ashrafulparan
commited on
Commit
โข
770c4eb
1
Parent(s):
55afaed
Upload folder using huggingface_hub
Browse files- checkpoint-1750/config.json +124 -0
- checkpoint-1750/model.safetensors +3 -0
- checkpoint-1750/optimizer.pt +3 -0
- checkpoint-1750/rng_state.pth +3 -0
- checkpoint-1750/scheduler.pt +3 -0
- checkpoint-1750/special_tokens_map.json +7 -0
- checkpoint-1750/tokenizer.json +0 -0
- checkpoint-1750/tokenizer_config.json +58 -0
- checkpoint-1750/trainer_state.json +66 -0
- checkpoint-1750/training_args.bin +3 -0
- checkpoint-1750/vocab.txt +0 -0
- runs/May19_20-54-35_45163d78f8b0/events.out.tfevents.1716152076.45163d78f8b0.25.0 +3 -0
checkpoint-1750/config.json
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-mix-ner",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "B-Appeal_to_Authority",
|
14 |
+
"1": "I-Appeal_to_Authority",
|
15 |
+
"2": "B-Appeal_to_Fear-Prejudice",
|
16 |
+
"3": "I-Appeal_to_Fear-Prejudice",
|
17 |
+
"4": "B-Appeal_to_Hypocrisy",
|
18 |
+
"5": "I-Appeal_to_Hypocrisy",
|
19 |
+
"6": "B-Appeal_to_Popularity",
|
20 |
+
"7": "I-Appeal_to_Popularity",
|
21 |
+
"8": "B-Appeal_to_Time",
|
22 |
+
"9": "I-Appeal_to_Time",
|
23 |
+
"10": "B-Appeal_to_Values",
|
24 |
+
"11": "I-Appeal_to_Values",
|
25 |
+
"12": "B-Causal_Oversimplification",
|
26 |
+
"13": "I-Causal_Oversimplification",
|
27 |
+
"14": "B-Consequential_Oversimplification",
|
28 |
+
"15": "I-Consequential_Oversimplification",
|
29 |
+
"16": "B-Conversation_Killer",
|
30 |
+
"17": "I-Conversation_Killer",
|
31 |
+
"18": "B-Doubt",
|
32 |
+
"19": "I-Doubt",
|
33 |
+
"20": "B-Exaggeration-Minimisation",
|
34 |
+
"21": "I-Exaggeration-Minimisation",
|
35 |
+
"22": "B-False_Dilemma-No_Choice",
|
36 |
+
"23": "I-False_Dilemma-No_Choice",
|
37 |
+
"24": "B-Flag_Waving",
|
38 |
+
"25": "I-Flag_Waving",
|
39 |
+
"26": "B-Guilt_by_Association",
|
40 |
+
"27": "I-Guilt_by_Association",
|
41 |
+
"28": "B-Loaded_Language",
|
42 |
+
"29": "I-Loaded_Language",
|
43 |
+
"30": "B-Name_Calling-Labeling",
|
44 |
+
"31": "I-Name_Calling-Labeling",
|
45 |
+
"32": "B-Obfuscation-Vagueness-Confusion",
|
46 |
+
"33": "I-Obfuscation-Vagueness-Confusion",
|
47 |
+
"34": "B-Questioning_the_Reputation",
|
48 |
+
"35": "I-Questioning_the_Reputation",
|
49 |
+
"36": "B-Red_Herring",
|
50 |
+
"37": "I-Red_Herring",
|
51 |
+
"38": "B-Repetition",
|
52 |
+
"39": "I-Repetition",
|
53 |
+
"40": "B-Slogans",
|
54 |
+
"41": "I-Slogans",
|
55 |
+
"42": "B-Straw_Man",
|
56 |
+
"43": "I-Straw_Man",
|
57 |
+
"44": "B-Whataboutism",
|
58 |
+
"45": "I-Whataboutism",
|
59 |
+
"46": "O"
|
60 |
+
},
|
61 |
+
"initializer_range": 0.02,
|
62 |
+
"intermediate_size": 3072,
|
63 |
+
"label2id": {
|
64 |
+
"B-Appeal_to_Authority": 0,
|
65 |
+
"B-Appeal_to_Fear-Prejudice": 2,
|
66 |
+
"B-Appeal_to_Hypocrisy": 4,
|
67 |
+
"B-Appeal_to_Popularity": 6,
|
68 |
+
"B-Appeal_to_Time": 8,
|
69 |
+
"B-Appeal_to_Values": 10,
|
70 |
+
"B-Causal_Oversimplification": 12,
|
71 |
+
"B-Consequential_Oversimplification": 14,
|
72 |
+
"B-Conversation_Killer": 16,
|
73 |
+
"B-Doubt": 18,
|
74 |
+
"B-Exaggeration-Minimisation": 20,
|
75 |
+
"B-False_Dilemma-No_Choice": 22,
|
76 |
+
"B-Flag_Waving": 24,
|
77 |
+
"B-Guilt_by_Association": 26,
|
78 |
+
"B-Loaded_Language": 28,
|
79 |
+
"B-Name_Calling-Labeling": 30,
|
80 |
+
"B-Obfuscation-Vagueness-Confusion": 32,
|
81 |
+
"B-Questioning_the_Reputation": 34,
|
82 |
+
"B-Red_Herring": 36,
|
83 |
+
"B-Repetition": 38,
|
84 |
+
"B-Slogans": 40,
|
85 |
+
"B-Straw_Man": 42,
|
86 |
+
"B-Whataboutism": 44,
|
87 |
+
"I-Appeal_to_Authority": 1,
|
88 |
+
"I-Appeal_to_Fear-Prejudice": 3,
|
89 |
+
"I-Appeal_to_Hypocrisy": 5,
|
90 |
+
"I-Appeal_to_Popularity": 7,
|
91 |
+
"I-Appeal_to_Time": 9,
|
92 |
+
"I-Appeal_to_Values": 11,
|
93 |
+
"I-Causal_Oversimplification": 13,
|
94 |
+
"I-Consequential_Oversimplification": 15,
|
95 |
+
"I-Conversation_Killer": 17,
|
96 |
+
"I-Doubt": 19,
|
97 |
+
"I-Exaggeration-Minimisation": 21,
|
98 |
+
"I-False_Dilemma-No_Choice": 23,
|
99 |
+
"I-Flag_Waving": 25,
|
100 |
+
"I-Guilt_by_Association": 27,
|
101 |
+
"I-Loaded_Language": 29,
|
102 |
+
"I-Name_Calling-Labeling": 31,
|
103 |
+
"I-Obfuscation-Vagueness-Confusion": 33,
|
104 |
+
"I-Questioning_the_Reputation": 35,
|
105 |
+
"I-Red_Herring": 37,
|
106 |
+
"I-Repetition": 39,
|
107 |
+
"I-Slogans": 41,
|
108 |
+
"I-Straw_Man": 43,
|
109 |
+
"I-Whataboutism": 45,
|
110 |
+
"O": 46
|
111 |
+
},
|
112 |
+
"layer_norm_eps": 1e-12,
|
113 |
+
"max_position_embeddings": 512,
|
114 |
+
"model_type": "bert",
|
115 |
+
"num_attention_heads": 12,
|
116 |
+
"num_hidden_layers": 12,
|
117 |
+
"pad_token_id": 0,
|
118 |
+
"position_embedding_type": "absolute",
|
119 |
+
"torch_dtype": "float32",
|
120 |
+
"transformers_version": "4.39.3",
|
121 |
+
"type_vocab_size": 2,
|
122 |
+
"use_cache": true,
|
123 |
+
"vocab_size": 30000
|
124 |
+
}
|
checkpoint-1750/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1046ce7cd80fb8b927c55054a3a2ae924f1ad445e3c10491f4e684af3474ee3
|
3 |
+
size 434130924
|
checkpoint-1750/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c270e0b130e87e200a9d44433623c390e4c893db6a04288aa5d02a0ca1cf6b0
|
3 |
+
size 868381498
|
checkpoint-1750/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ae7a6df5a53f51283cc0ccfdee18699c974ca86c07f03f6e4ac01d00140ce7
|
3 |
+
size 14244
|
checkpoint-1750/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecf4040ba2ac39afec760a17ef33d45442107a7d8dc3ff6e7bac7c52cba4663e
|
3 |
+
size 1064
|
checkpoint-1750/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 |
+
}
|
checkpoint-1750/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1750/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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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": false,
|
48 |
+
"full_tokenizer_file": null,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
checkpoint-1750/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.2963756322860718,
|
3 |
+
"best_model_checkpoint": "bert-propaganda-ner/checkpoint-1750",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1750,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.57,
|
13 |
+
"grad_norm": 3.605520486831665,
|
14 |
+
"learning_rate": 4.714285714285714e-05,
|
15 |
+
"loss": 1.2802,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7176097303014278,
|
21 |
+
"eval_f1": 0.09410755148741418,
|
22 |
+
"eval_loss": 1.2981841564178467,
|
23 |
+
"eval_precision": 0.28986784140969163,
|
24 |
+
"eval_recall": 0.05617210175857948,
|
25 |
+
"eval_runtime": 4.2298,
|
26 |
+
"eval_samples_per_second": 217.743,
|
27 |
+
"eval_steps_per_second": 27.425,
|
28 |
+
"step": 875
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 1.14,
|
32 |
+
"grad_norm": 2.260868787765503,
|
33 |
+
"learning_rate": 4.428571428571428e-05,
|
34 |
+
"loss": 1.1118,
|
35 |
+
"step": 1000
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.71,
|
39 |
+
"grad_norm": 7.614594459533691,
|
40 |
+
"learning_rate": 4.1428571428571437e-05,
|
41 |
+
"loss": 0.9205,
|
42 |
+
"step": 1500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.0,
|
46 |
+
"eval_accuracy": 0.6880236021041498,
|
47 |
+
"eval_f1": 0.16797458893871453,
|
48 |
+
"eval_loss": 1.2963756322860718,
|
49 |
+
"eval_precision": 0.18547555188776563,
|
50 |
+
"eval_recall": 0.15349154857435549,
|
51 |
+
"eval_runtime": 4.3987,
|
52 |
+
"eval_samples_per_second": 209.378,
|
53 |
+
"eval_steps_per_second": 26.371,
|
54 |
+
"step": 1750
|
55 |
+
}
|
56 |
+
],
|
57 |
+
"logging_steps": 500,
|
58 |
+
"max_steps": 8750,
|
59 |
+
"num_input_tokens_seen": 0,
|
60 |
+
"num_train_epochs": 10,
|
61 |
+
"save_steps": 500,
|
62 |
+
"total_flos": 553357099061862.0,
|
63 |
+
"train_batch_size": 8,
|
64 |
+
"trial_name": null,
|
65 |
+
"trial_params": null
|
66 |
+
}
|
checkpoint-1750/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:931fab3316d192f2a055e061762fa0954a4360c998fb1ae70d3e465d71b818a0
|
3 |
+
size 4984
|
checkpoint-1750/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/May19_20-54-35_45163d78f8b0/events.out.tfevents.1716152076.45163d78f8b0.25.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c92fb3410038d4c5de7d223f2f89ea59f42677c551f87a09614a201b10e2412
|
3 |
+
size 16396
|