Hugging Face's logo

SIRIS-Lab
/
org_type_classifier

TensorBoard
Safetensors
xlm-roberta
Model card Files Metrics Community
PabloAccuosto commited on
Commit
a7b659b
·
verified ·
1 Parent(s): 60a2e1f

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. .gitattributes +1 -0
  2. checkpoint-6000/config.json +42 -0
  3. checkpoint-6000/model.safetensors +3 -0
  4. checkpoint-6000/optimizer.pt +3 -0
  5. checkpoint-6000/rng_state.pth +3 -0
  6. checkpoint-6000/scheduler.pt +3 -0
  7. checkpoint-6000/trainer_state.json +181 -0
  8. checkpoint-6000/training_args.bin +3 -0
  9. checkpoint-8000/config.json +42 -0
  10. checkpoint-8000/model.safetensors +3 -0
  11. checkpoint-8000/optimizer.pt +3 -0
  12. checkpoint-8000/rng_state.pth +3 -0
  13. checkpoint-8000/scheduler.pt +3 -0
  14. checkpoint-8000/trainer_state.json +227 -0
  15. checkpoint-8000/training_args.bin +3 -0
  16. checkpoint-9000/config.json +42 -0
  17. checkpoint-9000/model.safetensors +3 -0
  18. checkpoint-9000/optimizer.pt +3 -0
  19. checkpoint-9000/rng_state.pth +3 -0
  20. checkpoint-9000/scheduler.pt +3 -0
  21. checkpoint-9000/trainer_state.json +250 -0
  22. checkpoint-9000/training_args.bin +3 -0
  23. config.json +42 -0
  24. logs/events.out.tfevents.1752269409.chirchiq.2358031.0 +3 -0
  25. logs/events.out.tfevents.1752269883.chirchiq.2359888.0 +3 -0
  26. model.safetensors +3 -0
  27. sentencepiece.bpe.model +3 -0
  28. special_tokens_map.json +51 -0
  29. tokenizer.json +3 -0
  30. tokenizer_config.json +55 -0
  31. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-6000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "PUB",
14
+ "1": "HES",
15
+ "2": "REC",
16
+ "3": "PRC",
17
+ "4": "OTH"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "HES": 1,
23
+ "OTH": 4,
24
+ "PRC": 3,
25
+ "PUB": 0,
26
+ "REC": 2
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "xlm-roberta",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.51.3",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 250002
42
+ }
checkpoint-6000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20240c60ea0f5e21f05dcf4a463dc844c101d8f277db417933671ab599c8c631
3
+ size 2239630972
checkpoint-6000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea5cc9b5043a07af2e030753482bf20975e566e2a36a22a7b3c724bf3a77456f
3
+ size 4479497361
checkpoint-6000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:161f5de155ae8bc168fbd5fc75743ed2bbfa760cf31b9594826edc81dbcd3a36
3
+ size 14244
checkpoint-6000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bafbf7dde49e9e18ef2c9ca18ec8282299e87d202e364e05b351457404e6f7c
3
+ size 1064
checkpoint-6000/trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6000,
3
+ "best_metric": 0.851636414605088,
4
+ "best_model_checkpoint": "./org_classifier_model/checkpoint-6000",
5
+ "epoch": 1.9218449711723253,
6
+ "eval_steps": 1000,
7
+ "global_step": 6000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1601537475976938,
14
+ "grad_norm": 22.990434646606445,
15
+ "learning_rate": 1.9960000000000002e-05,
16
+ "loss": 0.7456,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.3203074951953876,
21
+ "grad_norm": 9.93404483795166,
22
+ "learning_rate": 1.9339510258107216e-05,
23
+ "loss": 0.5528,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3203074951953876,
28
+ "eval_accuracy": 0.811759758917934,
29
+ "eval_loss": 0.5824143290519714,
30
+ "eval_runtime": 30.0195,
31
+ "eval_samples_per_second": 475.325,
32
+ "eval_steps_per_second": 14.857,
33
+ "step": 1000
34
+ },
35
+ {
36
+ "epoch": 0.48046124279308133,
37
+ "grad_norm": 5.326460361480713,
38
+ "learning_rate": 1.8677696889477167e-05,
39
+ "loss": 0.5355,
40
+ "step": 1500
41
+ },
42
+ {
43
+ "epoch": 0.6406149903907752,
44
+ "grad_norm": 6.59365177154541,
45
+ "learning_rate": 1.801588352084712e-05,
46
+ "loss": 0.5158,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 0.6406149903907752,
51
+ "eval_accuracy": 0.8352372275562407,
52
+ "eval_loss": 0.5138964056968689,
53
+ "eval_runtime": 30.0319,
54
+ "eval_samples_per_second": 475.129,
55
+ "eval_steps_per_second": 14.851,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.8007687379884689,
60
+ "grad_norm": 6.453884601593018,
61
+ "learning_rate": 1.7354070152217074e-05,
62
+ "loss": 0.4983,
63
+ "step": 2500
64
+ },
65
+ {
66
+ "epoch": 0.9609224855861627,
67
+ "grad_norm": 6.576064109802246,
68
+ "learning_rate": 1.669225678358703e-05,
69
+ "loss": 0.5021,
70
+ "step": 3000
71
+ },
72
+ {
73
+ "epoch": 0.9609224855861627,
74
+ "eval_accuracy": 0.8333450136659892,
75
+ "eval_loss": 0.5071538090705872,
76
+ "eval_runtime": 30.0672,
77
+ "eval_samples_per_second": 474.571,
78
+ "eval_steps_per_second": 14.833,
79
+ "step": 3000
80
+ },
81
+ {
82
+ "epoch": 1.1210762331838564,
83
+ "grad_norm": 5.708490371704102,
84
+ "learning_rate": 1.6030443414956985e-05,
85
+ "loss": 0.46,
86
+ "step": 3500
87
+ },
88
+ {
89
+ "epoch": 1.2812299807815504,
90
+ "grad_norm": 15.795042037963867,
91
+ "learning_rate": 1.5368630046326938e-05,
92
+ "loss": 0.4409,
93
+ "step": 4000
94
+ },
95
+ {
96
+ "epoch": 1.2812299807815504,
97
+ "eval_accuracy": 0.8442778050318873,
98
+ "eval_loss": 0.5220059752464294,
99
+ "eval_runtime": 30.0818,
100
+ "eval_samples_per_second": 474.339,
101
+ "eval_steps_per_second": 14.826,
102
+ "step": 4000
103
+ },
104
+ {
105
+ "epoch": 1.4413837283792441,
106
+ "grad_norm": 6.602006435394287,
107
+ "learning_rate": 1.4706816677696892e-05,
108
+ "loss": 0.4376,
109
+ "step": 4500
110
+ },
111
+ {
112
+ "epoch": 1.6015374759769379,
113
+ "grad_norm": 12.298784255981445,
114
+ "learning_rate": 1.4045003309066846e-05,
115
+ "loss": 0.4383,
116
+ "step": 5000
117
+ },
118
+ {
119
+ "epoch": 1.6015374759769379,
120
+ "eval_accuracy": 0.847361412853038,
121
+ "eval_loss": 0.48990970849990845,
122
+ "eval_runtime": 30.093,
123
+ "eval_samples_per_second": 474.164,
124
+ "eval_steps_per_second": 14.821,
125
+ "step": 5000
126
+ },
127
+ {
128
+ "epoch": 1.7616912235746316,
129
+ "grad_norm": 14.75070571899414,
130
+ "learning_rate": 1.3383189940436797e-05,
131
+ "loss": 0.4381,
132
+ "step": 5500
133
+ },
134
+ {
135
+ "epoch": 1.9218449711723253,
136
+ "grad_norm": 7.205745697021484,
137
+ "learning_rate": 1.2721376571806751e-05,
138
+ "loss": 0.4374,
139
+ "step": 6000
140
+ },
141
+ {
142
+ "epoch": 1.9218449711723253,
143
+ "eval_accuracy": 0.851636414605088,
144
+ "eval_loss": 0.48219674825668335,
145
+ "eval_runtime": 30.0821,
146
+ "eval_samples_per_second": 474.336,
147
+ "eval_steps_per_second": 14.826,
148
+ "step": 6000
149
+ }
150
+ ],
151
+ "logging_steps": 500,
152
+ "max_steps": 15610,
153
+ "num_input_tokens_seen": 0,
154
+ "num_train_epochs": 5,
155
+ "save_steps": 1000,
156
+ "stateful_callbacks": {
157
+ "EarlyStoppingCallback": {
158
+ "args": {
159
+ "early_stopping_patience": 3,
160
+ "early_stopping_threshold": 0.0
161
+ },
162
+ "attributes": {
163
+ "early_stopping_patience_counter": 0
164
+ }
165
+ },
166
+ "TrainerControl": {
167
+ "args": {
168
+ "should_epoch_stop": false,
169
+ "should_evaluate": false,
170
+ "should_log": false,
171
+ "should_save": true,
172
+ "should_training_stop": false
173
+ },
174
+ "attributes": {}
175
+ }
176
+ },
177
+ "total_flos": 4.47266352812759e+16,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }
checkpoint-6000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8169f4ad512c6b5dfdb778db3fd4fe8528a25dc60a09121d2539bba2f90ec6a9
3
+ size 5304
checkpoint-8000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "PUB",
14
+ "1": "HES",
15
+ "2": "REC",
16
+ "3": "PRC",
17
+ "4": "OTH"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "HES": 1,
23
+ "OTH": 4,
24
+ "PRC": 3,
25
+ "PUB": 0,
26
+ "REC": 2
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "xlm-roberta",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.51.3",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 250002
42
+ }
checkpoint-8000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca1387af0ae11be5046862e69a5fd7b2982d96a33a38f2c0365996754084d533
3
+ size 2239630972
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133e371640cfed5ef6f5167d60afd74787b8c45576ab166b9a12ae9e27f11b6c
3
+ size 4479497361
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a269f092b69dcede8841c4330d8087ee0e74a202d86800c6598948444a8b098b
3
+ size 14244
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265247ad5fe25e3e10a688e02cb610244a12018a7e4745bec055c67a51f8af74
3
+ size 1064
checkpoint-8000/trainer_state.json ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6000,
3
+ "best_metric": 0.851636414605088,
4
+ "best_model_checkpoint": "./org_classifier_model/checkpoint-6000",
5
+ "epoch": 2.5624599615631007,
6
+ "eval_steps": 1000,
7
+ "global_step": 8000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1601537475976938,
14
+ "grad_norm": 22.990434646606445,
15
+ "learning_rate": 1.9960000000000002e-05,
16
+ "loss": 0.7456,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.3203074951953876,
21
+ "grad_norm": 9.93404483795166,
22
+ "learning_rate": 1.9339510258107216e-05,
23
+ "loss": 0.5528,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3203074951953876,
28
+ "eval_accuracy": 0.811759758917934,
29
+ "eval_loss": 0.5824143290519714,
30
+ "eval_runtime": 30.0195,
31
+ "eval_samples_per_second": 475.325,
32
+ "eval_steps_per_second": 14.857,
33
+ "step": 1000
34
+ },
35
+ {
36
+ "epoch": 0.48046124279308133,
37
+ "grad_norm": 5.326460361480713,
38
+ "learning_rate": 1.8677696889477167e-05,
39
+ "loss": 0.5355,
40
+ "step": 1500
41
+ },
42
+ {
43
+ "epoch": 0.6406149903907752,
44
+ "grad_norm": 6.59365177154541,
45
+ "learning_rate": 1.801588352084712e-05,
46
+ "loss": 0.5158,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 0.6406149903907752,
51
+ "eval_accuracy": 0.8352372275562407,
52
+ "eval_loss": 0.5138964056968689,
53
+ "eval_runtime": 30.0319,
54
+ "eval_samples_per_second": 475.129,
55
+ "eval_steps_per_second": 14.851,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.8007687379884689,
60
+ "grad_norm": 6.453884601593018,
61
+ "learning_rate": 1.7354070152217074e-05,
62
+ "loss": 0.4983,
63
+ "step": 2500
64
+ },
65
+ {
66
+ "epoch": 0.9609224855861627,
67
+ "grad_norm": 6.576064109802246,
68
+ "learning_rate": 1.669225678358703e-05,
69
+ "loss": 0.5021,
70
+ "step": 3000
71
+ },
72
+ {
73
+ "epoch": 0.9609224855861627,
74
+ "eval_accuracy": 0.8333450136659892,
75
+ "eval_loss": 0.5071538090705872,
76
+ "eval_runtime": 30.0672,
77
+ "eval_samples_per_second": 474.571,
78
+ "eval_steps_per_second": 14.833,
79
+ "step": 3000
80
+ },
81
+ {
82
+ "epoch": 1.1210762331838564,
83
+ "grad_norm": 5.708490371704102,
84
+ "learning_rate": 1.6030443414956985e-05,
85
+ "loss": 0.46,
86
+ "step": 3500
87
+ },
88
+ {
89
+ "epoch": 1.2812299807815504,
90
+ "grad_norm": 15.795042037963867,
91
+ "learning_rate": 1.5368630046326938e-05,
92
+ "loss": 0.4409,
93
+ "step": 4000
94
+ },
95
+ {
96
+ "epoch": 1.2812299807815504,
97
+ "eval_accuracy": 0.8442778050318873,
98
+ "eval_loss": 0.5220059752464294,
99
+ "eval_runtime": 30.0818,
100
+ "eval_samples_per_second": 474.339,
101
+ "eval_steps_per_second": 14.826,
102
+ "step": 4000
103
+ },
104
+ {
105
+ "epoch": 1.4413837283792441,
106
+ "grad_norm": 6.602006435394287,
107
+ "learning_rate": 1.4706816677696892e-05,
108
+ "loss": 0.4376,
109
+ "step": 4500
110
+ },
111
+ {
112
+ "epoch": 1.6015374759769379,
113
+ "grad_norm": 12.298784255981445,
114
+ "learning_rate": 1.4045003309066846e-05,
115
+ "loss": 0.4383,
116
+ "step": 5000
117
+ },
118
+ {
119
+ "epoch": 1.6015374759769379,
120
+ "eval_accuracy": 0.847361412853038,
121
+ "eval_loss": 0.48990970849990845,
122
+ "eval_runtime": 30.093,
123
+ "eval_samples_per_second": 474.164,
124
+ "eval_steps_per_second": 14.821,
125
+ "step": 5000
126
+ },
127
+ {
128
+ "epoch": 1.7616912235746316,
129
+ "grad_norm": 14.75070571899414,
130
+ "learning_rate": 1.3383189940436797e-05,
131
+ "loss": 0.4381,
132
+ "step": 5500
133
+ },
134
+ {
135
+ "epoch": 1.9218449711723253,
136
+ "grad_norm": 7.205745697021484,
137
+ "learning_rate": 1.2721376571806751e-05,
138
+ "loss": 0.4374,
139
+ "step": 6000
140
+ },
141
+ {
142
+ "epoch": 1.9218449711723253,
143
+ "eval_accuracy": 0.851636414605088,
144
+ "eval_loss": 0.48219674825668335,
145
+ "eval_runtime": 30.0821,
146
+ "eval_samples_per_second": 474.336,
147
+ "eval_steps_per_second": 14.826,
148
+ "step": 6000
149
+ },
150
+ {
151
+ "epoch": 2.081998718770019,
152
+ "grad_norm": 17.99625015258789,
153
+ "learning_rate": 1.2059563203176705e-05,
154
+ "loss": 0.4013,
155
+ "step": 6500
156
+ },
157
+ {
158
+ "epoch": 2.242152466367713,
159
+ "grad_norm": 13.79088020324707,
160
+ "learning_rate": 1.1397749834546658e-05,
161
+ "loss": 0.3616,
162
+ "step": 7000
163
+ },
164
+ {
165
+ "epoch": 2.242152466367713,
166
+ "eval_accuracy": 0.8472913308571028,
167
+ "eval_loss": 0.5140058398246765,
168
+ "eval_runtime": 30.089,
169
+ "eval_samples_per_second": 474.226,
170
+ "eval_steps_per_second": 14.823,
171
+ "step": 7000
172
+ },
173
+ {
174
+ "epoch": 2.4023062139654066,
175
+ "grad_norm": 9.16767692565918,
176
+ "learning_rate": 1.0735936465916612e-05,
177
+ "loss": 0.365,
178
+ "step": 7500
179
+ },
180
+ {
181
+ "epoch": 2.5624599615631007,
182
+ "grad_norm": 7.064569473266602,
183
+ "learning_rate": 1.0074123097286566e-05,
184
+ "loss": 0.3803,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 2.5624599615631007,
189
+ "eval_accuracy": 0.8470110028733618,
190
+ "eval_loss": 0.5178127884864807,
191
+ "eval_runtime": 30.1282,
192
+ "eval_samples_per_second": 473.609,
193
+ "eval_steps_per_second": 14.803,
194
+ "step": 8000
195
+ }
196
+ ],
197
+ "logging_steps": 500,
198
+ "max_steps": 15610,
199
+ "num_input_tokens_seen": 0,
200
+ "num_train_epochs": 5,
201
+ "save_steps": 1000,
202
+ "stateful_callbacks": {
203
+ "EarlyStoppingCallback": {
204
+ "args": {
205
+ "early_stopping_patience": 3,
206
+ "early_stopping_threshold": 0.0
207
+ },
208
+ "attributes": {
209
+ "early_stopping_patience_counter": 2
210
+ }
211
+ },
212
+ "TrainerControl": {
213
+ "args": {
214
+ "should_epoch_stop": false,
215
+ "should_evaluate": false,
216
+ "should_log": false,
217
+ "should_save": true,
218
+ "should_training_stop": false
219
+ },
220
+ "attributes": {}
221
+ }
222
+ },
223
+ "total_flos": 5.963116465125581e+16,
224
+ "train_batch_size": 32,
225
+ "trial_name": null,
226
+ "trial_params": null
227
+ }
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8169f4ad512c6b5dfdb778db3fd4fe8528a25dc60a09121d2539bba2f90ec6a9
3
+ size 5304
checkpoint-9000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "PUB",
14
+ "1": "HES",
15
+ "2": "REC",
16
+ "3": "PRC",
17
+ "4": "OTH"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "HES": 1,
23
+ "OTH": 4,
24
+ "PRC": 3,
25
+ "PUB": 0,
26
+ "REC": 2
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "xlm-roberta",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.51.3",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 250002
42
+ }
checkpoint-9000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff1f834a7c8586b88b7e65d85fe4a2433d80e269df2bc46f89a84d3b981b06e
3
+ size 2239630972
checkpoint-9000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7dd50745dbac82ebb7df5626dc1a0677f343da17171525ad39e8795251e9d30
3
+ size 4479497361
checkpoint-9000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8ea69575729e2066458c1322728479c6fc1634be2add4436858a3ad3f8b8bd3
3
+ size 14244
checkpoint-9000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f32626018eb54ea023e3a6383e6114135dd4d9f4185740381d97364df3717d8b
3
+ size 1064
checkpoint-9000/trainer_state.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6000,
3
+ "best_metric": 0.851636414605088,
4
+ "best_model_checkpoint": "./org_classifier_model/checkpoint-6000",
5
+ "epoch": 2.8827674567584882,
6
+ "eval_steps": 1000,
7
+ "global_step": 9000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1601537475976938,
14
+ "grad_norm": 22.990434646606445,
15
+ "learning_rate": 1.9960000000000002e-05,
16
+ "loss": 0.7456,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.3203074951953876,
21
+ "grad_norm": 9.93404483795166,
22
+ "learning_rate": 1.9339510258107216e-05,
23
+ "loss": 0.5528,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3203074951953876,
28
+ "eval_accuracy": 0.811759758917934,
29
+ "eval_loss": 0.5824143290519714,
30
+ "eval_runtime": 30.0195,
31
+ "eval_samples_per_second": 475.325,
32
+ "eval_steps_per_second": 14.857,
33
+ "step": 1000
34
+ },
35
+ {
36
+ "epoch": 0.48046124279308133,
37
+ "grad_norm": 5.326460361480713,
38
+ "learning_rate": 1.8677696889477167e-05,
39
+ "loss": 0.5355,
40
+ "step": 1500
41
+ },
42
+ {
43
+ "epoch": 0.6406149903907752,
44
+ "grad_norm": 6.59365177154541,
45
+ "learning_rate": 1.801588352084712e-05,
46
+ "loss": 0.5158,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 0.6406149903907752,
51
+ "eval_accuracy": 0.8352372275562407,
52
+ "eval_loss": 0.5138964056968689,
53
+ "eval_runtime": 30.0319,
54
+ "eval_samples_per_second": 475.129,
55
+ "eval_steps_per_second": 14.851,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.8007687379884689,
60
+ "grad_norm": 6.453884601593018,
61
+ "learning_rate": 1.7354070152217074e-05,
62
+ "loss": 0.4983,
63
+ "step": 2500
64
+ },
65
+ {
66
+ "epoch": 0.9609224855861627,
67
+ "grad_norm": 6.576064109802246,
68
+ "learning_rate": 1.669225678358703e-05,
69
+ "loss": 0.5021,
70
+ "step": 3000
71
+ },
72
+ {
73
+ "epoch": 0.9609224855861627,
74
+ "eval_accuracy": 0.8333450136659892,
75
+ "eval_loss": 0.5071538090705872,
76
+ "eval_runtime": 30.0672,
77
+ "eval_samples_per_second": 474.571,
78
+ "eval_steps_per_second": 14.833,
79
+ "step": 3000
80
+ },
81
+ {
82
+ "epoch": 1.1210762331838564,
83
+ "grad_norm": 5.708490371704102,
84
+ "learning_rate": 1.6030443414956985e-05,
85
+ "loss": 0.46,
86
+ "step": 3500
87
+ },
88
+ {
89
+ "epoch": 1.2812299807815504,
90
+ "grad_norm": 15.795042037963867,
91
+ "learning_rate": 1.5368630046326938e-05,
92
+ "loss": 0.4409,
93
+ "step": 4000
94
+ },
95
+ {
96
+ "epoch": 1.2812299807815504,
97
+ "eval_accuracy": 0.8442778050318873,
98
+ "eval_loss": 0.5220059752464294,
99
+ "eval_runtime": 30.0818,
100
+ "eval_samples_per_second": 474.339,
101
+ "eval_steps_per_second": 14.826,
102
+ "step": 4000
103
+ },
104
+ {
105
+ "epoch": 1.4413837283792441,
106
+ "grad_norm": 6.602006435394287,
107
+ "learning_rate": 1.4706816677696892e-05,
108
+ "loss": 0.4376,
109
+ "step": 4500
110
+ },
111
+ {
112
+ "epoch": 1.6015374759769379,
113
+ "grad_norm": 12.298784255981445,
114
+ "learning_rate": 1.4045003309066846e-05,
115
+ "loss": 0.4383,
116
+ "step": 5000
117
+ },
118
+ {
119
+ "epoch": 1.6015374759769379,
120
+ "eval_accuracy": 0.847361412853038,
121
+ "eval_loss": 0.48990970849990845,
122
+ "eval_runtime": 30.093,
123
+ "eval_samples_per_second": 474.164,
124
+ "eval_steps_per_second": 14.821,
125
+ "step": 5000
126
+ },
127
+ {
128
+ "epoch": 1.7616912235746316,
129
+ "grad_norm": 14.75070571899414,
130
+ "learning_rate": 1.3383189940436797e-05,
131
+ "loss": 0.4381,
132
+ "step": 5500
133
+ },
134
+ {
135
+ "epoch": 1.9218449711723253,
136
+ "grad_norm": 7.205745697021484,
137
+ "learning_rate": 1.2721376571806751e-05,
138
+ "loss": 0.4374,
139
+ "step": 6000
140
+ },
141
+ {
142
+ "epoch": 1.9218449711723253,
143
+ "eval_accuracy": 0.851636414605088,
144
+ "eval_loss": 0.48219674825668335,
145
+ "eval_runtime": 30.0821,
146
+ "eval_samples_per_second": 474.336,
147
+ "eval_steps_per_second": 14.826,
148
+ "step": 6000
149
+ },
150
+ {
151
+ "epoch": 2.081998718770019,
152
+ "grad_norm": 17.99625015258789,
153
+ "learning_rate": 1.2059563203176705e-05,
154
+ "loss": 0.4013,
155
+ "step": 6500
156
+ },
157
+ {
158
+ "epoch": 2.242152466367713,
159
+ "grad_norm": 13.79088020324707,
160
+ "learning_rate": 1.1397749834546658e-05,
161
+ "loss": 0.3616,
162
+ "step": 7000
163
+ },
164
+ {
165
+ "epoch": 2.242152466367713,
166
+ "eval_accuracy": 0.8472913308571028,
167
+ "eval_loss": 0.5140058398246765,
168
+ "eval_runtime": 30.089,
169
+ "eval_samples_per_second": 474.226,
170
+ "eval_steps_per_second": 14.823,
171
+ "step": 7000
172
+ },
173
+ {
174
+ "epoch": 2.4023062139654066,
175
+ "grad_norm": 9.16767692565918,
176
+ "learning_rate": 1.0735936465916612e-05,
177
+ "loss": 0.365,
178
+ "step": 7500
179
+ },
180
+ {
181
+ "epoch": 2.5624599615631007,
182
+ "grad_norm": 7.064569473266602,
183
+ "learning_rate": 1.0074123097286566e-05,
184
+ "loss": 0.3803,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 2.5624599615631007,
189
+ "eval_accuracy": 0.8470110028733618,
190
+ "eval_loss": 0.5178127884864807,
191
+ "eval_runtime": 30.1282,
192
+ "eval_samples_per_second": 473.609,
193
+ "eval_steps_per_second": 14.803,
194
+ "step": 8000
195
+ },
196
+ {
197
+ "epoch": 2.7226137091607945,
198
+ "grad_norm": 9.597844123840332,
199
+ "learning_rate": 9.41230972865652e-06,
200
+ "loss": 0.3814,
201
+ "step": 8500
202
+ },
203
+ {
204
+ "epoch": 2.8827674567584882,
205
+ "grad_norm": 14.877305030822754,
206
+ "learning_rate": 8.750496360026473e-06,
207
+ "loss": 0.3687,
208
+ "step": 9000
209
+ },
210
+ {
211
+ "epoch": 2.8827674567584882,
212
+ "eval_accuracy": 0.8489732987595486,
213
+ "eval_loss": 0.5135728716850281,
214
+ "eval_runtime": 30.1334,
215
+ "eval_samples_per_second": 473.527,
216
+ "eval_steps_per_second": 14.801,
217
+ "step": 9000
218
+ }
219
+ ],
220
+ "logging_steps": 500,
221
+ "max_steps": 15610,
222
+ "num_input_tokens_seen": 0,
223
+ "num_train_epochs": 5,
224
+ "save_steps": 1000,
225
+ "stateful_callbacks": {
226
+ "EarlyStoppingCallback": {
227
+ "args": {
228
+ "early_stopping_patience": 3,
229
+ "early_stopping_threshold": 0.0
230
+ },
231
+ "attributes": {
232
+ "early_stopping_patience_counter": 3
233
+ }
234
+ },
235
+ "TrainerControl": {
236
+ "args": {
237
+ "should_epoch_stop": false,
238
+ "should_evaluate": false,
239
+ "should_log": false,
240
+ "should_save": true,
241
+ "should_training_stop": true
242
+ },
243
+ "attributes": {}
244
+ }
245
+ },
246
+ "total_flos": 6.708669112907981e+16,
247
+ "train_batch_size": 32,
248
+ "trial_name": null,
249
+ "trial_params": null
250
+ }
checkpoint-9000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8169f4ad512c6b5dfdb778db3fd4fe8528a25dc60a09121d2539bba2f90ec6a9
3
+ size 5304
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "PUB",
14
+ "1": "HES",
15
+ "2": "REC",
16
+ "3": "PRC",
17
+ "4": "OTH"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "HES": 1,
23
+ "OTH": 4,
24
+ "PRC": 3,
25
+ "PUB": 0,
26
+ "REC": 2
27
+ },
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "xlm-roberta",
31
+ "num_attention_heads": 16,
32
+ "num_hidden_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.51.3",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 250002
42
+ }
logs/events.out.tfevents.1752269409.chirchiq.2358031.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29068c1a9023c9c641d2f2086915dc3faeef5d70929249dab2a5850de40af3b2
3
+ size 5936
logs/events.out.tfevents.1752269883.chirchiq.2359888.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd7399cd92be498ce0e47e7b79aa00cc9d7c0bd66b7a187cb5e38b908a0258c
3
+ size 12250
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20240c60ea0f5e21f05dcf4a463dc844c101d8f277db417933671ab599c8c631
3
+ size 2239630972
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8169f4ad512c6b5dfdb778db3fd4fe8528a25dc60a09121d2539bba2f90ec6a9
3
+ size 5304