Hugging Face's logo

YagiASAFAS
/
PhilippinesPoliBERT

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
YagiASAFAS commited on
Commit
6554d8c
·
verified ·
1 Parent(s): 44987e5

Training in progress, epoch 1

Browse files
Files changed (34) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-1000/config.json +93 -0
  3. run-0/checkpoint-1000/model.safetensors +3 -0
  4. run-0/checkpoint-1000/optimizer.pt +3 -0
  5. run-0/checkpoint-1000/rng_state.pth +3 -0
  6. run-0/checkpoint-1000/scaler.pt +3 -0
  7. run-0/checkpoint-1000/scheduler.pt +3 -0
  8. run-0/checkpoint-1000/trainer_state.json +221 -0
  9. run-0/checkpoint-1000/training_args.bin +3 -0
  10. run-0/checkpoint-1250/config.json +93 -0
  11. run-0/checkpoint-1250/model.safetensors +3 -0
  12. run-0/checkpoint-1250/optimizer.pt +3 -0
  13. run-0/checkpoint-1250/rng_state.pth +3 -0
  14. run-0/checkpoint-1250/scaler.pt +3 -0
  15. run-0/checkpoint-1250/scheduler.pt +3 -0
  16. run-0/checkpoint-1250/trainer_state.json +261 -0
  17. run-0/checkpoint-1250/training_args.bin +3 -0
  18. run-0/checkpoint-750/config.json +93 -0
  19. run-0/checkpoint-750/model.safetensors +3 -0
  20. run-0/checkpoint-750/optimizer.pt +3 -0
  21. run-0/checkpoint-750/rng_state.pth +3 -0
  22. run-0/checkpoint-750/scaler.pt +3 -0
  23. run-0/checkpoint-750/scheduler.pt +3 -0
  24. run-0/checkpoint-750/trainer_state.json +174 -0
  25. run-0/checkpoint-750/training_args.bin +3 -0
  26. run-1/checkpoint-250/config.json +93 -0
  27. run-1/checkpoint-250/model.safetensors +3 -0
  28. run-1/checkpoint-250/optimizer.pt +3 -0
  29. run-1/checkpoint-250/rng_state.pth +3 -0
  30. run-1/checkpoint-250/scaler.pt +3 -0
  31. run-1/checkpoint-250/scheduler.pt +3 -0
  32. run-1/checkpoint-250/trainer_state.json +87 -0
  33. run-1/checkpoint-250/training_args.bin +3 -0
  34. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c10e176fdda2bbd3351169b018330cf2712ed225d339ebff8d6d92bebfa3d62
3
  size 438050928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3e3d0e23abfd10cd04263e92f7139e3d7989458d4230241b4119150b2b0cc1
3
  size 438050928
run-0/checkpoint-1000/config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_10": 10,
51
+ "LABEL_11": 11,
52
+ "LABEL_12": 12,
53
+ "LABEL_13": 13,
54
+ "LABEL_14": 14,
55
+ "LABEL_15": 15,
56
+ "LABEL_16": 16,
57
+ "LABEL_17": 17,
58
+ "LABEL_18": 18,
59
+ "LABEL_19": 19,
60
+ "LABEL_2": 2,
61
+ "LABEL_20": 20,
62
+ "LABEL_21": 21,
63
+ "LABEL_22": 22,
64
+ "LABEL_23": 23,
65
+ "LABEL_24": 24,
66
+ "LABEL_25": 25,
67
+ "LABEL_26": 26,
68
+ "LABEL_27": 27,
69
+ "LABEL_28": 28,
70
+ "LABEL_29": 29,
71
+ "LABEL_3": 3,
72
+ "LABEL_30": 30,
73
+ "LABEL_31": 31,
74
+ "LABEL_4": 4,
75
+ "LABEL_5": 5,
76
+ "LABEL_6": 6,
77
+ "LABEL_7": 7,
78
+ "LABEL_8": 8,
79
+ "LABEL_9": 9
80
+ },
81
+ "layer_norm_eps": 1e-12,
82
+ "max_position_embeddings": 512,
83
+ "model_type": "bert",
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12,
86
+ "pad_token_id": 0,
87
+ "position_embedding_type": "absolute",
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.52.4",
90
+ "type_vocab_size": 2,
91
+ "use_cache": true,
92
+ "vocab_size": 30522
93
+ }
run-0/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81f7332954f9c4411148d59e6930f6f7b9879b85ba1312c5e8362a618cd02ca
3
+ size 438050928
run-0/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9be348ee33d60b41da573a4f9a14c607adcdf1fe0060d971bb8cca842a88188
3
+ size 876222970
run-0/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895ec29675e68d1b3c1927e42320e3a12af8a184e10c106999c38ddae836cafc
3
+ size 14244
run-0/checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d643f3b1fa6e7f2e7696bb8298271160631938d1d72585227171fa7bfea4f5a7
3
+ size 988
run-0/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:271bf330a655e6eccdde31974d5751ec6d75071126ee77f1d128d56478ec17cb
3
+ size 1064
run-0/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 0.9404726444079806,
4
+ "best_model_checkpoint": "./results/run-0/checkpoint-1000",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 2.211637020111084,
15
+ "learning_rate": 9.900000000000002e-06,
16
+ "loss": 1.75,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 2.2066681385040283,
22
+ "learning_rate": 1.9900000000000003e-05,
23
+ "loss": 0.7186,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.877,
29
+ "eval_clientelism_f1": 0.8727154934437543,
30
+ "eval_discipline_among_poor_accuracy": 0.962,
31
+ "eval_discipline_among_poor_f1": 0.9548079780361758,
32
+ "eval_economic_policy_accuracy": 0.845,
33
+ "eval_economic_policy_f1": 0.8275336377725352,
34
+ "eval_loss": 0.5389634370803833,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.801,
36
+ "eval_marcos_duterte_alliance_f1": 0.7935514430956958,
37
+ "eval_overall_accuracy": 0.8163750000000001,
38
+ "eval_overall_f1": 0.7848721167513537,
39
+ "eval_populism_accuracy": 0.621,
40
+ "eval_populism_f1": 0.5425494979676228,
41
+ "eval_regionalism_accuracy": 0.9635,
42
+ "eval_regionalism_f1": 0.9484502912073425,
43
+ "eval_runtime": 2.5195,
44
+ "eval_samples_per_second": 793.804,
45
+ "eval_security_accuracy": 0.779,
46
+ "eval_security_f1": 0.7221720339580379,
47
+ "eval_steps_per_second": 49.613,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.6825,
49
+ "eval_uniteam_positive_campaign_f1": 0.6171965585296657,
50
+ "step": 250
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "grad_norm": 1.5873570442199707,
55
+ "learning_rate": 2.98e-05,
56
+ "loss": 0.5417,
57
+ "step": 300
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "grad_norm": 2.1269659996032715,
62
+ "learning_rate": 3.9800000000000005e-05,
63
+ "loss": 0.4113,
64
+ "step": 400
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "grad_norm": 2.084075689315796,
69
+ "learning_rate": 4.9800000000000004e-05,
70
+ "loss": 0.3332,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_clientelism_accuracy": 0.942,
76
+ "eval_clientelism_f1": 0.9378017112924797,
77
+ "eval_discipline_among_poor_accuracy": 0.9715,
78
+ "eval_discipline_among_poor_f1": 0.9674839420508164,
79
+ "eval_economic_policy_accuracy": 0.927,
80
+ "eval_economic_policy_f1": 0.9177125504120144,
81
+ "eval_loss": 0.2974419593811035,
82
+ "eval_marcos_duterte_alliance_accuracy": 0.8775,
83
+ "eval_marcos_duterte_alliance_f1": 0.8621949066505684,
84
+ "eval_overall_accuracy": 0.9068750000000001,
85
+ "eval_overall_f1": 0.8953833720038622,
86
+ "eval_populism_accuracy": 0.771,
87
+ "eval_populism_f1": 0.7395767105953643,
88
+ "eval_regionalism_accuracy": 0.974,
89
+ "eval_regionalism_f1": 0.9697515588365819,
90
+ "eval_runtime": 2.632,
91
+ "eval_samples_per_second": 759.884,
92
+ "eval_security_accuracy": 0.935,
93
+ "eval_security_f1": 0.9260316892579109,
94
+ "eval_steps_per_second": 47.493,
95
+ "eval_uniteam_positive_campaign_accuracy": 0.857,
96
+ "eval_uniteam_positive_campaign_f1": 0.8425139069351617,
97
+ "step": 500
98
+ },
99
+ {
100
+ "epoch": 2.4,
101
+ "grad_norm": 1.4838664531707764,
102
+ "learning_rate": 4.346666666666667e-05,
103
+ "loss": 0.2446,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 2.8,
108
+ "grad_norm": 1.0963153839111328,
109
+ "learning_rate": 3.68e-05,
110
+ "loss": 0.2118,
111
+ "step": 700
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_clientelism_accuracy": 0.955,
116
+ "eval_clientelism_f1": 0.9540882727805983,
117
+ "eval_discipline_among_poor_accuracy": 0.975,
118
+ "eval_discipline_among_poor_f1": 0.9739612085042895,
119
+ "eval_economic_policy_accuracy": 0.957,
120
+ "eval_economic_policy_f1": 0.9565414325164922,
121
+ "eval_loss": 0.2261473685503006,
122
+ "eval_marcos_duterte_alliance_accuracy": 0.937,
123
+ "eval_marcos_duterte_alliance_f1": 0.9310010194978973,
124
+ "eval_overall_accuracy": 0.940125,
125
+ "eval_overall_f1": 0.9381674413054875,
126
+ "eval_populism_accuracy": 0.875,
127
+ "eval_populism_f1": 0.8736043447000833,
128
+ "eval_regionalism_accuracy": 0.9755,
129
+ "eval_regionalism_f1": 0.9767141680598718,
130
+ "eval_runtime": 2.49,
131
+ "eval_samples_per_second": 803.227,
132
+ "eval_security_accuracy": 0.951,
133
+ "eval_security_f1": 0.9472241490134273,
134
+ "eval_steps_per_second": 50.202,
135
+ "eval_uniteam_positive_campaign_accuracy": 0.8955,
136
+ "eval_uniteam_positive_campaign_f1": 0.8922049353712407,
137
+ "step": 750
138
+ },
139
+ {
140
+ "epoch": 3.2,
141
+ "grad_norm": 2.1868464946746826,
142
+ "learning_rate": 3.0133333333333335e-05,
143
+ "loss": 0.1716,
144
+ "step": 800
145
+ },
146
+ {
147
+ "epoch": 3.6,
148
+ "grad_norm": 0.8582445979118347,
149
+ "learning_rate": 2.3466666666666667e-05,
150
+ "loss": 0.1459,
151
+ "step": 900
152
+ },
153
+ {
154
+ "epoch": 4.0,
155
+ "grad_norm": 1.0211741924285889,
156
+ "learning_rate": 1.6800000000000002e-05,
157
+ "loss": 0.1406,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 4.0,
162
+ "eval_clientelism_accuracy": 0.949,
163
+ "eval_clientelism_f1": 0.9496538943379389,
164
+ "eval_discipline_among_poor_accuracy": 0.978,
165
+ "eval_discipline_among_poor_f1": 0.9762168341809155,
166
+ "eval_economic_policy_accuracy": 0.9565,
167
+ "eval_economic_policy_f1": 0.9561472436065863,
168
+ "eval_loss": 0.21427316963672638,
169
+ "eval_marcos_duterte_alliance_accuracy": 0.936,
170
+ "eval_marcos_duterte_alliance_f1": 0.9299279957159572,
171
+ "eval_overall_accuracy": 0.94225,
172
+ "eval_overall_f1": 0.9404726444079806,
173
+ "eval_populism_accuracy": 0.8795,
174
+ "eval_populism_f1": 0.8776516252949659,
175
+ "eval_regionalism_accuracy": 0.9805,
176
+ "eval_regionalism_f1": 0.9802434825122209,
177
+ "eval_runtime": 2.8809,
178
+ "eval_samples_per_second": 694.226,
179
+ "eval_security_accuracy": 0.953,
180
+ "eval_security_f1": 0.9500894899049392,
181
+ "eval_steps_per_second": 43.389,
182
+ "eval_uniteam_positive_campaign_accuracy": 0.9055,
183
+ "eval_uniteam_positive_campaign_f1": 0.9038505897103205,
184
+ "step": 1000
185
+ }
186
+ ],
187
+ "logging_steps": 100,
188
+ "max_steps": 1250,
189
+ "num_input_tokens_seen": 0,
190
+ "num_train_epochs": 5,
191
+ "save_steps": 500,
192
+ "stateful_callbacks": {
193
+ "EarlyStoppingCallback": {
194
+ "args": {
195
+ "early_stopping_patience": 2,
196
+ "early_stopping_threshold": 0.0
197
+ },
198
+ "attributes": {
199
+ "early_stopping_patience_counter": 0
200
+ }
201
+ },
202
+ "TrainerControl": {
203
+ "args": {
204
+ "should_epoch_stop": false,
205
+ "should_evaluate": false,
206
+ "should_log": false,
207
+ "should_save": true,
208
+ "should_training_stop": false
209
+ },
210
+ "attributes": {}
211
+ }
212
+ },
213
+ "total_flos": 8421821644800000.0,
214
+ "train_batch_size": 16,
215
+ "trial_name": null,
216
+ "trial_params": {
217
+ "gradient_accumulation_steps": 2,
218
+ "learning_rate": 5e-05,
219
+ "num_train_epochs": 5
220
+ }
221
+ }
run-0/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4ac1a107b3124d98dbf288d9cdadb50fd3cc361819791ad8ed26935eeffe26
3
+ size 5368
run-0/checkpoint-1250/config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_10": 10,
51
+ "LABEL_11": 11,
52
+ "LABEL_12": 12,
53
+ "LABEL_13": 13,
54
+ "LABEL_14": 14,
55
+ "LABEL_15": 15,
56
+ "LABEL_16": 16,
57
+ "LABEL_17": 17,
58
+ "LABEL_18": 18,
59
+ "LABEL_19": 19,
60
+ "LABEL_2": 2,
61
+ "LABEL_20": 20,
62
+ "LABEL_21": 21,
63
+ "LABEL_22": 22,
64
+ "LABEL_23": 23,
65
+ "LABEL_24": 24,
66
+ "LABEL_25": 25,
67
+ "LABEL_26": 26,
68
+ "LABEL_27": 27,
69
+ "LABEL_28": 28,
70
+ "LABEL_29": 29,
71
+ "LABEL_3": 3,
72
+ "LABEL_30": 30,
73
+ "LABEL_31": 31,
74
+ "LABEL_4": 4,
75
+ "LABEL_5": 5,
76
+ "LABEL_6": 6,
77
+ "LABEL_7": 7,
78
+ "LABEL_8": 8,
79
+ "LABEL_9": 9
80
+ },
81
+ "layer_norm_eps": 1e-12,
82
+ "max_position_embeddings": 512,
83
+ "model_type": "bert",
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12,
86
+ "pad_token_id": 0,
87
+ "position_embedding_type": "absolute",
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.52.4",
90
+ "type_vocab_size": 2,
91
+ "use_cache": true,
92
+ "vocab_size": 30522
93
+ }
run-0/checkpoint-1250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93c2bd76f6ba0b7aeea45f31cc8826b14c96ff4cb914c80434a96de62758a10
3
+ size 438050928
run-0/checkpoint-1250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc7fc4cfbaa8765e7259a9b68b143291aa0a7fec272e49ae66aa0abcfe8df30
3
+ size 876222970
run-0/checkpoint-1250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e075e1532db1c17ec921b935a69934372058cf583818c89d05c8bc844c362dc2
3
+ size 14244
run-0/checkpoint-1250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e91cb5f9c8af0e3b2c523d445ba560a4a016464486c5cb43ed7e37dcf89efc1
3
+ size 988
run-0/checkpoint-1250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cba07c233d37fae5bea0432f4724f5797e92fbb31c40167c14cb0b0d42a50261
3
+ size 1064
run-0/checkpoint-1250/trainer_state.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1250,
3
+ "best_metric": 0.945155568914976,
4
+ "best_model_checkpoint": "./results/run-0/checkpoint-1250",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1250,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 2.211637020111084,
15
+ "learning_rate": 9.900000000000002e-06,
16
+ "loss": 1.75,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 2.2066681385040283,
22
+ "learning_rate": 1.9900000000000003e-05,
23
+ "loss": 0.7186,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.877,
29
+ "eval_clientelism_f1": 0.8727154934437543,
30
+ "eval_discipline_among_poor_accuracy": 0.962,
31
+ "eval_discipline_among_poor_f1": 0.9548079780361758,
32
+ "eval_economic_policy_accuracy": 0.845,
33
+ "eval_economic_policy_f1": 0.8275336377725352,
34
+ "eval_loss": 0.5389634370803833,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.801,
36
+ "eval_marcos_duterte_alliance_f1": 0.7935514430956958,
37
+ "eval_overall_accuracy": 0.8163750000000001,
38
+ "eval_overall_f1": 0.7848721167513537,
39
+ "eval_populism_accuracy": 0.621,
40
+ "eval_populism_f1": 0.5425494979676228,
41
+ "eval_regionalism_accuracy": 0.9635,
42
+ "eval_regionalism_f1": 0.9484502912073425,
43
+ "eval_runtime": 2.5195,
44
+ "eval_samples_per_second": 793.804,
45
+ "eval_security_accuracy": 0.779,
46
+ "eval_security_f1": 0.7221720339580379,
47
+ "eval_steps_per_second": 49.613,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.6825,
49
+ "eval_uniteam_positive_campaign_f1": 0.6171965585296657,
50
+ "step": 250
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "grad_norm": 1.5873570442199707,
55
+ "learning_rate": 2.98e-05,
56
+ "loss": 0.5417,
57
+ "step": 300
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "grad_norm": 2.1269659996032715,
62
+ "learning_rate": 3.9800000000000005e-05,
63
+ "loss": 0.4113,
64
+ "step": 400
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "grad_norm": 2.084075689315796,
69
+ "learning_rate": 4.9800000000000004e-05,
70
+ "loss": 0.3332,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_clientelism_accuracy": 0.942,
76
+ "eval_clientelism_f1": 0.9378017112924797,
77
+ "eval_discipline_among_poor_accuracy": 0.9715,
78
+ "eval_discipline_among_poor_f1": 0.9674839420508164,
79
+ "eval_economic_policy_accuracy": 0.927,
80
+ "eval_economic_policy_f1": 0.9177125504120144,
81
+ "eval_loss": 0.2974419593811035,
82
+ "eval_marcos_duterte_alliance_accuracy": 0.8775,
83
+ "eval_marcos_duterte_alliance_f1": 0.8621949066505684,
84
+ "eval_overall_accuracy": 0.9068750000000001,
85
+ "eval_overall_f1": 0.8953833720038622,
86
+ "eval_populism_accuracy": 0.771,
87
+ "eval_populism_f1": 0.7395767105953643,
88
+ "eval_regionalism_accuracy": 0.974,
89
+ "eval_regionalism_f1": 0.9697515588365819,
90
+ "eval_runtime": 2.632,
91
+ "eval_samples_per_second": 759.884,
92
+ "eval_security_accuracy": 0.935,
93
+ "eval_security_f1": 0.9260316892579109,
94
+ "eval_steps_per_second": 47.493,
95
+ "eval_uniteam_positive_campaign_accuracy": 0.857,
96
+ "eval_uniteam_positive_campaign_f1": 0.8425139069351617,
97
+ "step": 500
98
+ },
99
+ {
100
+ "epoch": 2.4,
101
+ "grad_norm": 1.4838664531707764,
102
+ "learning_rate": 4.346666666666667e-05,
103
+ "loss": 0.2446,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 2.8,
108
+ "grad_norm": 1.0963153839111328,
109
+ "learning_rate": 3.68e-05,
110
+ "loss": 0.2118,
111
+ "step": 700
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_clientelism_accuracy": 0.955,
116
+ "eval_clientelism_f1": 0.9540882727805983,
117
+ "eval_discipline_among_poor_accuracy": 0.975,
118
+ "eval_discipline_among_poor_f1": 0.9739612085042895,
119
+ "eval_economic_policy_accuracy": 0.957,
120
+ "eval_economic_policy_f1": 0.9565414325164922,
121
+ "eval_loss": 0.2261473685503006,
122
+ "eval_marcos_duterte_alliance_accuracy": 0.937,
123
+ "eval_marcos_duterte_alliance_f1": 0.9310010194978973,
124
+ "eval_overall_accuracy": 0.940125,
125
+ "eval_overall_f1": 0.9381674413054875,
126
+ "eval_populism_accuracy": 0.875,
127
+ "eval_populism_f1": 0.8736043447000833,
128
+ "eval_regionalism_accuracy": 0.9755,
129
+ "eval_regionalism_f1": 0.9767141680598718,
130
+ "eval_runtime": 2.49,
131
+ "eval_samples_per_second": 803.227,
132
+ "eval_security_accuracy": 0.951,
133
+ "eval_security_f1": 0.9472241490134273,
134
+ "eval_steps_per_second": 50.202,
135
+ "eval_uniteam_positive_campaign_accuracy": 0.8955,
136
+ "eval_uniteam_positive_campaign_f1": 0.8922049353712407,
137
+ "step": 750
138
+ },
139
+ {
140
+ "epoch": 3.2,
141
+ "grad_norm": 2.1868464946746826,
142
+ "learning_rate": 3.0133333333333335e-05,
143
+ "loss": 0.1716,
144
+ "step": 800
145
+ },
146
+ {
147
+ "epoch": 3.6,
148
+ "grad_norm": 0.8582445979118347,
149
+ "learning_rate": 2.3466666666666667e-05,
150
+ "loss": 0.1459,
151
+ "step": 900
152
+ },
153
+ {
154
+ "epoch": 4.0,
155
+ "grad_norm": 1.0211741924285889,
156
+ "learning_rate": 1.6800000000000002e-05,
157
+ "loss": 0.1406,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 4.0,
162
+ "eval_clientelism_accuracy": 0.949,
163
+ "eval_clientelism_f1": 0.9496538943379389,
164
+ "eval_discipline_among_poor_accuracy": 0.978,
165
+ "eval_discipline_among_poor_f1": 0.9762168341809155,
166
+ "eval_economic_policy_accuracy": 0.9565,
167
+ "eval_economic_policy_f1": 0.9561472436065863,
168
+ "eval_loss": 0.21427316963672638,
169
+ "eval_marcos_duterte_alliance_accuracy": 0.936,
170
+ "eval_marcos_duterte_alliance_f1": 0.9299279957159572,
171
+ "eval_overall_accuracy": 0.94225,
172
+ "eval_overall_f1": 0.9404726444079806,
173
+ "eval_populism_accuracy": 0.8795,
174
+ "eval_populism_f1": 0.8776516252949659,
175
+ "eval_regionalism_accuracy": 0.9805,
176
+ "eval_regionalism_f1": 0.9802434825122209,
177
+ "eval_runtime": 2.8809,
178
+ "eval_samples_per_second": 694.226,
179
+ "eval_security_accuracy": 0.953,
180
+ "eval_security_f1": 0.9500894899049392,
181
+ "eval_steps_per_second": 43.389,
182
+ "eval_uniteam_positive_campaign_accuracy": 0.9055,
183
+ "eval_uniteam_positive_campaign_f1": 0.9038505897103205,
184
+ "step": 1000
185
+ },
186
+ {
187
+ "epoch": 4.4,
188
+ "grad_norm": 0.6913638114929199,
189
+ "learning_rate": 1.0133333333333333e-05,
190
+ "loss": 0.1194,
191
+ "step": 1100
192
+ },
193
+ {
194
+ "epoch": 4.8,
195
+ "grad_norm": 0.5919657945632935,
196
+ "learning_rate": 3.466666666666667e-06,
197
+ "loss": 0.1064,
198
+ "step": 1200
199
+ },
200
+ {
201
+ "epoch": 5.0,
202
+ "eval_clientelism_accuracy": 0.9595,
203
+ "eval_clientelism_f1": 0.9585378078020401,
204
+ "eval_discipline_among_poor_accuracy": 0.9775,
205
+ "eval_discipline_among_poor_f1": 0.9767062499904495,
206
+ "eval_economic_policy_accuracy": 0.9575,
207
+ "eval_economic_policy_f1": 0.9573575756252577,
208
+ "eval_loss": 0.2044605165719986,
209
+ "eval_marcos_duterte_alliance_accuracy": 0.9415,
210
+ "eval_marcos_duterte_alliance_f1": 0.9352451189949524,
211
+ "eval_overall_accuracy": 0.9469375,
212
+ "eval_overall_f1": 0.945155568914976,
213
+ "eval_populism_accuracy": 0.8885,
214
+ "eval_populism_f1": 0.8870995956032895,
215
+ "eval_regionalism_accuracy": 0.9805,
216
+ "eval_regionalism_f1": 0.9805137433817731,
217
+ "eval_runtime": 2.5946,
218
+ "eval_samples_per_second": 770.836,
219
+ "eval_security_accuracy": 0.958,
220
+ "eval_security_f1": 0.9547363250386048,
221
+ "eval_steps_per_second": 48.177,
222
+ "eval_uniteam_positive_campaign_accuracy": 0.9125,
223
+ "eval_uniteam_positive_campaign_f1": 0.9110481348834406,
224
+ "step": 1250
225
+ }
226
+ ],
227
+ "logging_steps": 100,
228
+ "max_steps": 1250,
229
+ "num_input_tokens_seen": 0,
230
+ "num_train_epochs": 5,
231
+ "save_steps": 500,
232
+ "stateful_callbacks": {
233
+ "EarlyStoppingCallback": {
234
+ "args": {
235
+ "early_stopping_patience": 2,
236
+ "early_stopping_threshold": 0.0
237
+ },
238
+ "attributes": {
239
+ "early_stopping_patience_counter": 0
240
+ }
241
+ },
242
+ "TrainerControl": {
243
+ "args": {
244
+ "should_epoch_stop": false,
245
+ "should_evaluate": false,
246
+ "should_log": false,
247
+ "should_save": true,
248
+ "should_training_stop": true
249
+ },
250
+ "attributes": {}
251
+ }
252
+ },
253
+ "total_flos": 1.010618597376e+16,
254
+ "train_batch_size": 16,
255
+ "trial_name": null,
256
+ "trial_params": {
257
+ "gradient_accumulation_steps": 2,
258
+ "learning_rate": 5e-05,
259
+ "num_train_epochs": 5
260
+ }
261
+ }
run-0/checkpoint-1250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4ac1a107b3124d98dbf288d9cdadb50fd3cc361819791ad8ed26935eeffe26
3
+ size 5368
run-0/checkpoint-750/config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_10": 10,
51
+ "LABEL_11": 11,
52
+ "LABEL_12": 12,
53
+ "LABEL_13": 13,
54
+ "LABEL_14": 14,
55
+ "LABEL_15": 15,
56
+ "LABEL_16": 16,
57
+ "LABEL_17": 17,
58
+ "LABEL_18": 18,
59
+ "LABEL_19": 19,
60
+ "LABEL_2": 2,
61
+ "LABEL_20": 20,
62
+ "LABEL_21": 21,
63
+ "LABEL_22": 22,
64
+ "LABEL_23": 23,
65
+ "LABEL_24": 24,
66
+ "LABEL_25": 25,
67
+ "LABEL_26": 26,
68
+ "LABEL_27": 27,
69
+ "LABEL_28": 28,
70
+ "LABEL_29": 29,
71
+ "LABEL_3": 3,
72
+ "LABEL_30": 30,
73
+ "LABEL_31": 31,
74
+ "LABEL_4": 4,
75
+ "LABEL_5": 5,
76
+ "LABEL_6": 6,
77
+ "LABEL_7": 7,
78
+ "LABEL_8": 8,
79
+ "LABEL_9": 9
80
+ },
81
+ "layer_norm_eps": 1e-12,
82
+ "max_position_embeddings": 512,
83
+ "model_type": "bert",
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12,
86
+ "pad_token_id": 0,
87
+ "position_embedding_type": "absolute",
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.52.4",
90
+ "type_vocab_size": 2,
91
+ "use_cache": true,
92
+ "vocab_size": 30522
93
+ }
run-0/checkpoint-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d6e1617d030b4f15a7190a0073cb9d1fdc8e7cb054eebe08315e92ba6acbd9
3
+ size 438050928
run-0/checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bfb915e1d7a2624230e4d40a69cc6eac16e29b9258d62b5c7be0cf8608bc23
3
+ size 876222970
run-0/checkpoint-750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4f28eda59ed807ad79d8c5ee4c38e6dc5bdb88151d1f8b85343fdb7c170e46
3
+ size 14244
run-0/checkpoint-750/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dae178ac445c445b11ee854f95d0f6d821b25d5c3a2c2613dfc742c6c9e4190
3
+ size 988
run-0/checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39535a3b687e70d3665b31da931c24fcd91004cc025fb8fd89d3875a66cc3ef1
3
+ size 1064
run-0/checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 750,
3
+ "best_metric": 0.9381674413054875,
4
+ "best_model_checkpoint": "./results/run-0/checkpoint-750",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 750,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 2.211637020111084,
15
+ "learning_rate": 9.900000000000002e-06,
16
+ "loss": 1.75,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 2.2066681385040283,
22
+ "learning_rate": 1.9900000000000003e-05,
23
+ "loss": 0.7186,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.877,
29
+ "eval_clientelism_f1": 0.8727154934437543,
30
+ "eval_discipline_among_poor_accuracy": 0.962,
31
+ "eval_discipline_among_poor_f1": 0.9548079780361758,
32
+ "eval_economic_policy_accuracy": 0.845,
33
+ "eval_economic_policy_f1": 0.8275336377725352,
34
+ "eval_loss": 0.5389634370803833,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.801,
36
+ "eval_marcos_duterte_alliance_f1": 0.7935514430956958,
37
+ "eval_overall_accuracy": 0.8163750000000001,
38
+ "eval_overall_f1": 0.7848721167513537,
39
+ "eval_populism_accuracy": 0.621,
40
+ "eval_populism_f1": 0.5425494979676228,
41
+ "eval_regionalism_accuracy": 0.9635,
42
+ "eval_regionalism_f1": 0.9484502912073425,
43
+ "eval_runtime": 2.5195,
44
+ "eval_samples_per_second": 793.804,
45
+ "eval_security_accuracy": 0.779,
46
+ "eval_security_f1": 0.7221720339580379,
47
+ "eval_steps_per_second": 49.613,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.6825,
49
+ "eval_uniteam_positive_campaign_f1": 0.6171965585296657,
50
+ "step": 250
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "grad_norm": 1.5873570442199707,
55
+ "learning_rate": 2.98e-05,
56
+ "loss": 0.5417,
57
+ "step": 300
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "grad_norm": 2.1269659996032715,
62
+ "learning_rate": 3.9800000000000005e-05,
63
+ "loss": 0.4113,
64
+ "step": 400
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "grad_norm": 2.084075689315796,
69
+ "learning_rate": 4.9800000000000004e-05,
70
+ "loss": 0.3332,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_clientelism_accuracy": 0.942,
76
+ "eval_clientelism_f1": 0.9378017112924797,
77
+ "eval_discipline_among_poor_accuracy": 0.9715,
78
+ "eval_discipline_among_poor_f1": 0.9674839420508164,
79
+ "eval_economic_policy_accuracy": 0.927,
80
+ "eval_economic_policy_f1": 0.9177125504120144,
81
+ "eval_loss": 0.2974419593811035,
82
+ "eval_marcos_duterte_alliance_accuracy": 0.8775,
83
+ "eval_marcos_duterte_alliance_f1": 0.8621949066505684,
84
+ "eval_overall_accuracy": 0.9068750000000001,
85
+ "eval_overall_f1": 0.8953833720038622,
86
+ "eval_populism_accuracy": 0.771,
87
+ "eval_populism_f1": 0.7395767105953643,
88
+ "eval_regionalism_accuracy": 0.974,
89
+ "eval_regionalism_f1": 0.9697515588365819,
90
+ "eval_runtime": 2.632,
91
+ "eval_samples_per_second": 759.884,
92
+ "eval_security_accuracy": 0.935,
93
+ "eval_security_f1": 0.9260316892579109,
94
+ "eval_steps_per_second": 47.493,
95
+ "eval_uniteam_positive_campaign_accuracy": 0.857,
96
+ "eval_uniteam_positive_campaign_f1": 0.8425139069351617,
97
+ "step": 500
98
+ },
99
+ {
100
+ "epoch": 2.4,
101
+ "grad_norm": 1.4838664531707764,
102
+ "learning_rate": 4.346666666666667e-05,
103
+ "loss": 0.2446,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 2.8,
108
+ "grad_norm": 1.0963153839111328,
109
+ "learning_rate": 3.68e-05,
110
+ "loss": 0.2118,
111
+ "step": 700
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_clientelism_accuracy": 0.955,
116
+ "eval_clientelism_f1": 0.9540882727805983,
117
+ "eval_discipline_among_poor_accuracy": 0.975,
118
+ "eval_discipline_among_poor_f1": 0.9739612085042895,
119
+ "eval_economic_policy_accuracy": 0.957,
120
+ "eval_economic_policy_f1": 0.9565414325164922,
121
+ "eval_loss": 0.2261473685503006,
122
+ "eval_marcos_duterte_alliance_accuracy": 0.937,
123
+ "eval_marcos_duterte_alliance_f1": 0.9310010194978973,
124
+ "eval_overall_accuracy": 0.940125,
125
+ "eval_overall_f1": 0.9381674413054875,
126
+ "eval_populism_accuracy": 0.875,
127
+ "eval_populism_f1": 0.8736043447000833,
128
+ "eval_regionalism_accuracy": 0.9755,
129
+ "eval_regionalism_f1": 0.9767141680598718,
130
+ "eval_runtime": 2.49,
131
+ "eval_samples_per_second": 803.227,
132
+ "eval_security_accuracy": 0.951,
133
+ "eval_security_f1": 0.9472241490134273,
134
+ "eval_steps_per_second": 50.202,
135
+ "eval_uniteam_positive_campaign_accuracy": 0.8955,
136
+ "eval_uniteam_positive_campaign_f1": 0.8922049353712407,
137
+ "step": 750
138
+ }
139
+ ],
140
+ "logging_steps": 100,
141
+ "max_steps": 1250,
142
+ "num_input_tokens_seen": 0,
143
+ "num_train_epochs": 5,
144
+ "save_steps": 500,
145
+ "stateful_callbacks": {
146
+ "EarlyStoppingCallback": {
147
+ "args": {
148
+ "early_stopping_patience": 2,
149
+ "early_stopping_threshold": 0.0
150
+ },
151
+ "attributes": {
152
+ "early_stopping_patience_counter": 0
153
+ }
154
+ },
155
+ "TrainerControl": {
156
+ "args": {
157
+ "should_epoch_stop": false,
158
+ "should_evaluate": false,
159
+ "should_log": false,
160
+ "should_save": true,
161
+ "should_training_stop": false
162
+ },
163
+ "attributes": {}
164
+ }
165
+ },
166
+ "total_flos": 5895275151360000.0,
167
+ "train_batch_size": 16,
168
+ "trial_name": null,
169
+ "trial_params": {
170
+ "gradient_accumulation_steps": 2,
171
+ "learning_rate": 5e-05,
172
+ "num_train_epochs": 5
173
+ }
174
+ }
run-0/checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4ac1a107b3124d98dbf288d9cdadb50fd3cc361819791ad8ed26935eeffe26
3
+ size 5368
run-1/checkpoint-250/config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1,
50
+ "LABEL_10": 10,
51
+ "LABEL_11": 11,
52
+ "LABEL_12": 12,
53
+ "LABEL_13": 13,
54
+ "LABEL_14": 14,
55
+ "LABEL_15": 15,
56
+ "LABEL_16": 16,
57
+ "LABEL_17": 17,
58
+ "LABEL_18": 18,
59
+ "LABEL_19": 19,
60
+ "LABEL_2": 2,
61
+ "LABEL_20": 20,
62
+ "LABEL_21": 21,
63
+ "LABEL_22": 22,
64
+ "LABEL_23": 23,
65
+ "LABEL_24": 24,
66
+ "LABEL_25": 25,
67
+ "LABEL_26": 26,
68
+ "LABEL_27": 27,
69
+ "LABEL_28": 28,
70
+ "LABEL_29": 29,
71
+ "LABEL_3": 3,
72
+ "LABEL_30": 30,
73
+ "LABEL_31": 31,
74
+ "LABEL_4": 4,
75
+ "LABEL_5": 5,
76
+ "LABEL_6": 6,
77
+ "LABEL_7": 7,
78
+ "LABEL_8": 8,
79
+ "LABEL_9": 9
80
+ },
81
+ "layer_norm_eps": 1e-12,
82
+ "max_position_embeddings": 512,
83
+ "model_type": "bert",
84
+ "num_attention_heads": 12,
85
+ "num_hidden_layers": 12,
86
+ "pad_token_id": 0,
87
+ "position_embedding_type": "absolute",
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.52.4",
90
+ "type_vocab_size": 2,
91
+ "use_cache": true,
92
+ "vocab_size": 30522
93
+ }
run-1/checkpoint-250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3e3d0e23abfd10cd04263e92f7139e3d7989458d4230241b4119150b2b0cc1
3
+ size 438050928
run-1/checkpoint-250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05db514be9b1c3b26ea46331e2ab7ca52556c60b24d63298187bd057bf19c109
3
+ size 876222970
run-1/checkpoint-250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799803ad7ab7f8698f94ca574007f727508e835fc64b1230bf7233244f9b79ed
3
+ size 14244
run-1/checkpoint-250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccec82ecb1db9fee8431a9924525ac42c65eba373a478c5528e653b68744a6a9
3
+ size 988
run-1/checkpoint-250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b485be78cb685d4243d740ccc1343f868273aee2b966cb129d251580bf8de0
3
+ size 1064
run-1/checkpoint-250/trainer_state.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 250,
3
+ "best_metric": 0.8101538870990168,
4
+ "best_model_checkpoint": "./results/run-1/checkpoint-250",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 250,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4,
14
+ "grad_norm": 2.2372634410858154,
15
+ "learning_rate": 1.386e-05,
16
+ "loss": 1.6196,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.8478903770446777,
22
+ "learning_rate": 2.7859999999999998e-05,
23
+ "loss": 0.6614,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.892,
29
+ "eval_clientelism_f1": 0.8863746119538058,
30
+ "eval_discipline_among_poor_accuracy": 0.9655,
31
+ "eval_discipline_among_poor_f1": 0.9576399746758272,
32
+ "eval_economic_policy_accuracy": 0.8645,
33
+ "eval_economic_policy_f1": 0.8491439650565535,
34
+ "eval_loss": 0.4812721610069275,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.8435,
36
+ "eval_marcos_duterte_alliance_f1": 0.8372167355558567,
37
+ "eval_overall_accuracy": 0.8363125,
38
+ "eval_overall_f1": 0.8101538870990168,
39
+ "eval_populism_accuracy": 0.63,
40
+ "eval_populism_f1": 0.5504519653535573,
41
+ "eval_regionalism_accuracy": 0.964,
42
+ "eval_regionalism_f1": 0.9491734238530157,
43
+ "eval_runtime": 2.5732,
44
+ "eval_samples_per_second": 777.23,
45
+ "eval_security_accuracy": 0.834,
46
+ "eval_security_f1": 0.8091472896076669,
47
+ "eval_steps_per_second": 48.577,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.697,
49
+ "eval_uniteam_positive_campaign_f1": 0.6420831307358515,
50
+ "step": 250
51
+ }
52
+ ],
53
+ "logging_steps": 100,
54
+ "max_steps": 4000,
55
+ "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 16,
57
+ "save_steps": 500,
58
+ "stateful_callbacks": {
59
+ "EarlyStoppingCallback": {
60
+ "args": {
61
+ "early_stopping_patience": 2,
62
+ "early_stopping_threshold": 0.0
63
+ },
64
+ "attributes": {
65
+ "early_stopping_patience_counter": 0
66
+ }
67
+ },
68
+ "TrainerControl": {
69
+ "args": {
70
+ "should_epoch_stop": false,
71
+ "should_evaluate": false,
72
+ "should_log": false,
73
+ "should_save": true,
74
+ "should_training_stop": false
75
+ },
76
+ "attributes": {}
77
+ }
78
+ },
79
+ "total_flos": 1684364328960000.0,
80
+ "train_batch_size": 16,
81
+ "trial_name": null,
82
+ "trial_params": {
83
+ "gradient_accumulation_steps": 2,
84
+ "learning_rate": 7e-05,
85
+ "num_train_epochs": 16
86
+ }
87
+ }
run-1/checkpoint-250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242093e864aa968f85e32cc08fbf0d46ecaaf3b4ae1ccefbe829d0a78153bce9
3
+ size 5368
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e4ac1a107b3124d98dbf288d9cdadb50fd3cc361819791ad8ed26935eeffe26
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242093e864aa968f85e32cc08fbf0d46ecaaf3b4ae1ccefbe829d0a78153bce9
3
  size 5368