Hugging Face's logo

krishbharath
/
kannada_model

TensorBoard
Safetensors
bert
Model card Files
xet
Metrics Community
krishbharath commited on
Commit
9935e2d
·
verified ·
1 Parent(s): 542d2ee

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. checkpoint-30/config.json +31 -0
  2. checkpoint-30/generation_config.json +5 -0
  3. checkpoint-30/model.safetensors +3 -0
  4. checkpoint-30/optimizer.pt +3 -0
  5. checkpoint-30/rng_state.pth +3 -0
  6. checkpoint-30/scheduler.pt +3 -0
  7. checkpoint-30/trainer_state.json +32 -0
  8. checkpoint-30/training_args.bin +3 -0
  9. checkpoint-300/config.json +31 -0
  10. checkpoint-300/generation_config.json +5 -0
  11. checkpoint-300/model.safetensors +3 -0
  12. checkpoint-300/optimizer.pt +3 -0
  13. checkpoint-300/rng_state.pth +3 -0
  14. checkpoint-300/scheduler.pt +3 -0
  15. checkpoint-300/trainer_state.json +32 -0
  16. checkpoint-300/training_args.bin +3 -0
  17. config.json +31 -0
  18. generation_config.json +5 -0
  19. model.safetensors +3 -0
  20. runs/Feb15_04-49-55_9d3194bbf66e/events.out.tfevents.1739595000.9d3194bbf66e.788.0 +3 -0
  21. runs/Feb15_04-54-21_9d3194bbf66e/events.out.tfevents.1739595262.9d3194bbf66e.788.1 +3 -0
  22. runs/Feb15_05-06-57_9d3194bbf66e/events.out.tfevents.1739596018.9d3194bbf66e.788.2 +3 -0
  23. training_args.bin +3 -0
checkpoint-30/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.48.3",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-30/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.48.3"
5
+ }
checkpoint-30/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71adbcbe50e97bb3ae5a6a1d2b3147a7d9599c2cefe039d783c5a37c6a322cd
3
+ size 711921812
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e82770e7e98bc878555f51cd9d57b64d03bfa5a10d1b1c242050fe84ff4c495e
3
+ size 1423965114
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1077855ca40fd0699111042332000b791403af0a42f0b9686580d2d7ed4c6e03
3
+ size 14244
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
3
+ size 1064
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 30,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 10000,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 30234134649600.0,
29
+ "train_batch_size": 16,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44887d880f92f9dd5a61a314d6d57490cda21058e1a72f539b4bac2ff5c33586
3
+ size 5304
checkpoint-300/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/kannada_model",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.48.3",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
checkpoint-300/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.48.3"
5
+ }
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c276c128e54699b4c364369c528a8e6d8162fa23962d1df080c947f949a9cba2
3
+ size 711921812
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2574dcb1f8066835c3cbfc0c31117325683ec54890f8ea384f86912f08f31005
3
+ size 1423965114
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138f52f460b93c95ab0ed02e9df6999a2caf4824640d9bf213026bbc38b9655b
3
+ size 14244
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cabdd96162ecddbb53d954d7eb1984d5ac789bd18a1ad68743eeb1f283f45df1
3
+ size 1064
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 30.0,
5
+ "eval_steps": 500,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 300,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 30,
15
+ "save_steps": 10000,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 302341346496000.0,
29
+ "train_batch_size": 16,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c26a8030952627e38560b18e5651e7f2446c01a59ba051a60ae0219ae558e35
3
+ size 5304
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/kannada_model",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.48.3",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 119547
31
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.48.3"
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c276c128e54699b4c364369c528a8e6d8162fa23962d1df080c947f949a9cba2
3
+ size 711921812
runs/Feb15_04-49-55_9d3194bbf66e/events.out.tfevents.1739595000.9d3194bbf66e.788.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c2b60f573bc20115101f9ffbb27fd28f9455580aa156ed56618223a016a8f9
3
+ size 5553
runs/Feb15_04-54-21_9d3194bbf66e/events.out.tfevents.1739595262.9d3194bbf66e.788.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ba247934c57c4f5fcafad8284aff13f4e5a9525cfcb89b2b4acccbaceced6e7
3
+ size 5548
runs/Feb15_05-06-57_9d3194bbf66e/events.out.tfevents.1739596018.9d3194bbf66e.788.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf493e14e540a2812d460fd88cbac590d43a6462fe1cb9629a328295c32c810
3
+ size 5582
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c26a8030952627e38560b18e5651e7f2446c01a59ba051a60ae0219ae558e35
3
+ size 5304