680809bf2fd260a526d413893574c6b1e0802d95a0ce33e52d5
3
+ size 1082746042
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d29a9974cf45a3c76c534b0043894d7aaa847d5a5fce754c3a414698716b42
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93754e2ca02042c8abce040086fb00995437b814de831f023a199f3f5495d180
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.202643171806167,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.202643171806167,
13
+ "grad_norm": 0.23331858217716217,
14
+ "learning_rate": 1.3289280469897211e-05,
15
+ "loss": 0.5185,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 681,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 3,
23
+ "save_steps": 500,
24
+ "stateful_callbacks": {
25
+ "TrainerControl": {
26
+ "args": {
27
+ "should_epoch_stop": false,
28
+ "should_evaluate": false,
29
+ "should_log": false,
30
+ "should_save": true,
31
+ "should_training_stop": false
32
+ },
33
+ "attributes": {}
34
+ }
35
+ },
36
+ "total_flos": 529680217804800.0,
37
+ "train_batch_size": 8,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c0f1bc738d5c36ec64330a87648f050781f486f92516f228188c074f95304a
3
+ size 5304
checkpoint-681/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
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
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8,
34
+ "LABEL_9": 9
35
+ },
36
+ "max_position_embeddings": 512,
37
+ "model_type": "distilbert",
38
+ "n_heads": 12,
39
+ "n_layers": 6,
40
+ "output_past": true,
41
+ "pad_token_id": 0,
42
+ "problem_type": "single_label_classification",
43
+ "qa_dropout": 0.1,
44
+ "seq_classif_dropout": 0.2,
45
+ "sinusoidal_pos_embds": false,
46
+ "tie_weights_": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.49.0",
49
+ "vocab_size": 119547
50
+ }
checkpoint-681/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bacde270c5b1b96a3796e73f111fcea222919ec721e4b662a188588a8b5c986
3
+ size 541341984
checkpoint-681/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82dd412d9c4e36df5d6bb2427f6d75f2c57f82abb981a99b83db12e45f7aa96e
3
+ size 1082746042
checkpoint-681/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afff371cc9eb83b3cbe43dd95ad61d348a9776abe4ef1c8846c2deef2ab6c82f
3
+ size 14244
checkpoint-681/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0478cedf48961038fa4261586cd19dcf6cba45326f593452be48c9827f742e8c
3
+ size 1064
checkpoint-681/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 681,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.202643171806167,
13
+ "grad_norm": 0.23331858217716217,
14
+ "learning_rate": 1.3289280469897211e-05,
15
+ "loss": 0.5185,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 681,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 3,
23
+ "save_steps": 500,
24
+ "stateful_callbacks": {
25
+ "TrainerControl": {
26
+ "args": {
27
+ "should_epoch_stop": false,
28
+ "should_evaluate": false,
29
+ "should_log": false,
30
+ "should_save": true,
31
+ "should_training_stop": true
32
+ },
33
+ "attributes": {}
34
+ }
35
+ },
36
+ "total_flos": 721387890432000.0,
37
+ "train_batch_size": 8,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-681/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80c0f1bc738d5c36ec64330a87648f050781f486f92516f228188c074f95304a
3
+ size 5304