Hugging Face's logo

bytop
/
propaganda-detection-historical-context

Text Classification
Safetensors
English
distilbert
propaganda-detection
historical-context
geopolitical-analysis
fine-tuned
Model card Files
xet
Community
jayubba commited on
Commit
44045f4
·
verified ·
1 Parent(s): c394e53

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. checkpoint-100/config.json +32 -0
  2. checkpoint-100/model.safetensors +3 -0
  3. checkpoint-100/optimizer.pt +3 -0
  4. checkpoint-100/rng_state.pth +3 -0
  5. checkpoint-100/scheduler.pt +3 -0
  6. checkpoint-100/trainer_state.json +110 -0
  7. checkpoint-100/training_args.bin +3 -0
  8. checkpoint-150/config.json +32 -0
  9. checkpoint-150/model.safetensors +3 -0
  10. checkpoint-150/optimizer.pt +3 -0
  11. checkpoint-150/rng_state.pth +3 -0
  12. checkpoint-150/scheduler.pt +3 -0
  13. checkpoint-150/trainer_state.json +140 -0
  14. checkpoint-150/training_args.bin +3 -0
  15. checkpoint-170/config.json +32 -0
  16. checkpoint-170/model.safetensors +3 -0
  17. checkpoint-170/optimizer.pt +3 -0
  18. checkpoint-170/rng_state.pth +3 -0
  19. checkpoint-170/scheduler.pt +3 -0
  20. checkpoint-170/trainer_state.json +147 -0
  21. checkpoint-170/training_args.bin +3 -0
  22. checkpoint-50/config.json +32 -0
  23. checkpoint-50/model.safetensors +3 -0
  24. checkpoint-50/optimizer.pt +3 -0
  25. checkpoint-50/rng_state.pth +3 -0
  26. checkpoint-50/scheduler.pt +3 -0
  27. checkpoint-50/trainer_state.json +73 -0
  28. checkpoint-50/training_args.bin +3 -0
  29. config.json +32 -0
  30. model.safetensors +3 -0
  31. special_tokens_map.json +7 -0
  32. tokenizer.json +0 -0
  33. tokenizer_config.json +58 -0
  34. training_args.bin +3 -0
  35. vocab.txt +0 -0
checkpoint-100/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NO_PROPAGANDA",
12
+ "1": "PROPAGANDA"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NO_PROPAGANDA": 0,
17
+ "PROPAGANDA": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.0",
31
+ "vocab_size": 30522
32
+ }
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b40ec77fcea9874ba26b4959c208ca183a5b0a9979f5b1492ec527beebba5d
3
+ size 267832560
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03876619c607a25589d3043112609a0ed4957784480ecab7079ca739b26286f7
3
+ size 535724875
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b1e5ce7a350c52ef18aceb7dce8450b476076d04fd51abbdfbe08e044226c5
3
+ size 14455
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa96e9dd2f0645fb9398462471f2827293fad2aaa1882cf2e3bf9ed7fcd6aa5
3
+ size 1465
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "./historical_context_model/checkpoint-100",
5
+ "epoch": 2.9411764705882355,
6
+ "eval_steps": 50,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5882352941176471,
14
+ "grad_norm": 18.39331817626953,
15
+ "learning_rate": 7.600000000000001e-06,
16
+ "loss": 1.6188,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.1764705882352942,
21
+ "grad_norm": 0.4266556203365326,
22
+ "learning_rate": 1.5600000000000003e-05,
23
+ "loss": 0.8957,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 1.4705882352941178,
28
+ "eval_accuracy": 0.9411764705882353,
29
+ "eval_f1": 0.9545454545454546,
30
+ "eval_false_negatives": 0,
31
+ "eval_false_positives": 2,
32
+ "eval_loss": 0.2349591851234436,
33
+ "eval_precision": 0.9130434782608695,
34
+ "eval_recall": 1.0,
35
+ "eval_runtime": 0.3506,
36
+ "eval_samples_per_second": 96.981,
37
+ "eval_steps_per_second": 25.672,
38
+ "eval_true_negatives": 11,
39
+ "eval_true_positives": 21,
40
+ "step": 50
41
+ },
42
+ {
43
+ "epoch": 1.7647058823529411,
44
+ "grad_norm": 70.80919647216797,
45
+ "learning_rate": 1.8500000000000002e-05,
46
+ "loss": 0.6766,
47
+ "step": 60
48
+ },
49
+ {
50
+ "epoch": 2.3529411764705883,
51
+ "grad_norm": 0.1207428127527237,
52
+ "learning_rate": 1.5166666666666667e-05,
53
+ "loss": 0.043,
54
+ "step": 80
55
+ },
56
+ {
57
+ "epoch": 2.9411764705882355,
58
+ "grad_norm": 0.039772335439920425,
59
+ "learning_rate": 1.1833333333333334e-05,
60
+ "loss": 0.0113,
61
+ "step": 100
62
+ },
63
+ {
64
+ "epoch": 2.9411764705882355,
65
+ "eval_accuracy": 1.0,
66
+ "eval_f1": 1.0,
67
+ "eval_false_negatives": 0,
68
+ "eval_false_positives": 0,
69
+ "eval_loss": 0.002691805362701416,
70
+ "eval_precision": 1.0,
71
+ "eval_recall": 1.0,
72
+ "eval_runtime": 0.3133,
73
+ "eval_samples_per_second": 108.537,
74
+ "eval_steps_per_second": 28.73,
75
+ "eval_true_negatives": 13,
76
+ "eval_true_positives": 21,
77
+ "step": 100
78
+ }
79
+ ],
80
+ "logging_steps": 20,
81
+ "max_steps": 170,
82
+ "num_input_tokens_seen": 0,
83
+ "num_train_epochs": 5,
84
+ "save_steps": 50,
85
+ "stateful_callbacks": {
86
+ "EarlyStoppingCallback": {
87
+ "args": {
88
+ "early_stopping_patience": 3,
89
+ "early_stopping_threshold": 0.0
90
+ },
91
+ "attributes": {
92
+ "early_stopping_patience_counter": 0
93
+ }
94
+ },
95
+ "TrainerControl": {
96
+ "args": {
97
+ "should_epoch_stop": false,
98
+ "should_evaluate": false,
99
+ "should_log": false,
100
+ "should_save": true,
101
+ "should_training_stop": false
102
+ },
103
+ "attributes": {}
104
+ }
105
+ },
106
+ "total_flos": 52457089867776.0,
107
+ "train_batch_size": 4,
108
+ "trial_name": null,
109
+ "trial_params": null
110
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e39bd5d50eae761cab3ffb3ad01df99902ef9ada25ac512e0a4ec4f3444c4
3
+ size 5713
checkpoint-150/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NO_PROPAGANDA",
12
+ "1": "PROPAGANDA"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NO_PROPAGANDA": 0,
17
+ "PROPAGANDA": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.0",
31
+ "vocab_size": 30522
32
+ }
checkpoint-150/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec5158271113dfe81271b70287ae780090c3d4cd810086eb23b2b58c3a71765
3
+ size 267832560
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f62653c94a539d83525f008374fb7cb53ab251720b2449b2c5941b0ed61729dc
3
+ size 535724875
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67627e3b026c4c5d776980914bd7f99f2f9814ae6ac5a3bd1d93ee8d2ff6784f
3
+ size 14455
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2ae4675352e8971a2287366ebed66ecbaf6423dc705c9ed0b64ae1a75df21a
3
+ size 1465
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "./historical_context_model/checkpoint-100",
5
+ "epoch": 4.411764705882353,
6
+ "eval_steps": 50,
7
+ "global_step": 150,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5882352941176471,
14
+ "grad_norm": 18.39331817626953,
15
+ "learning_rate": 7.600000000000001e-06,
16
+ "loss": 1.6188,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.1764705882352942,
21
+ "grad_norm": 0.4266556203365326,
22
+ "learning_rate": 1.5600000000000003e-05,
23
+ "loss": 0.8957,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 1.4705882352941178,
28
+ "eval_accuracy": 0.9411764705882353,
29
+ "eval_f1": 0.9545454545454546,
30
+ "eval_false_negatives": 0,
31
+ "eval_false_positives": 2,
32
+ "eval_loss": 0.2349591851234436,
33
+ "eval_precision": 0.9130434782608695,
34
+ "eval_recall": 1.0,
35
+ "eval_runtime": 0.3506,
36
+ "eval_samples_per_second": 96.981,
37
+ "eval_steps_per_second": 25.672,
38
+ "eval_true_negatives": 11,
39
+ "eval_true_positives": 21,
40
+ "step": 50
41
+ },
42
+ {
43
+ "epoch": 1.7647058823529411,
44
+ "grad_norm": 70.80919647216797,
45
+ "learning_rate": 1.8500000000000002e-05,
46
+ "loss": 0.6766,
47
+ "step": 60
48
+ },
49
+ {
50
+ "epoch": 2.3529411764705883,
51
+ "grad_norm": 0.1207428127527237,
52
+ "learning_rate": 1.5166666666666667e-05,
53
+ "loss": 0.043,
54
+ "step": 80
55
+ },
56
+ {
57
+ "epoch": 2.9411764705882355,
58
+ "grad_norm": 0.039772335439920425,
59
+ "learning_rate": 1.1833333333333334e-05,
60
+ "loss": 0.0113,
61
+ "step": 100
62
+ },
63
+ {
64
+ "epoch": 2.9411764705882355,
65
+ "eval_accuracy": 1.0,
66
+ "eval_f1": 1.0,
67
+ "eval_false_negatives": 0,
68
+ "eval_false_positives": 0,
69
+ "eval_loss": 0.002691805362701416,
70
+ "eval_precision": 1.0,
71
+ "eval_recall": 1.0,
72
+ "eval_runtime": 0.3133,
73
+ "eval_samples_per_second": 108.537,
74
+ "eval_steps_per_second": 28.73,
75
+ "eval_true_negatives": 13,
76
+ "eval_true_positives": 21,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 3.5294117647058822,
81
+ "grad_norm": 0.07621269673109055,
82
+ "learning_rate": 8.5e-06,
83
+ "loss": 0.1213,
84
+ "step": 120
85
+ },
86
+ {
87
+ "epoch": 4.117647058823529,
88
+ "grad_norm": 0.029289739206433296,
89
+ "learning_rate": 5.1666666666666675e-06,
90
+ "loss": 0.0016,
91
+ "step": 140
92
+ },
93
+ {
94
+ "epoch": 4.411764705882353,
95
+ "eval_accuracy": 1.0,
96
+ "eval_f1": 1.0,
97
+ "eval_false_negatives": 0,
98
+ "eval_false_positives": 0,
99
+ "eval_loss": 0.0018045820761471987,
100
+ "eval_precision": 1.0,
101
+ "eval_recall": 1.0,
102
+ "eval_runtime": 0.3292,
103
+ "eval_samples_per_second": 103.268,
104
+ "eval_steps_per_second": 27.336,
105
+ "eval_true_negatives": 13,
106
+ "eval_true_positives": 21,
107
+ "step": 150
108
+ }
109
+ ],
110
+ "logging_steps": 20,
111
+ "max_steps": 170,
112
+ "num_input_tokens_seen": 0,
113
+ "num_train_epochs": 5,
114
+ "save_steps": 50,
115
+ "stateful_callbacks": {
116
+ "EarlyStoppingCallback": {
117
+ "args": {
118
+ "early_stopping_patience": 3,
119
+ "early_stopping_threshold": 0.0
120
+ },
121
+ "attributes": {
122
+ "early_stopping_patience_counter": 1
123
+ }
124
+ },
125
+ "TrainerControl": {
126
+ "args": {
127
+ "should_epoch_stop": false,
128
+ "should_evaluate": false,
129
+ "should_log": false,
130
+ "should_save": true,
131
+ "should_training_stop": false
132
+ },
133
+ "attributes": {}
134
+ }
135
+ },
136
+ "total_flos": 78420700004352.0,
137
+ "train_batch_size": 4,
138
+ "trial_name": null,
139
+ "trial_params": null
140
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e39bd5d50eae761cab3ffb3ad01df99902ef9ada25ac512e0a4ec4f3444c4
3
+ size 5713
checkpoint-170/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NO_PROPAGANDA",
12
+ "1": "PROPAGANDA"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NO_PROPAGANDA": 0,
17
+ "PROPAGANDA": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.0",
31
+ "vocab_size": 30522
32
+ }
checkpoint-170/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ba88d34b3f7e6ff286fa9b35d4208829b954fc38850e8502d0b8ca5b8499bd
3
+ size 267832560
checkpoint-170/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb5ee3a0a01a9542ca8d1b9b34881d87f6360595241949da64389dc3b9fda62
3
+ size 535724875
checkpoint-170/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67627e3b026c4c5d776980914bd7f99f2f9814ae6ac5a3bd1d93ee8d2ff6784f
3
+ size 14455
checkpoint-170/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0128de21b53851bb3982e5c9530baedf7f481541e897f025f1f435ff787d15b1
3
+ size 1465
checkpoint-170/trainer_state.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "./historical_context_model/checkpoint-100",
5
+ "epoch": 5.0,
6
+ "eval_steps": 50,
7
+ "global_step": 170,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5882352941176471,
14
+ "grad_norm": 18.39331817626953,
15
+ "learning_rate": 7.600000000000001e-06,
16
+ "loss": 1.6188,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.1764705882352942,
21
+ "grad_norm": 0.4266556203365326,
22
+ "learning_rate": 1.5600000000000003e-05,
23
+ "loss": 0.8957,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 1.4705882352941178,
28
+ "eval_accuracy": 0.9411764705882353,
29
+ "eval_f1": 0.9545454545454546,
30
+ "eval_false_negatives": 0,
31
+ "eval_false_positives": 2,
32
+ "eval_loss": 0.2349591851234436,
33
+ "eval_precision": 0.9130434782608695,
34
+ "eval_recall": 1.0,
35
+ "eval_runtime": 0.3506,
36
+ "eval_samples_per_second": 96.981,
37
+ "eval_steps_per_second": 25.672,
38
+ "eval_true_negatives": 11,
39
+ "eval_true_positives": 21,
40
+ "step": 50
41
+ },
42
+ {
43
+ "epoch": 1.7647058823529411,
44
+ "grad_norm": 70.80919647216797,
45
+ "learning_rate": 1.8500000000000002e-05,
46
+ "loss": 0.6766,
47
+ "step": 60
48
+ },
49
+ {
50
+ "epoch": 2.3529411764705883,
51
+ "grad_norm": 0.1207428127527237,
52
+ "learning_rate": 1.5166666666666667e-05,
53
+ "loss": 0.043,
54
+ "step": 80
55
+ },
56
+ {
57
+ "epoch": 2.9411764705882355,
58
+ "grad_norm": 0.039772335439920425,
59
+ "learning_rate": 1.1833333333333334e-05,
60
+ "loss": 0.0113,
61
+ "step": 100
62
+ },
63
+ {
64
+ "epoch": 2.9411764705882355,
65
+ "eval_accuracy": 1.0,
66
+ "eval_f1": 1.0,
67
+ "eval_false_negatives": 0,
68
+ "eval_false_positives": 0,
69
+ "eval_loss": 0.002691805362701416,
70
+ "eval_precision": 1.0,
71
+ "eval_recall": 1.0,
72
+ "eval_runtime": 0.3133,
73
+ "eval_samples_per_second": 108.537,
74
+ "eval_steps_per_second": 28.73,
75
+ "eval_true_negatives": 13,
76
+ "eval_true_positives": 21,
77
+ "step": 100
78
+ },
79
+ {
80
+ "epoch": 3.5294117647058822,
81
+ "grad_norm": 0.07621269673109055,
82
+ "learning_rate": 8.5e-06,
83
+ "loss": 0.1213,
84
+ "step": 120
85
+ },
86
+ {
87
+ "epoch": 4.117647058823529,
88
+ "grad_norm": 0.029289739206433296,
89
+ "learning_rate": 5.1666666666666675e-06,
90
+ "loss": 0.0016,
91
+ "step": 140
92
+ },
93
+ {
94
+ "epoch": 4.411764705882353,
95
+ "eval_accuracy": 1.0,
96
+ "eval_f1": 1.0,
97
+ "eval_false_negatives": 0,
98
+ "eval_false_positives": 0,
99
+ "eval_loss": 0.0018045820761471987,
100
+ "eval_precision": 1.0,
101
+ "eval_recall": 1.0,
102
+ "eval_runtime": 0.3292,
103
+ "eval_samples_per_second": 103.268,
104
+ "eval_steps_per_second": 27.336,
105
+ "eval_true_negatives": 13,
106
+ "eval_true_positives": 21,
107
+ "step": 150
108
+ },
109
+ {
110
+ "epoch": 4.705882352941177,
111
+ "grad_norm": 0.03248094394803047,
112
+ "learning_rate": 1.8333333333333333e-06,
113
+ "loss": 0.0019,
114
+ "step": 160
115
+ }
116
+ ],
117
+ "logging_steps": 20,
118
+ "max_steps": 170,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 5,
121
+ "save_steps": 50,
122
+ "stateful_callbacks": {
123
+ "EarlyStoppingCallback": {
124
+ "args": {
125
+ "early_stopping_patience": 3,
126
+ "early_stopping_threshold": 0.0
127
+ },
128
+ "attributes": {
129
+ "early_stopping_patience_counter": 1
130
+ }
131
+ },
132
+ "TrainerControl": {
133
+ "args": {
134
+ "should_epoch_stop": false,
135
+ "should_evaluate": false,
136
+ "should_log": false,
137
+ "should_save": true,
138
+ "should_training_stop": true
139
+ },
140
+ "attributes": {}
141
+ }
142
+ },
143
+ "total_flos": 88753157099520.0,
144
+ "train_batch_size": 4,
145
+ "trial_name": null,
146
+ "trial_params": null
147
+ }
checkpoint-170/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e39bd5d50eae761cab3ffb3ad01df99902ef9ada25ac512e0a4ec4f3444c4
3
+ size 5713
checkpoint-50/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NO_PROPAGANDA",
12
+ "1": "PROPAGANDA"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NO_PROPAGANDA": 0,
17
+ "PROPAGANDA": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.0",
31
+ "vocab_size": 30522
32
+ }
checkpoint-50/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49ee86afd6207bf2eaff6eb214e653cde382bb9c7ecb0386e6accbcdec84ee1
3
+ size 267832560
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5529c243db1b8fa1653838ad0fe145986709c479e2058a0a46a6a4f186ba0794
3
+ size 535724875
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
3
+ size 14455
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2012725ae5230f89f2499e4b51994960061e167a7e852304927f5435ede869
3
+ size 1465
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 50,
3
+ "best_metric": 0.9545454545454546,
4
+ "best_model_checkpoint": "./historical_context_model/checkpoint-50",
5
+ "epoch": 1.4705882352941178,
6
+ "eval_steps": 50,
7
+ "global_step": 50,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5882352941176471,
14
+ "grad_norm": 18.39331817626953,
15
+ "learning_rate": 7.600000000000001e-06,
16
+ "loss": 1.6188,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.1764705882352942,
21
+ "grad_norm": 0.4266556203365326,
22
+ "learning_rate": 1.5600000000000003e-05,
23
+ "loss": 0.8957,
24
+ "step": 40
25
+ },
26
+ {
27
+ "epoch": 1.4705882352941178,
28
+ "eval_accuracy": 0.9411764705882353,
29
+ "eval_f1": 0.9545454545454546,
30
+ "eval_false_negatives": 0,
31
+ "eval_false_positives": 2,
32
+ "eval_loss": 0.2349591851234436,
33
+ "eval_precision": 0.9130434782608695,
34
+ "eval_recall": 1.0,
35
+ "eval_runtime": 0.3506,
36
+ "eval_samples_per_second": 96.981,
37
+ "eval_steps_per_second": 25.672,
38
+ "eval_true_negatives": 11,
39
+ "eval_true_positives": 21,
40
+ "step": 50
41
+ }
42
+ ],
43
+ "logging_steps": 20,
44
+ "max_steps": 170,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 5,
47
+ "save_steps": 50,
48
+ "stateful_callbacks": {
49
+ "EarlyStoppingCallback": {
50
+ "args": {
51
+ "early_stopping_patience": 3,
52
+ "early_stopping_threshold": 0.0
53
+ },
54
+ "attributes": {
55
+ "early_stopping_patience_counter": 0
56
+ }
57
+ },
58
+ "TrainerControl": {
59
+ "args": {
60
+ "should_epoch_stop": false,
61
+ "should_evaluate": false,
62
+ "should_log": false,
63
+ "should_save": true,
64
+ "should_training_stop": false
65
+ },
66
+ "attributes": {}
67
+ }
68
+ },
69
+ "total_flos": 26228544933888.0,
70
+ "train_batch_size": 4,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e39bd5d50eae761cab3ffb3ad01df99902ef9ada25ac512e0a4ec4f3444c4
3
+ size 5713
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "hidden_dim": 3072,
10
+ "id2label": {
11
+ "0": "NO_PROPAGANDA",
12
+ "1": "PROPAGANDA"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "NO_PROPAGANDA": 0,
17
+ "PROPAGANDA": 1
18
+ },
19
+ "max_position_embeddings": 512,
20
+ "model_type": "distilbert",
21
+ "n_heads": 12,
22
+ "n_layers": 6,
23
+ "pad_token_id": 0,
24
+ "problem_type": "single_label_classification",
25
+ "qa_dropout": 0.1,
26
+ "seq_classif_dropout": 0.2,
27
+ "sinusoidal_pos_embds": false,
28
+ "tie_weights_": true,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.55.0",
31
+ "vocab_size": 30522
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b40ec77fcea9874ba26b4959c208ca183a5b0a9979f5b1492ec527beebba5d
3
+ size 267832560
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285e39bd5d50eae761cab3ffb3ad01df99902ef9ada25ac512e0a4ec4f3444c4
3
+ size 5713
vocab.txt ADDED
The diff for this file is too large to render. See raw diff