Hugging Face's logo

junaid1993
/
bot_detection_model

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Model card Files
xet
Metrics Community
junaid1993 commited on
Commit
3d4d09c
·
verified ·
1 Parent(s): add712b

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-1000/config.json +28 -0
  2. checkpoint-1000/model.safetensors +3 -0
  3. checkpoint-1000/optimizer.pt +3 -0
  4. checkpoint-1000/rng_state.pth +3 -0
  5. checkpoint-1000/scheduler.pt +3 -0
  6. checkpoint-1000/trainer_state.json +35 -0
  7. checkpoint-1000/training_args.bin +3 -0
  8. checkpoint-1500/config.json +28 -0
  9. checkpoint-1500/model.safetensors +3 -0
  10. checkpoint-1500/optimizer.pt +3 -0
  11. checkpoint-1500/rng_state.pth +3 -0
  12. checkpoint-1500/scheduler.pt +3 -0
  13. checkpoint-1500/trainer_state.json +42 -0
  14. checkpoint-1500/training_args.bin +3 -0
  15. checkpoint-2000/config.json +28 -0
  16. checkpoint-2000/model.safetensors +3 -0
  17. checkpoint-2000/optimizer.pt +3 -0
  18. checkpoint-2000/rng_state.pth +3 -0
  19. checkpoint-2000/scheduler.pt +3 -0
  20. checkpoint-2000/trainer_state.json +49 -0
  21. checkpoint-2000/training_args.bin +3 -0
  22. checkpoint-2500/config.json +28 -0
  23. checkpoint-2500/model.safetensors +3 -0
  24. checkpoint-2500/optimizer.pt +3 -0
  25. checkpoint-2500/rng_state.pth +3 -0
  26. checkpoint-2500/scheduler.pt +3 -0
  27. checkpoint-2500/trainer_state.json +56 -0
  28. checkpoint-2500/training_args.bin +3 -0
  29. checkpoint-3000/config.json +28 -0
  30. checkpoint-3000/model.safetensors +3 -0
  31. checkpoint-3000/optimizer.pt +3 -0
  32. checkpoint-3000/rng_state.pth +3 -0
  33. checkpoint-3000/scheduler.pt +3 -0
  34. checkpoint-3000/trainer_state.json +63 -0
  35. checkpoint-3000/training_args.bin +3 -0
  36. checkpoint-500/config.json +28 -0
  37. checkpoint-500/model.safetensors +3 -0
  38. checkpoint-500/optimizer.pt +3 -0
  39. checkpoint-500/rng_state.pth +3 -0
  40. checkpoint-500/scheduler.pt +3 -0
  41. checkpoint-500/trainer_state.json +28 -0
  42. checkpoint-500/training_args.bin +3 -0
  43. config.json +28 -0
  44. merges.txt +0 -0
  45. model.safetensors +3 -0
  46. runs/Mar04_13-37-51_64a347a5a1d1/events.out.tfevents.1709559471.64a347a5a1d1.10449.0 +3 -0
  47. special_tokens_map.json +15 -0
  48. tokenizer.json +0 -0
  49. tokenizer_config.json +57 -0
  50. training_args.bin +3 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad04f32dfc88574d2c480356bd9725fc8ab1471d4ace4be4bb44e0c6a175ffee
3
+ size 328492280
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f893d86b0c3a3e541eeeb25b079fa484b688fd3d3337a47befb7a399f63c6c46
3
+ size 657044666
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f6aa5123325342023d8d4b15a9e136a18c64f497bdc523f81dbf5e56de7bddf
3
+ size 13990
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddf064baf2c2fbf6a79cafdb27bcbebaa03613021de7f3ca16f0e3d084f7f982
3
+ size 1064
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.32393909944930355,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 2.8126683235168457,
14
+ "learning_rate": 4.190152251376741e-05,
15
+ "loss": 0.6948,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 0.774754524230957,
21
+ "learning_rate": 3.380304502753482e-05,
22
+ "loss": 0.6891,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 3087,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 1,
30
+ "save_steps": 500,
31
+ "total_flos": 8279212416000.0,
32
+ "train_batch_size": 8,
33
+ "trial_name": null,
34
+ "trial_params": null
35
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856
checkpoint-1500/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4dfd3e9f0d68e5c16d478ddde90568b0c39c23577d04861b9c90e2f17035fe
3
+ size 328492280
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14cfe9fd6dc6dd7b089a52eb7f6bc841abbb5d4a8f0d68da3da2585834559b25
3
+ size 657044666
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9cb9c1a18c6d2b26b55fce3fdcdb44cef885bda039b3f5c11624c642b4a4b0
3
+ size 13990
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d412f438e2c1880353d97e300b4befe510f139a89da625932231190074abd181
3
+ size 1064
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4859086491739553,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 2.8126683235168457,
14
+ "learning_rate": 4.190152251376741e-05,
15
+ "loss": 0.6948,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 0.774754524230957,
21
+ "learning_rate": 3.380304502753482e-05,
22
+ "loss": 0.6891,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.49,
27
+ "grad_norm": 1.5728782415390015,
28
+ "learning_rate": 2.5704567541302237e-05,
29
+ "loss": 0.6892,
30
+ "step": 1500
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 3087,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 1,
37
+ "save_steps": 500,
38
+ "total_flos": 12418818624000.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856
checkpoint-2000/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d90e015d0de0ed883143e9351a00031756cfed74050c84a8f5ecfa21dc6979cd
3
+ size 328492280
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1835ebd9915864cc039b3c399574650ec2e68ed433d3de560cdb3665accaef6f
3
+ size 657044666
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc66cb56dec632de5233e24aac2009cb5e2244874e9945397a31d3434c69b6e2
3
+ size 13990
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8bcd7f84e1b76aafb4007b9866bd0b6f79fee767b1ddd2665b7982da2f8bd4e
3
+ size 1064
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6478781988986071,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 2.8126683235168457,
14
+ "learning_rate": 4.190152251376741e-05,
15
+ "loss": 0.6948,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 0.774754524230957,
21
+ "learning_rate": 3.380304502753482e-05,
22
+ "loss": 0.6891,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.49,
27
+ "grad_norm": 1.5728782415390015,
28
+ "learning_rate": 2.5704567541302237e-05,
29
+ "loss": 0.6892,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.65,
34
+ "grad_norm": 0.850047767162323,
35
+ "learning_rate": 1.760609005506965e-05,
36
+ "loss": 0.6902,
37
+ "step": 2000
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 3087,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 1,
44
+ "save_steps": 500,
45
+ "total_flos": 16558424832000.0,
46
+ "train_batch_size": 8,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856
checkpoint-2500/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8585ba66db06af8a1a866534dfba95508ac9a229a5fbf9b7e4314a83d96c4f
3
+ size 328492280
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:822ed02b982353dfdbac575c6fd28d053b378cf8087f62660eb4d29e3f9df81b
3
+ size 657044666
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb3532c23d5a27538e1da535c13be50a58bb92f0a0c32efadf0bb905711f735a
3
+ size 13990
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d4bddb319bd31c8b49f4c336b2b05338d12f54f024a71b76bbf4c584b40bd7
3
+ size 1064
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8098477486232588,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 2.8126683235168457,
14
+ "learning_rate": 4.190152251376741e-05,
15
+ "loss": 0.6948,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 0.774754524230957,
21
+ "learning_rate": 3.380304502753482e-05,
22
+ "loss": 0.6891,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.49,
27
+ "grad_norm": 1.5728782415390015,
28
+ "learning_rate": 2.5704567541302237e-05,
29
+ "loss": 0.6892,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.65,
34
+ "grad_norm": 0.850047767162323,
35
+ "learning_rate": 1.760609005506965e-05,
36
+ "loss": 0.6902,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.81,
41
+ "grad_norm": 1.3977242708206177,
42
+ "learning_rate": 9.50761256883706e-06,
43
+ "loss": 0.6881,
44
+ "step": 2500
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 3087,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 1,
51
+ "save_steps": 500,
52
+ "total_flos": 20698031040000.0,
53
+ "train_batch_size": 8,
54
+ "trial_name": null,
55
+ "trial_params": null
56
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856
checkpoint-3000/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8d0447b6b800442c5422d675216b6723930a6e2041c4e67c84d15bd9566e41
3
+ size 328492280
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e40cf52a64256192d4c2915ea8a0818a50d848d2f370b6e7bf9cf4cfc65019
3
+ size 657044666
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b6ce948887d437fd59b4b504daa310dee6beab013d68bc42655a434b67e896
3
+ size 13990
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9972b9d7ddcffb7321e8a23038db6d465c7cf27fe9363b9a117f22271dad22f
3
+ size 1064
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9718172983479106,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.16,
13
+ "grad_norm": 2.8126683235168457,
14
+ "learning_rate": 4.190152251376741e-05,
15
+ "loss": 0.6948,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.32,
20
+ "grad_norm": 0.774754524230957,
21
+ "learning_rate": 3.380304502753482e-05,
22
+ "loss": 0.6891,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.49,
27
+ "grad_norm": 1.5728782415390015,
28
+ "learning_rate": 2.5704567541302237e-05,
29
+ "loss": 0.6892,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.65,
34
+ "grad_norm": 0.850047767162323,
35
+ "learning_rate": 1.760609005506965e-05,
36
+ "loss": 0.6902,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.81,
41
+ "grad_norm": 1.3977242708206177,
42
+ "learning_rate": 9.50761256883706e-06,
43
+ "loss": 0.6881,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.97,
48
+ "grad_norm": 0.7325876355171204,
49
+ "learning_rate": 1.4091350826044704e-06,
50
+ "loss": 0.6845,
51
+ "step": 3000
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 3087,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 1,
58
+ "save_steps": 500,
59
+ "total_flos": 24837637248000.0,
60
+ "train_batch_size": 8,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856
checkpoint-500/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7146381afbf9f82787905306bd04eead645a30d99f2a859711ad8cb4fc958f61
3
+ size 328492280
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b73f20f705f132dc7d91e0aea355b0b93b0b716f33e0f4ceec83a5f38b5c2f
3
+ size 657044666
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5dcbab304e1f957ed9b34dcb276c355097bd5aa159e593fda91254f68a0df6d
3
+ size 13990
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21681fea5b78d5b547cfc6cb989f5c101024169a9db3a62e46801881ccb3ba5
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.16196954972465177,
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": 0.16,
13
+ "grad_norm": 2.8126683235168457,
14
+ "learning_rate": 4.190152251376741e-05,
15
+ "loss": 0.6948,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 3087,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 1,
23
+ "save_steps": 500,
24
+ "total_flos": 4139606208000.0,
25
+ "train_batch_size": 8,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86db8e81c01a09310376aaa659ae6ee1348629d6f46fe350bf33105a499d3c02
3
+ size 328492280
runs/Mar04_13-37-51_64a347a5a1d1/events.out.tfevents.1709559471.64a347a5a1d1.10449.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96c94844049aab790f9ded4a5e6700c09c411951bdac701855ecf2d935463cc
3
+ size 6165
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0883b104017115ede6a860fe41b785fa4b262d4342a529cd1ecace2971edae
3
+ size 4856