Hugging Face's logo

uvegesistvan
/
EGD_RoBERTa_large

Text Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
text-embeddings-inference
Model card Files
xet
 Metrics Community
uvegesistvan commited on
Commit
a49ad25
·
verified ·
1 Parent(s): af81bef

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. checkpoint-220/config.json +39 -0
  2. checkpoint-220/model.safetensors +3 -0
  3. checkpoint-220/optimizer.pt +3 -0
  4. checkpoint-220/rng_state.pth +3 -0
  5. checkpoint-220/scheduler.pt +3 -0
  6. checkpoint-220/trainer_state.json +80 -0
  7. checkpoint-220/training_args.bin +3 -0
  8. checkpoint-330/config.json +39 -0
  9. checkpoint-330/model.safetensors +3 -0
  10. checkpoint-330/optimizer.pt +3 -0
  11. checkpoint-330/rng_state.pth +3 -0
  12. checkpoint-330/scheduler.pt +3 -0
  13. checkpoint-330/trainer_state.json +99 -0
  14. checkpoint-330/training_args.bin +3 -0
  15. checkpoint-440/config.json +39 -0
  16. checkpoint-440/model.safetensors +3 -0
  17. checkpoint-440/optimizer.pt +3 -0
  18. checkpoint-440/rng_state.pth +3 -0
  19. checkpoint-440/scheduler.pt +3 -0
  20. checkpoint-440/trainer_state.json +118 -0
  21. checkpoint-440/training_args.bin +3 -0
  22. config.json +39 -0
  23. events.out.tfevents.1740187133.c25ddd7ed770.556.5 +3 -0
  24. events.out.tfevents.1740188267.c25ddd7ed770.556.6 +3 -0
  25. events.out.tfevents.1740227431.c4da036077fd.558.0 +3 -0
  26. model.safetensors +3 -0
  27. training_args.bin +3 -0
checkpoint-220/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "output_past": true,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.49.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 250002
39
+ }
checkpoint-220/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15fd6d2e2942facddb768fdd457411767d8af46edd914ab6034c904441cb57a6
3
+ size 2239622772
checkpoint-220/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa034fb272cab05bcb800a0021316d0d9225eb5b7d41247f69ccff04e7bd693
3
+ size 4479480977
checkpoint-220/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a8945986fdf276814bb9fcf3d014144a7ab7beda128fd30b71700b2f56a166
3
+ size 14244
checkpoint-220/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef0f25b020de9bb99bd949c0bad4080f1934ecdb3db5a40e8402ee7c0ca0b1b
3
+ size 1064
checkpoint-220/trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3450152781653978,
3
+ "best_model_checkpoint": "model/checkpoint-220",
4
+ "epoch": 2.0,
5
+ "eval_steps": 50,
6
+ "global_step": 220,
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
+ "grad_norm": 14.104873657226562,
14
+ "learning_rate": 1.9411764705882355e-05,
15
+ "loss": 1.0961,
16
+ "step": 110
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.16542473919523099,
21
+ "eval_f1": 0.09270349246290698,
22
+ "eval_loss": 1.1632992029190063,
23
+ "eval_precision": 0.7526470851636933,
24
+ "eval_recall": 0.16542473919523099,
25
+ "eval_runtime": 11.4036,
26
+ "eval_samples_per_second": 58.841,
27
+ "eval_steps_per_second": 3.683,
28
+ "step": 110
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 15.977469444274902,
33
+ "learning_rate": 1.2941176470588238e-05,
34
+ "loss": 1.0752,
35
+ "step": 220
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.33084947839046197,
40
+ "eval_f1": 0.3450152781653978,
41
+ "eval_loss": 1.1183565855026245,
42
+ "eval_precision": 0.7820931798943933,
43
+ "eval_recall": 0.33084947839046197,
44
+ "eval_runtime": 11.4177,
45
+ "eval_samples_per_second": 58.768,
46
+ "eval_steps_per_second": 3.679,
47
+ "step": 220
48
+ }
49
+ ],
50
+ "logging_steps": 50,
51
+ "max_steps": 440,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 4,
54
+ "save_steps": 50,
55
+ "stateful_callbacks": {
56
+ "EarlyStoppingCallback": {
57
+ "args": {
58
+ "early_stopping_patience": 2,
59
+ "early_stopping_threshold": 0.0
60
+ },
61
+ "attributes": {
62
+ "early_stopping_patience_counter": 0
63
+ }
64
+ },
65
+ "TrainerControl": {
66
+ "args": {
67
+ "should_epoch_stop": false,
68
+ "should_evaluate": false,
69
+ "should_log": false,
70
+ "should_save": true,
71
+ "should_training_stop": false
72
+ },
73
+ "attributes": {}
74
+ }
75
+ },
76
+ "total_flos": 1637408937808896.0,
77
+ "train_batch_size": 16,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
checkpoint-220/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9684d927709f4d5cdefc54d1297b55a6cfd92ae95600254c4598dc0d0475eef0
3
+ size 5240
checkpoint-330/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "output_past": true,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.49.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 250002
39
+ }
checkpoint-330/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4071caba28974bd3eeb8caf68869b1a8962758d0338481bd3884976ad323d224
3
+ size 2239622772
checkpoint-330/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f26833509df65469eac49fd63d6b946baa81b0ef524060ad3fdfca61ac6bb1
3
+ size 4479480977
checkpoint-330/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4359dddfae0b2df287463e78b69fff6b32b9b6bee5ef505a6f8b51d7ce1fb3c2
3
+ size 14244
checkpoint-330/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d536d301311d909d60302f49b8f30d3ceccb26f43e05725ac027f4ac3054f2
3
+ size 1064
checkpoint-330/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6472613106954174,
3
+ "best_model_checkpoint": "model/checkpoint-330",
4
+ "epoch": 3.0,
5
+ "eval_steps": 50,
6
+ "global_step": 330,
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
+ "grad_norm": 14.104873657226562,
14
+ "learning_rate": 1.9411764705882355e-05,
15
+ "loss": 1.0961,
16
+ "step": 110
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.16542473919523099,
21
+ "eval_f1": 0.09270349246290698,
22
+ "eval_loss": 1.1632992029190063,
23
+ "eval_precision": 0.7526470851636933,
24
+ "eval_recall": 0.16542473919523099,
25
+ "eval_runtime": 11.4036,
26
+ "eval_samples_per_second": 58.841,
27
+ "eval_steps_per_second": 3.683,
28
+ "step": 110
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 15.977469444274902,
33
+ "learning_rate": 1.2941176470588238e-05,
34
+ "loss": 1.0752,
35
+ "step": 220
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.33084947839046197,
40
+ "eval_f1": 0.3450152781653978,
41
+ "eval_loss": 1.1183565855026245,
42
+ "eval_precision": 0.7820931798943933,
43
+ "eval_recall": 0.33084947839046197,
44
+ "eval_runtime": 11.4177,
45
+ "eval_samples_per_second": 58.768,
46
+ "eval_steps_per_second": 3.679,
47
+ "step": 220
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 40.54887390136719,
52
+ "learning_rate": 6.470588235294119e-06,
53
+ "loss": 0.7862,
54
+ "step": 330
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.6095380029806259,
59
+ "eval_f1": 0.6472613106954174,
60
+ "eval_loss": 1.0126910209655762,
61
+ "eval_precision": 0.84273606233572,
62
+ "eval_recall": 0.6095380029806259,
63
+ "eval_runtime": 11.4004,
64
+ "eval_samples_per_second": 58.858,
65
+ "eval_steps_per_second": 3.684,
66
+ "step": 330
67
+ }
68
+ ],
69
+ "logging_steps": 50,
70
+ "max_steps": 440,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 4,
73
+ "save_steps": 50,
74
+ "stateful_callbacks": {
75
+ "EarlyStoppingCallback": {
76
+ "args": {
77
+ "early_stopping_patience": 2,
78
+ "early_stopping_threshold": 0.0
79
+ },
80
+ "attributes": {
81
+ "early_stopping_patience_counter": 0
82
+ }
83
+ },
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": false
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 2456113406713344.0,
96
+ "train_batch_size": 16,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-330/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9684d927709f4d5cdefc54d1297b55a6cfd92ae95600254c4598dc0d0475eef0
3
+ size 5240
checkpoint-440/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "output_past": true,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.49.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 250002
39
+ }
checkpoint-440/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab23a1044dd50e31fa53764ee3de096ae62774049d9d1a6167ef9ce1915b3b8f
3
+ size 2239622772
checkpoint-440/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37103ed5156a97516b10199e76f9f8d566966ee64d388557ad3fc68c9525622
3
+ size 4479480977
checkpoint-440/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7e830ef5909a8ee999d4991c57845983e1bf1f91f4406b97cb64ff5e7bd9d7
3
+ size 14244
checkpoint-440/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215c51e34a5c67eca5f71a27f27694b15a51d582331af872de4f78dcb7a6341d
3
+ size 1064
checkpoint-440/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7103335474207665,
3
+ "best_model_checkpoint": "model/checkpoint-440",
4
+ "epoch": 4.0,
5
+ "eval_steps": 50,
6
+ "global_step": 440,
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
+ "grad_norm": 14.104873657226562,
14
+ "learning_rate": 1.9411764705882355e-05,
15
+ "loss": 1.0961,
16
+ "step": 110
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.16542473919523099,
21
+ "eval_f1": 0.09270349246290698,
22
+ "eval_loss": 1.1632992029190063,
23
+ "eval_precision": 0.7526470851636933,
24
+ "eval_recall": 0.16542473919523099,
25
+ "eval_runtime": 11.4036,
26
+ "eval_samples_per_second": 58.841,
27
+ "eval_steps_per_second": 3.683,
28
+ "step": 110
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 15.977469444274902,
33
+ "learning_rate": 1.2941176470588238e-05,
34
+ "loss": 1.0752,
35
+ "step": 220
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.33084947839046197,
40
+ "eval_f1": 0.3450152781653978,
41
+ "eval_loss": 1.1183565855026245,
42
+ "eval_precision": 0.7820931798943933,
43
+ "eval_recall": 0.33084947839046197,
44
+ "eval_runtime": 11.4177,
45
+ "eval_samples_per_second": 58.768,
46
+ "eval_steps_per_second": 3.679,
47
+ "step": 220
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 40.54887390136719,
52
+ "learning_rate": 6.470588235294119e-06,
53
+ "loss": 0.7862,
54
+ "step": 330
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.6095380029806259,
59
+ "eval_f1": 0.6472613106954174,
60
+ "eval_loss": 1.0126910209655762,
61
+ "eval_precision": 0.84273606233572,
62
+ "eval_recall": 0.6095380029806259,
63
+ "eval_runtime": 11.4004,
64
+ "eval_samples_per_second": 58.858,
65
+ "eval_steps_per_second": 3.684,
66
+ "step": 330
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 44.22657775878906,
71
+ "learning_rate": 0.0,
72
+ "loss": 0.5056,
73
+ "step": 440
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.6780923994038748,
78
+ "eval_f1": 0.7103335474207665,
79
+ "eval_loss": 0.8806248903274536,
80
+ "eval_precision": 0.8547034562620667,
81
+ "eval_recall": 0.6780923994038748,
82
+ "eval_runtime": 11.4401,
83
+ "eval_samples_per_second": 58.653,
84
+ "eval_steps_per_second": 3.671,
85
+ "step": 440
86
+ }
87
+ ],
88
+ "logging_steps": 50,
89
+ "max_steps": 440,
90
+ "num_input_tokens_seen": 0,
91
+ "num_train_epochs": 4,
92
+ "save_steps": 50,
93
+ "stateful_callbacks": {
94
+ "EarlyStoppingCallback": {
95
+ "args": {
96
+ "early_stopping_patience": 2,
97
+ "early_stopping_threshold": 0.0
98
+ },
99
+ "attributes": {
100
+ "early_stopping_patience_counter": 0
101
+ }
102
+ },
103
+ "TrainerControl": {
104
+ "args": {
105
+ "should_epoch_stop": false,
106
+ "should_evaluate": false,
107
+ "should_log": false,
108
+ "should_save": true,
109
+ "should_training_stop": true
110
+ },
111
+ "attributes": {}
112
+ }
113
+ },
114
+ "total_flos": 3274817875617792.0,
115
+ "train_batch_size": 16,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
checkpoint-440/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9684d927709f4d5cdefc54d1297b55a6cfd92ae95600254c4598dc0d0475eef0
3
+ size 5240
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": 1024,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2
24
+ },
25
+ "layer_norm_eps": 1e-05,
26
+ "max_position_embeddings": 514,
27
+ "model_type": "xlm-roberta",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "output_past": true,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.49.0",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 250002
39
+ }
events.out.tfevents.1740187133.c25ddd7ed770.556.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064ec7ccb0709a42a6bdf17e8b38afe133935f1d95f0006ddc1726f107f08cb7
3
+ size 8109
events.out.tfevents.1740188267.c25ddd7ed770.556.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30950d04df1dcfcc7aae3e31f598c74d5559c3712a16e4f4e42e947ad8941d9b
3
+ size 8109
events.out.tfevents.1740227431.c4da036077fd.558.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ff7825c988f7ce0b53b9f024407c08bec22bf740388f5ec22e294d67c0d34b2
3
+ size 8264
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab23a1044dd50e31fa53764ee3de096ae62774049d9d1a6167ef9ce1915b3b8f
3
+ size 2239622772
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9684d927709f4d5cdefc54d1297b55a6cfd92ae95600254c4598dc0d0475eef0
3
+ size 5240