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
d678842
·
verified ·
1 Parent(s): de7723e

Training in progress, epoch 1

Browse files
Files changed (34) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-1000/config.json +93 -0
  3. run-2/checkpoint-1000/model.safetensors +3 -0
  4. run-2/checkpoint-1000/optimizer.pt +3 -0
  5. run-2/checkpoint-1000/rng_state.pth +3 -0
  6. run-2/checkpoint-1000/scaler.pt +3 -0
  7. run-2/checkpoint-1000/scheduler.pt +3 -0
  8. run-2/checkpoint-1000/trainer_state.json +221 -0
  9. run-2/checkpoint-1000/training_args.bin +3 -0
  10. run-2/checkpoint-1250/config.json +93 -0
  11. run-2/checkpoint-1250/model.safetensors +3 -0
  12. run-2/checkpoint-1250/optimizer.pt +3 -0
  13. run-2/checkpoint-1250/rng_state.pth +3 -0
  14. run-2/checkpoint-1250/scaler.pt +3 -0
  15. run-2/checkpoint-1250/scheduler.pt +3 -0
  16. run-2/checkpoint-1250/trainer_state.json +261 -0
  17. run-2/checkpoint-1250/training_args.bin +3 -0
  18. run-2/checkpoint-750/config.json +93 -0
  19. run-2/checkpoint-750/model.safetensors +3 -0
  20. run-2/checkpoint-750/optimizer.pt +3 -0
  21. run-2/checkpoint-750/rng_state.pth +3 -0
  22. run-2/checkpoint-750/scaler.pt +3 -0
  23. run-2/checkpoint-750/scheduler.pt +3 -0
  24. run-2/checkpoint-750/trainer_state.json +174 -0
  25. run-2/checkpoint-750/training_args.bin +3 -0
  26. run-3/checkpoint-125/config.json +93 -0
  27. run-3/checkpoint-125/model.safetensors +3 -0
  28. run-3/checkpoint-125/optimizer.pt +3 -0
  29. run-3/checkpoint-125/rng_state.pth +3 -0
  30. run-3/checkpoint-125/scaler.pt +3 -0
  31. run-3/checkpoint-125/scheduler.pt +3 -0
  32. run-3/checkpoint-125/trainer_state.json +80 -0
  33. run-3/checkpoint-125/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 sha256:58fbf83a5dfd0f1b72fd9a4dffb486738a2a0c7aeb0a909d8c62224393145608
3
  size 438050928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1eb23c4286bb70d60d37d169b4eb4cdef72b61f202122c30bc3dc70490c88d5
3
  size 438050928
run-2/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-2/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd644eb1cba868925e4e9d98f38fc0bbcbf03d4236fd6168287da38fac0515e
3
+ size 438050928
run-2/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a434390b13116d75a2374e8d05c4512aa2d9bde83fb1984269025dc57922ec
3
+ size 876222970
run-2/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-2/checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
3
+ size 988
run-2/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973ca42b92d2145c5e30a6c46bf31f069380c8349a7b567f0da38d34836145f3
3
+ size 1064
run-2/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 0.9414763117147434,
4
+ "best_model_checkpoint": "./results/run-2/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": 1.9651439189910889,
15
+ "learning_rate": 1.386e-05,
16
+ "loss": 1.62,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.7124375104904175,
22
+ "learning_rate": 2.7859999999999998e-05,
23
+ "loss": 0.6715,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.906,
29
+ "eval_clientelism_f1": 0.897770957127279,
30
+ "eval_discipline_among_poor_accuracy": 0.968,
31
+ "eval_discipline_among_poor_f1": 0.9615640823822642,
32
+ "eval_economic_policy_accuracy": 0.875,
33
+ "eval_economic_policy_f1": 0.860741831908876,
34
+ "eval_loss": 0.47158536314964294,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.846,
36
+ "eval_marcos_duterte_alliance_f1": 0.839269429776376,
37
+ "eval_overall_accuracy": 0.8419375,
38
+ "eval_overall_f1": 0.8147702755950403,
39
+ "eval_populism_accuracy": 0.645,
40
+ "eval_populism_f1": 0.5639441230465639,
41
+ "eval_regionalism_accuracy": 0.963,
42
+ "eval_regionalism_f1": 0.9482946255564284,
43
+ "eval_runtime": 2.5786,
44
+ "eval_samples_per_second": 775.6,
45
+ "eval_security_accuracy": 0.8275,
46
+ "eval_security_f1": 0.8006718398296887,
47
+ "eval_steps_per_second": 48.475,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.705,
49
+ "eval_uniteam_positive_campaign_f1": 0.645905315132846,
50
+ "step": 250
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "grad_norm": 1.057538390159607,
55
+ "learning_rate": 4.1859999999999996e-05,
56
+ "loss": 0.4761,
57
+ "step": 300
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "grad_norm": 1.3597612380981445,
62
+ "learning_rate": 5.586e-05,
63
+ "loss": 0.3424,
64
+ "step": 400
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "grad_norm": 1.4431722164154053,
69
+ "learning_rate": 6.986e-05,
70
+ "loss": 0.2992,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_clientelism_accuracy": 0.949,
76
+ "eval_clientelism_f1": 0.9452056048035566,
77
+ "eval_discipline_among_poor_accuracy": 0.975,
78
+ "eval_discipline_among_poor_f1": 0.9713251858526694,
79
+ "eval_economic_policy_accuracy": 0.946,
80
+ "eval_economic_policy_f1": 0.9447796444638326,
81
+ "eval_loss": 0.2847972512245178,
82
+ "eval_marcos_duterte_alliance_accuracy": 0.905,
83
+ "eval_marcos_duterte_alliance_f1": 0.8931059723613894,
84
+ "eval_overall_accuracy": 0.9166874999999999,
85
+ "eval_overall_f1": 0.9105488176533825,
86
+ "eval_populism_accuracy": 0.7845,
87
+ "eval_populism_f1": 0.7756216085131521,
88
+ "eval_regionalism_accuracy": 0.977,
89
+ "eval_regionalism_f1": 0.9741474164644311,
90
+ "eval_runtime": 2.6526,
91
+ "eval_samples_per_second": 753.967,
92
+ "eval_security_accuracy": 0.943,
93
+ "eval_security_f1": 0.934999506345517,
94
+ "eval_steps_per_second": 47.123,
95
+ "eval_uniteam_positive_campaign_accuracy": 0.854,
96
+ "eval_uniteam_positive_campaign_f1": 0.8452056024225119,
97
+ "step": 500
98
+ },
99
+ {
100
+ "epoch": 2.4,
101
+ "grad_norm": 1.2808622121810913,
102
+ "learning_rate": 6.0759999999999994e-05,
103
+ "loss": 0.2152,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 2.8,
108
+ "grad_norm": 0.9503875970840454,
109
+ "learning_rate": 5.142666666666667e-05,
110
+ "loss": 0.1943,
111
+ "step": 700
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_clientelism_accuracy": 0.954,
116
+ "eval_clientelism_f1": 0.9527297868951113,
117
+ "eval_discipline_among_poor_accuracy": 0.977,
118
+ "eval_discipline_among_poor_f1": 0.975000371636688,
119
+ "eval_economic_policy_accuracy": 0.9495,
120
+ "eval_economic_policy_f1": 0.9493495071116878,
121
+ "eval_loss": 0.2306518405675888,
122
+ "eval_marcos_duterte_alliance_accuracy": 0.9325,
123
+ "eval_marcos_duterte_alliance_f1": 0.9269038834173264,
124
+ "eval_overall_accuracy": 0.9380625,
125
+ "eval_overall_f1": 0.9368632136576173,
126
+ "eval_populism_accuracy": 0.8745,
127
+ "eval_populism_f1": 0.8748340797000174,
128
+ "eval_regionalism_accuracy": 0.9735,
129
+ "eval_regionalism_f1": 0.9749884932130427,
130
+ "eval_runtime": 2.7943,
131
+ "eval_samples_per_second": 715.749,
132
+ "eval_security_accuracy": 0.953,
133
+ "eval_security_f1": 0.9496585291837848,
134
+ "eval_steps_per_second": 44.734,
135
+ "eval_uniteam_positive_campaign_accuracy": 0.8905,
136
+ "eval_uniteam_positive_campaign_f1": 0.8914410581032797,
137
+ "step": 750
138
+ },
139
+ {
140
+ "epoch": 3.2,
141
+ "grad_norm": 0.7700262069702148,
142
+ "learning_rate": 4.209333333333333e-05,
143
+ "loss": 0.155,
144
+ "step": 800
145
+ },
146
+ {
147
+ "epoch": 3.6,
148
+ "grad_norm": 0.646346390247345,
149
+ "learning_rate": 3.276e-05,
150
+ "loss": 0.1326,
151
+ "step": 900
152
+ },
153
+ {
154
+ "epoch": 4.0,
155
+ "grad_norm": 0.8825557231903076,
156
+ "learning_rate": 2.3426666666666664e-05,
157
+ "loss": 0.1271,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 4.0,
162
+ "eval_clientelism_accuracy": 0.953,
163
+ "eval_clientelism_f1": 0.9530642870880963,
164
+ "eval_discipline_among_poor_accuracy": 0.9735,
165
+ "eval_discipline_among_poor_f1": 0.9718915263402587,
166
+ "eval_economic_policy_accuracy": 0.9575,
167
+ "eval_economic_policy_f1": 0.9571061555033147,
168
+ "eval_loss": 0.21463848650455475,
169
+ "eval_marcos_duterte_alliance_accuracy": 0.935,
170
+ "eval_marcos_duterte_alliance_f1": 0.9294683134335573,
171
+ "eval_overall_accuracy": 0.9431875,
172
+ "eval_overall_f1": 0.9414763117147434,
173
+ "eval_populism_accuracy": 0.889,
174
+ "eval_populism_f1": 0.8882672567299156,
175
+ "eval_regionalism_accuracy": 0.979,
176
+ "eval_regionalism_f1": 0.9783012417980759,
177
+ "eval_runtime": 2.5606,
178
+ "eval_samples_per_second": 781.072,
179
+ "eval_security_accuracy": 0.9555,
180
+ "eval_security_f1": 0.9523932010152734,
181
+ "eval_steps_per_second": 48.817,
182
+ "eval_uniteam_positive_campaign_accuracy": 0.903,
183
+ "eval_uniteam_positive_campaign_f1": 0.9013185118094562,
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": 7e-05,
219
+ "num_train_epochs": 5
220
+ }
221
+ }
run-2/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00db87b530f828066f2ef5374605ff7c067cf8bcaf6d07e1ad2162b4b005b6c2
3
+ size 5368
run-2/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-2/checkpoint-1250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2969858d95c2dce93a840aa08aa3087fec871ad83392c711ccd5defb3d9cb5
3
+ size 438050928
run-2/checkpoint-1250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c743a2d689ece1d562a42b7f603e00ae333a1ffbab25d1ec8df1d26b84e872a8
3
+ size 876222970
run-2/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-2/checkpoint-1250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f1986269c74ce38fd01c56e0770c176375c55daeed6953aaf84f06cae775ba
3
+ size 988
run-2/checkpoint-1250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8f1f74b2ddc5f3bcefc3afc5761b8b1e0d3a04d708169af990768b4a718d20
3
+ size 1064
run-2/checkpoint-1250/trainer_state.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1250,
3
+ "best_metric": 0.9440323611457324,
4
+ "best_model_checkpoint": "./results/run-2/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": 1.9651439189910889,
15
+ "learning_rate": 1.386e-05,
16
+ "loss": 1.62,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.7124375104904175,
22
+ "learning_rate": 2.7859999999999998e-05,
23
+ "loss": 0.6715,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.906,
29
+ "eval_clientelism_f1": 0.897770957127279,
30
+ "eval_discipline_among_poor_accuracy": 0.968,
31
+ "eval_discipline_among_poor_f1": 0.9615640823822642,
32
+ "eval_economic_policy_accuracy": 0.875,
33
+ "eval_economic_policy_f1": 0.860741831908876,
34
+ "eval_loss": 0.47158536314964294,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.846,
36
+ "eval_marcos_duterte_alliance_f1": 0.839269429776376,
37
+ "eval_overall_accuracy": 0.8419375,
38
+ "eval_overall_f1": 0.8147702755950403,
39
+ "eval_populism_accuracy": 0.645,
40
+ "eval_populism_f1": 0.5639441230465639,
41
+ "eval_regionalism_accuracy": 0.963,
42
+ "eval_regionalism_f1": 0.9482946255564284,
43
+ "eval_runtime": 2.5786,
44
+ "eval_samples_per_second": 775.6,
45
+ "eval_security_accuracy": 0.8275,
46
+ "eval_security_f1": 0.8006718398296887,
47
+ "eval_steps_per_second": 48.475,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.705,
49
+ "eval_uniteam_positive_campaign_f1": 0.645905315132846,
50
+ "step": 250
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "grad_norm": 1.057538390159607,
55
+ "learning_rate": 4.1859999999999996e-05,
56
+ "loss": 0.4761,
57
+ "step": 300
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "grad_norm": 1.3597612380981445,
62
+ "learning_rate": 5.586e-05,
63
+ "loss": 0.3424,
64
+ "step": 400
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "grad_norm": 1.4431722164154053,
69
+ "learning_rate": 6.986e-05,
70
+ "loss": 0.2992,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_clientelism_accuracy": 0.949,
76
+ "eval_clientelism_f1": 0.9452056048035566,
77
+ "eval_discipline_among_poor_accuracy": 0.975,
78
+ "eval_discipline_among_poor_f1": 0.9713251858526694,
79
+ "eval_economic_policy_accuracy": 0.946,
80
+ "eval_economic_policy_f1": 0.9447796444638326,
81
+ "eval_loss": 0.2847972512245178,
82
+ "eval_marcos_duterte_alliance_accuracy": 0.905,
83
+ "eval_marcos_duterte_alliance_f1": 0.8931059723613894,
84
+ "eval_overall_accuracy": 0.9166874999999999,
85
+ "eval_overall_f1": 0.9105488176533825,
86
+ "eval_populism_accuracy": 0.7845,
87
+ "eval_populism_f1": 0.7756216085131521,
88
+ "eval_regionalism_accuracy": 0.977,
89
+ "eval_regionalism_f1": 0.9741474164644311,
90
+ "eval_runtime": 2.6526,
91
+ "eval_samples_per_second": 753.967,
92
+ "eval_security_accuracy": 0.943,
93
+ "eval_security_f1": 0.934999506345517,
94
+ "eval_steps_per_second": 47.123,
95
+ "eval_uniteam_positive_campaign_accuracy": 0.854,
96
+ "eval_uniteam_positive_campaign_f1": 0.8452056024225119,
97
+ "step": 500
98
+ },
99
+ {
100
+ "epoch": 2.4,
101
+ "grad_norm": 1.2808622121810913,
102
+ "learning_rate": 6.0759999999999994e-05,
103
+ "loss": 0.2152,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 2.8,
108
+ "grad_norm": 0.9503875970840454,
109
+ "learning_rate": 5.142666666666667e-05,
110
+ "loss": 0.1943,
111
+ "step": 700
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_clientelism_accuracy": 0.954,
116
+ "eval_clientelism_f1": 0.9527297868951113,
117
+ "eval_discipline_among_poor_accuracy": 0.977,
118
+ "eval_discipline_among_poor_f1": 0.975000371636688,
119
+ "eval_economic_policy_accuracy": 0.9495,
120
+ "eval_economic_policy_f1": 0.9493495071116878,
121
+ "eval_loss": 0.2306518405675888,
122
+ "eval_marcos_duterte_alliance_accuracy": 0.9325,
123
+ "eval_marcos_duterte_alliance_f1": 0.9269038834173264,
124
+ "eval_overall_accuracy": 0.9380625,
125
+ "eval_overall_f1": 0.9368632136576173,
126
+ "eval_populism_accuracy": 0.8745,
127
+ "eval_populism_f1": 0.8748340797000174,
128
+ "eval_regionalism_accuracy": 0.9735,
129
+ "eval_regionalism_f1": 0.9749884932130427,
130
+ "eval_runtime": 2.7943,
131
+ "eval_samples_per_second": 715.749,
132
+ "eval_security_accuracy": 0.953,
133
+ "eval_security_f1": 0.9496585291837848,
134
+ "eval_steps_per_second": 44.734,
135
+ "eval_uniteam_positive_campaign_accuracy": 0.8905,
136
+ "eval_uniteam_positive_campaign_f1": 0.8914410581032797,
137
+ "step": 750
138
+ },
139
+ {
140
+ "epoch": 3.2,
141
+ "grad_norm": 0.7700262069702148,
142
+ "learning_rate": 4.209333333333333e-05,
143
+ "loss": 0.155,
144
+ "step": 800
145
+ },
146
+ {
147
+ "epoch": 3.6,
148
+ "grad_norm": 0.646346390247345,
149
+ "learning_rate": 3.276e-05,
150
+ "loss": 0.1326,
151
+ "step": 900
152
+ },
153
+ {
154
+ "epoch": 4.0,
155
+ "grad_norm": 0.8825557231903076,
156
+ "learning_rate": 2.3426666666666664e-05,
157
+ "loss": 0.1271,
158
+ "step": 1000
159
+ },
160
+ {
161
+ "epoch": 4.0,
162
+ "eval_clientelism_accuracy": 0.953,
163
+ "eval_clientelism_f1": 0.9530642870880963,
164
+ "eval_discipline_among_poor_accuracy": 0.9735,
165
+ "eval_discipline_among_poor_f1": 0.9718915263402587,
166
+ "eval_economic_policy_accuracy": 0.9575,
167
+ "eval_economic_policy_f1": 0.9571061555033147,
168
+ "eval_loss": 0.21463848650455475,
169
+ "eval_marcos_duterte_alliance_accuracy": 0.935,
170
+ "eval_marcos_duterte_alliance_f1": 0.9294683134335573,
171
+ "eval_overall_accuracy": 0.9431875,
172
+ "eval_overall_f1": 0.9414763117147434,
173
+ "eval_populism_accuracy": 0.889,
174
+ "eval_populism_f1": 0.8882672567299156,
175
+ "eval_regionalism_accuracy": 0.979,
176
+ "eval_regionalism_f1": 0.9783012417980759,
177
+ "eval_runtime": 2.5606,
178
+ "eval_samples_per_second": 781.072,
179
+ "eval_security_accuracy": 0.9555,
180
+ "eval_security_f1": 0.9523932010152734,
181
+ "eval_steps_per_second": 48.817,
182
+ "eval_uniteam_positive_campaign_accuracy": 0.903,
183
+ "eval_uniteam_positive_campaign_f1": 0.9013185118094562,
184
+ "step": 1000
185
+ },
186
+ {
187
+ "epoch": 4.4,
188
+ "grad_norm": 0.6359074711799622,
189
+ "learning_rate": 1.4093333333333333e-05,
190
+ "loss": 0.1052,
191
+ "step": 1100
192
+ },
193
+ {
194
+ "epoch": 4.8,
195
+ "grad_norm": 0.7204127907752991,
196
+ "learning_rate": 4.76e-06,
197
+ "loss": 0.093,
198
+ "step": 1200
199
+ },
200
+ {
201
+ "epoch": 5.0,
202
+ "eval_clientelism_accuracy": 0.9605,
203
+ "eval_clientelism_f1": 0.9598378695080977,
204
+ "eval_discipline_among_poor_accuracy": 0.9775,
205
+ "eval_discipline_among_poor_f1": 0.9752991563048182,
206
+ "eval_economic_policy_accuracy": 0.958,
207
+ "eval_economic_policy_f1": 0.9578000392532403,
208
+ "eval_loss": 0.20537178218364716,
209
+ "eval_marcos_duterte_alliance_accuracy": 0.944,
210
+ "eval_marcos_duterte_alliance_f1": 0.938033209852473,
211
+ "eval_overall_accuracy": 0.9458125,
212
+ "eval_overall_f1": 0.9440323611457324,
213
+ "eval_populism_accuracy": 0.8905,
214
+ "eval_populism_f1": 0.8894935397931775,
215
+ "eval_regionalism_accuracy": 0.9815,
216
+ "eval_regionalism_f1": 0.9812972117328942,
217
+ "eval_runtime": 2.3936,
218
+ "eval_samples_per_second": 835.557,
219
+ "eval_security_accuracy": 0.9545,
220
+ "eval_security_f1": 0.9512383521837636,
221
+ "eval_steps_per_second": 52.222,
222
+ "eval_uniteam_positive_campaign_accuracy": 0.9,
223
+ "eval_uniteam_positive_campaign_f1": 0.899259510537395,
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": 7e-05,
259
+ "num_train_epochs": 5
260
+ }
261
+ }
run-2/checkpoint-1250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00db87b530f828066f2ef5374605ff7c067cf8bcaf6d07e1ad2162b4b005b6c2
3
+ size 5368
run-2/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-2/checkpoint-750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808582b9cc17178cc14e0f74f5d024452a9d04a7a4201ad7063501558f6cd336
3
+ size 438050928
run-2/checkpoint-750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a409175314ee85b05a73d63e6ff68bc3fb28b2439fa2007a50aa11821496a1
3
+ size 876222970
run-2/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-2/checkpoint-750/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c81c4bed410b5f7275224ab7c747fbdb55beb1b2bd651a613603d5868aa5a2d9
3
+ size 988
run-2/checkpoint-750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d975b57d7cb8d2ee1ed6615e320380089883d27823ebb20b6b01e4f67f42d8b
3
+ size 1064
run-2/checkpoint-750/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 750,
3
+ "best_metric": 0.9368632136576173,
4
+ "best_model_checkpoint": "./results/run-2/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": 1.9651439189910889,
15
+ "learning_rate": 1.386e-05,
16
+ "loss": 1.62,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.8,
21
+ "grad_norm": 1.7124375104904175,
22
+ "learning_rate": 2.7859999999999998e-05,
23
+ "loss": 0.6715,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_clientelism_accuracy": 0.906,
29
+ "eval_clientelism_f1": 0.897770957127279,
30
+ "eval_discipline_among_poor_accuracy": 0.968,
31
+ "eval_discipline_among_poor_f1": 0.9615640823822642,
32
+ "eval_economic_policy_accuracy": 0.875,
33
+ "eval_economic_policy_f1": 0.860741831908876,
34
+ "eval_loss": 0.47158536314964294,
35
+ "eval_marcos_duterte_alliance_accuracy": 0.846,
36
+ "eval_marcos_duterte_alliance_f1": 0.839269429776376,
37
+ "eval_overall_accuracy": 0.8419375,
38
+ "eval_overall_f1": 0.8147702755950403,
39
+ "eval_populism_accuracy": 0.645,
40
+ "eval_populism_f1": 0.5639441230465639,
41
+ "eval_regionalism_accuracy": 0.963,
42
+ "eval_regionalism_f1": 0.9482946255564284,
43
+ "eval_runtime": 2.5786,
44
+ "eval_samples_per_second": 775.6,
45
+ "eval_security_accuracy": 0.8275,
46
+ "eval_security_f1": 0.8006718398296887,
47
+ "eval_steps_per_second": 48.475,
48
+ "eval_uniteam_positive_campaign_accuracy": 0.705,
49
+ "eval_uniteam_positive_campaign_f1": 0.645905315132846,
50
+ "step": 250
51
+ },
52
+ {
53
+ "epoch": 1.2,
54
+ "grad_norm": 1.057538390159607,
55
+ "learning_rate": 4.1859999999999996e-05,
56
+ "loss": 0.4761,
57
+ "step": 300
58
+ },
59
+ {
60
+ "epoch": 1.6,
61
+ "grad_norm": 1.3597612380981445,
62
+ "learning_rate": 5.586e-05,
63
+ "loss": 0.3424,
64
+ "step": 400
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "grad_norm": 1.4431722164154053,
69
+ "learning_rate": 6.986e-05,
70
+ "loss": 0.2992,
71
+ "step": 500
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "eval_clientelism_accuracy": 0.949,
76
+ "eval_clientelism_f1": 0.9452056048035566,
77
+ "eval_discipline_among_poor_accuracy": 0.975,
78
+ "eval_discipline_among_poor_f1": 0.9713251858526694,
79
+ "eval_economic_policy_accuracy": 0.946,
80
+ "eval_economic_policy_f1": 0.9447796444638326,
81
+ "eval_loss": 0.2847972512245178,
82
+ "eval_marcos_duterte_alliance_accuracy": 0.905,
83
+ "eval_marcos_duterte_alliance_f1": 0.8931059723613894,
84
+ "eval_overall_accuracy": 0.9166874999999999,
85
+ "eval_overall_f1": 0.9105488176533825,
86
+ "eval_populism_accuracy": 0.7845,
87
+ "eval_populism_f1": 0.7756216085131521,
88
+ "eval_regionalism_accuracy": 0.977,
89
+ "eval_regionalism_f1": 0.9741474164644311,
90
+ "eval_runtime": 2.6526,
91
+ "eval_samples_per_second": 753.967,
92
+ "eval_security_accuracy": 0.943,
93
+ "eval_security_f1": 0.934999506345517,
94
+ "eval_steps_per_second": 47.123,
95
+ "eval_uniteam_positive_campaign_accuracy": 0.854,
96
+ "eval_uniteam_positive_campaign_f1": 0.8452056024225119,
97
+ "step": 500
98
+ },
99
+ {
100
+ "epoch": 2.4,
101
+ "grad_norm": 1.2808622121810913,
102
+ "learning_rate": 6.0759999999999994e-05,
103
+ "loss": 0.2152,
104
+ "step": 600
105
+ },
106
+ {
107
+ "epoch": 2.8,
108
+ "grad_norm": 0.9503875970840454,
109
+ "learning_rate": 5.142666666666667e-05,
110
+ "loss": 0.1943,
111
+ "step": 700
112
+ },
113
+ {
114
+ "epoch": 3.0,
115
+ "eval_clientelism_accuracy": 0.954,
116
+ "eval_clientelism_f1": 0.9527297868951113,
117
+ "eval_discipline_among_poor_accuracy": 0.977,
118
+ "eval_discipline_among_poor_f1": 0.975000371636688,
119
+ "eval_economic_policy_accuracy": 0.9495,
120
+ "eval_economic_policy_f1": 0.9493495071116878,
121
+ "eval_loss": 0.2306518405675888,
122
+ "eval_marcos_duterte_alliance_accuracy": 0.9325,
123
+ "eval_marcos_duterte_alliance_f1": 0.9269038834173264,
124
+ "eval_overall_accuracy": 0.9380625,
125
+ "eval_overall_f1": 0.9368632136576173,
126
+ "eval_populism_accuracy": 0.8745,
127
+ "eval_populism_f1": 0.8748340797000174,
128
+ "eval_regionalism_accuracy": 0.9735,
129
+ "eval_regionalism_f1": 0.9749884932130427,
130
+ "eval_runtime": 2.7943,
131
+ "eval_samples_per_second": 715.749,
132
+ "eval_security_accuracy": 0.953,
133
+ "eval_security_f1": 0.9496585291837848,
134
+ "eval_steps_per_second": 44.734,
135
+ "eval_uniteam_positive_campaign_accuracy": 0.8905,
136
+ "eval_uniteam_positive_campaign_f1": 0.8914410581032797,
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": 7e-05,
172
+ "num_train_epochs": 5
173
+ }
174
+ }
run-2/checkpoint-750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00db87b530f828066f2ef5374605ff7c067cf8bcaf6d07e1ad2162b4b005b6c2
3
+ size 5368
run-3/checkpoint-125/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-3/checkpoint-125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1eb23c4286bb70d60d37d169b4eb4cdef72b61f202122c30bc3dc70490c88d5
3
+ size 438050928
run-3/checkpoint-125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a736f2ba4a71589fdd75362155e09e41897aead5cdc665037e549e91a4bc42
3
+ size 876222970
run-3/checkpoint-125/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-3/checkpoint-125/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ec4bc8ac5689de95220cb2c918e80da7bc5dbd574ea051273889b34f7a4e18
3
+ size 988
run-3/checkpoint-125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cfe190de1a75396ad38ec62083e147ff07aaec92a9a25aa4684d42a688f26ae
3
+ size 1064
run-3/checkpoint-125/trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 125,
3
+ "best_metric": 0.7271188688911245,
4
+ "best_model_checkpoint": "./results/run-3/checkpoint-125",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 125,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.8,
14
+ "grad_norm": 1.825743556022644,
15
+ "learning_rate": 9.900000000000002e-06,
16
+ "loss": 1.7201,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_clientelism_accuracy": 0.8205,
22
+ "eval_clientelism_f1": 0.7482918732782369,
23
+ "eval_discipline_among_poor_accuracy": 0.955,
24
+ "eval_discipline_among_poor_f1": 0.9330179028132993,
25
+ "eval_economic_policy_accuracy": 0.7925,
26
+ "eval_economic_policy_f1": 0.7007601115760111,
27
+ "eval_loss": 0.7271444797515869,
28
+ "eval_marcos_duterte_alliance_accuracy": 0.769,
29
+ "eval_marcos_duterte_alliance_f1": 0.7375199658801759,
30
+ "eval_overall_accuracy": 0.790125,
31
+ "eval_overall_f1": 0.7271188688911245,
32
+ "eval_populism_accuracy": 0.5955,
33
+ "eval_populism_f1": 0.5190889398077297,
34
+ "eval_regionalism_accuracy": 0.941,
35
+ "eval_regionalism_f1": 0.9123967027305513,
36
+ "eval_runtime": 2.4983,
37
+ "eval_samples_per_second": 800.535,
38
+ "eval_security_accuracy": 0.773,
39
+ "eval_security_f1": 0.6801353637901861,
40
+ "eval_steps_per_second": 50.033,
41
+ "eval_uniteam_positive_campaign_accuracy": 0.6745,
42
+ "eval_uniteam_positive_campaign_f1": 0.5857400912528054,
43
+ "step": 125
44
+ }
45
+ ],
46
+ "logging_steps": 100,
47
+ "max_steps": 625,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 5,
50
+ "save_steps": 500,
51
+ "stateful_callbacks": {
52
+ "EarlyStoppingCallback": {
53
+ "args": {
54
+ "early_stopping_patience": 2,
55
+ "early_stopping_threshold": 0.0
56
+ },
57
+ "attributes": {
58
+ "early_stopping_patience_counter": 0
59
+ }
60
+ },
61
+ "TrainerControl": {
62
+ "args": {
63
+ "should_epoch_stop": false,
64
+ "should_evaluate": false,
65
+ "should_log": false,
66
+ "should_save": true,
67
+ "should_training_stop": false
68
+ },
69
+ "attributes": {}
70
+ }
71
+ },
72
+ "total_flos": 1684364328960000.0,
73
+ "train_batch_size": 16,
74
+ "trial_name": null,
75
+ "trial_params": {
76
+ "gradient_accumulation_steps": 4,
77
+ "learning_rate": 5e-05,
78
+ "num_train_epochs": 5
79
+ }
80
+ }
run-3/checkpoint-125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548010b4f91c450431306186acf7c2d2640e58960634c399b136e2be17e8cbe9
3
+ size 5368
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00db87b530f828066f2ef5374605ff7c067cf8bcaf6d07e1ad2162b4b005b6c2
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548010b4f91c450431306186acf7c2d2640e58960634c399b136e2be17e8cbe9
3
  size 5368