Hugging Face's logo

ghanahmada
/
sailer-kuhperdata

Safetensors
bert
Model card Files
xet
 Community
ghanahmada commited on
Commit
5c93848
·
verified ·
1 Parent(s): b10320a

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. checkpoint-500/config.json +36 -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/scaler.pt +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/trainer_state.json +41 -0
  8. checkpoint-816/config.json +36 -0
  9. checkpoint-816/model.safetensors +3 -0
  10. checkpoint-816/optimizer.pt +3 -0
  11. checkpoint-816/rng_state.pth +3 -0
  12. checkpoint-816/scaler.pt +3 -0
  13. checkpoint-816/scheduler.pt +3 -0
  14. checkpoint-816/trainer_state.json +41 -0
  15. config.json +36 -0
  16. model.safetensors +3 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +16 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "LABEL_0"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "is_decoder": false,
21
+ "label2id": {
22
+ "LABEL_0": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "tie_word_embeddings": true,
32
+ "transformers_version": "5.3.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a353869b4dd941ee8df983fbce1ae1218c3adc86597f1ce38ec6fef1fa6a93a0
3
+ size 437951304
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f0233e5e761f8e967ec414d4a1ff2dd65ff1c9dedd248955d8522681ab32e7
3
+ size 871301195
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a536a5706d7d927ba34b82810dff3b418ef4c3aa7829150b8ea2325e0c13afd
3
+ size 14645
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d93148a7d44d3973d18d8ac5b45844f3cfe8c524c8e92cadf9b233402632c9f
3
+ size 1383
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad2f0927a6021b4a1e1d15595f0fd869d118abb2abb12e93c356f5afa2d0e28
3
+ size 1465
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.8382352941176472,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.8382352941176472,
14
+ "grad_norm": 78.5142822265625,
15
+ "learning_rate": 2.1594005449591283e-06,
16
+ "loss": 23.270005859375,
17
+ "step": 500
18
+ }
19
+ ],
20
+ "logging_steps": 500,
21
+ "max_steps": 816,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 3,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": false
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 0.0,
38
+ "train_batch_size": 4,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
checkpoint-816/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "LABEL_0"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "is_decoder": false,
21
+ "label2id": {
22
+ "LABEL_0": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "tie_word_embeddings": true,
32
+ "transformers_version": "5.3.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-816/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6999e3a00cd48712304d80af9519ac0fbd2af501225ecc24c229b9661448246
3
+ size 437951304
checkpoint-816/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc25a41e086c2443a170d365dd4737afe93667605bba350e04f2d39aebcc761c
3
+ size 871301195
checkpoint-816/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae5b12ed215ceafb77f6a5e290e47337cfad275bebd66690cd61e436bd679f6
3
+ size 14645
checkpoint-816/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9240999bbe5a9146375bdb073018ce00c962ecdbc371b0a14128cef7f1fa501f
3
+ size 1383
checkpoint-816/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82f2ca7a0e367f70537ad3bb66b1a8f720027c4809a6af53dcd967a15a83bc0
3
+ size 1465
checkpoint-816/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 816,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.8382352941176472,
14
+ "grad_norm": 78.5142822265625,
15
+ "learning_rate": 2.1594005449591283e-06,
16
+ "loss": 23.270005859375,
17
+ "step": 500
18
+ }
19
+ ],
20
+ "logging_steps": 500,
21
+ "max_steps": 816,
22
+ "num_input_tokens_seen": 0,
23
+ "num_train_epochs": 3,
24
+ "save_steps": 500,
25
+ "stateful_callbacks": {
26
+ "TrainerControl": {
27
+ "args": {
28
+ "should_epoch_stop": false,
29
+ "should_evaluate": false,
30
+ "should_log": false,
31
+ "should_save": true,
32
+ "should_training_stop": true
33
+ },
34
+ "attributes": {}
35
+ }
36
+ },
37
+ "total_flos": 0.0,
38
+ "train_batch_size": 4,
39
+ "trial_name": null,
40
+ "trial_params": null
41
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "LABEL_0"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "is_decoder": false,
21
+ "label2id": {
22
+ "LABEL_0": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "tie_word_embeddings": true,
32
+ "transformers_version": "5.3.0",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6999e3a00cd48712304d80af9519ac0fbd2af501225ecc24c229b9661448246
3
+ size 437951304
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": true,
6
+ "is_local": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }