Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- telecom_arabert_final/checkpoint-3500/config.json +47 -0
- telecom_arabert_final/checkpoint-3500/model.safetensors +3 -0
- telecom_arabert_final/checkpoint-3500/optimizer.pt +3 -0
- telecom_arabert_final/checkpoint-3500/rng_state.pth +3 -0
- telecom_arabert_final/checkpoint-3500/scheduler.pt +3 -0
- telecom_arabert_final/checkpoint-3500/special_tokens_map.json +37 -0
- telecom_arabert_final/checkpoint-3500/tokenizer.json +0 -0
- telecom_arabert_final/checkpoint-3500/tokenizer_config.json +339 -0
- telecom_arabert_final/checkpoint-3500/trainer_state.json +524 -0
- telecom_arabert_final/checkpoint-3500/training_args.bin +3 -0
- telecom_arabert_final/checkpoint-3500/vocab.txt +0 -0
- telecom_arabert_final/checkpoint-3570/config.json +47 -0
- telecom_arabert_final/checkpoint-3570/model.safetensors +3 -0
- telecom_arabert_final/checkpoint-3570/optimizer.pt +3 -0
- telecom_arabert_final/checkpoint-3570/rng_state.pth +3 -0
- telecom_arabert_final/checkpoint-3570/scheduler.pt +3 -0
- telecom_arabert_final/checkpoint-3570/special_tokens_map.json +37 -0
- telecom_arabert_final/checkpoint-3570/tokenizer.json +0 -0
- telecom_arabert_final/checkpoint-3570/tokenizer_config.json +339 -0
- telecom_arabert_final/checkpoint-3570/trainer_state.json +531 -0
- telecom_arabert_final/checkpoint-3570/training_args.bin +3 -0
- telecom_arabert_final/checkpoint-3570/vocab.txt +0 -0
- telecom_arabert_final/config.json +47 -0
- telecom_arabert_final/model.safetensors +3 -0
- telecom_arabert_final/special_tokens_map.json +37 -0
- telecom_arabert_final/tokenizer.json +0 -0
- telecom_arabert_final/tokenizer_config.json +339 -0
- telecom_arabert_final/training_args.bin +3 -0
- telecom_arabert_final/vocab.txt +0 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/config.json +54 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/model.safetensors +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/optimizer.pt +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/rng_state.pth +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/scheduler.pt +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/special_tokens_map.json +37 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/tokenizer.json +0 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/tokenizer_config.json +58 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/trainer_state.json +242 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/training_args.bin +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-48/vocab.txt +0 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/config.json +54 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/model.safetensors +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/optimizer.pt +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/rng_state.pth +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/scheduler.pt +3 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/special_tokens_map.json +37 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/tokenizer.json +0 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/tokenizer_config.json +58 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/trainer_state.json +345 -0
- telecom_arabert_large_full_pipeline/checkpoint-72/training_args.bin +3 -0
telecom_arabert_final/checkpoint-3500/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": 1,
|
| 13 |
+
"1": 2,
|
| 14 |
+
"2": 3,
|
| 15 |
+
"3": 4,
|
| 16 |
+
"4": 5,
|
| 17 |
+
"5": 6,
|
| 18 |
+
"6": 7,
|
| 19 |
+
"7": 8,
|
| 20 |
+
"8": 9
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 4096,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"1": 0,
|
| 26 |
+
"2": 1,
|
| 27 |
+
"3": 2,
|
| 28 |
+
"4": 3,
|
| 29 |
+
"5": 4,
|
| 30 |
+
"6": 5,
|
| 31 |
+
"7": 6,
|
| 32 |
+
"8": 7,
|
| 33 |
+
"9": 8
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-12,
|
| 36 |
+
"max_position_embeddings": 512,
|
| 37 |
+
"model_type": "bert",
|
| 38 |
+
"num_attention_heads": 16,
|
| 39 |
+
"num_hidden_layers": 24,
|
| 40 |
+
"pad_token_id": 31,
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"transformers_version": "4.57.3",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 64000
|
| 47 |
+
}
|
telecom_arabert_final/checkpoint-3500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:787abfe5bb8f3fe523e638940559ac1f36cebc8fb7a2a42a0910bbff3d00832a
|
| 3 |
+
size 1477777444
|
telecom_arabert_final/checkpoint-3500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73339f2e9ddcdbe35863081457469e967aed6759881ac5fa45c573344484e337
|
| 3 |
+
size 2955795454
|
telecom_arabert_final/checkpoint-3500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e732663d20c02e7eabada2dadee86f59d804a3b68cf1423a3279d070fffc3269
|
| 3 |
+
size 14645
|
telecom_arabert_final/checkpoint-3500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa7ee6cd5a22d1d2a1d785ebd09e035c31cb61786fe2af98d444dfeb888b1d69
|
| 3 |
+
size 1465
|
telecom_arabert_final/checkpoint-3500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
telecom_arabert_final/checkpoint-3500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_final/checkpoint-3500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "+ا",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "+ك",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "ب+",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "+هم",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "+ات",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "+ي",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "ل+",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "+هما",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "+نا",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "+ن",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "+ها",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "+كما",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "+ة",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "ف+",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "+كم",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "+كن",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "+ت",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[بريد]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[مستخدم]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "لل+",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "ال+",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[رابط]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "س+",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "+ان",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "+وا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "+ه",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "+ون",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "+هن",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "+ين",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": true,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "��+",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": true,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "ك+",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": true,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[UNK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[CLS]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[SEP]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[MASK]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": false,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"extra_special_tokens": {},
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ك",
|
| 302 |
+
"+كما",
|
| 303 |
+
"ك+",
|
| 304 |
+
"+وا",
|
| 305 |
+
"+ين",
|
| 306 |
+
"و+",
|
| 307 |
+
"+كن",
|
| 308 |
+
"+ان",
|
| 309 |
+
"+هم",
|
| 310 |
+
"+ة",
|
| 311 |
+
"[بريد]",
|
| 312 |
+
"لل+",
|
| 313 |
+
"+ي",
|
| 314 |
+
"+ت",
|
| 315 |
+
"+ن",
|
| 316 |
+
"س+",
|
| 317 |
+
"ل+",
|
| 318 |
+
"[مستخدم]",
|
| 319 |
+
"+كم",
|
| 320 |
+
"+ا",
|
| 321 |
+
"ب+",
|
| 322 |
+
"ف+",
|
| 323 |
+
"+نا",
|
| 324 |
+
"+ها",
|
| 325 |
+
"+ون",
|
| 326 |
+
"+هما",
|
| 327 |
+
"ال+",
|
| 328 |
+
"+ه",
|
| 329 |
+
"+هن",
|
| 330 |
+
"+ات",
|
| 331 |
+
"[رابط]"
|
| 332 |
+
],
|
| 333 |
+
"pad_token": "[PAD]",
|
| 334 |
+
"sep_token": "[SEP]",
|
| 335 |
+
"strip_accents": null,
|
| 336 |
+
"tokenize_chinese_chars": true,
|
| 337 |
+
"tokenizer_class": "BertTokenizer",
|
| 338 |
+
"unk_token": "[UNK]"
|
| 339 |
+
}
|
telecom_arabert_final/checkpoint-3500/trainer_state.json
ADDED
|
@@ -0,0 +1,524 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.62745098039215,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.9803921568627451,
|
| 14 |
+
"grad_norm": 11.002342224121094,
|
| 15 |
+
"learning_rate": 1.3725490196078432e-05,
|
| 16 |
+
"loss": 2.3419,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.9607843137254903,
|
| 21 |
+
"grad_norm": 29.423385620117188,
|
| 22 |
+
"learning_rate": 2.773109243697479e-05,
|
| 23 |
+
"loss": 2.1727,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.9411764705882355,
|
| 28 |
+
"grad_norm": 26.981374740600586,
|
| 29 |
+
"learning_rate": 4.173669467787115e-05,
|
| 30 |
+
"loss": 2.0203,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.9215686274509802,
|
| 35 |
+
"grad_norm": 13.149168968200684,
|
| 36 |
+
"learning_rate": 5.574229691876751e-05,
|
| 37 |
+
"loss": 1.688,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 4.901960784313726,
|
| 42 |
+
"grad_norm": 4.1570916175842285,
|
| 43 |
+
"learning_rate": 6.974789915966386e-05,
|
| 44 |
+
"loss": 2.1775,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.882352941176471,
|
| 49 |
+
"grad_norm": 7.508273124694824,
|
| 50 |
+
"learning_rate": 8.375350140056023e-05,
|
| 51 |
+
"loss": 2.2603,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 6.862745098039216,
|
| 56 |
+
"grad_norm": 5.582854270935059,
|
| 57 |
+
"learning_rate": 9.775910364145658e-05,
|
| 58 |
+
"loss": 2.2469,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 7.8431372549019605,
|
| 63 |
+
"grad_norm": 6.001800060272217,
|
| 64 |
+
"learning_rate": 9.869281045751635e-05,
|
| 65 |
+
"loss": 2.2533,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 8.823529411764707,
|
| 70 |
+
"grad_norm": 6.843214511871338,
|
| 71 |
+
"learning_rate": 9.713663243075009e-05,
|
| 72 |
+
"loss": 2.2437,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 9.803921568627452,
|
| 77 |
+
"grad_norm": 6.001797676086426,
|
| 78 |
+
"learning_rate": 9.558045440398382e-05,
|
| 79 |
+
"loss": 2.2406,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 10.784313725490197,
|
| 84 |
+
"grad_norm": 4.675999164581299,
|
| 85 |
+
"learning_rate": 9.402427637721756e-05,
|
| 86 |
+
"loss": 2.2353,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.764705882352942,
|
| 91 |
+
"grad_norm": 6.9409966468811035,
|
| 92 |
+
"learning_rate": 9.246809835045129e-05,
|
| 93 |
+
"loss": 2.2288,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 12.745098039215687,
|
| 98 |
+
"grad_norm": 7.809481143951416,
|
| 99 |
+
"learning_rate": 9.091192032368503e-05,
|
| 100 |
+
"loss": 2.237,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 13.72549019607843,
|
| 105 |
+
"grad_norm": 5.771924018859863,
|
| 106 |
+
"learning_rate": 8.935574229691877e-05,
|
| 107 |
+
"loss": 2.234,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 14.705882352941176,
|
| 112 |
+
"grad_norm": 3.7695183753967285,
|
| 113 |
+
"learning_rate": 8.779956427015251e-05,
|
| 114 |
+
"loss": 2.2398,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 15.686274509803921,
|
| 119 |
+
"grad_norm": 5.8638529777526855,
|
| 120 |
+
"learning_rate": 8.624338624338625e-05,
|
| 121 |
+
"loss": 2.2241,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 16.666666666666668,
|
| 126 |
+
"grad_norm": 7.440635681152344,
|
| 127 |
+
"learning_rate": 8.468720821661998e-05,
|
| 128 |
+
"loss": 2.2256,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 17.647058823529413,
|
| 133 |
+
"grad_norm": 4.2441182136535645,
|
| 134 |
+
"learning_rate": 8.313103018985372e-05,
|
| 135 |
+
"loss": 2.2298,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 18.627450980392158,
|
| 140 |
+
"grad_norm": 7.42420768737793,
|
| 141 |
+
"learning_rate": 8.157485216308745e-05,
|
| 142 |
+
"loss": 2.2233,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 19.607843137254903,
|
| 147 |
+
"grad_norm": 4.213704586029053,
|
| 148 |
+
"learning_rate": 8.001867413632121e-05,
|
| 149 |
+
"loss": 2.2313,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 20.58823529411765,
|
| 154 |
+
"grad_norm": 6.308703422546387,
|
| 155 |
+
"learning_rate": 7.846249610955494e-05,
|
| 156 |
+
"loss": 2.2259,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 21.568627450980394,
|
| 161 |
+
"grad_norm": 8.95936393737793,
|
| 162 |
+
"learning_rate": 7.690631808278868e-05,
|
| 163 |
+
"loss": 2.2334,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 22.54901960784314,
|
| 168 |
+
"grad_norm": 7.726138591766357,
|
| 169 |
+
"learning_rate": 7.53501400560224e-05,
|
| 170 |
+
"loss": 2.2271,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 23.529411764705884,
|
| 175 |
+
"grad_norm": 5.980637550354004,
|
| 176 |
+
"learning_rate": 7.379396202925615e-05,
|
| 177 |
+
"loss": 2.2278,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 24.509803921568626,
|
| 182 |
+
"grad_norm": 5.208985805511475,
|
| 183 |
+
"learning_rate": 7.223778400248989e-05,
|
| 184 |
+
"loss": 2.2258,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 25.49019607843137,
|
| 189 |
+
"grad_norm": 3.785893678665161,
|
| 190 |
+
"learning_rate": 7.068160597572363e-05,
|
| 191 |
+
"loss": 2.2354,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 26.470588235294116,
|
| 196 |
+
"grad_norm": 7.314659595489502,
|
| 197 |
+
"learning_rate": 6.912542794895737e-05,
|
| 198 |
+
"loss": 2.2371,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 27.45098039215686,
|
| 203 |
+
"grad_norm": 5.165799617767334,
|
| 204 |
+
"learning_rate": 6.75692499221911e-05,
|
| 205 |
+
"loss": 2.2302,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 28.431372549019606,
|
| 210 |
+
"grad_norm": 6.496328353881836,
|
| 211 |
+
"learning_rate": 6.601307189542484e-05,
|
| 212 |
+
"loss": 2.2252,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 29.41176470588235,
|
| 217 |
+
"grad_norm": 3.1437888145446777,
|
| 218 |
+
"learning_rate": 6.445689386865857e-05,
|
| 219 |
+
"loss": 2.2292,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 30.392156862745097,
|
| 224 |
+
"grad_norm": 5.930662631988525,
|
| 225 |
+
"learning_rate": 6.290071584189231e-05,
|
| 226 |
+
"loss": 2.2307,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 31.372549019607842,
|
| 231 |
+
"grad_norm": 6.53542947769165,
|
| 232 |
+
"learning_rate": 6.134453781512605e-05,
|
| 233 |
+
"loss": 2.2195,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 32.35294117647059,
|
| 238 |
+
"grad_norm": 6.8471198081970215,
|
| 239 |
+
"learning_rate": 5.9788359788359794e-05,
|
| 240 |
+
"loss": 2.2292,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 33.333333333333336,
|
| 245 |
+
"grad_norm": 5.49623441696167,
|
| 246 |
+
"learning_rate": 5.823218176159353e-05,
|
| 247 |
+
"loss": 2.2269,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 34.31372549019608,
|
| 252 |
+
"grad_norm": 3.214643716812134,
|
| 253 |
+
"learning_rate": 5.6676003734827264e-05,
|
| 254 |
+
"loss": 2.2251,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 35.294117647058826,
|
| 259 |
+
"grad_norm": 6.643034934997559,
|
| 260 |
+
"learning_rate": 5.5119825708061e-05,
|
| 261 |
+
"loss": 2.2226,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 36.27450980392157,
|
| 266 |
+
"grad_norm": 5.6264753341674805,
|
| 267 |
+
"learning_rate": 5.356364768129474e-05,
|
| 268 |
+
"loss": 2.221,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 37.254901960784316,
|
| 273 |
+
"grad_norm": 5.2604265213012695,
|
| 274 |
+
"learning_rate": 5.200746965452848e-05,
|
| 275 |
+
"loss": 2.2268,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 38.23529411764706,
|
| 280 |
+
"grad_norm": 3.1051926612854004,
|
| 281 |
+
"learning_rate": 5.045129162776222e-05,
|
| 282 |
+
"loss": 2.2193,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 39.21568627450981,
|
| 287 |
+
"grad_norm": 5.157900333404541,
|
| 288 |
+
"learning_rate": 4.889511360099596e-05,
|
| 289 |
+
"loss": 2.2209,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 40.19607843137255,
|
| 294 |
+
"grad_norm": 6.348704814910889,
|
| 295 |
+
"learning_rate": 4.7338935574229694e-05,
|
| 296 |
+
"loss": 2.2401,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 41.1764705882353,
|
| 301 |
+
"grad_norm": 6.165525436401367,
|
| 302 |
+
"learning_rate": 4.5782757547463436e-05,
|
| 303 |
+
"loss": 2.2289,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 42.15686274509804,
|
| 308 |
+
"grad_norm": 3.2731242179870605,
|
| 309 |
+
"learning_rate": 4.422657952069717e-05,
|
| 310 |
+
"loss": 2.222,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 43.13725490196079,
|
| 315 |
+
"grad_norm": 4.991629123687744,
|
| 316 |
+
"learning_rate": 4.2670401493930905e-05,
|
| 317 |
+
"loss": 2.213,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 44.11764705882353,
|
| 322 |
+
"grad_norm": 5.966474533081055,
|
| 323 |
+
"learning_rate": 4.111422346716465e-05,
|
| 324 |
+
"loss": 2.2211,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 45.09803921568628,
|
| 329 |
+
"grad_norm": 6.867234230041504,
|
| 330 |
+
"learning_rate": 3.955804544039838e-05,
|
| 331 |
+
"loss": 2.2265,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 46.07843137254902,
|
| 336 |
+
"grad_norm": 5.227305889129639,
|
| 337 |
+
"learning_rate": 3.800186741363212e-05,
|
| 338 |
+
"loss": 2.219,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 47.05882352941177,
|
| 343 |
+
"grad_norm": 4.603776931762695,
|
| 344 |
+
"learning_rate": 3.644568938686586e-05,
|
| 345 |
+
"loss": 2.22,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 48.03921568627451,
|
| 350 |
+
"grad_norm": 6.5035858154296875,
|
| 351 |
+
"learning_rate": 3.48895113600996e-05,
|
| 352 |
+
"loss": 2.2192,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 49.01960784313726,
|
| 357 |
+
"grad_norm": 7.140364170074463,
|
| 358 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 359 |
+
"loss": 2.2181,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 50.0,
|
| 364 |
+
"grad_norm": 10.780461311340332,
|
| 365 |
+
"learning_rate": 3.1777155306567077e-05,
|
| 366 |
+
"loss": 2.2234,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 50.98039215686274,
|
| 371 |
+
"grad_norm": 4.444032669067383,
|
| 372 |
+
"learning_rate": 3.022097727980081e-05,
|
| 373 |
+
"loss": 2.2186,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 51.96078431372549,
|
| 378 |
+
"grad_norm": 3.78542160987854,
|
| 379 |
+
"learning_rate": 2.8664799253034546e-05,
|
| 380 |
+
"loss": 2.2215,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 52.94117647058823,
|
| 385 |
+
"grad_norm": 5.9261322021484375,
|
| 386 |
+
"learning_rate": 2.7108621226268288e-05,
|
| 387 |
+
"loss": 2.2197,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 53.92156862745098,
|
| 392 |
+
"grad_norm": 3.300880193710327,
|
| 393 |
+
"learning_rate": 2.5552443199502023e-05,
|
| 394 |
+
"loss": 2.2125,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 54.90196078431372,
|
| 399 |
+
"grad_norm": 5.05993127822876,
|
| 400 |
+
"learning_rate": 2.3996265172735765e-05,
|
| 401 |
+
"loss": 2.2114,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 55.88235294117647,
|
| 406 |
+
"grad_norm": 5.635678768157959,
|
| 407 |
+
"learning_rate": 2.24400871459695e-05,
|
| 408 |
+
"loss": 2.2213,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 56.86274509803921,
|
| 413 |
+
"grad_norm": 6.652504920959473,
|
| 414 |
+
"learning_rate": 2.0883909119203238e-05,
|
| 415 |
+
"loss": 2.2239,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 57.84313725490196,
|
| 420 |
+
"grad_norm": 7.9634623527526855,
|
| 421 |
+
"learning_rate": 1.9327731092436976e-05,
|
| 422 |
+
"loss": 2.2289,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 58.8235294117647,
|
| 427 |
+
"grad_norm": 5.01388692855835,
|
| 428 |
+
"learning_rate": 1.777155306567071e-05,
|
| 429 |
+
"loss": 2.2282,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 59.80392156862745,
|
| 434 |
+
"grad_norm": 4.071011066436768,
|
| 435 |
+
"learning_rate": 1.6215375038904453e-05,
|
| 436 |
+
"loss": 2.225,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 60.78431372549019,
|
| 441 |
+
"grad_norm": 4.984341621398926,
|
| 442 |
+
"learning_rate": 1.4659197012138189e-05,
|
| 443 |
+
"loss": 2.2174,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 61.76470588235294,
|
| 448 |
+
"grad_norm": 5.719054698944092,
|
| 449 |
+
"learning_rate": 1.3103018985371926e-05,
|
| 450 |
+
"loss": 2.2223,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 62.745098039215684,
|
| 455 |
+
"grad_norm": 4.165637016296387,
|
| 456 |
+
"learning_rate": 1.1546840958605664e-05,
|
| 457 |
+
"loss": 2.2154,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 63.72549019607843,
|
| 462 |
+
"grad_norm": 6.845320224761963,
|
| 463 |
+
"learning_rate": 9.990662931839404e-06,
|
| 464 |
+
"loss": 2.2144,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 64.70588235294117,
|
| 469 |
+
"grad_norm": 4.848325252532959,
|
| 470 |
+
"learning_rate": 8.43448490507314e-06,
|
| 471 |
+
"loss": 2.2189,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 65.68627450980392,
|
| 476 |
+
"grad_norm": 7.032234191894531,
|
| 477 |
+
"learning_rate": 6.878306878306878e-06,
|
| 478 |
+
"loss": 2.2217,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 66.66666666666667,
|
| 483 |
+
"grad_norm": 3.573167085647583,
|
| 484 |
+
"learning_rate": 5.322128851540616e-06,
|
| 485 |
+
"loss": 2.2184,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 67.6470588235294,
|
| 490 |
+
"grad_norm": 5.0887885093688965,
|
| 491 |
+
"learning_rate": 3.7659508247743545e-06,
|
| 492 |
+
"loss": 2.217,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 68.62745098039215,
|
| 497 |
+
"grad_norm": 4.107006549835205,
|
| 498 |
+
"learning_rate": 2.209772798008092e-06,
|
| 499 |
+
"loss": 2.2137,
|
| 500 |
+
"step": 3500
|
| 501 |
+
}
|
| 502 |
+
],
|
| 503 |
+
"logging_steps": 50,
|
| 504 |
+
"max_steps": 3570,
|
| 505 |
+
"num_input_tokens_seen": 0,
|
| 506 |
+
"num_train_epochs": 70,
|
| 507 |
+
"save_steps": 500,
|
| 508 |
+
"stateful_callbacks": {
|
| 509 |
+
"TrainerControl": {
|
| 510 |
+
"args": {
|
| 511 |
+
"should_epoch_stop": false,
|
| 512 |
+
"should_evaluate": false,
|
| 513 |
+
"should_log": false,
|
| 514 |
+
"should_save": true,
|
| 515 |
+
"should_training_stop": false
|
| 516 |
+
},
|
| 517 |
+
"attributes": {}
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"total_flos": 5.152397594484941e+16,
|
| 521 |
+
"train_batch_size": 32,
|
| 522 |
+
"trial_name": null,
|
| 523 |
+
"trial_params": null
|
| 524 |
+
}
|
telecom_arabert_final/checkpoint-3500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f404697feee606a570b4c324874ebe1d187761105966fe2473f0e223ba2c5b60
|
| 3 |
+
size 5841
|
telecom_arabert_final/checkpoint-3500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_final/checkpoint-3570/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": 1,
|
| 13 |
+
"1": 2,
|
| 14 |
+
"2": 3,
|
| 15 |
+
"3": 4,
|
| 16 |
+
"4": 5,
|
| 17 |
+
"5": 6,
|
| 18 |
+
"6": 7,
|
| 19 |
+
"7": 8,
|
| 20 |
+
"8": 9
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 4096,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"1": 0,
|
| 26 |
+
"2": 1,
|
| 27 |
+
"3": 2,
|
| 28 |
+
"4": 3,
|
| 29 |
+
"5": 4,
|
| 30 |
+
"6": 5,
|
| 31 |
+
"7": 6,
|
| 32 |
+
"8": 7,
|
| 33 |
+
"9": 8
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-12,
|
| 36 |
+
"max_position_embeddings": 512,
|
| 37 |
+
"model_type": "bert",
|
| 38 |
+
"num_attention_heads": 16,
|
| 39 |
+
"num_hidden_layers": 24,
|
| 40 |
+
"pad_token_id": 31,
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"transformers_version": "4.57.3",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 64000
|
| 47 |
+
}
|
telecom_arabert_final/checkpoint-3570/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d93707e820c2358b259f9fbc6bccdc94db28d36fdf85a1f7fee6f2d664a534a5
|
| 3 |
+
size 1477777444
|
telecom_arabert_final/checkpoint-3570/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45e1d87035bd055c7d4208b97fce6f286bcb4d24b5038893895234fc044febae
|
| 3 |
+
size 2955795454
|
telecom_arabert_final/checkpoint-3570/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e53609e170b8ad1794f20ce93a33016717728f19d3b7bed7de5ad7037c6d4b2
|
| 3 |
+
size 14645
|
telecom_arabert_final/checkpoint-3570/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c9cd677a65bc06d25cfe0cd4edfa3ba4f94ffaf30bb5f6f3486d155d9f361e5
|
| 3 |
+
size 1465
|
telecom_arabert_final/checkpoint-3570/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
telecom_arabert_final/checkpoint-3570/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_final/checkpoint-3570/tokenizer_config.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "+ا",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "+ك",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "ب+",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "+هم",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "+ات",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "+ي",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "ل+",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "+هما",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "+نا",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "+ن",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "+ها",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "+كما",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "+ة",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "ف+",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "+كم",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "+كن",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "+ت",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[بريد]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[مستخدم]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "لل+",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "ال+",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[رابط]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "س+",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "+ان",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "+وا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "+ه",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "+ون",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "+هن",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "+ين",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": true,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "��+",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": true,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "ك+",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": true,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[UNK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[CLS]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[SEP]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[MASK]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": false,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"extra_special_tokens": {},
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ك",
|
| 302 |
+
"+كما",
|
| 303 |
+
"ك+",
|
| 304 |
+
"+وا",
|
| 305 |
+
"+ين",
|
| 306 |
+
"و+",
|
| 307 |
+
"+كن",
|
| 308 |
+
"+ان",
|
| 309 |
+
"+هم",
|
| 310 |
+
"+ة",
|
| 311 |
+
"[بريد]",
|
| 312 |
+
"لل+",
|
| 313 |
+
"+ي",
|
| 314 |
+
"+ت",
|
| 315 |
+
"+ن",
|
| 316 |
+
"س+",
|
| 317 |
+
"ل+",
|
| 318 |
+
"[مستخدم]",
|
| 319 |
+
"+كم",
|
| 320 |
+
"+ا",
|
| 321 |
+
"ب+",
|
| 322 |
+
"ف+",
|
| 323 |
+
"+نا",
|
| 324 |
+
"+ها",
|
| 325 |
+
"+ون",
|
| 326 |
+
"+هما",
|
| 327 |
+
"ال+",
|
| 328 |
+
"+ه",
|
| 329 |
+
"+هن",
|
| 330 |
+
"+ات",
|
| 331 |
+
"[رابط]"
|
| 332 |
+
],
|
| 333 |
+
"pad_token": "[PAD]",
|
| 334 |
+
"sep_token": "[SEP]",
|
| 335 |
+
"strip_accents": null,
|
| 336 |
+
"tokenize_chinese_chars": true,
|
| 337 |
+
"tokenizer_class": "BertTokenizer",
|
| 338 |
+
"unk_token": "[UNK]"
|
| 339 |
+
}
|
telecom_arabert_final/checkpoint-3570/trainer_state.json
ADDED
|
@@ -0,0 +1,531 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3570,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.9803921568627451,
|
| 14 |
+
"grad_norm": 11.002342224121094,
|
| 15 |
+
"learning_rate": 1.3725490196078432e-05,
|
| 16 |
+
"loss": 2.3419,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.9607843137254903,
|
| 21 |
+
"grad_norm": 29.423385620117188,
|
| 22 |
+
"learning_rate": 2.773109243697479e-05,
|
| 23 |
+
"loss": 2.1727,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.9411764705882355,
|
| 28 |
+
"grad_norm": 26.981374740600586,
|
| 29 |
+
"learning_rate": 4.173669467787115e-05,
|
| 30 |
+
"loss": 2.0203,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.9215686274509802,
|
| 35 |
+
"grad_norm": 13.149168968200684,
|
| 36 |
+
"learning_rate": 5.574229691876751e-05,
|
| 37 |
+
"loss": 1.688,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 4.901960784313726,
|
| 42 |
+
"grad_norm": 4.1570916175842285,
|
| 43 |
+
"learning_rate": 6.974789915966386e-05,
|
| 44 |
+
"loss": 2.1775,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.882352941176471,
|
| 49 |
+
"grad_norm": 7.508273124694824,
|
| 50 |
+
"learning_rate": 8.375350140056023e-05,
|
| 51 |
+
"loss": 2.2603,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 6.862745098039216,
|
| 56 |
+
"grad_norm": 5.582854270935059,
|
| 57 |
+
"learning_rate": 9.775910364145658e-05,
|
| 58 |
+
"loss": 2.2469,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 7.8431372549019605,
|
| 63 |
+
"grad_norm": 6.001800060272217,
|
| 64 |
+
"learning_rate": 9.869281045751635e-05,
|
| 65 |
+
"loss": 2.2533,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 8.823529411764707,
|
| 70 |
+
"grad_norm": 6.843214511871338,
|
| 71 |
+
"learning_rate": 9.713663243075009e-05,
|
| 72 |
+
"loss": 2.2437,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 9.803921568627452,
|
| 77 |
+
"grad_norm": 6.001797676086426,
|
| 78 |
+
"learning_rate": 9.558045440398382e-05,
|
| 79 |
+
"loss": 2.2406,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 10.784313725490197,
|
| 84 |
+
"grad_norm": 4.675999164581299,
|
| 85 |
+
"learning_rate": 9.402427637721756e-05,
|
| 86 |
+
"loss": 2.2353,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.764705882352942,
|
| 91 |
+
"grad_norm": 6.9409966468811035,
|
| 92 |
+
"learning_rate": 9.246809835045129e-05,
|
| 93 |
+
"loss": 2.2288,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 12.745098039215687,
|
| 98 |
+
"grad_norm": 7.809481143951416,
|
| 99 |
+
"learning_rate": 9.091192032368503e-05,
|
| 100 |
+
"loss": 2.237,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 13.72549019607843,
|
| 105 |
+
"grad_norm": 5.771924018859863,
|
| 106 |
+
"learning_rate": 8.935574229691877e-05,
|
| 107 |
+
"loss": 2.234,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 14.705882352941176,
|
| 112 |
+
"grad_norm": 3.7695183753967285,
|
| 113 |
+
"learning_rate": 8.779956427015251e-05,
|
| 114 |
+
"loss": 2.2398,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 15.686274509803921,
|
| 119 |
+
"grad_norm": 5.8638529777526855,
|
| 120 |
+
"learning_rate": 8.624338624338625e-05,
|
| 121 |
+
"loss": 2.2241,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 16.666666666666668,
|
| 126 |
+
"grad_norm": 7.440635681152344,
|
| 127 |
+
"learning_rate": 8.468720821661998e-05,
|
| 128 |
+
"loss": 2.2256,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 17.647058823529413,
|
| 133 |
+
"grad_norm": 4.2441182136535645,
|
| 134 |
+
"learning_rate": 8.313103018985372e-05,
|
| 135 |
+
"loss": 2.2298,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 18.627450980392158,
|
| 140 |
+
"grad_norm": 7.42420768737793,
|
| 141 |
+
"learning_rate": 8.157485216308745e-05,
|
| 142 |
+
"loss": 2.2233,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 19.607843137254903,
|
| 147 |
+
"grad_norm": 4.213704586029053,
|
| 148 |
+
"learning_rate": 8.001867413632121e-05,
|
| 149 |
+
"loss": 2.2313,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 20.58823529411765,
|
| 154 |
+
"grad_norm": 6.308703422546387,
|
| 155 |
+
"learning_rate": 7.846249610955494e-05,
|
| 156 |
+
"loss": 2.2259,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 21.568627450980394,
|
| 161 |
+
"grad_norm": 8.95936393737793,
|
| 162 |
+
"learning_rate": 7.690631808278868e-05,
|
| 163 |
+
"loss": 2.2334,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 22.54901960784314,
|
| 168 |
+
"grad_norm": 7.726138591766357,
|
| 169 |
+
"learning_rate": 7.53501400560224e-05,
|
| 170 |
+
"loss": 2.2271,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 23.529411764705884,
|
| 175 |
+
"grad_norm": 5.980637550354004,
|
| 176 |
+
"learning_rate": 7.379396202925615e-05,
|
| 177 |
+
"loss": 2.2278,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 24.509803921568626,
|
| 182 |
+
"grad_norm": 5.208985805511475,
|
| 183 |
+
"learning_rate": 7.223778400248989e-05,
|
| 184 |
+
"loss": 2.2258,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 25.49019607843137,
|
| 189 |
+
"grad_norm": 3.785893678665161,
|
| 190 |
+
"learning_rate": 7.068160597572363e-05,
|
| 191 |
+
"loss": 2.2354,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 26.470588235294116,
|
| 196 |
+
"grad_norm": 7.314659595489502,
|
| 197 |
+
"learning_rate": 6.912542794895737e-05,
|
| 198 |
+
"loss": 2.2371,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 27.45098039215686,
|
| 203 |
+
"grad_norm": 5.165799617767334,
|
| 204 |
+
"learning_rate": 6.75692499221911e-05,
|
| 205 |
+
"loss": 2.2302,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 28.431372549019606,
|
| 210 |
+
"grad_norm": 6.496328353881836,
|
| 211 |
+
"learning_rate": 6.601307189542484e-05,
|
| 212 |
+
"loss": 2.2252,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 29.41176470588235,
|
| 217 |
+
"grad_norm": 3.1437888145446777,
|
| 218 |
+
"learning_rate": 6.445689386865857e-05,
|
| 219 |
+
"loss": 2.2292,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 30.392156862745097,
|
| 224 |
+
"grad_norm": 5.930662631988525,
|
| 225 |
+
"learning_rate": 6.290071584189231e-05,
|
| 226 |
+
"loss": 2.2307,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 31.372549019607842,
|
| 231 |
+
"grad_norm": 6.53542947769165,
|
| 232 |
+
"learning_rate": 6.134453781512605e-05,
|
| 233 |
+
"loss": 2.2195,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 32.35294117647059,
|
| 238 |
+
"grad_norm": 6.8471198081970215,
|
| 239 |
+
"learning_rate": 5.9788359788359794e-05,
|
| 240 |
+
"loss": 2.2292,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 33.333333333333336,
|
| 245 |
+
"grad_norm": 5.49623441696167,
|
| 246 |
+
"learning_rate": 5.823218176159353e-05,
|
| 247 |
+
"loss": 2.2269,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 34.31372549019608,
|
| 252 |
+
"grad_norm": 3.214643716812134,
|
| 253 |
+
"learning_rate": 5.6676003734827264e-05,
|
| 254 |
+
"loss": 2.2251,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 35.294117647058826,
|
| 259 |
+
"grad_norm": 6.643034934997559,
|
| 260 |
+
"learning_rate": 5.5119825708061e-05,
|
| 261 |
+
"loss": 2.2226,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 36.27450980392157,
|
| 266 |
+
"grad_norm": 5.6264753341674805,
|
| 267 |
+
"learning_rate": 5.356364768129474e-05,
|
| 268 |
+
"loss": 2.221,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 37.254901960784316,
|
| 273 |
+
"grad_norm": 5.2604265213012695,
|
| 274 |
+
"learning_rate": 5.200746965452848e-05,
|
| 275 |
+
"loss": 2.2268,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 38.23529411764706,
|
| 280 |
+
"grad_norm": 3.1051926612854004,
|
| 281 |
+
"learning_rate": 5.045129162776222e-05,
|
| 282 |
+
"loss": 2.2193,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 39.21568627450981,
|
| 287 |
+
"grad_norm": 5.157900333404541,
|
| 288 |
+
"learning_rate": 4.889511360099596e-05,
|
| 289 |
+
"loss": 2.2209,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 40.19607843137255,
|
| 294 |
+
"grad_norm": 6.348704814910889,
|
| 295 |
+
"learning_rate": 4.7338935574229694e-05,
|
| 296 |
+
"loss": 2.2401,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 41.1764705882353,
|
| 301 |
+
"grad_norm": 6.165525436401367,
|
| 302 |
+
"learning_rate": 4.5782757547463436e-05,
|
| 303 |
+
"loss": 2.2289,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 42.15686274509804,
|
| 308 |
+
"grad_norm": 3.2731242179870605,
|
| 309 |
+
"learning_rate": 4.422657952069717e-05,
|
| 310 |
+
"loss": 2.222,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 43.13725490196079,
|
| 315 |
+
"grad_norm": 4.991629123687744,
|
| 316 |
+
"learning_rate": 4.2670401493930905e-05,
|
| 317 |
+
"loss": 2.213,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 44.11764705882353,
|
| 322 |
+
"grad_norm": 5.966474533081055,
|
| 323 |
+
"learning_rate": 4.111422346716465e-05,
|
| 324 |
+
"loss": 2.2211,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 45.09803921568628,
|
| 329 |
+
"grad_norm": 6.867234230041504,
|
| 330 |
+
"learning_rate": 3.955804544039838e-05,
|
| 331 |
+
"loss": 2.2265,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 46.07843137254902,
|
| 336 |
+
"grad_norm": 5.227305889129639,
|
| 337 |
+
"learning_rate": 3.800186741363212e-05,
|
| 338 |
+
"loss": 2.219,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 47.05882352941177,
|
| 343 |
+
"grad_norm": 4.603776931762695,
|
| 344 |
+
"learning_rate": 3.644568938686586e-05,
|
| 345 |
+
"loss": 2.22,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 48.03921568627451,
|
| 350 |
+
"grad_norm": 6.5035858154296875,
|
| 351 |
+
"learning_rate": 3.48895113600996e-05,
|
| 352 |
+
"loss": 2.2192,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 49.01960784313726,
|
| 357 |
+
"grad_norm": 7.140364170074463,
|
| 358 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 359 |
+
"loss": 2.2181,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 50.0,
|
| 364 |
+
"grad_norm": 10.780461311340332,
|
| 365 |
+
"learning_rate": 3.1777155306567077e-05,
|
| 366 |
+
"loss": 2.2234,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 50.98039215686274,
|
| 371 |
+
"grad_norm": 4.444032669067383,
|
| 372 |
+
"learning_rate": 3.022097727980081e-05,
|
| 373 |
+
"loss": 2.2186,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 51.96078431372549,
|
| 378 |
+
"grad_norm": 3.78542160987854,
|
| 379 |
+
"learning_rate": 2.8664799253034546e-05,
|
| 380 |
+
"loss": 2.2215,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 52.94117647058823,
|
| 385 |
+
"grad_norm": 5.9261322021484375,
|
| 386 |
+
"learning_rate": 2.7108621226268288e-05,
|
| 387 |
+
"loss": 2.2197,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 53.92156862745098,
|
| 392 |
+
"grad_norm": 3.300880193710327,
|
| 393 |
+
"learning_rate": 2.5552443199502023e-05,
|
| 394 |
+
"loss": 2.2125,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 54.90196078431372,
|
| 399 |
+
"grad_norm": 5.05993127822876,
|
| 400 |
+
"learning_rate": 2.3996265172735765e-05,
|
| 401 |
+
"loss": 2.2114,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 55.88235294117647,
|
| 406 |
+
"grad_norm": 5.635678768157959,
|
| 407 |
+
"learning_rate": 2.24400871459695e-05,
|
| 408 |
+
"loss": 2.2213,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 56.86274509803921,
|
| 413 |
+
"grad_norm": 6.652504920959473,
|
| 414 |
+
"learning_rate": 2.0883909119203238e-05,
|
| 415 |
+
"loss": 2.2239,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 57.84313725490196,
|
| 420 |
+
"grad_norm": 7.9634623527526855,
|
| 421 |
+
"learning_rate": 1.9327731092436976e-05,
|
| 422 |
+
"loss": 2.2289,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 58.8235294117647,
|
| 427 |
+
"grad_norm": 5.01388692855835,
|
| 428 |
+
"learning_rate": 1.777155306567071e-05,
|
| 429 |
+
"loss": 2.2282,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 59.80392156862745,
|
| 434 |
+
"grad_norm": 4.071011066436768,
|
| 435 |
+
"learning_rate": 1.6215375038904453e-05,
|
| 436 |
+
"loss": 2.225,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 60.78431372549019,
|
| 441 |
+
"grad_norm": 4.984341621398926,
|
| 442 |
+
"learning_rate": 1.4659197012138189e-05,
|
| 443 |
+
"loss": 2.2174,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 61.76470588235294,
|
| 448 |
+
"grad_norm": 5.719054698944092,
|
| 449 |
+
"learning_rate": 1.3103018985371926e-05,
|
| 450 |
+
"loss": 2.2223,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 62.745098039215684,
|
| 455 |
+
"grad_norm": 4.165637016296387,
|
| 456 |
+
"learning_rate": 1.1546840958605664e-05,
|
| 457 |
+
"loss": 2.2154,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 63.72549019607843,
|
| 462 |
+
"grad_norm": 6.845320224761963,
|
| 463 |
+
"learning_rate": 9.990662931839404e-06,
|
| 464 |
+
"loss": 2.2144,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 64.70588235294117,
|
| 469 |
+
"grad_norm": 4.848325252532959,
|
| 470 |
+
"learning_rate": 8.43448490507314e-06,
|
| 471 |
+
"loss": 2.2189,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 65.68627450980392,
|
| 476 |
+
"grad_norm": 7.032234191894531,
|
| 477 |
+
"learning_rate": 6.878306878306878e-06,
|
| 478 |
+
"loss": 2.2217,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 66.66666666666667,
|
| 483 |
+
"grad_norm": 3.573167085647583,
|
| 484 |
+
"learning_rate": 5.322128851540616e-06,
|
| 485 |
+
"loss": 2.2184,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 67.6470588235294,
|
| 490 |
+
"grad_norm": 5.0887885093688965,
|
| 491 |
+
"learning_rate": 3.7659508247743545e-06,
|
| 492 |
+
"loss": 2.217,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 68.62745098039215,
|
| 497 |
+
"grad_norm": 4.107006549835205,
|
| 498 |
+
"learning_rate": 2.209772798008092e-06,
|
| 499 |
+
"loss": 2.2137,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 69.6078431372549,
|
| 504 |
+
"grad_norm": 5.1878886222839355,
|
| 505 |
+
"learning_rate": 6.535947712418301e-07,
|
| 506 |
+
"loss": 2.2193,
|
| 507 |
+
"step": 3550
|
| 508 |
+
}
|
| 509 |
+
],
|
| 510 |
+
"logging_steps": 50,
|
| 511 |
+
"max_steps": 3570,
|
| 512 |
+
"num_input_tokens_seen": 0,
|
| 513 |
+
"num_train_epochs": 70,
|
| 514 |
+
"save_steps": 500,
|
| 515 |
+
"stateful_callbacks": {
|
| 516 |
+
"TrainerControl": {
|
| 517 |
+
"args": {
|
| 518 |
+
"should_epoch_stop": false,
|
| 519 |
+
"should_evaluate": false,
|
| 520 |
+
"should_log": false,
|
| 521 |
+
"should_save": true,
|
| 522 |
+
"should_training_stop": true
|
| 523 |
+
},
|
| 524 |
+
"attributes": {}
|
| 525 |
+
}
|
| 526 |
+
},
|
| 527 |
+
"total_flos": 5.254819273686528e+16,
|
| 528 |
+
"train_batch_size": 32,
|
| 529 |
+
"trial_name": null,
|
| 530 |
+
"trial_params": null
|
| 531 |
+
}
|
telecom_arabert_final/checkpoint-3570/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f404697feee606a570b4c324874ebe1d187761105966fe2473f0e223ba2c5b60
|
| 3 |
+
size 5841
|
telecom_arabert_final/checkpoint-3570/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_final/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": 1,
|
| 13 |
+
"1": 2,
|
| 14 |
+
"2": 3,
|
| 15 |
+
"3": 4,
|
| 16 |
+
"4": 5,
|
| 17 |
+
"5": 6,
|
| 18 |
+
"6": 7,
|
| 19 |
+
"7": 8,
|
| 20 |
+
"8": 9
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 4096,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"1": 0,
|
| 26 |
+
"2": 1,
|
| 27 |
+
"3": 2,
|
| 28 |
+
"4": 3,
|
| 29 |
+
"5": 4,
|
| 30 |
+
"6": 5,
|
| 31 |
+
"7": 6,
|
| 32 |
+
"8": 7,
|
| 33 |
+
"9": 8
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-12,
|
| 36 |
+
"max_position_embeddings": 512,
|
| 37 |
+
"model_type": "bert",
|
| 38 |
+
"num_attention_heads": 16,
|
| 39 |
+
"num_hidden_layers": 24,
|
| 40 |
+
"pad_token_id": 31,
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"transformers_version": "4.57.3",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 64000
|
| 47 |
+
}
|
telecom_arabert_final/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d93707e820c2358b259f9fbc6bccdc94db28d36fdf85a1f7fee6f2d664a534a5
|
| 3 |
+
size 1477777444
|
telecom_arabert_final/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
telecom_arabert_final/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_final/tokenizer_config.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "+ا",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "+ك",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "ب+",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "+هم",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "+ات",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "+ي",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "ل+",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "+هما",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "+نا",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "+ن",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "+ها",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "+كما",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "+ة",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "ف+",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "+كم",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "+كن",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "+ت",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[بريد]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[مستخدم]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "لل+",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "ال+",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[رابط]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "س+",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "+ان",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "+وا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "+ه",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "+ون",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "+هن",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "+ين",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": true,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "��+",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": true,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "ك+",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": true,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[UNK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[CLS]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[SEP]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[MASK]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": false,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"extra_special_tokens": {},
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ك",
|
| 302 |
+
"+كما",
|
| 303 |
+
"ك+",
|
| 304 |
+
"+وا",
|
| 305 |
+
"+ين",
|
| 306 |
+
"و+",
|
| 307 |
+
"+كن",
|
| 308 |
+
"+ان",
|
| 309 |
+
"+هم",
|
| 310 |
+
"+ة",
|
| 311 |
+
"[بريد]",
|
| 312 |
+
"لل+",
|
| 313 |
+
"+ي",
|
| 314 |
+
"+ت",
|
| 315 |
+
"+ن",
|
| 316 |
+
"س+",
|
| 317 |
+
"ل+",
|
| 318 |
+
"[مستخدم]",
|
| 319 |
+
"+كم",
|
| 320 |
+
"+ا",
|
| 321 |
+
"ب+",
|
| 322 |
+
"ف+",
|
| 323 |
+
"+نا",
|
| 324 |
+
"+ها",
|
| 325 |
+
"+ون",
|
| 326 |
+
"+هما",
|
| 327 |
+
"ال+",
|
| 328 |
+
"+ه",
|
| 329 |
+
"+هن",
|
| 330 |
+
"+ات",
|
| 331 |
+
"[رابط]"
|
| 332 |
+
],
|
| 333 |
+
"pad_token": "[PAD]",
|
| 334 |
+
"sep_token": "[SEP]",
|
| 335 |
+
"strip_accents": null,
|
| 336 |
+
"tokenize_chinese_chars": true,
|
| 337 |
+
"tokenizer_class": "BertTokenizer",
|
| 338 |
+
"unk_token": "[UNK]"
|
| 339 |
+
}
|
telecom_arabert_final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f404697feee606a570b4c324874ebe1d187761105966fe2473f0e223ba2c5b60
|
| 3 |
+
size 5841
|
telecom_arabert_final/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_large_full_pipeline/checkpoint-48/config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 1,
|
| 15 |
+
"1": 2,
|
| 16 |
+
"2": 3,
|
| 17 |
+
"3": 4,
|
| 18 |
+
"4": 5,
|
| 19 |
+
"5": 6,
|
| 20 |
+
"6": 7,
|
| 21 |
+
"7": 8,
|
| 22 |
+
"8": 9
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 3072,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"1": 0,
|
| 28 |
+
"2": 1,
|
| 29 |
+
"3": 2,
|
| 30 |
+
"4": 3,
|
| 31 |
+
"5": 4,
|
| 32 |
+
"6": 5,
|
| 33 |
+
"7": 6,
|
| 34 |
+
"8": 7,
|
| 35 |
+
"9": 8
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"model_type": "bert",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_hidden_layers": 12,
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"pooler_fc_size": 768,
|
| 44 |
+
"pooler_num_attention_heads": 12,
|
| 45 |
+
"pooler_num_fc_layers": 3,
|
| 46 |
+
"pooler_size_per_head": 128,
|
| 47 |
+
"pooler_type": "first_token_transform",
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"transformers_version": "4.57.3",
|
| 51 |
+
"type_vocab_size": 2,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 100000
|
| 54 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-48/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:353da92582a55d807297cea6472435ef357ed14d1b3964021d78587799369c43
|
| 3 |
+
size 651416604
|
telecom_arabert_large_full_pipeline/checkpoint-48/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8ecd0597dd4956fde48a8772a9e7c24c94eefe86d1cc29a7973479dd533b416
|
| 3 |
+
size 1302957451
|
telecom_arabert_large_full_pipeline/checkpoint-48/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed81f7db8d606ed1bb9b292fae282ac039995f720a9d6914c62e680e24c7ca19
|
| 3 |
+
size 14645
|
telecom_arabert_large_full_pipeline/checkpoint-48/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d365d688f8b5d88411103bae117a83936714556abc6d35a086b9815020627c5a
|
| 3 |
+
size 1465
|
telecom_arabert_large_full_pipeline/checkpoint-48/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-48/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_large_full_pipeline/checkpoint-48/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": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 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 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-48/trainer_state.json
ADDED
|
@@ -0,0 +1,242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 48,
|
| 3 |
+
"best_metric": 0.7628623647339323,
|
| 4 |
+
"best_model_checkpoint": "./telecom_arabert_large_full_pipeline/checkpoint-48",
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 48,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.18333333333333332,
|
| 15 |
+
"eval_f1_class_1": 0.5714285714285714,
|
| 16 |
+
"eval_f1_class_2": 0.0,
|
| 17 |
+
"eval_f1_class_3": 0.08695652173913043,
|
| 18 |
+
"eval_f1_class_4": 0.0,
|
| 19 |
+
"eval_f1_class_5": 0.14285714285714285,
|
| 20 |
+
"eval_f1_class_6": 0.0,
|
| 21 |
+
"eval_f1_class_7": 0.15384615384615385,
|
| 22 |
+
"eval_f1_class_8": 0.0,
|
| 23 |
+
"eval_f1_class_9": 0.4782608695652174,
|
| 24 |
+
"eval_f1_macro": 0.1592610288262462,
|
| 25 |
+
"eval_f1_weighted": 0.1646121993948081,
|
| 26 |
+
"eval_loss": 2.19708251953125,
|
| 27 |
+
"eval_precision_macro": 0.22300011411617027,
|
| 28 |
+
"eval_precision_weighted": 0.23096456692913386,
|
| 29 |
+
"eval_recall_macro": 0.20279146863815056,
|
| 30 |
+
"eval_recall_weighted": 0.18333333333333332,
|
| 31 |
+
"eval_runtime": 0.3659,
|
| 32 |
+
"eval_samples_per_second": 491.975,
|
| 33 |
+
"eval_steps_per_second": 2.733,
|
| 34 |
+
"step": 6
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"eval_accuracy": 0.32222222222222224,
|
| 39 |
+
"eval_f1_class_1": 0.7894736842105263,
|
| 40 |
+
"eval_f1_class_2": 0.0,
|
| 41 |
+
"eval_f1_class_3": 0.17391304347826086,
|
| 42 |
+
"eval_f1_class_4": 0.0,
|
| 43 |
+
"eval_f1_class_5": 0.22807017543859648,
|
| 44 |
+
"eval_f1_class_6": 0.14814814814814814,
|
| 45 |
+
"eval_f1_class_7": 0.22857142857142856,
|
| 46 |
+
"eval_f1_class_8": 0.0,
|
| 47 |
+
"eval_f1_class_9": 0.7719298245614035,
|
| 48 |
+
"eval_f1_macro": 0.26001181160092934,
|
| 49 |
+
"eval_f1_weighted": 0.26565195866746844,
|
| 50 |
+
"eval_loss": 2.146738052368164,
|
| 51 |
+
"eval_precision_macro": 0.2969712657540264,
|
| 52 |
+
"eval_precision_weighted": 0.30471977589915855,
|
| 53 |
+
"eval_recall_macro": 0.34401095805726306,
|
| 54 |
+
"eval_recall_weighted": 0.32222222222222224,
|
| 55 |
+
"eval_runtime": 0.3684,
|
| 56 |
+
"eval_samples_per_second": 488.604,
|
| 57 |
+
"eval_steps_per_second": 2.714,
|
| 58 |
+
"step": 12
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 3.0,
|
| 62 |
+
"eval_accuracy": 0.5611111111111111,
|
| 63 |
+
"eval_f1_class_1": 0.8163265306122449,
|
| 64 |
+
"eval_f1_class_2": 0.5882352941176471,
|
| 65 |
+
"eval_f1_class_3": 0.4,
|
| 66 |
+
"eval_f1_class_4": 0.6486486486486487,
|
| 67 |
+
"eval_f1_class_5": 0.35714285714285715,
|
| 68 |
+
"eval_f1_class_6": 0.25,
|
| 69 |
+
"eval_f1_class_7": 0.8181818181818182,
|
| 70 |
+
"eval_f1_class_8": 0.0,
|
| 71 |
+
"eval_f1_class_9": 0.7457627118644068,
|
| 72 |
+
"eval_f1_macro": 0.5138108733964025,
|
| 73 |
+
"eval_f1_weighted": 0.5241442923315164,
|
| 74 |
+
"eval_loss": 2.027998208999634,
|
| 75 |
+
"eval_precision_macro": 0.5503880544762977,
|
| 76 |
+
"eval_precision_weighted": 0.56245523793883,
|
| 77 |
+
"eval_recall_macro": 0.5638005023050117,
|
| 78 |
+
"eval_recall_weighted": 0.5611111111111111,
|
| 79 |
+
"eval_runtime": 0.3388,
|
| 80 |
+
"eval_samples_per_second": 531.312,
|
| 81 |
+
"eval_steps_per_second": 2.952,
|
| 82 |
+
"step": 18
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.0,
|
| 86 |
+
"eval_accuracy": 0.6777777777777778,
|
| 87 |
+
"eval_f1_class_1": 0.7916666666666666,
|
| 88 |
+
"eval_f1_class_2": 0.6415094339622641,
|
| 89 |
+
"eval_f1_class_3": 0.4,
|
| 90 |
+
"eval_f1_class_4": 0.8,
|
| 91 |
+
"eval_f1_class_5": 0.6428571428571429,
|
| 92 |
+
"eval_f1_class_6": 0.2727272727272727,
|
| 93 |
+
"eval_f1_class_7": 0.8936170212765957,
|
| 94 |
+
"eval_f1_class_8": 0.4878048780487805,
|
| 95 |
+
"eval_f1_class_9": 0.7857142857142857,
|
| 96 |
+
"eval_f1_macro": 0.6350996334725564,
|
| 97 |
+
"eval_f1_weighted": 0.6471254592295707,
|
| 98 |
+
"eval_loss": 1.8633366823196411,
|
| 99 |
+
"eval_precision_macro": 0.6883335240112735,
|
| 100 |
+
"eval_precision_weighted": 0.6948434226567218,
|
| 101 |
+
"eval_recall_macro": 0.6644582867863256,
|
| 102 |
+
"eval_recall_weighted": 0.6777777777777778,
|
| 103 |
+
"eval_runtime": 0.3623,
|
| 104 |
+
"eval_samples_per_second": 496.871,
|
| 105 |
+
"eval_steps_per_second": 2.76,
|
| 106 |
+
"step": 24
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 4.181818181818182,
|
| 110 |
+
"grad_norm": 1.3243730068206787,
|
| 111 |
+
"learning_rate": 1.925925925925926e-05,
|
| 112 |
+
"loss": 2.1096,
|
| 113 |
+
"step": 25
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 5.0,
|
| 117 |
+
"eval_accuracy": 0.7444444444444445,
|
| 118 |
+
"eval_f1_class_1": 0.8085106382978723,
|
| 119 |
+
"eval_f1_class_2": 0.68,
|
| 120 |
+
"eval_f1_class_3": 0.46153846153846156,
|
| 121 |
+
"eval_f1_class_4": 0.9,
|
| 122 |
+
"eval_f1_class_5": 0.782608695652174,
|
| 123 |
+
"eval_f1_class_6": 0.45454545454545453,
|
| 124 |
+
"eval_f1_class_7": 0.9166666666666666,
|
| 125 |
+
"eval_f1_class_8": 0.64,
|
| 126 |
+
"eval_f1_class_9": 0.8148148148148148,
|
| 127 |
+
"eval_f1_macro": 0.7176316368350493,
|
| 128 |
+
"eval_f1_weighted": 0.7252298335926662,
|
| 129 |
+
"eval_loss": 1.6966552734375,
|
| 130 |
+
"eval_precision_macro": 0.7965824365465943,
|
| 131 |
+
"eval_precision_weighted": 0.7860274061528542,
|
| 132 |
+
"eval_recall_macro": 0.726896653946055,
|
| 133 |
+
"eval_recall_weighted": 0.7444444444444445,
|
| 134 |
+
"eval_runtime": 0.3663,
|
| 135 |
+
"eval_samples_per_second": 491.368,
|
| 136 |
+
"eval_steps_per_second": 2.73,
|
| 137 |
+
"step": 30
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 6.0,
|
| 141 |
+
"eval_accuracy": 0.7388888888888889,
|
| 142 |
+
"eval_f1_class_1": 0.8085106382978723,
|
| 143 |
+
"eval_f1_class_2": 0.6808510638297872,
|
| 144 |
+
"eval_f1_class_3": 0.46153846153846156,
|
| 145 |
+
"eval_f1_class_4": 0.8571428571428571,
|
| 146 |
+
"eval_f1_class_5": 0.8695652173913043,
|
| 147 |
+
"eval_f1_class_6": 0.3,
|
| 148 |
+
"eval_f1_class_7": 0.92,
|
| 149 |
+
"eval_f1_class_8": 0.6153846153846154,
|
| 150 |
+
"eval_f1_class_9": 0.8301886792452831,
|
| 151 |
+
"eval_f1_macro": 0.7047979480922423,
|
| 152 |
+
"eval_f1_weighted": 0.7113735565144463,
|
| 153 |
+
"eval_loss": 1.5490903854370117,
|
| 154 |
+
"eval_precision_macro": 0.7956664734442512,
|
| 155 |
+
"eval_precision_weighted": 0.7799277677055455,
|
| 156 |
+
"eval_recall_macro": 0.721445841142301,
|
| 157 |
+
"eval_recall_weighted": 0.7388888888888889,
|
| 158 |
+
"eval_runtime": 0.3635,
|
| 159 |
+
"eval_samples_per_second": 495.151,
|
| 160 |
+
"eval_steps_per_second": 2.751,
|
| 161 |
+
"step": 36
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 7.0,
|
| 165 |
+
"eval_accuracy": 0.75,
|
| 166 |
+
"eval_f1_class_1": 0.8837209302325582,
|
| 167 |
+
"eval_f1_class_2": 0.6956521739130435,
|
| 168 |
+
"eval_f1_class_3": 0.5185185185185185,
|
| 169 |
+
"eval_f1_class_4": 0.8372093023255814,
|
| 170 |
+
"eval_f1_class_5": 0.88,
|
| 171 |
+
"eval_f1_class_6": 0.3,
|
| 172 |
+
"eval_f1_class_7": 0.9019607843137255,
|
| 173 |
+
"eval_f1_class_8": 0.6153846153846154,
|
| 174 |
+
"eval_f1_class_9": 0.8301886792452831,
|
| 175 |
+
"eval_f1_macro": 0.7180705559925916,
|
| 176 |
+
"eval_f1_weighted": 0.72352293998154,
|
| 177 |
+
"eval_loss": 1.4178283214569092,
|
| 178 |
+
"eval_precision_macro": 0.7969289656487724,
|
| 179 |
+
"eval_precision_weighted": 0.7836037157957447,
|
| 180 |
+
"eval_recall_macro": 0.7358408029056838,
|
| 181 |
+
"eval_recall_weighted": 0.75,
|
| 182 |
+
"eval_runtime": 0.367,
|
| 183 |
+
"eval_samples_per_second": 490.53,
|
| 184 |
+
"eval_steps_per_second": 2.725,
|
| 185 |
+
"step": 42
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.0,
|
| 189 |
+
"eval_accuracy": 0.7777777777777778,
|
| 190 |
+
"eval_f1_class_1": 0.8837209302325582,
|
| 191 |
+
"eval_f1_class_2": 0.7111111111111111,
|
| 192 |
+
"eval_f1_class_3": 0.5714285714285714,
|
| 193 |
+
"eval_f1_class_4": 0.8571428571428571,
|
| 194 |
+
"eval_f1_class_5": 0.9230769230769231,
|
| 195 |
+
"eval_f1_class_6": 0.5217391304347826,
|
| 196 |
+
"eval_f1_class_7": 0.9019607843137255,
|
| 197 |
+
"eval_f1_class_8": 0.6274509803921569,
|
| 198 |
+
"eval_f1_class_9": 0.8627450980392157,
|
| 199 |
+
"eval_f1_macro": 0.7622640429079891,
|
| 200 |
+
"eval_f1_weighted": 0.7628623647339323,
|
| 201 |
+
"eval_loss": 1.312013864517212,
|
| 202 |
+
"eval_precision_macro": 0.8140437018697889,
|
| 203 |
+
"eval_precision_weighted": 0.8017353312280849,
|
| 204 |
+
"eval_recall_macro": 0.7698436078063214,
|
| 205 |
+
"eval_recall_weighted": 0.7777777777777778,
|
| 206 |
+
"eval_runtime": 0.3727,
|
| 207 |
+
"eval_samples_per_second": 482.939,
|
| 208 |
+
"eval_steps_per_second": 2.683,
|
| 209 |
+
"step": 48
|
| 210 |
+
}
|
| 211 |
+
],
|
| 212 |
+
"logging_steps": 25,
|
| 213 |
+
"max_steps": 180,
|
| 214 |
+
"num_input_tokens_seen": 0,
|
| 215 |
+
"num_train_epochs": 30,
|
| 216 |
+
"save_steps": 500,
|
| 217 |
+
"stateful_callbacks": {
|
| 218 |
+
"EarlyStoppingCallback": {
|
| 219 |
+
"args": {
|
| 220 |
+
"early_stopping_patience": 5,
|
| 221 |
+
"early_stopping_threshold": 0.001
|
| 222 |
+
},
|
| 223 |
+
"attributes": {
|
| 224 |
+
"early_stopping_patience_counter": 0
|
| 225 |
+
}
|
| 226 |
+
},
|
| 227 |
+
"TrainerControl": {
|
| 228 |
+
"args": {
|
| 229 |
+
"should_epoch_stop": false,
|
| 230 |
+
"should_evaluate": false,
|
| 231 |
+
"should_log": false,
|
| 232 |
+
"should_save": true,
|
| 233 |
+
"should_training_stop": false
|
| 234 |
+
},
|
| 235 |
+
"attributes": {}
|
| 236 |
+
}
|
| 237 |
+
},
|
| 238 |
+
"total_flos": 1695594202435584.0,
|
| 239 |
+
"train_batch_size": 160,
|
| 240 |
+
"trial_name": null,
|
| 241 |
+
"trial_params": null
|
| 242 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-48/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b28c2db508479b89cb58a872b64cfbcc28b46676db066513513feaca9b31a7da
|
| 3 |
+
size 5905
|
telecom_arabert_large_full_pipeline/checkpoint-48/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_large_full_pipeline/checkpoint-72/config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": 1,
|
| 15 |
+
"1": 2,
|
| 16 |
+
"2": 3,
|
| 17 |
+
"3": 4,
|
| 18 |
+
"4": 5,
|
| 19 |
+
"5": 6,
|
| 20 |
+
"6": 7,
|
| 21 |
+
"7": 8,
|
| 22 |
+
"8": 9
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 3072,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"1": 0,
|
| 28 |
+
"2": 1,
|
| 29 |
+
"3": 2,
|
| 30 |
+
"4": 3,
|
| 31 |
+
"5": 4,
|
| 32 |
+
"6": 5,
|
| 33 |
+
"7": 6,
|
| 34 |
+
"8": 7,
|
| 35 |
+
"9": 8
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"max_position_embeddings": 512,
|
| 39 |
+
"model_type": "bert",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_hidden_layers": 12,
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"pooler_fc_size": 768,
|
| 44 |
+
"pooler_num_attention_heads": 12,
|
| 45 |
+
"pooler_num_fc_layers": 3,
|
| 46 |
+
"pooler_size_per_head": 128,
|
| 47 |
+
"pooler_type": "first_token_transform",
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"transformers_version": "4.57.3",
|
| 51 |
+
"type_vocab_size": 2,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 100000
|
| 54 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-72/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95cc3fb5ea499edec915d668631bf192b5d064fc5461063832470d43f1ca1e90
|
| 3 |
+
size 651416604
|
telecom_arabert_large_full_pipeline/checkpoint-72/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3f94719757a8fccf66b778561cc97c532248148de23e1474dc75066d7add5d8
|
| 3 |
+
size 1302957451
|
telecom_arabert_large_full_pipeline/checkpoint-72/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb95f7d7bf153d4fa9636c2bf94a178abec6949dd10bccab105a52aa9f1a5b64
|
| 3 |
+
size 14645
|
telecom_arabert_large_full_pipeline/checkpoint-72/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d540913d7068686cd197cdd6dad9cd0c6efcea37f2e2f13ea9b201be99bd7ac
|
| 3 |
+
size 1465
|
telecom_arabert_large_full_pipeline/checkpoint-72/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-72/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
telecom_arabert_large_full_pipeline/checkpoint-72/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": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 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 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-72/trainer_state.json
ADDED
|
@@ -0,0 +1,345 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 48,
|
| 3 |
+
"best_metric": 0.7628623647339323,
|
| 4 |
+
"best_model_checkpoint": "./telecom_arabert_large_full_pipeline/checkpoint-48",
|
| 5 |
+
"epoch": 12.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 72,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"eval_accuracy": 0.18333333333333332,
|
| 15 |
+
"eval_f1_class_1": 0.5714285714285714,
|
| 16 |
+
"eval_f1_class_2": 0.0,
|
| 17 |
+
"eval_f1_class_3": 0.08695652173913043,
|
| 18 |
+
"eval_f1_class_4": 0.0,
|
| 19 |
+
"eval_f1_class_5": 0.14285714285714285,
|
| 20 |
+
"eval_f1_class_6": 0.0,
|
| 21 |
+
"eval_f1_class_7": 0.15384615384615385,
|
| 22 |
+
"eval_f1_class_8": 0.0,
|
| 23 |
+
"eval_f1_class_9": 0.4782608695652174,
|
| 24 |
+
"eval_f1_macro": 0.1592610288262462,
|
| 25 |
+
"eval_f1_weighted": 0.1646121993948081,
|
| 26 |
+
"eval_loss": 2.19708251953125,
|
| 27 |
+
"eval_precision_macro": 0.22300011411617027,
|
| 28 |
+
"eval_precision_weighted": 0.23096456692913386,
|
| 29 |
+
"eval_recall_macro": 0.20279146863815056,
|
| 30 |
+
"eval_recall_weighted": 0.18333333333333332,
|
| 31 |
+
"eval_runtime": 0.3659,
|
| 32 |
+
"eval_samples_per_second": 491.975,
|
| 33 |
+
"eval_steps_per_second": 2.733,
|
| 34 |
+
"step": 6
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.0,
|
| 38 |
+
"eval_accuracy": 0.32222222222222224,
|
| 39 |
+
"eval_f1_class_1": 0.7894736842105263,
|
| 40 |
+
"eval_f1_class_2": 0.0,
|
| 41 |
+
"eval_f1_class_3": 0.17391304347826086,
|
| 42 |
+
"eval_f1_class_4": 0.0,
|
| 43 |
+
"eval_f1_class_5": 0.22807017543859648,
|
| 44 |
+
"eval_f1_class_6": 0.14814814814814814,
|
| 45 |
+
"eval_f1_class_7": 0.22857142857142856,
|
| 46 |
+
"eval_f1_class_8": 0.0,
|
| 47 |
+
"eval_f1_class_9": 0.7719298245614035,
|
| 48 |
+
"eval_f1_macro": 0.26001181160092934,
|
| 49 |
+
"eval_f1_weighted": 0.26565195866746844,
|
| 50 |
+
"eval_loss": 2.146738052368164,
|
| 51 |
+
"eval_precision_macro": 0.2969712657540264,
|
| 52 |
+
"eval_precision_weighted": 0.30471977589915855,
|
| 53 |
+
"eval_recall_macro": 0.34401095805726306,
|
| 54 |
+
"eval_recall_weighted": 0.32222222222222224,
|
| 55 |
+
"eval_runtime": 0.3684,
|
| 56 |
+
"eval_samples_per_second": 488.604,
|
| 57 |
+
"eval_steps_per_second": 2.714,
|
| 58 |
+
"step": 12
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 3.0,
|
| 62 |
+
"eval_accuracy": 0.5611111111111111,
|
| 63 |
+
"eval_f1_class_1": 0.8163265306122449,
|
| 64 |
+
"eval_f1_class_2": 0.5882352941176471,
|
| 65 |
+
"eval_f1_class_3": 0.4,
|
| 66 |
+
"eval_f1_class_4": 0.6486486486486487,
|
| 67 |
+
"eval_f1_class_5": 0.35714285714285715,
|
| 68 |
+
"eval_f1_class_6": 0.25,
|
| 69 |
+
"eval_f1_class_7": 0.8181818181818182,
|
| 70 |
+
"eval_f1_class_8": 0.0,
|
| 71 |
+
"eval_f1_class_9": 0.7457627118644068,
|
| 72 |
+
"eval_f1_macro": 0.5138108733964025,
|
| 73 |
+
"eval_f1_weighted": 0.5241442923315164,
|
| 74 |
+
"eval_loss": 2.027998208999634,
|
| 75 |
+
"eval_precision_macro": 0.5503880544762977,
|
| 76 |
+
"eval_precision_weighted": 0.56245523793883,
|
| 77 |
+
"eval_recall_macro": 0.5638005023050117,
|
| 78 |
+
"eval_recall_weighted": 0.5611111111111111,
|
| 79 |
+
"eval_runtime": 0.3388,
|
| 80 |
+
"eval_samples_per_second": 531.312,
|
| 81 |
+
"eval_steps_per_second": 2.952,
|
| 82 |
+
"step": 18
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.0,
|
| 86 |
+
"eval_accuracy": 0.6777777777777778,
|
| 87 |
+
"eval_f1_class_1": 0.7916666666666666,
|
| 88 |
+
"eval_f1_class_2": 0.6415094339622641,
|
| 89 |
+
"eval_f1_class_3": 0.4,
|
| 90 |
+
"eval_f1_class_4": 0.8,
|
| 91 |
+
"eval_f1_class_5": 0.6428571428571429,
|
| 92 |
+
"eval_f1_class_6": 0.2727272727272727,
|
| 93 |
+
"eval_f1_class_7": 0.8936170212765957,
|
| 94 |
+
"eval_f1_class_8": 0.4878048780487805,
|
| 95 |
+
"eval_f1_class_9": 0.7857142857142857,
|
| 96 |
+
"eval_f1_macro": 0.6350996334725564,
|
| 97 |
+
"eval_f1_weighted": 0.6471254592295707,
|
| 98 |
+
"eval_loss": 1.8633366823196411,
|
| 99 |
+
"eval_precision_macro": 0.6883335240112735,
|
| 100 |
+
"eval_precision_weighted": 0.6948434226567218,
|
| 101 |
+
"eval_recall_macro": 0.6644582867863256,
|
| 102 |
+
"eval_recall_weighted": 0.6777777777777778,
|
| 103 |
+
"eval_runtime": 0.3623,
|
| 104 |
+
"eval_samples_per_second": 496.871,
|
| 105 |
+
"eval_steps_per_second": 2.76,
|
| 106 |
+
"step": 24
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 4.181818181818182,
|
| 110 |
+
"grad_norm": 1.3243730068206787,
|
| 111 |
+
"learning_rate": 1.925925925925926e-05,
|
| 112 |
+
"loss": 2.1096,
|
| 113 |
+
"step": 25
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 5.0,
|
| 117 |
+
"eval_accuracy": 0.7444444444444445,
|
| 118 |
+
"eval_f1_class_1": 0.8085106382978723,
|
| 119 |
+
"eval_f1_class_2": 0.68,
|
| 120 |
+
"eval_f1_class_3": 0.46153846153846156,
|
| 121 |
+
"eval_f1_class_4": 0.9,
|
| 122 |
+
"eval_f1_class_5": 0.782608695652174,
|
| 123 |
+
"eval_f1_class_6": 0.45454545454545453,
|
| 124 |
+
"eval_f1_class_7": 0.9166666666666666,
|
| 125 |
+
"eval_f1_class_8": 0.64,
|
| 126 |
+
"eval_f1_class_9": 0.8148148148148148,
|
| 127 |
+
"eval_f1_macro": 0.7176316368350493,
|
| 128 |
+
"eval_f1_weighted": 0.7252298335926662,
|
| 129 |
+
"eval_loss": 1.6966552734375,
|
| 130 |
+
"eval_precision_macro": 0.7965824365465943,
|
| 131 |
+
"eval_precision_weighted": 0.7860274061528542,
|
| 132 |
+
"eval_recall_macro": 0.726896653946055,
|
| 133 |
+
"eval_recall_weighted": 0.7444444444444445,
|
| 134 |
+
"eval_runtime": 0.3663,
|
| 135 |
+
"eval_samples_per_second": 491.368,
|
| 136 |
+
"eval_steps_per_second": 2.73,
|
| 137 |
+
"step": 30
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 6.0,
|
| 141 |
+
"eval_accuracy": 0.7388888888888889,
|
| 142 |
+
"eval_f1_class_1": 0.8085106382978723,
|
| 143 |
+
"eval_f1_class_2": 0.6808510638297872,
|
| 144 |
+
"eval_f1_class_3": 0.46153846153846156,
|
| 145 |
+
"eval_f1_class_4": 0.8571428571428571,
|
| 146 |
+
"eval_f1_class_5": 0.8695652173913043,
|
| 147 |
+
"eval_f1_class_6": 0.3,
|
| 148 |
+
"eval_f1_class_7": 0.92,
|
| 149 |
+
"eval_f1_class_8": 0.6153846153846154,
|
| 150 |
+
"eval_f1_class_9": 0.8301886792452831,
|
| 151 |
+
"eval_f1_macro": 0.7047979480922423,
|
| 152 |
+
"eval_f1_weighted": 0.7113735565144463,
|
| 153 |
+
"eval_loss": 1.5490903854370117,
|
| 154 |
+
"eval_precision_macro": 0.7956664734442512,
|
| 155 |
+
"eval_precision_weighted": 0.7799277677055455,
|
| 156 |
+
"eval_recall_macro": 0.721445841142301,
|
| 157 |
+
"eval_recall_weighted": 0.7388888888888889,
|
| 158 |
+
"eval_runtime": 0.3635,
|
| 159 |
+
"eval_samples_per_second": 495.151,
|
| 160 |
+
"eval_steps_per_second": 2.751,
|
| 161 |
+
"step": 36
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 7.0,
|
| 165 |
+
"eval_accuracy": 0.75,
|
| 166 |
+
"eval_f1_class_1": 0.8837209302325582,
|
| 167 |
+
"eval_f1_class_2": 0.6956521739130435,
|
| 168 |
+
"eval_f1_class_3": 0.5185185185185185,
|
| 169 |
+
"eval_f1_class_4": 0.8372093023255814,
|
| 170 |
+
"eval_f1_class_5": 0.88,
|
| 171 |
+
"eval_f1_class_6": 0.3,
|
| 172 |
+
"eval_f1_class_7": 0.9019607843137255,
|
| 173 |
+
"eval_f1_class_8": 0.6153846153846154,
|
| 174 |
+
"eval_f1_class_9": 0.8301886792452831,
|
| 175 |
+
"eval_f1_macro": 0.7180705559925916,
|
| 176 |
+
"eval_f1_weighted": 0.72352293998154,
|
| 177 |
+
"eval_loss": 1.4178283214569092,
|
| 178 |
+
"eval_precision_macro": 0.7969289656487724,
|
| 179 |
+
"eval_precision_weighted": 0.7836037157957447,
|
| 180 |
+
"eval_recall_macro": 0.7358408029056838,
|
| 181 |
+
"eval_recall_weighted": 0.75,
|
| 182 |
+
"eval_runtime": 0.367,
|
| 183 |
+
"eval_samples_per_second": 490.53,
|
| 184 |
+
"eval_steps_per_second": 2.725,
|
| 185 |
+
"step": 42
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 8.0,
|
| 189 |
+
"eval_accuracy": 0.7777777777777778,
|
| 190 |
+
"eval_f1_class_1": 0.8837209302325582,
|
| 191 |
+
"eval_f1_class_2": 0.7111111111111111,
|
| 192 |
+
"eval_f1_class_3": 0.5714285714285714,
|
| 193 |
+
"eval_f1_class_4": 0.8571428571428571,
|
| 194 |
+
"eval_f1_class_5": 0.9230769230769231,
|
| 195 |
+
"eval_f1_class_6": 0.5217391304347826,
|
| 196 |
+
"eval_f1_class_7": 0.9019607843137255,
|
| 197 |
+
"eval_f1_class_8": 0.6274509803921569,
|
| 198 |
+
"eval_f1_class_9": 0.8627450980392157,
|
| 199 |
+
"eval_f1_macro": 0.7622640429079891,
|
| 200 |
+
"eval_f1_weighted": 0.7628623647339323,
|
| 201 |
+
"eval_loss": 1.312013864517212,
|
| 202 |
+
"eval_precision_macro": 0.8140437018697889,
|
| 203 |
+
"eval_precision_weighted": 0.8017353312280849,
|
| 204 |
+
"eval_recall_macro": 0.7698436078063214,
|
| 205 |
+
"eval_recall_weighted": 0.7777777777777778,
|
| 206 |
+
"eval_runtime": 0.3727,
|
| 207 |
+
"eval_samples_per_second": 482.939,
|
| 208 |
+
"eval_steps_per_second": 2.683,
|
| 209 |
+
"step": 48
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 8.363636363636363,
|
| 213 |
+
"grad_norm": 1.4433997869491577,
|
| 214 |
+
"learning_rate": 1.617283950617284e-05,
|
| 215 |
+
"loss": 1.5965,
|
| 216 |
+
"step": 50
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 9.0,
|
| 220 |
+
"eval_accuracy": 0.7555555555555555,
|
| 221 |
+
"eval_f1_class_1": 0.8571428571428571,
|
| 222 |
+
"eval_f1_class_2": 0.6956521739130435,
|
| 223 |
+
"eval_f1_class_3": 0.5454545454545454,
|
| 224 |
+
"eval_f1_class_4": 0.8095238095238095,
|
| 225 |
+
"eval_f1_class_5": 0.88,
|
| 226 |
+
"eval_f1_class_6": 0.38095238095238093,
|
| 227 |
+
"eval_f1_class_7": 0.9583333333333334,
|
| 228 |
+
"eval_f1_class_8": 0.6153846153846154,
|
| 229 |
+
"eval_f1_class_9": 0.8627450980392157,
|
| 230 |
+
"eval_f1_macro": 0.7339098681937557,
|
| 231 |
+
"eval_f1_weighted": 0.7396587315308543,
|
| 232 |
+
"eval_loss": 1.2228145599365234,
|
| 233 |
+
"eval_precision_macro": 0.7868104118104118,
|
| 234 |
+
"eval_precision_weighted": 0.7780141155141155,
|
| 235 |
+
"eval_recall_macro": 0.7429615459397394,
|
| 236 |
+
"eval_recall_weighted": 0.7555555555555555,
|
| 237 |
+
"eval_runtime": 0.3511,
|
| 238 |
+
"eval_samples_per_second": 512.682,
|
| 239 |
+
"eval_steps_per_second": 2.848,
|
| 240 |
+
"step": 54
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 10.0,
|
| 244 |
+
"eval_accuracy": 0.7666666666666667,
|
| 245 |
+
"eval_f1_class_1": 0.9,
|
| 246 |
+
"eval_f1_class_2": 0.6818181818181818,
|
| 247 |
+
"eval_f1_class_3": 0.6060606060606061,
|
| 248 |
+
"eval_f1_class_4": 0.7804878048780488,
|
| 249 |
+
"eval_f1_class_5": 0.8571428571428571,
|
| 250 |
+
"eval_f1_class_6": 0.45454545454545453,
|
| 251 |
+
"eval_f1_class_7": 0.92,
|
| 252 |
+
"eval_f1_class_8": 0.6538461538461539,
|
| 253 |
+
"eval_f1_class_9": 0.88,
|
| 254 |
+
"eval_f1_macro": 0.7482112286990337,
|
| 255 |
+
"eval_f1_weighted": 0.753576160063965,
|
| 256 |
+
"eval_loss": 1.160414457321167,
|
| 257 |
+
"eval_precision_macro": 0.7897515036403926,
|
| 258 |
+
"eval_precision_weighted": 0.7847359019581241,
|
| 259 |
+
"eval_recall_macro": 0.7574109739340592,
|
| 260 |
+
"eval_recall_weighted": 0.7666666666666667,
|
| 261 |
+
"eval_runtime": 0.3614,
|
| 262 |
+
"eval_samples_per_second": 498.021,
|
| 263 |
+
"eval_steps_per_second": 2.767,
|
| 264 |
+
"step": 60
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 11.0,
|
| 268 |
+
"eval_accuracy": 0.7666666666666667,
|
| 269 |
+
"eval_f1_class_1": 0.9,
|
| 270 |
+
"eval_f1_class_2": 0.6666666666666666,
|
| 271 |
+
"eval_f1_class_3": 0.6060606060606061,
|
| 272 |
+
"eval_f1_class_4": 0.7804878048780488,
|
| 273 |
+
"eval_f1_class_5": 0.8461538461538461,
|
| 274 |
+
"eval_f1_class_6": 0.5,
|
| 275 |
+
"eval_f1_class_7": 0.9387755102040817,
|
| 276 |
+
"eval_f1_class_8": 0.6538461538461539,
|
| 277 |
+
"eval_f1_class_9": 0.88,
|
| 278 |
+
"eval_f1_macro": 0.7524433986454891,
|
| 279 |
+
"eval_f1_weighted": 0.757895338240286,
|
| 280 |
+
"eval_loss": 1.110926628112793,
|
| 281 |
+
"eval_precision_macro": 0.780160539049428,
|
| 282 |
+
"eval_precision_weighted": 0.7765173427395649,
|
| 283 |
+
"eval_recall_macro": 0.755399913099469,
|
| 284 |
+
"eval_recall_weighted": 0.7666666666666667,
|
| 285 |
+
"eval_runtime": 0.3601,
|
| 286 |
+
"eval_samples_per_second": 499.805,
|
| 287 |
+
"eval_steps_per_second": 2.777,
|
| 288 |
+
"step": 66
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 12.0,
|
| 292 |
+
"eval_accuracy": 0.7611111111111111,
|
| 293 |
+
"eval_f1_class_1": 0.9230769230769231,
|
| 294 |
+
"eval_f1_class_2": 0.6122448979591837,
|
| 295 |
+
"eval_f1_class_3": 0.5882352941176471,
|
| 296 |
+
"eval_f1_class_4": 0.7804878048780488,
|
| 297 |
+
"eval_f1_class_5": 0.8461538461538461,
|
| 298 |
+
"eval_f1_class_6": 0.43478260869565216,
|
| 299 |
+
"eval_f1_class_7": 0.96,
|
| 300 |
+
"eval_f1_class_8": 0.6666666666666666,
|
| 301 |
+
"eval_f1_class_9": 0.88,
|
| 302 |
+
"eval_f1_macro": 0.7435164490608853,
|
| 303 |
+
"eval_f1_weighted": 0.7509109303019138,
|
| 304 |
+
"eval_loss": 1.0815963745117188,
|
| 305 |
+
"eval_precision_macro": 0.7752474236644432,
|
| 306 |
+
"eval_precision_weighted": 0.7736567304070833,
|
| 307 |
+
"eval_recall_macro": 0.7488639653870506,
|
| 308 |
+
"eval_recall_weighted": 0.7611111111111111,
|
| 309 |
+
"eval_runtime": 0.3547,
|
| 310 |
+
"eval_samples_per_second": 507.407,
|
| 311 |
+
"eval_steps_per_second": 2.819,
|
| 312 |
+
"step": 72
|
| 313 |
+
}
|
| 314 |
+
],
|
| 315 |
+
"logging_steps": 25,
|
| 316 |
+
"max_steps": 180,
|
| 317 |
+
"num_input_tokens_seen": 0,
|
| 318 |
+
"num_train_epochs": 30,
|
| 319 |
+
"save_steps": 500,
|
| 320 |
+
"stateful_callbacks": {
|
| 321 |
+
"EarlyStoppingCallback": {
|
| 322 |
+
"args": {
|
| 323 |
+
"early_stopping_patience": 5,
|
| 324 |
+
"early_stopping_threshold": 0.001
|
| 325 |
+
},
|
| 326 |
+
"attributes": {
|
| 327 |
+
"early_stopping_patience_counter": 4
|
| 328 |
+
}
|
| 329 |
+
},
|
| 330 |
+
"TrainerControl": {
|
| 331 |
+
"args": {
|
| 332 |
+
"should_epoch_stop": false,
|
| 333 |
+
"should_evaluate": false,
|
| 334 |
+
"should_log": false,
|
| 335 |
+
"should_save": true,
|
| 336 |
+
"should_training_stop": false
|
| 337 |
+
},
|
| 338 |
+
"attributes": {}
|
| 339 |
+
}
|
| 340 |
+
},
|
| 341 |
+
"total_flos": 2543391303653376.0,
|
| 342 |
+
"train_batch_size": 160,
|
| 343 |
+
"trial_name": null,
|
| 344 |
+
"trial_params": null
|
| 345 |
+
}
|
telecom_arabert_large_full_pipeline/checkpoint-72/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b28c2db508479b89cb58a872b64cfbcc28b46676db066513513feaca9b31a7da
|
| 3 |
+
size 5905
|