Upload folder using huggingface_hub
Browse files- checkpoint-34500/config.json +72 -0
- checkpoint-34500/model.safetensors +3 -0
- checkpoint-34500/optimizer.pt +3 -0
- checkpoint-34500/rng_state.pth +3 -0
- checkpoint-34500/scheduler.pt +3 -0
- checkpoint-34500/special_tokens_map.json +37 -0
- checkpoint-34500/tokenizer.json +0 -0
- checkpoint-34500/tokenizer_config.json +338 -0
- checkpoint-34500/trainer_state.json +1551 -0
- checkpoint-34500/training_args.bin +3 -0
- checkpoint-34500/vocab.txt +0 -0
- checkpoint-35000/config.json +72 -0
- checkpoint-35000/model.safetensors +3 -0
- checkpoint-35000/optimizer.pt +3 -0
- checkpoint-35000/rng_state.pth +3 -0
- checkpoint-35000/scheduler.pt +3 -0
- checkpoint-35000/special_tokens_map.json +37 -0
- checkpoint-35000/tokenizer.json +0 -0
- checkpoint-35000/tokenizer_config.json +338 -0
- checkpoint-35000/trainer_state.json +1573 -0
- checkpoint-35000/training_args.bin +3 -0
- checkpoint-35000/vocab.txt +0 -0
checkpoint-34500/config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_10": 10,
|
| 40 |
+
"LABEL_11": 11,
|
| 41 |
+
"LABEL_12": 12,
|
| 42 |
+
"LABEL_13": 13,
|
| 43 |
+
"LABEL_14": 14,
|
| 44 |
+
"LABEL_15": 15,
|
| 45 |
+
"LABEL_16": 16,
|
| 46 |
+
"LABEL_17": 17,
|
| 47 |
+
"LABEL_18": 18,
|
| 48 |
+
"LABEL_19": 19,
|
| 49 |
+
"LABEL_2": 2,
|
| 50 |
+
"LABEL_20": 20,
|
| 51 |
+
"LABEL_3": 3,
|
| 52 |
+
"LABEL_4": 4,
|
| 53 |
+
"LABEL_5": 5,
|
| 54 |
+
"LABEL_6": 6,
|
| 55 |
+
"LABEL_7": 7,
|
| 56 |
+
"LABEL_8": 8,
|
| 57 |
+
"LABEL_9": 9
|
| 58 |
+
},
|
| 59 |
+
"layer_norm_eps": 1e-12,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"model_type": "bert",
|
| 62 |
+
"num_attention_heads": 12,
|
| 63 |
+
"num_hidden_layers": 12,
|
| 64 |
+
"pad_token_id": 0,
|
| 65 |
+
"position_embedding_type": "absolute",
|
| 66 |
+
"problem_type": "single_label_classification",
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.41.2",
|
| 69 |
+
"type_vocab_size": 2,
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 64000
|
| 72 |
+
}
|
checkpoint-34500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33dfa22bccfaa6b2a7f8e7b6eb58091036b3fa425de2d7c46606a71ab41e217f
|
| 3 |
+
size 540861516
|
checkpoint-34500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c93eeddebf9a37b4e5ad87be15b22c360f2c6b958c7a3cd28cb0b301e662cc
|
| 3 |
+
size 1081844491
|
checkpoint-34500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da15b9fd1c3ce858b2574748eb9827bd50fe1ada2e04a975f19cb65eef8f9cf
|
| 3 |
+
size 14645
|
checkpoint-34500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aa457b498d34d55485c49d1333c3017403ddf7d63732bfc398129607e3ec743
|
| 3 |
+
size 1465
|
checkpoint-34500/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 |
+
}
|
checkpoint-34500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-34500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"mask_token": "[MASK]",
|
| 297 |
+
"max_len": 512,
|
| 298 |
+
"model_max_length": 512,
|
| 299 |
+
"never_split": [
|
| 300 |
+
"+ك",
|
| 301 |
+
"+كما",
|
| 302 |
+
"ك+",
|
| 303 |
+
"+وا",
|
| 304 |
+
"+ين",
|
| 305 |
+
"و+",
|
| 306 |
+
"+كن",
|
| 307 |
+
"+ان",
|
| 308 |
+
"+هم",
|
| 309 |
+
"+ة",
|
| 310 |
+
"[بريد]",
|
| 311 |
+
"لل+",
|
| 312 |
+
"+ي",
|
| 313 |
+
"+ت",
|
| 314 |
+
"+ن",
|
| 315 |
+
"س+",
|
| 316 |
+
"ل+",
|
| 317 |
+
"[مستخدم]",
|
| 318 |
+
"+كم",
|
| 319 |
+
"+ا",
|
| 320 |
+
"ب+",
|
| 321 |
+
"ف+",
|
| 322 |
+
"+نا",
|
| 323 |
+
"+ها",
|
| 324 |
+
"+ون",
|
| 325 |
+
"+هما",
|
| 326 |
+
"ال+",
|
| 327 |
+
"+ه",
|
| 328 |
+
"+هن",
|
| 329 |
+
"+ات",
|
| 330 |
+
"[رابط]"
|
| 331 |
+
],
|
| 332 |
+
"pad_token": "[PAD]",
|
| 333 |
+
"sep_token": "[SEP]",
|
| 334 |
+
"strip_accents": null,
|
| 335 |
+
"tokenize_chinese_chars": true,
|
| 336 |
+
"tokenizer_class": "BertTokenizer",
|
| 337 |
+
"unk_token": "[UNK]"
|
| 338 |
+
}
|
checkpoint-34500/trainer_state.json
ADDED
|
@@ -0,0 +1,1551 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8982632597992836,
|
| 3 |
+
"best_model_checkpoint": "./arabert_author_model/checkpoint-34500",
|
| 4 |
+
"epoch": 3.929384965831435,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 34500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05694760820045558,
|
| 13 |
+
"grad_norm": 15.19107437133789,
|
| 14 |
+
"learning_rate": 1.1343963553530753e-05,
|
| 15 |
+
"loss": 2.7205,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05694760820045558,
|
| 20 |
+
"eval_accuracy": 0.3750300697618475,
|
| 21 |
+
"eval_f1_macro": 0.28596660166175775,
|
| 22 |
+
"eval_f1_micro": 0.3750300697618475,
|
| 23 |
+
"eval_loss": 2.32218337059021,
|
| 24 |
+
"eval_precision_macro": 0.3865217733215992,
|
| 25 |
+
"eval_precision_micro": 0.3750300697618475,
|
| 26 |
+
"eval_recall_macro": 0.3672924033460141,
|
| 27 |
+
"eval_recall_micro": 0.3750300697618475,
|
| 28 |
+
"eval_runtime": 9.1613,
|
| 29 |
+
"eval_samples_per_second": 453.755,
|
| 30 |
+
"eval_steps_per_second": 56.76,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11389521640091116,
|
| 35 |
+
"grad_norm": 21.725738525390625,
|
| 36 |
+
"learning_rate": 2.2710706150341686e-05,
|
| 37 |
+
"loss": 1.6025,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11389521640091116,
|
| 42 |
+
"eval_accuracy": 0.4892951647822949,
|
| 43 |
+
"eval_f1_macro": 0.4406771878616986,
|
| 44 |
+
"eval_f1_micro": 0.4892951647822949,
|
| 45 |
+
"eval_loss": 1.6631975173950195,
|
| 46 |
+
"eval_precision_macro": 0.56733686366756,
|
| 47 |
+
"eval_precision_micro": 0.4892951647822949,
|
| 48 |
+
"eval_recall_macro": 0.48704653807602066,
|
| 49 |
+
"eval_recall_micro": 0.4892951647822949,
|
| 50 |
+
"eval_runtime": 8.477,
|
| 51 |
+
"eval_samples_per_second": 490.385,
|
| 52 |
+
"eval_steps_per_second": 61.342,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.17084282460136674,
|
| 57 |
+
"grad_norm": 13.716214179992676,
|
| 58 |
+
"learning_rate": 3.4100227790432806e-05,
|
| 59 |
+
"loss": 1.0328,
|
| 60 |
+
"step": 1500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.17084282460136674,
|
| 64 |
+
"eval_accuracy": 0.6615347606446957,
|
| 65 |
+
"eval_f1_macro": 0.5830637518928246,
|
| 66 |
+
"eval_f1_micro": 0.6615347606446957,
|
| 67 |
+
"eval_loss": 1.1024270057678223,
|
| 68 |
+
"eval_precision_macro": 0.697472543022928,
|
| 69 |
+
"eval_precision_micro": 0.6615347606446957,
|
| 70 |
+
"eval_recall_macro": 0.6033302465966366,
|
| 71 |
+
"eval_recall_micro": 0.6615347606446957,
|
| 72 |
+
"eval_runtime": 8.4612,
|
| 73 |
+
"eval_samples_per_second": 491.299,
|
| 74 |
+
"eval_steps_per_second": 61.457,
|
| 75 |
+
"step": 1500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.22779043280182232,
|
| 79 |
+
"grad_norm": 17.078737258911133,
|
| 80 |
+
"learning_rate": 4.548974943052392e-05,
|
| 81 |
+
"loss": 0.8504,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.22779043280182232,
|
| 86 |
+
"eval_accuracy": 0.639162857830166,
|
| 87 |
+
"eval_f1_macro": 0.5476482518700577,
|
| 88 |
+
"eval_f1_micro": 0.639162857830166,
|
| 89 |
+
"eval_loss": 1.2488256692886353,
|
| 90 |
+
"eval_precision_macro": 0.668531963924838,
|
| 91 |
+
"eval_precision_micro": 0.639162857830166,
|
| 92 |
+
"eval_recall_macro": 0.5729925283587635,
|
| 93 |
+
"eval_recall_micro": 0.639162857830166,
|
| 94 |
+
"eval_runtime": 8.6485,
|
| 95 |
+
"eval_samples_per_second": 480.664,
|
| 96 |
+
"eval_steps_per_second": 60.126,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.2847380410022779,
|
| 101 |
+
"grad_norm": 45.41240692138672,
|
| 102 |
+
"learning_rate": 5.6856492027334856e-05,
|
| 103 |
+
"loss": 0.7882,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.2847380410022779,
|
| 108 |
+
"eval_accuracy": 0.6523935530430599,
|
| 109 |
+
"eval_f1_macro": 0.5994264876841328,
|
| 110 |
+
"eval_f1_micro": 0.6523935530430599,
|
| 111 |
+
"eval_loss": 1.2463157176971436,
|
| 112 |
+
"eval_precision_macro": 0.6529647074997418,
|
| 113 |
+
"eval_precision_micro": 0.6523935530430599,
|
| 114 |
+
"eval_recall_macro": 0.6436371671271747,
|
| 115 |
+
"eval_recall_micro": 0.6523935530430599,
|
| 116 |
+
"eval_runtime": 8.4613,
|
| 117 |
+
"eval_samples_per_second": 491.293,
|
| 118 |
+
"eval_steps_per_second": 61.456,
|
| 119 |
+
"step": 2500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.3416856492027335,
|
| 123 |
+
"grad_norm": 17.272947311401367,
|
| 124 |
+
"learning_rate": 6.824601366742597e-05,
|
| 125 |
+
"loss": 0.8087,
|
| 126 |
+
"step": 3000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.3416856492027335,
|
| 130 |
+
"eval_accuracy": 0.7055568919894154,
|
| 131 |
+
"eval_f1_macro": 0.6265017927625092,
|
| 132 |
+
"eval_f1_micro": 0.7055568919894154,
|
| 133 |
+
"eval_loss": 1.2766073942184448,
|
| 134 |
+
"eval_precision_macro": 0.6878658131219406,
|
| 135 |
+
"eval_precision_micro": 0.7055568919894154,
|
| 136 |
+
"eval_recall_macro": 0.6658140911489481,
|
| 137 |
+
"eval_recall_micro": 0.7055568919894154,
|
| 138 |
+
"eval_runtime": 8.9536,
|
| 139 |
+
"eval_samples_per_second": 464.281,
|
| 140 |
+
"eval_steps_per_second": 58.077,
|
| 141 |
+
"step": 3000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.39863325740318906,
|
| 145 |
+
"grad_norm": 36.27668380737305,
|
| 146 |
+
"learning_rate": 7.96355353075171e-05,
|
| 147 |
+
"loss": 0.7887,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.39863325740318906,
|
| 152 |
+
"eval_accuracy": 0.7149386576858311,
|
| 153 |
+
"eval_f1_macro": 0.6616726950770662,
|
| 154 |
+
"eval_f1_micro": 0.7149386576858311,
|
| 155 |
+
"eval_loss": 1.1627144813537598,
|
| 156 |
+
"eval_precision_macro": 0.7514554135519156,
|
| 157 |
+
"eval_precision_micro": 0.7149386576858311,
|
| 158 |
+
"eval_recall_macro": 0.6834968200252539,
|
| 159 |
+
"eval_recall_micro": 0.7149386576858311,
|
| 160 |
+
"eval_runtime": 8.4816,
|
| 161 |
+
"eval_samples_per_second": 490.118,
|
| 162 |
+
"eval_steps_per_second": 61.309,
|
| 163 |
+
"step": 3500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.45558086560364464,
|
| 167 |
+
"grad_norm": 3.0386502742767334,
|
| 168 |
+
"learning_rate": 7.995372539966228e-05,
|
| 169 |
+
"loss": 0.7357,
|
| 170 |
+
"step": 4000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.45558086560364464,
|
| 174 |
+
"eval_accuracy": 0.7611258118835699,
|
| 175 |
+
"eval_f1_macro": 0.6745353046335729,
|
| 176 |
+
"eval_f1_micro": 0.7611258118835699,
|
| 177 |
+
"eval_loss": 0.9807717800140381,
|
| 178 |
+
"eval_precision_macro": 0.7007756446431578,
|
| 179 |
+
"eval_precision_micro": 0.7611258118835699,
|
| 180 |
+
"eval_recall_macro": 0.7425048520300992,
|
| 181 |
+
"eval_recall_micro": 0.7611258118835699,
|
| 182 |
+
"eval_runtime": 8.4828,
|
| 183 |
+
"eval_samples_per_second": 490.05,
|
| 184 |
+
"eval_steps_per_second": 61.3,
|
| 185 |
+
"step": 4000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5125284738041003,
|
| 189 |
+
"grad_norm": 2.7381744384765625,
|
| 190 |
+
"learning_rate": 7.980884762455173e-05,
|
| 191 |
+
"loss": 0.7022,
|
| 192 |
+
"step": 4500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5125284738041003,
|
| 196 |
+
"eval_accuracy": 0.76088525378879,
|
| 197 |
+
"eval_f1_macro": 0.6871238458955197,
|
| 198 |
+
"eval_f1_micro": 0.76088525378879,
|
| 199 |
+
"eval_loss": 1.1158560514450073,
|
| 200 |
+
"eval_precision_macro": 0.7591168248124284,
|
| 201 |
+
"eval_precision_micro": 0.76088525378879,
|
| 202 |
+
"eval_recall_macro": 0.7099914791461782,
|
| 203 |
+
"eval_recall_micro": 0.76088525378879,
|
| 204 |
+
"eval_runtime": 9.0538,
|
| 205 |
+
"eval_samples_per_second": 459.145,
|
| 206 |
+
"eval_steps_per_second": 57.435,
|
| 207 |
+
"step": 4500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5694760820045558,
|
| 211 |
+
"grad_norm": 32.207054138183594,
|
| 212 |
+
"learning_rate": 7.956625791551662e-05,
|
| 213 |
+
"loss": 0.6587,
|
| 214 |
+
"step": 5000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.5694760820045558,
|
| 218 |
+
"eval_accuracy": 0.8008178975222516,
|
| 219 |
+
"eval_f1_macro": 0.76243086871798,
|
| 220 |
+
"eval_f1_micro": 0.8008178975222516,
|
| 221 |
+
"eval_loss": 0.8932181000709534,
|
| 222 |
+
"eval_precision_macro": 0.7876270109291943,
|
| 223 |
+
"eval_precision_micro": 0.8008178975222516,
|
| 224 |
+
"eval_recall_macro": 0.7876260076814952,
|
| 225 |
+
"eval_recall_micro": 0.8008178975222516,
|
| 226 |
+
"eval_runtime": 8.5148,
|
| 227 |
+
"eval_samples_per_second": 488.207,
|
| 228 |
+
"eval_steps_per_second": 61.07,
|
| 229 |
+
"step": 5000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.6264236902050114,
|
| 233 |
+
"grad_norm": 0.29054978489875793,
|
| 234 |
+
"learning_rate": 7.922558317223566e-05,
|
| 235 |
+
"loss": 0.5719,
|
| 236 |
+
"step": 5500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6264236902050114,
|
| 240 |
+
"eval_accuracy": 0.773875390906904,
|
| 241 |
+
"eval_f1_macro": 0.7249768597960354,
|
| 242 |
+
"eval_f1_micro": 0.773875390906904,
|
| 243 |
+
"eval_loss": 0.9966481328010559,
|
| 244 |
+
"eval_precision_macro": 0.7358501532705917,
|
| 245 |
+
"eval_precision_micro": 0.773875390906904,
|
| 246 |
+
"eval_recall_macro": 0.7614420126439011,
|
| 247 |
+
"eval_recall_micro": 0.773875390906904,
|
| 248 |
+
"eval_runtime": 8.4793,
|
| 249 |
+
"eval_samples_per_second": 490.251,
|
| 250 |
+
"eval_steps_per_second": 61.326,
|
| 251 |
+
"step": 5500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.683371298405467,
|
| 255 |
+
"grad_norm": 1.0872896909713745,
|
| 256 |
+
"learning_rate": 7.878805260363261e-05,
|
| 257 |
+
"loss": 0.6425,
|
| 258 |
+
"step": 6000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.683371298405467,
|
| 262 |
+
"eval_accuracy": 0.771710368053885,
|
| 263 |
+
"eval_f1_macro": 0.7254677224325083,
|
| 264 |
+
"eval_f1_micro": 0.771710368053885,
|
| 265 |
+
"eval_loss": 0.9605371952056885,
|
| 266 |
+
"eval_precision_macro": 0.8005336996598393,
|
| 267 |
+
"eval_precision_micro": 0.771710368053885,
|
| 268 |
+
"eval_recall_macro": 0.7547512504988463,
|
| 269 |
+
"eval_recall_micro": 0.771710368053885,
|
| 270 |
+
"eval_runtime": 8.4743,
|
| 271 |
+
"eval_samples_per_second": 490.54,
|
| 272 |
+
"eval_steps_per_second": 61.362,
|
| 273 |
+
"step": 6000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.7403189066059226,
|
| 277 |
+
"grad_norm": 189.1195068359375,
|
| 278 |
+
"learning_rate": 7.82547465603587e-05,
|
| 279 |
+
"loss": 0.5433,
|
| 280 |
+
"step": 6500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7403189066059226,
|
| 284 |
+
"eval_accuracy": 0.7700264613904257,
|
| 285 |
+
"eval_f1_macro": 0.740451647791416,
|
| 286 |
+
"eval_f1_micro": 0.7700264613904257,
|
| 287 |
+
"eval_loss": 1.0783036947250366,
|
| 288 |
+
"eval_precision_macro": 0.769666104173451,
|
| 289 |
+
"eval_precision_micro": 0.7700264613904257,
|
| 290 |
+
"eval_recall_macro": 0.7659213860833466,
|
| 291 |
+
"eval_recall_micro": 0.7700264613904257,
|
| 292 |
+
"eval_runtime": 8.4608,
|
| 293 |
+
"eval_samples_per_second": 491.328,
|
| 294 |
+
"eval_steps_per_second": 61.46,
|
| 295 |
+
"step": 6500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.7972665148063781,
|
| 299 |
+
"grad_norm": 0.5625237822532654,
|
| 300 |
+
"learning_rate": 7.762833068916386e-05,
|
| 301 |
+
"loss": 0.5736,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.7972665148063781,
|
| 306 |
+
"eval_accuracy": 0.7782054366129421,
|
| 307 |
+
"eval_f1_macro": 0.6779030343365783,
|
| 308 |
+
"eval_f1_micro": 0.7782054366129421,
|
| 309 |
+
"eval_loss": 1.0509027242660522,
|
| 310 |
+
"eval_precision_macro": 0.7339555194909612,
|
| 311 |
+
"eval_precision_micro": 0.7782054366129421,
|
| 312 |
+
"eval_recall_macro": 0.6828886626680506,
|
| 313 |
+
"eval_recall_micro": 0.7782054366129421,
|
| 314 |
+
"eval_runtime": 8.481,
|
| 315 |
+
"eval_samples_per_second": 490.156,
|
| 316 |
+
"eval_steps_per_second": 61.314,
|
| 317 |
+
"step": 7000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8542141230068337,
|
| 321 |
+
"grad_norm": 64.8875503540039,
|
| 322 |
+
"learning_rate": 7.690784156928418e-05,
|
| 323 |
+
"loss": 0.5273,
|
| 324 |
+
"step": 7500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8542141230068337,
|
| 328 |
+
"eval_accuracy": 0.7774837623286024,
|
| 329 |
+
"eval_f1_macro": 0.7006759117702724,
|
| 330 |
+
"eval_f1_micro": 0.7774837623286024,
|
| 331 |
+
"eval_loss": 1.083090901374817,
|
| 332 |
+
"eval_precision_macro": 0.7615638623524419,
|
| 333 |
+
"eval_precision_micro": 0.7774837623286024,
|
| 334 |
+
"eval_recall_macro": 0.7385809772355115,
|
| 335 |
+
"eval_recall_micro": 0.7774837623286024,
|
| 336 |
+
"eval_runtime": 8.4704,
|
| 337 |
+
"eval_samples_per_second": 490.769,
|
| 338 |
+
"eval_steps_per_second": 61.39,
|
| 339 |
+
"step": 7500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9111617312072893,
|
| 343 |
+
"grad_norm": 0.9078112840652466,
|
| 344 |
+
"learning_rate": 7.609621959255558e-05,
|
| 345 |
+
"loss": 0.5268,
|
| 346 |
+
"step": 8000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9111617312072893,
|
| 350 |
+
"eval_accuracy": 0.7445273033437575,
|
| 351 |
+
"eval_f1_macro": 0.699580887402278,
|
| 352 |
+
"eval_f1_micro": 0.7445273033437575,
|
| 353 |
+
"eval_loss": 1.3979923725128174,
|
| 354 |
+
"eval_precision_macro": 0.7001048011829232,
|
| 355 |
+
"eval_precision_micro": 0.7445273033437575,
|
| 356 |
+
"eval_recall_macro": 0.7726266308290096,
|
| 357 |
+
"eval_recall_micro": 0.7445273033437575,
|
| 358 |
+
"eval_runtime": 8.4384,
|
| 359 |
+
"eval_samples_per_second": 492.631,
|
| 360 |
+
"eval_steps_per_second": 61.623,
|
| 361 |
+
"step": 8000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.9681093394077449,
|
| 365 |
+
"grad_norm": 42.65549850463867,
|
| 366 |
+
"learning_rate": 7.519735782617663e-05,
|
| 367 |
+
"loss": 0.5462,
|
| 368 |
+
"step": 8500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.9681093394077449,
|
| 372 |
+
"eval_accuracy": 0.8287226365167187,
|
| 373 |
+
"eval_f1_macro": 0.7785313462283256,
|
| 374 |
+
"eval_f1_micro": 0.8287226365167187,
|
| 375 |
+
"eval_loss": 0.9026873111724854,
|
| 376 |
+
"eval_precision_macro": 0.7868255645583773,
|
| 377 |
+
"eval_precision_micro": 0.8287226365167187,
|
| 378 |
+
"eval_recall_macro": 0.8024053906273642,
|
| 379 |
+
"eval_recall_micro": 0.8287226365167187,
|
| 380 |
+
"eval_runtime": 8.4335,
|
| 381 |
+
"eval_samples_per_second": 492.916,
|
| 382 |
+
"eval_steps_per_second": 61.659,
|
| 383 |
+
"step": 8500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.0250569476082005,
|
| 387 |
+
"grad_norm": 0.9462873935699463,
|
| 388 |
+
"learning_rate": 7.420987383057407e-05,
|
| 389 |
+
"loss": 0.486,
|
| 390 |
+
"step": 9000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.0250569476082005,
|
| 394 |
+
"eval_accuracy": 0.7211931681501083,
|
| 395 |
+
"eval_f1_macro": 0.6932948143152837,
|
| 396 |
+
"eval_f1_micro": 0.7211931681501083,
|
| 397 |
+
"eval_loss": 1.7263842821121216,
|
| 398 |
+
"eval_precision_macro": 0.7360552900892146,
|
| 399 |
+
"eval_precision_micro": 0.7211931681501083,
|
| 400 |
+
"eval_recall_macro": 0.7409941847523269,
|
| 401 |
+
"eval_recall_micro": 0.7211931681501083,
|
| 402 |
+
"eval_runtime": 8.473,
|
| 403 |
+
"eval_samples_per_second": 490.615,
|
| 404 |
+
"eval_steps_per_second": 61.371,
|
| 405 |
+
"step": 9000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.082004555808656,
|
| 409 |
+
"grad_norm": 0.8366897106170654,
|
| 410 |
+
"learning_rate": 7.314014528807089e-05,
|
| 411 |
+
"loss": 0.4458,
|
| 412 |
+
"step": 9500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.082004555808656,
|
| 416 |
+
"eval_accuracy": 0.8186191965359635,
|
| 417 |
+
"eval_f1_macro": 0.7675006381723768,
|
| 418 |
+
"eval_f1_micro": 0.8186191965359635,
|
| 419 |
+
"eval_loss": 0.9773014783859253,
|
| 420 |
+
"eval_precision_macro": 0.7844621076644617,
|
| 421 |
+
"eval_precision_micro": 0.8186191965359635,
|
| 422 |
+
"eval_recall_macro": 0.8041851318048103,
|
| 423 |
+
"eval_recall_micro": 0.8186191965359635,
|
| 424 |
+
"eval_runtime": 8.4706,
|
| 425 |
+
"eval_samples_per_second": 490.754,
|
| 426 |
+
"eval_steps_per_second": 61.389,
|
| 427 |
+
"step": 9500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.1389521640091116,
|
| 431 |
+
"grad_norm": 2.115098237991333,
|
| 432 |
+
"learning_rate": 7.198652696785955e-05,
|
| 433 |
+
"loss": 0.4102,
|
| 434 |
+
"step": 10000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1389521640091116,
|
| 438 |
+
"eval_accuracy": 0.8316093336540774,
|
| 439 |
+
"eval_f1_macro": 0.7933624073358755,
|
| 440 |
+
"eval_f1_micro": 0.8316093336540774,
|
| 441 |
+
"eval_loss": 0.967036247253418,
|
| 442 |
+
"eval_precision_macro": 0.7949251475033909,
|
| 443 |
+
"eval_precision_micro": 0.8316093336540774,
|
| 444 |
+
"eval_recall_macro": 0.8274655786829063,
|
| 445 |
+
"eval_recall_micro": 0.8316093336540774,
|
| 446 |
+
"eval_runtime": 8.4509,
|
| 447 |
+
"eval_samples_per_second": 491.9,
|
| 448 |
+
"eval_steps_per_second": 61.532,
|
| 449 |
+
"step": 10000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.1958997722095672,
|
| 453 |
+
"grad_norm": 1.0413740873336792,
|
| 454 |
+
"learning_rate": 7.075392750273938e-05,
|
| 455 |
+
"loss": 0.3773,
|
| 456 |
+
"step": 10500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.1958997722095672,
|
| 460 |
+
"eval_accuracy": 0.8171758479672842,
|
| 461 |
+
"eval_f1_macro": 0.7981622962245145,
|
| 462 |
+
"eval_f1_micro": 0.8171758479672842,
|
| 463 |
+
"eval_loss": 0.9198176860809326,
|
| 464 |
+
"eval_precision_macro": 0.819291401144176,
|
| 465 |
+
"eval_precision_micro": 0.8171758479672842,
|
| 466 |
+
"eval_recall_macro": 0.8245482183363974,
|
| 467 |
+
"eval_recall_micro": 0.8171758479672842,
|
| 468 |
+
"eval_runtime": 8.4577,
|
| 469 |
+
"eval_samples_per_second": 491.505,
|
| 470 |
+
"eval_steps_per_second": 61.482,
|
| 471 |
+
"step": 10500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.2528473804100229,
|
| 475 |
+
"grad_norm": 7.1126203536987305,
|
| 476 |
+
"learning_rate": 6.94453904277921e-05,
|
| 477 |
+
"loss": 0.3796,
|
| 478 |
+
"step": 11000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.2528473804100229,
|
| 482 |
+
"eval_accuracy": 0.7741159490016839,
|
| 483 |
+
"eval_f1_macro": 0.7334267874337288,
|
| 484 |
+
"eval_f1_micro": 0.7741159490016839,
|
| 485 |
+
"eval_loss": 1.324471116065979,
|
| 486 |
+
"eval_precision_macro": 0.7554977548108798,
|
| 487 |
+
"eval_precision_micro": 0.7741159490016839,
|
| 488 |
+
"eval_recall_macro": 0.7865189643712818,
|
| 489 |
+
"eval_recall_micro": 0.7741159490016839,
|
| 490 |
+
"eval_runtime": 8.4546,
|
| 491 |
+
"eval_samples_per_second": 491.688,
|
| 492 |
+
"eval_steps_per_second": 61.505,
|
| 493 |
+
"step": 11000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3097949886104785,
|
| 497 |
+
"grad_norm": 85.53689575195312,
|
| 498 |
+
"learning_rate": 6.806414678327537e-05,
|
| 499 |
+
"loss": 0.4432,
|
| 500 |
+
"step": 11500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.3097949886104785,
|
| 504 |
+
"eval_accuracy": 0.8092374308395478,
|
| 505 |
+
"eval_f1_macro": 0.7438442519057924,
|
| 506 |
+
"eval_f1_micro": 0.8092374308395478,
|
| 507 |
+
"eval_loss": 1.1105079650878906,
|
| 508 |
+
"eval_precision_macro": 0.7748012629794462,
|
| 509 |
+
"eval_precision_micro": 0.8092374308395478,
|
| 510 |
+
"eval_recall_macro": 0.7783932685192183,
|
| 511 |
+
"eval_recall_micro": 0.8092374308395478,
|
| 512 |
+
"eval_runtime": 8.4968,
|
| 513 |
+
"eval_samples_per_second": 489.244,
|
| 514 |
+
"eval_steps_per_second": 61.2,
|
| 515 |
+
"step": 11500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.366742596810934,
|
| 519 |
+
"grad_norm": 1.0569897890090942,
|
| 520 |
+
"learning_rate": 6.661360713653681e-05,
|
| 521 |
+
"loss": 0.389,
|
| 522 |
+
"step": 12000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.366742596810934,
|
| 526 |
+
"eval_accuracy": 0.8128458022612461,
|
| 527 |
+
"eval_f1_macro": 0.7595338289100665,
|
| 528 |
+
"eval_f1_micro": 0.8128458022612461,
|
| 529 |
+
"eval_loss": 1.0267034769058228,
|
| 530 |
+
"eval_precision_macro": 0.7590761169934961,
|
| 531 |
+
"eval_precision_micro": 0.8128458022612461,
|
| 532 |
+
"eval_recall_macro": 0.8036606747506161,
|
| 533 |
+
"eval_recall_micro": 0.8128458022612461,
|
| 534 |
+
"eval_runtime": 8.4648,
|
| 535 |
+
"eval_samples_per_second": 491.09,
|
| 536 |
+
"eval_steps_per_second": 61.431,
|
| 537 |
+
"step": 12000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.4236902050113895,
|
| 541 |
+
"grad_norm": 14.686357498168945,
|
| 542 |
+
"learning_rate": 6.509735316063996e-05,
|
| 543 |
+
"loss": 0.6087,
|
| 544 |
+
"step": 12500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.4236902050113895,
|
| 548 |
+
"eval_accuracy": 0.8443589126774116,
|
| 549 |
+
"eval_f1_macro": 0.7997974993396904,
|
| 550 |
+
"eval_f1_micro": 0.8443589126774116,
|
| 551 |
+
"eval_loss": 0.9193519353866577,
|
| 552 |
+
"eval_precision_macro": 0.7894219117254144,
|
| 553 |
+
"eval_precision_micro": 0.8443589126774116,
|
| 554 |
+
"eval_recall_macro": 0.833108777347993,
|
| 555 |
+
"eval_recall_micro": 0.8443589126774116,
|
| 556 |
+
"eval_runtime": 8.4379,
|
| 557 |
+
"eval_samples_per_second": 492.657,
|
| 558 |
+
"eval_steps_per_second": 61.627,
|
| 559 |
+
"step": 12500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.4806378132118452,
|
| 563 |
+
"grad_norm": 0.05014890432357788,
|
| 564 |
+
"learning_rate": 6.352234452003862e-05,
|
| 565 |
+
"loss": 0.4803,
|
| 566 |
+
"step": 13000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.4806378132118452,
|
| 570 |
+
"eval_accuracy": 0.8535001202790474,
|
| 571 |
+
"eval_f1_macro": 0.8265458036830905,
|
| 572 |
+
"eval_f1_micro": 0.8535001202790474,
|
| 573 |
+
"eval_loss": 0.879317581653595,
|
| 574 |
+
"eval_precision_macro": 0.8329036145166532,
|
| 575 |
+
"eval_precision_micro": 0.8535001202790474,
|
| 576 |
+
"eval_recall_macro": 0.8340628674797995,
|
| 577 |
+
"eval_recall_micro": 0.8535001202790474,
|
| 578 |
+
"eval_runtime": 8.4157,
|
| 579 |
+
"eval_samples_per_second": 493.96,
|
| 580 |
+
"eval_steps_per_second": 61.79,
|
| 581 |
+
"step": 13000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.5375854214123006,
|
| 585 |
+
"grad_norm": 40.28041076660156,
|
| 586 |
+
"learning_rate": 6.188948654276723e-05,
|
| 587 |
+
"loss": 0.5513,
|
| 588 |
+
"step": 13500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.5375854214123006,
|
| 592 |
+
"eval_accuracy": 0.7782054366129421,
|
| 593 |
+
"eval_f1_macro": 0.7066835334217871,
|
| 594 |
+
"eval_f1_micro": 0.7782054366129421,
|
| 595 |
+
"eval_loss": 1.1909141540527344,
|
| 596 |
+
"eval_precision_macro": 0.7255202837659691,
|
| 597 |
+
"eval_precision_micro": 0.7782054366129421,
|
| 598 |
+
"eval_recall_macro": 0.7402758652568006,
|
| 599 |
+
"eval_recall_micro": 0.7782054366129421,
|
| 600 |
+
"eval_runtime": 8.4835,
|
| 601 |
+
"eval_samples_per_second": 490.012,
|
| 602 |
+
"eval_steps_per_second": 61.296,
|
| 603 |
+
"step": 13500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.5945330296127562,
|
| 607 |
+
"grad_norm": 8.929847717285156,
|
| 608 |
+
"learning_rate": 6.019936353958699e-05,
|
| 609 |
+
"loss": 0.693,
|
| 610 |
+
"step": 14000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.5945330296127562,
|
| 614 |
+
"eval_accuracy": 0.2460909309598268,
|
| 615 |
+
"eval_f1_macro": 0.20336556842910194,
|
| 616 |
+
"eval_f1_micro": 0.2460909309598268,
|
| 617 |
+
"eval_loss": 2.8277578353881836,
|
| 618 |
+
"eval_precision_macro": 0.5226671539146224,
|
| 619 |
+
"eval_precision_micro": 0.2460909309598268,
|
| 620 |
+
"eval_recall_macro": 0.1936798727163823,
|
| 621 |
+
"eval_recall_micro": 0.2460909309598268,
|
| 622 |
+
"eval_runtime": 8.4782,
|
| 623 |
+
"eval_samples_per_second": 490.315,
|
| 624 |
+
"eval_steps_per_second": 61.334,
|
| 625 |
+
"step": 14000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6514806378132119,
|
| 629 |
+
"grad_norm": 28.1862735748291,
|
| 630 |
+
"learning_rate": 5.8459364260048594e-05,
|
| 631 |
+
"loss": 0.9646,
|
| 632 |
+
"step": 14500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6514806378132119,
|
| 636 |
+
"eval_accuracy": 0.8246331489054607,
|
| 637 |
+
"eval_f1_macro": 0.7913907456133474,
|
| 638 |
+
"eval_f1_micro": 0.8246331489054607,
|
| 639 |
+
"eval_loss": 0.948131799697876,
|
| 640 |
+
"eval_precision_macro": 0.799701208597097,
|
| 641 |
+
"eval_precision_micro": 0.8246331489054607,
|
| 642 |
+
"eval_recall_macro": 0.8123299807423895,
|
| 643 |
+
"eval_recall_micro": 0.8246331489054607,
|
| 644 |
+
"eval_runtime": 8.4643,
|
| 645 |
+
"eval_samples_per_second": 491.124,
|
| 646 |
+
"eval_steps_per_second": 61.435,
|
| 647 |
+
"step": 14500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.7084282460136673,
|
| 651 |
+
"grad_norm": 7.083284854888916,
|
| 652 |
+
"learning_rate": 5.6673785111054136e-05,
|
| 653 |
+
"loss": 0.462,
|
| 654 |
+
"step": 15000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.7084282460136673,
|
| 658 |
+
"eval_accuracy": 0.8472456098147703,
|
| 659 |
+
"eval_f1_macro": 0.8091993297668394,
|
| 660 |
+
"eval_f1_micro": 0.8472456098147703,
|
| 661 |
+
"eval_loss": 0.8667464256286621,
|
| 662 |
+
"eval_precision_macro": 0.8198322314440802,
|
| 663 |
+
"eval_precision_micro": 0.8472456098147703,
|
| 664 |
+
"eval_recall_macro": 0.8266325847969769,
|
| 665 |
+
"eval_recall_micro": 0.8472456098147703,
|
| 666 |
+
"eval_runtime": 8.4589,
|
| 667 |
+
"eval_samples_per_second": 491.435,
|
| 668 |
+
"eval_steps_per_second": 61.474,
|
| 669 |
+
"step": 15000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.7653758542141231,
|
| 673 |
+
"grad_norm": 65.16443634033203,
|
| 674 |
+
"learning_rate": 5.484703504533721e-05,
|
| 675 |
+
"loss": 0.4093,
|
| 676 |
+
"step": 15500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.7653758542141231,
|
| 680 |
+
"eval_accuracy": 0.8116430117873467,
|
| 681 |
+
"eval_f1_macro": 0.7700885656504642,
|
| 682 |
+
"eval_f1_micro": 0.8116430117873467,
|
| 683 |
+
"eval_loss": 1.1932649612426758,
|
| 684 |
+
"eval_precision_macro": 0.8232095109547221,
|
| 685 |
+
"eval_precision_micro": 0.8116430117873467,
|
| 686 |
+
"eval_recall_macro": 0.775800293436143,
|
| 687 |
+
"eval_recall_micro": 0.8116430117873467,
|
| 688 |
+
"eval_runtime": 8.4735,
|
| 689 |
+
"eval_samples_per_second": 490.589,
|
| 690 |
+
"eval_steps_per_second": 61.368,
|
| 691 |
+
"step": 15500
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.8223234624145785,
|
| 695 |
+
"grad_norm": 15.238636016845703,
|
| 696 |
+
"learning_rate": 5.2983624674875084e-05,
|
| 697 |
+
"loss": 0.349,
|
| 698 |
+
"step": 16000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.8223234624145785,
|
| 702 |
+
"eval_accuracy": 0.8799615107048352,
|
| 703 |
+
"eval_f1_macro": 0.8377281287378512,
|
| 704 |
+
"eval_f1_micro": 0.8799615107048352,
|
| 705 |
+
"eval_loss": 0.7749123573303223,
|
| 706 |
+
"eval_precision_macro": 0.8358272736538074,
|
| 707 |
+
"eval_precision_micro": 0.8799615107048352,
|
| 708 |
+
"eval_recall_macro": 0.8723899950094214,
|
| 709 |
+
"eval_recall_micro": 0.8799615107048352,
|
| 710 |
+
"eval_runtime": 8.4617,
|
| 711 |
+
"eval_samples_per_second": 491.272,
|
| 712 |
+
"eval_steps_per_second": 61.453,
|
| 713 |
+
"step": 16000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.8792710706150342,
|
| 717 |
+
"grad_norm": 1.931815505027771,
|
| 718 |
+
"learning_rate": 5.108815513328386e-05,
|
| 719 |
+
"loss": 0.3333,
|
| 720 |
+
"step": 16500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.8792710706150342,
|
| 724 |
+
"eval_accuracy": 0.8799615107048352,
|
| 725 |
+
"eval_f1_macro": 0.851689807067872,
|
| 726 |
+
"eval_f1_micro": 0.8799615107048352,
|
| 727 |
+
"eval_loss": 0.6482954025268555,
|
| 728 |
+
"eval_precision_macro": 0.8439980638748368,
|
| 729 |
+
"eval_precision_micro": 0.8799615107048352,
|
| 730 |
+
"eval_recall_macro": 0.8709009740944947,
|
| 731 |
+
"eval_recall_micro": 0.8799615107048352,
|
| 732 |
+
"eval_runtime": 8.4707,
|
| 733 |
+
"eval_samples_per_second": 490.751,
|
| 734 |
+
"eval_steps_per_second": 61.388,
|
| 735 |
+
"step": 16500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.9362186788154898,
|
| 739 |
+
"grad_norm": 14.734030723571777,
|
| 740 |
+
"learning_rate": 4.916530671469754e-05,
|
| 741 |
+
"loss": 0.3449,
|
| 742 |
+
"step": 17000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.9362186788154898,
|
| 746 |
+
"eval_accuracy": 0.7890305508780371,
|
| 747 |
+
"eval_f1_macro": 0.7375164837600725,
|
| 748 |
+
"eval_f1_micro": 0.7890305508780371,
|
| 749 |
+
"eval_loss": 1.2130000591278076,
|
| 750 |
+
"eval_precision_macro": 0.7696829158091395,
|
| 751 |
+
"eval_precision_micro": 0.7890305508780371,
|
| 752 |
+
"eval_recall_macro": 0.7545432686041814,
|
| 753 |
+
"eval_recall_micro": 0.7890305508780371,
|
| 754 |
+
"eval_runtime": 8.448,
|
| 755 |
+
"eval_samples_per_second": 492.07,
|
| 756 |
+
"eval_steps_per_second": 61.553,
|
| 757 |
+
"step": 17000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.9931662870159452,
|
| 761 |
+
"grad_norm": 4.0362091064453125,
|
| 762 |
+
"learning_rate": 4.7219827317183907e-05,
|
| 763 |
+
"loss": 0.2982,
|
| 764 |
+
"step": 17500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.9931662870159452,
|
| 768 |
+
"eval_accuracy": 0.8599951888381044,
|
| 769 |
+
"eval_f1_macro": 0.8354955249556116,
|
| 770 |
+
"eval_f1_micro": 0.8599951888381044,
|
| 771 |
+
"eval_loss": 0.8803524374961853,
|
| 772 |
+
"eval_precision_macro": 0.8342493543222153,
|
| 773 |
+
"eval_precision_micro": 0.8599951888381044,
|
| 774 |
+
"eval_recall_macro": 0.8556466165427711,
|
| 775 |
+
"eval_recall_micro": 0.8599951888381044,
|
| 776 |
+
"eval_runtime": 8.4723,
|
| 777 |
+
"eval_samples_per_second": 490.66,
|
| 778 |
+
"eval_steps_per_second": 61.377,
|
| 779 |
+
"step": 17500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.050113895216401,
|
| 783 |
+
"grad_norm": 0.7534123659133911,
|
| 784 |
+
"learning_rate": 4.525652071923279e-05,
|
| 785 |
+
"loss": 0.2348,
|
| 786 |
+
"step": 18000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.050113895216401,
|
| 790 |
+
"eval_accuracy": 0.8448400288669714,
|
| 791 |
+
"eval_f1_macro": 0.8190720986060728,
|
| 792 |
+
"eval_f1_micro": 0.8448400288669714,
|
| 793 |
+
"eval_loss": 1.1245763301849365,
|
| 794 |
+
"eval_precision_macro": 0.8337767355676724,
|
| 795 |
+
"eval_precision_micro": 0.8448400288669714,
|
| 796 |
+
"eval_recall_macro": 0.8557743090961959,
|
| 797 |
+
"eval_recall_micro": 0.8448400288669714,
|
| 798 |
+
"eval_runtime": 8.4721,
|
| 799 |
+
"eval_samples_per_second": 490.667,
|
| 800 |
+
"eval_steps_per_second": 61.378,
|
| 801 |
+
"step": 18000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.1070615034168565,
|
| 805 |
+
"grad_norm": 1.4927374124526978,
|
| 806 |
+
"learning_rate": 4.328023471826429e-05,
|
| 807 |
+
"loss": 0.2299,
|
| 808 |
+
"step": 18500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.1070615034168565,
|
| 812 |
+
"eval_accuracy": 0.8708203031031995,
|
| 813 |
+
"eval_f1_macro": 0.8303241771039817,
|
| 814 |
+
"eval_f1_micro": 0.8708203031031995,
|
| 815 |
+
"eval_loss": 0.8329204320907593,
|
| 816 |
+
"eval_precision_macro": 0.83267401976066,
|
| 817 |
+
"eval_precision_micro": 0.8708203031031995,
|
| 818 |
+
"eval_recall_macro": 0.8610797711013763,
|
| 819 |
+
"eval_recall_micro": 0.8708203031031995,
|
| 820 |
+
"eval_runtime": 8.4578,
|
| 821 |
+
"eval_samples_per_second": 491.498,
|
| 822 |
+
"eval_steps_per_second": 61.482,
|
| 823 |
+
"step": 18500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.164009111617312,
|
| 827 |
+
"grad_norm": 1.7383619546890259,
|
| 828 |
+
"learning_rate": 4.129584916044555e-05,
|
| 829 |
+
"loss": 0.2468,
|
| 830 |
+
"step": 19000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.164009111617312,
|
| 834 |
+
"eval_accuracy": 0.8773153716622565,
|
| 835 |
+
"eval_f1_macro": 0.846177762458016,
|
| 836 |
+
"eval_f1_micro": 0.8773153716622565,
|
| 837 |
+
"eval_loss": 0.7664415836334229,
|
| 838 |
+
"eval_precision_macro": 0.8368864405451267,
|
| 839 |
+
"eval_precision_micro": 0.8773153716622565,
|
| 840 |
+
"eval_recall_macro": 0.8780489137762446,
|
| 841 |
+
"eval_recall_micro": 0.8773153716622565,
|
| 842 |
+
"eval_runtime": 8.4381,
|
| 843 |
+
"eval_samples_per_second": 492.645,
|
| 844 |
+
"eval_steps_per_second": 61.625,
|
| 845 |
+
"step": 19000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.2209567198177678,
|
| 849 |
+
"grad_norm": 400.013916015625,
|
| 850 |
+
"learning_rate": 3.930826389137262e-05,
|
| 851 |
+
"loss": 0.1899,
|
| 852 |
+
"step": 19500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.2209567198177678,
|
| 856 |
+
"eval_accuracy": 0.8862160211691124,
|
| 857 |
+
"eval_f1_macro": 0.8558563382552302,
|
| 858 |
+
"eval_f1_micro": 0.8862160211691124,
|
| 859 |
+
"eval_loss": 0.7495226263999939,
|
| 860 |
+
"eval_precision_macro": 0.8555231307289006,
|
| 861 |
+
"eval_precision_micro": 0.8862160211691124,
|
| 862 |
+
"eval_recall_macro": 0.8758801511510593,
|
| 863 |
+
"eval_recall_micro": 0.8862160211691124,
|
| 864 |
+
"eval_runtime": 8.4445,
|
| 865 |
+
"eval_samples_per_second": 492.274,
|
| 866 |
+
"eval_steps_per_second": 61.579,
|
| 867 |
+
"step": 19500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.277904328018223,
|
| 871 |
+
"grad_norm": 2.0449647903442383,
|
| 872 |
+
"learning_rate": 3.732635344608829e-05,
|
| 873 |
+
"loss": 0.1977,
|
| 874 |
+
"step": 20000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.277904328018223,
|
| 878 |
+
"eval_accuracy": 0.8551840269425066,
|
| 879 |
+
"eval_f1_macro": 0.8198359165864053,
|
| 880 |
+
"eval_f1_micro": 0.8551840269425066,
|
| 881 |
+
"eval_loss": 1.0149922370910645,
|
| 882 |
+
"eval_precision_macro": 0.8328051392132652,
|
| 883 |
+
"eval_precision_micro": 0.8551840269425066,
|
| 884 |
+
"eval_recall_macro": 0.853902169918103,
|
| 885 |
+
"eval_recall_micro": 0.8551840269425066,
|
| 886 |
+
"eval_runtime": 8.4355,
|
| 887 |
+
"eval_samples_per_second": 492.798,
|
| 888 |
+
"eval_steps_per_second": 61.644,
|
| 889 |
+
"step": 20000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.334851936218679,
|
| 893 |
+
"grad_norm": 0.7749654650688171,
|
| 894 |
+
"learning_rate": 3.534706966798757e-05,
|
| 895 |
+
"loss": 0.2314,
|
| 896 |
+
"step": 20500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.334851936218679,
|
| 900 |
+
"eval_accuracy": 0.8948761125811884,
|
| 901 |
+
"eval_f1_macro": 0.8659539030629905,
|
| 902 |
+
"eval_f1_micro": 0.8948761125811884,
|
| 903 |
+
"eval_loss": 0.6898870468139648,
|
| 904 |
+
"eval_precision_macro": 0.8564830162508421,
|
| 905 |
+
"eval_precision_micro": 0.8948761125811884,
|
| 906 |
+
"eval_recall_macro": 0.8978688795664334,
|
| 907 |
+
"eval_recall_micro": 0.8948761125811884,
|
| 908 |
+
"eval_runtime": 8.4412,
|
| 909 |
+
"eval_samples_per_second": 492.466,
|
| 910 |
+
"eval_steps_per_second": 61.603,
|
| 911 |
+
"step": 20500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.3917995444191344,
|
| 915 |
+
"grad_norm": 0.007438243832439184,
|
| 916 |
+
"learning_rate": 3.337927490728384e-05,
|
| 917 |
+
"loss": 0.203,
|
| 918 |
+
"step": 21000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.3917995444191344,
|
| 922 |
+
"eval_accuracy": 0.8984844840028867,
|
| 923 |
+
"eval_f1_macro": 0.8654367599963082,
|
| 924 |
+
"eval_f1_micro": 0.8984844840028867,
|
| 925 |
+
"eval_loss": 0.6225568652153015,
|
| 926 |
+
"eval_precision_macro": 0.8710584795534867,
|
| 927 |
+
"eval_precision_micro": 0.8984844840028867,
|
| 928 |
+
"eval_recall_macro": 0.8907316535034207,
|
| 929 |
+
"eval_recall_micro": 0.8984844840028867,
|
| 930 |
+
"eval_runtime": 8.4582,
|
| 931 |
+
"eval_samples_per_second": 491.477,
|
| 932 |
+
"eval_steps_per_second": 61.479,
|
| 933 |
+
"step": 21000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.44874715261959,
|
| 937 |
+
"grad_norm": 1.0429240465164185,
|
| 938 |
+
"learning_rate": 3.142782804357047e-05,
|
| 939 |
+
"loss": 0.1784,
|
| 940 |
+
"step": 21500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.44874715261959,
|
| 944 |
+
"eval_accuracy": 0.8806831849891749,
|
| 945 |
+
"eval_f1_macro": 0.8516903935082014,
|
| 946 |
+
"eval_f1_micro": 0.8806831849891749,
|
| 947 |
+
"eval_loss": 0.8446455001831055,
|
| 948 |
+
"eval_precision_macro": 0.86002376045135,
|
| 949 |
+
"eval_precision_micro": 0.8806831849891749,
|
| 950 |
+
"eval_recall_macro": 0.8768325982997476,
|
| 951 |
+
"eval_recall_micro": 0.8806831849891749,
|
| 952 |
+
"eval_runtime": 8.4659,
|
| 953 |
+
"eval_samples_per_second": 491.026,
|
| 954 |
+
"eval_steps_per_second": 61.423,
|
| 955 |
+
"step": 21500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.5056947608200457,
|
| 959 |
+
"grad_norm": 89.87359619140625,
|
| 960 |
+
"learning_rate": 2.9497547590207118e-05,
|
| 961 |
+
"loss": 0.2044,
|
| 962 |
+
"step": 22000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.5056947608200457,
|
| 966 |
+
"eval_accuracy": 0.8556651431320664,
|
| 967 |
+
"eval_f1_macro": 0.8466413367690651,
|
| 968 |
+
"eval_f1_micro": 0.8556651431320664,
|
| 969 |
+
"eval_loss": 0.9901952743530273,
|
| 970 |
+
"eval_precision_macro": 0.8512325160929325,
|
| 971 |
+
"eval_precision_micro": 0.8556651431320664,
|
| 972 |
+
"eval_recall_macro": 0.875509109034969,
|
| 973 |
+
"eval_recall_micro": 0.8556651431320664,
|
| 974 |
+
"eval_runtime": 8.5077,
|
| 975 |
+
"eval_samples_per_second": 488.617,
|
| 976 |
+
"eval_steps_per_second": 61.121,
|
| 977 |
+
"step": 22000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.562642369020501,
|
| 981 |
+
"grad_norm": 0.013815644197165966,
|
| 982 |
+
"learning_rate": 2.759319979644478e-05,
|
| 983 |
+
"loss": 0.1914,
|
| 984 |
+
"step": 22500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.562642369020501,
|
| 988 |
+
"eval_accuracy": 0.8927110897281694,
|
| 989 |
+
"eval_f1_macro": 0.8644517343056812,
|
| 990 |
+
"eval_f1_micro": 0.8927110897281694,
|
| 991 |
+
"eval_loss": 0.7158553004264832,
|
| 992 |
+
"eval_precision_macro": 0.8493787111870335,
|
| 993 |
+
"eval_precision_micro": 0.8927110897281694,
|
| 994 |
+
"eval_recall_macro": 0.898066885887026,
|
| 995 |
+
"eval_recall_micro": 0.8927110897281694,
|
| 996 |
+
"eval_runtime": 8.4749,
|
| 997 |
+
"eval_samples_per_second": 490.509,
|
| 998 |
+
"eval_steps_per_second": 61.358,
|
| 999 |
+
"step": 22500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.619589977220957,
|
| 1003 |
+
"grad_norm": 4.245390892028809,
|
| 1004 |
+
"learning_rate": 2.5719486878601176e-05,
|
| 1005 |
+
"loss": 0.1639,
|
| 1006 |
+
"step": 23000
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.619589977220957,
|
| 1010 |
+
"eval_accuracy": 0.8864565792638922,
|
| 1011 |
+
"eval_f1_macro": 0.8458899447458572,
|
| 1012 |
+
"eval_f1_micro": 0.8864565792638922,
|
| 1013 |
+
"eval_loss": 0.729199230670929,
|
| 1014 |
+
"eval_precision_macro": 0.8401968974647541,
|
| 1015 |
+
"eval_precision_micro": 0.8864565792638922,
|
| 1016 |
+
"eval_recall_macro": 0.8805776786360812,
|
| 1017 |
+
"eval_recall_micro": 0.8864565792638922,
|
| 1018 |
+
"eval_runtime": 8.4586,
|
| 1019 |
+
"eval_samples_per_second": 491.451,
|
| 1020 |
+
"eval_steps_per_second": 61.476,
|
| 1021 |
+
"step": 23000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.6765375854214124,
|
| 1025 |
+
"grad_norm": 1.427230715751648,
|
| 1026 |
+
"learning_rate": 2.3881035409346452e-05,
|
| 1027 |
+
"loss": 0.218,
|
| 1028 |
+
"step": 23500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.6765375854214124,
|
| 1032 |
+
"eval_accuracy": 0.8965600192446476,
|
| 1033 |
+
"eval_f1_macro": 0.8710100150868682,
|
| 1034 |
+
"eval_f1_micro": 0.8965600192446476,
|
| 1035 |
+
"eval_loss": 0.6507639288902283,
|
| 1036 |
+
"eval_precision_macro": 0.8627987859589317,
|
| 1037 |
+
"eval_precision_micro": 0.8965600192446476,
|
| 1038 |
+
"eval_recall_macro": 0.8951286903819264,
|
| 1039 |
+
"eval_recall_micro": 0.8965600192446476,
|
| 1040 |
+
"eval_runtime": 8.4672,
|
| 1041 |
+
"eval_samples_per_second": 490.955,
|
| 1042 |
+
"eval_steps_per_second": 61.414,
|
| 1043 |
+
"step": 23500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.733485193621868,
|
| 1047 |
+
"grad_norm": 0.07296980172395706,
|
| 1048 |
+
"learning_rate": 2.208238489376805e-05,
|
| 1049 |
+
"loss": 0.1723,
|
| 1050 |
+
"step": 24000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.733485193621868,
|
| 1054 |
+
"eval_accuracy": 0.9023334135193649,
|
| 1055 |
+
"eval_f1_macro": 0.8816239296246752,
|
| 1056 |
+
"eval_f1_micro": 0.9023334135193649,
|
| 1057 |
+
"eval_loss": 0.6424487233161926,
|
| 1058 |
+
"eval_precision_macro": 0.8835852425011356,
|
| 1059 |
+
"eval_precision_micro": 0.9023334135193649,
|
| 1060 |
+
"eval_recall_macro": 0.8920920740693067,
|
| 1061 |
+
"eval_recall_micro": 0.9023334135193649,
|
| 1062 |
+
"eval_runtime": 8.4613,
|
| 1063 |
+
"eval_samples_per_second": 491.296,
|
| 1064 |
+
"eval_steps_per_second": 61.456,
|
| 1065 |
+
"step": 24000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.7904328018223232,
|
| 1069 |
+
"grad_norm": 125.23475646972656,
|
| 1070 |
+
"learning_rate": 2.0331438324793375e-05,
|
| 1071 |
+
"loss": 0.1682,
|
| 1072 |
+
"step": 24500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.7904328018223232,
|
| 1076 |
+
"eval_accuracy": 0.8972816935289872,
|
| 1077 |
+
"eval_f1_macro": 0.8822737330613647,
|
| 1078 |
+
"eval_f1_micro": 0.8972816935289872,
|
| 1079 |
+
"eval_loss": 0.6842340230941772,
|
| 1080 |
+
"eval_precision_macro": 0.8827282408108892,
|
| 1081 |
+
"eval_precision_micro": 0.8972816935289872,
|
| 1082 |
+
"eval_recall_macro": 0.8944889961638287,
|
| 1083 |
+
"eval_recall_micro": 0.8972816935289872,
|
| 1084 |
+
"eval_runtime": 8.4764,
|
| 1085 |
+
"eval_samples_per_second": 490.419,
|
| 1086 |
+
"eval_steps_per_second": 61.347,
|
| 1087 |
+
"step": 24500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.847380410022779,
|
| 1091 |
+
"grad_norm": 0.5098503828048706,
|
| 1092 |
+
"learning_rate": 1.8628863347570347e-05,
|
| 1093 |
+
"loss": 0.1441,
|
| 1094 |
+
"step": 25000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.847380410022779,
|
| 1098 |
+
"eval_accuracy": 0.8948761125811884,
|
| 1099 |
+
"eval_f1_macro": 0.8736085811230334,
|
| 1100 |
+
"eval_f1_micro": 0.8948761125811884,
|
| 1101 |
+
"eval_loss": 0.7110973596572876,
|
| 1102 |
+
"eval_precision_macro": 0.8674915707955687,
|
| 1103 |
+
"eval_precision_micro": 0.8948761125811884,
|
| 1104 |
+
"eval_recall_macro": 0.901699859992757,
|
| 1105 |
+
"eval_recall_micro": 0.8948761125811884,
|
| 1106 |
+
"eval_runtime": 8.4537,
|
| 1107 |
+
"eval_samples_per_second": 491.739,
|
| 1108 |
+
"eval_steps_per_second": 61.512,
|
| 1109 |
+
"step": 25000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.9043280182232345,
|
| 1113 |
+
"grad_norm": 0.8350435495376587,
|
| 1114 |
+
"learning_rate": 1.6975596030661532e-05,
|
| 1115 |
+
"loss": 0.1625,
|
| 1116 |
+
"step": 25500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.9043280182232345,
|
| 1120 |
+
"eval_accuracy": 0.9030550878037046,
|
| 1121 |
+
"eval_f1_macro": 0.8779275841497265,
|
| 1122 |
+
"eval_f1_micro": 0.9030550878037046,
|
| 1123 |
+
"eval_loss": 0.6505866050720215,
|
| 1124 |
+
"eval_precision_macro": 0.8690908487688577,
|
| 1125 |
+
"eval_precision_micro": 0.9030550878037046,
|
| 1126 |
+
"eval_recall_macro": 0.9045801541095179,
|
| 1127 |
+
"eval_recall_micro": 0.9030550878037046,
|
| 1128 |
+
"eval_runtime": 8.4694,
|
| 1129 |
+
"eval_samples_per_second": 490.823,
|
| 1130 |
+
"eval_steps_per_second": 61.397,
|
| 1131 |
+
"step": 25500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.9612756264236904,
|
| 1135 |
+
"grad_norm": 0.08747211843729019,
|
| 1136 |
+
"learning_rate": 1.537918058104578e-05,
|
| 1137 |
+
"loss": 0.1494,
|
| 1138 |
+
"step": 26000
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.9612756264236904,
|
| 1142 |
+
"eval_accuracy": 0.9090690401732018,
|
| 1143 |
+
"eval_f1_macro": 0.8830141025055214,
|
| 1144 |
+
"eval_f1_micro": 0.9090690401732018,
|
| 1145 |
+
"eval_loss": 0.5693129301071167,
|
| 1146 |
+
"eval_precision_macro": 0.8816974949312945,
|
| 1147 |
+
"eval_precision_micro": 0.9090690401732018,
|
| 1148 |
+
"eval_recall_macro": 0.9015040014659215,
|
| 1149 |
+
"eval_recall_micro": 0.9090690401732018,
|
| 1150 |
+
"eval_runtime": 8.5221,
|
| 1151 |
+
"eval_samples_per_second": 487.793,
|
| 1152 |
+
"eval_steps_per_second": 61.018,
|
| 1153 |
+
"step": 26000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.0182232346241458,
|
| 1157 |
+
"grad_norm": 2.089958906173706,
|
| 1158 |
+
"learning_rate": 1.3843558868376073e-05,
|
| 1159 |
+
"loss": 0.1306,
|
| 1160 |
+
"step": 26500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.0182232346241458,
|
| 1164 |
+
"eval_accuracy": 0.9179696896800578,
|
| 1165 |
+
"eval_f1_macro": 0.8947539710239703,
|
| 1166 |
+
"eval_f1_micro": 0.9179696896800578,
|
| 1167 |
+
"eval_loss": 0.534771203994751,
|
| 1168 |
+
"eval_precision_macro": 0.8923066730381018,
|
| 1169 |
+
"eval_precision_micro": 0.9179696896800578,
|
| 1170 |
+
"eval_recall_macro": 0.9121332598176911,
|
| 1171 |
+
"eval_recall_micro": 0.9179696896800578,
|
| 1172 |
+
"eval_runtime": 8.5905,
|
| 1173 |
+
"eval_samples_per_second": 483.909,
|
| 1174 |
+
"eval_steps_per_second": 60.532,
|
| 1175 |
+
"step": 26500
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 3.075170842824601,
|
| 1179 |
+
"grad_norm": 0.0017847216222435236,
|
| 1180 |
+
"learning_rate": 1.2372522650386443e-05,
|
| 1181 |
+
"loss": 0.0929,
|
| 1182 |
+
"step": 27000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 3.075170842824601,
|
| 1186 |
+
"eval_accuracy": 0.9162857830165985,
|
| 1187 |
+
"eval_f1_macro": 0.8899287169854497,
|
| 1188 |
+
"eval_f1_micro": 0.9162857830165985,
|
| 1189 |
+
"eval_loss": 0.5843378305435181,
|
| 1190 |
+
"eval_precision_macro": 0.8796301981250076,
|
| 1191 |
+
"eval_precision_micro": 0.9162857830165985,
|
| 1192 |
+
"eval_recall_macro": 0.9152639619070458,
|
| 1193 |
+
"eval_recall_micro": 0.9162857830165985,
|
| 1194 |
+
"eval_runtime": 8.4184,
|
| 1195 |
+
"eval_samples_per_second": 493.798,
|
| 1196 |
+
"eval_steps_per_second": 61.769,
|
| 1197 |
+
"step": 27000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.132118451025057,
|
| 1201 |
+
"grad_norm": 0.7512030601501465,
|
| 1202 |
+
"learning_rate": 1.096970421028209e-05,
|
| 1203 |
+
"loss": 0.1351,
|
| 1204 |
+
"step": 27500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 3.132118451025057,
|
| 1208 |
+
"eval_accuracy": 0.9023334135193649,
|
| 1209 |
+
"eval_f1_macro": 0.8733006387364801,
|
| 1210 |
+
"eval_f1_micro": 0.9023334135193649,
|
| 1211 |
+
"eval_loss": 0.6913191080093384,
|
| 1212 |
+
"eval_precision_macro": 0.8611014409270759,
|
| 1213 |
+
"eval_precision_micro": 0.9023334135193649,
|
| 1214 |
+
"eval_recall_macro": 0.9038150903313851,
|
| 1215 |
+
"eval_recall_micro": 0.9023334135193649,
|
| 1216 |
+
"eval_runtime": 8.4379,
|
| 1217 |
+
"eval_samples_per_second": 492.656,
|
| 1218 |
+
"eval_steps_per_second": 61.626,
|
| 1219 |
+
"step": 27500
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 3.1890660592255125,
|
| 1223 |
+
"grad_norm": 0.005041371565312147,
|
| 1224 |
+
"learning_rate": 9.638567387904402e-06,
|
| 1225 |
+
"loss": 0.0907,
|
| 1226 |
+
"step": 28000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.1890660592255125,
|
| 1230 |
+
"eval_accuracy": 0.9206158287226365,
|
| 1231 |
+
"eval_f1_macro": 0.8974407788451421,
|
| 1232 |
+
"eval_f1_micro": 0.9206158287226365,
|
| 1233 |
+
"eval_loss": 0.5801523327827454,
|
| 1234 |
+
"eval_precision_macro": 0.8882950671220116,
|
| 1235 |
+
"eval_precision_micro": 0.9206158287226365,
|
| 1236 |
+
"eval_recall_macro": 0.9136820970599899,
|
| 1237 |
+
"eval_recall_micro": 0.9206158287226365,
|
| 1238 |
+
"eval_runtime": 8.4725,
|
| 1239 |
+
"eval_samples_per_second": 490.649,
|
| 1240 |
+
"eval_steps_per_second": 61.375,
|
| 1241 |
+
"step": 28000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.2460136674259683,
|
| 1245 |
+
"grad_norm": 0.6128404140472412,
|
| 1246 |
+
"learning_rate": 8.382399026816216e-06,
|
| 1247 |
+
"loss": 0.117,
|
| 1248 |
+
"step": 28500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.2460136674259683,
|
| 1252 |
+
"eval_accuracy": 0.9105123887418811,
|
| 1253 |
+
"eval_f1_macro": 0.8877368293575257,
|
| 1254 |
+
"eval_f1_micro": 0.9105123887418811,
|
| 1255 |
+
"eval_loss": 0.6602935791015625,
|
| 1256 |
+
"eval_precision_macro": 0.8839485939859522,
|
| 1257 |
+
"eval_precision_micro": 0.9105123887418811,
|
| 1258 |
+
"eval_recall_macro": 0.905732720534913,
|
| 1259 |
+
"eval_recall_micro": 0.9105123887418811,
|
| 1260 |
+
"eval_runtime": 8.482,
|
| 1261 |
+
"eval_samples_per_second": 490.097,
|
| 1262 |
+
"eval_steps_per_second": 61.306,
|
| 1263 |
+
"step": 28500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.3029612756264237,
|
| 1267 |
+
"grad_norm": 0.0018906695768237114,
|
| 1268 |
+
"learning_rate": 7.2065771743884275e-06,
|
| 1269 |
+
"loss": 0.0986,
|
| 1270 |
+
"step": 29000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.3029612756264237,
|
| 1274 |
+
"eval_accuracy": 0.9105123887418811,
|
| 1275 |
+
"eval_f1_macro": 0.887646044144043,
|
| 1276 |
+
"eval_f1_micro": 0.9105123887418811,
|
| 1277 |
+
"eval_loss": 0.6138319969177246,
|
| 1278 |
+
"eval_precision_macro": 0.887907584612917,
|
| 1279 |
+
"eval_precision_micro": 0.9105123887418811,
|
| 1280 |
+
"eval_recall_macro": 0.9029879731406512,
|
| 1281 |
+
"eval_recall_micro": 0.9105123887418811,
|
| 1282 |
+
"eval_runtime": 8.4603,
|
| 1283 |
+
"eval_samples_per_second": 491.355,
|
| 1284 |
+
"eval_steps_per_second": 61.464,
|
| 1285 |
+
"step": 29000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 3.359908883826879,
|
| 1289 |
+
"grad_norm": 1.5009195804595947,
|
| 1290 |
+
"learning_rate": 6.109293429462298e-06,
|
| 1291 |
+
"loss": 0.1196,
|
| 1292 |
+
"step": 29500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.359908883826879,
|
| 1296 |
+
"eval_accuracy": 0.9131585277844599,
|
| 1297 |
+
"eval_f1_macro": 0.8922838073892356,
|
| 1298 |
+
"eval_f1_micro": 0.9131585277844599,
|
| 1299 |
+
"eval_loss": 0.6528560519218445,
|
| 1300 |
+
"eval_precision_macro": 0.8910787251464412,
|
| 1301 |
+
"eval_precision_micro": 0.9131585277844599,
|
| 1302 |
+
"eval_recall_macro": 0.9099849910959319,
|
| 1303 |
+
"eval_recall_micro": 0.9131585277844599,
|
| 1304 |
+
"eval_runtime": 8.4579,
|
| 1305 |
+
"eval_samples_per_second": 491.492,
|
| 1306 |
+
"eval_steps_per_second": 61.481,
|
| 1307 |
+
"step": 29500
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.416856492027335,
|
| 1311 |
+
"grad_norm": 2.331648349761963,
|
| 1312 |
+
"learning_rate": 5.0956926304652455e-06,
|
| 1313 |
+
"loss": 0.1056,
|
| 1314 |
+
"step": 30000
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.416856492027335,
|
| 1318 |
+
"eval_accuracy": 0.9131585277844599,
|
| 1319 |
+
"eval_f1_macro": 0.8919235957427174,
|
| 1320 |
+
"eval_f1_micro": 0.9131585277844599,
|
| 1321 |
+
"eval_loss": 0.6215759515762329,
|
| 1322 |
+
"eval_precision_macro": 0.884609220404625,
|
| 1323 |
+
"eval_precision_micro": 0.9131585277844599,
|
| 1324 |
+
"eval_recall_macro": 0.9135941017288176,
|
| 1325 |
+
"eval_recall_micro": 0.9131585277844599,
|
| 1326 |
+
"eval_runtime": 8.4442,
|
| 1327 |
+
"eval_samples_per_second": 492.29,
|
| 1328 |
+
"eval_steps_per_second": 61.581,
|
| 1329 |
+
"step": 30000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.4738041002277904,
|
| 1333 |
+
"grad_norm": 148.2794189453125,
|
| 1334 |
+
"learning_rate": 4.168277560886878e-06,
|
| 1335 |
+
"loss": 0.1106,
|
| 1336 |
+
"step": 30500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.4738041002277904,
|
| 1340 |
+
"eval_accuracy": 0.9201347125330768,
|
| 1341 |
+
"eval_f1_macro": 0.891345440347701,
|
| 1342 |
+
"eval_f1_micro": 0.9201347125330768,
|
| 1343 |
+
"eval_loss": 0.5669803023338318,
|
| 1344 |
+
"eval_precision_macro": 0.8817511779041877,
|
| 1345 |
+
"eval_precision_micro": 0.9201347125330768,
|
| 1346 |
+
"eval_recall_macro": 0.9129521474780394,
|
| 1347 |
+
"eval_recall_micro": 0.9201347125330768,
|
| 1348 |
+
"eval_runtime": 8.4316,
|
| 1349 |
+
"eval_samples_per_second": 493.024,
|
| 1350 |
+
"eval_steps_per_second": 61.672,
|
| 1351 |
+
"step": 30500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 3.5307517084282463,
|
| 1355 |
+
"grad_norm": 4.748849868774414,
|
| 1356 |
+
"learning_rate": 3.3293381943799983e-06,
|
| 1357 |
+
"loss": 0.0953,
|
| 1358 |
+
"step": 31000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 3.5307517084282463,
|
| 1362 |
+
"eval_accuracy": 0.9189319220591773,
|
| 1363 |
+
"eval_f1_macro": 0.8934567988898604,
|
| 1364 |
+
"eval_f1_micro": 0.9189319220591773,
|
| 1365 |
+
"eval_loss": 0.569622278213501,
|
| 1366 |
+
"eval_precision_macro": 0.8825638399763271,
|
| 1367 |
+
"eval_precision_micro": 0.9189319220591773,
|
| 1368 |
+
"eval_recall_macro": 0.9187150647269768,
|
| 1369 |
+
"eval_recall_micro": 0.9189319220591773,
|
| 1370 |
+
"eval_runtime": 8.4421,
|
| 1371 |
+
"eval_samples_per_second": 492.411,
|
| 1372 |
+
"eval_steps_per_second": 61.596,
|
| 1373 |
+
"step": 31000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 3.5876993166287017,
|
| 1377 |
+
"grad_norm": 1.284857153892517,
|
| 1378 |
+
"learning_rate": 2.580946040356764e-06,
|
| 1379 |
+
"loss": 0.0989,
|
| 1380 |
+
"step": 31500
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 3.5876993166287017,
|
| 1384 |
+
"eval_accuracy": 0.9194130382487371,
|
| 1385 |
+
"eval_f1_macro": 0.8981523298720768,
|
| 1386 |
+
"eval_f1_micro": 0.9194130382487371,
|
| 1387 |
+
"eval_loss": 0.5652771592140198,
|
| 1388 |
+
"eval_precision_macro": 0.8854580096444836,
|
| 1389 |
+
"eval_precision_micro": 0.9194130382487371,
|
| 1390 |
+
"eval_recall_macro": 0.9219999897271275,
|
| 1391 |
+
"eval_recall_micro": 0.9194130382487371,
|
| 1392 |
+
"eval_runtime": 8.43,
|
| 1393 |
+
"eval_samples_per_second": 493.122,
|
| 1394 |
+
"eval_steps_per_second": 61.685,
|
| 1395 |
+
"step": 31500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.644646924829157,
|
| 1399 |
+
"grad_norm": 1.4339042901992798,
|
| 1400 |
+
"learning_rate": 1.9249490290167914e-06,
|
| 1401 |
+
"loss": 0.0989,
|
| 1402 |
+
"step": 32000
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 3.644646924829157,
|
| 1406 |
+
"eval_accuracy": 0.9138802020687996,
|
| 1407 |
+
"eval_f1_macro": 0.89412218234686,
|
| 1408 |
+
"eval_f1_micro": 0.9138802020687996,
|
| 1409 |
+
"eval_loss": 0.6019502282142639,
|
| 1410 |
+
"eval_precision_macro": 0.882568682117879,
|
| 1411 |
+
"eval_precision_micro": 0.9138802020687996,
|
| 1412 |
+
"eval_recall_macro": 0.9175339639156622,
|
| 1413 |
+
"eval_recall_micro": 0.9138802020687996,
|
| 1414 |
+
"eval_runtime": 8.4297,
|
| 1415 |
+
"eval_samples_per_second": 493.138,
|
| 1416 |
+
"eval_steps_per_second": 61.687,
|
| 1417 |
+
"step": 32000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.7015945330296125,
|
| 1421 |
+
"grad_norm": 0.7662363648414612,
|
| 1422 |
+
"learning_rate": 1.3629669484372722e-06,
|
| 1423 |
+
"loss": 0.0876,
|
| 1424 |
+
"step": 32500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.7015945330296125,
|
| 1428 |
+
"eval_accuracy": 0.9167668992061583,
|
| 1429 |
+
"eval_f1_macro": 0.8960433945398601,
|
| 1430 |
+
"eval_f1_micro": 0.9167668992061583,
|
| 1431 |
+
"eval_loss": 0.578229546546936,
|
| 1432 |
+
"eval_precision_macro": 0.8823539415499122,
|
| 1433 |
+
"eval_precision_micro": 0.9167668992061583,
|
| 1434 |
+
"eval_recall_macro": 0.9211442367709737,
|
| 1435 |
+
"eval_recall_micro": 0.9167668992061583,
|
| 1436 |
+
"eval_runtime": 8.4419,
|
| 1437 |
+
"eval_samples_per_second": 492.426,
|
| 1438 |
+
"eval_steps_per_second": 61.598,
|
| 1439 |
+
"step": 32500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 3.7585421412300684,
|
| 1443 |
+
"grad_norm": 0.8838233947753906,
|
| 1444 |
+
"learning_rate": 8.963874449915156e-07,
|
| 1445 |
+
"loss": 0.1004,
|
| 1446 |
+
"step": 33000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 3.7585421412300684,
|
| 1450 |
+
"eval_accuracy": 0.9186913639643974,
|
| 1451 |
+
"eval_f1_macro": 0.8974164477796313,
|
| 1452 |
+
"eval_f1_micro": 0.9186913639643974,
|
| 1453 |
+
"eval_loss": 0.5638399720191956,
|
| 1454 |
+
"eval_precision_macro": 0.8850042534249818,
|
| 1455 |
+
"eval_precision_micro": 0.9186913639643974,
|
| 1456 |
+
"eval_recall_macro": 0.9204573653096998,
|
| 1457 |
+
"eval_recall_micro": 0.9186913639643974,
|
| 1458 |
+
"eval_runtime": 8.4287,
|
| 1459 |
+
"eval_samples_per_second": 493.198,
|
| 1460 |
+
"eval_steps_per_second": 61.694,
|
| 1461 |
+
"step": 33000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 3.8154897494305238,
|
| 1465 |
+
"grad_norm": 0.8862270712852478,
|
| 1466 |
+
"learning_rate": 5.263625969720654e-07,
|
| 1467 |
+
"loss": 0.1163,
|
| 1468 |
+
"step": 33500
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 3.8154897494305238,
|
| 1472 |
+
"eval_accuracy": 0.9189319220591773,
|
| 1473 |
+
"eval_f1_macro": 0.8978554181419179,
|
| 1474 |
+
"eval_f1_micro": 0.9189319220591773,
|
| 1475 |
+
"eval_loss": 0.5575982332229614,
|
| 1476 |
+
"eval_precision_macro": 0.8842809438001717,
|
| 1477 |
+
"eval_precision_micro": 0.9189319220591773,
|
| 1478 |
+
"eval_recall_macro": 0.9207880969765441,
|
| 1479 |
+
"eval_recall_micro": 0.9189319220591773,
|
| 1480 |
+
"eval_runtime": 8.4411,
|
| 1481 |
+
"eval_samples_per_second": 492.47,
|
| 1482 |
+
"eval_steps_per_second": 61.603,
|
| 1483 |
+
"step": 33500
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 3.8724373576309796,
|
| 1487 |
+
"grad_norm": 0.0018380646361038089,
|
| 1488 |
+
"learning_rate": 2.5380606987847725e-07,
|
| 1489 |
+
"loss": 0.1014,
|
| 1490 |
+
"step": 34000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 3.8724373576309796,
|
| 1494 |
+
"eval_accuracy": 0.9184508058696175,
|
| 1495 |
+
"eval_f1_macro": 0.8970972466165426,
|
| 1496 |
+
"eval_f1_micro": 0.9184508058696175,
|
| 1497 |
+
"eval_loss": 0.5561444759368896,
|
| 1498 |
+
"eval_precision_macro": 0.8836350789167062,
|
| 1499 |
+
"eval_precision_micro": 0.9184508058696175,
|
| 1500 |
+
"eval_recall_macro": 0.9206973516595941,
|
| 1501 |
+
"eval_recall_micro": 0.9184508058696175,
|
| 1502 |
+
"eval_runtime": 8.432,
|
| 1503 |
+
"eval_samples_per_second": 493.002,
|
| 1504 |
+
"eval_steps_per_second": 61.67,
|
| 1505 |
+
"step": 34000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.929384965831435,
|
| 1509 |
+
"grad_norm": 1.3534623384475708,
|
| 1510 |
+
"learning_rate": 7.939086039413291e-08,
|
| 1511 |
+
"loss": 0.0948,
|
| 1512 |
+
"step": 34500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 3.929384965831435,
|
| 1516 |
+
"eval_accuracy": 0.9191724801539571,
|
| 1517 |
+
"eval_f1_macro": 0.8982632597992836,
|
| 1518 |
+
"eval_f1_micro": 0.9191724801539571,
|
| 1519 |
+
"eval_loss": 0.5567488074302673,
|
| 1520 |
+
"eval_precision_macro": 0.8854065999210586,
|
| 1521 |
+
"eval_precision_micro": 0.9191724801539571,
|
| 1522 |
+
"eval_recall_macro": 0.9212323971384597,
|
| 1523 |
+
"eval_recall_micro": 0.9191724801539571,
|
| 1524 |
+
"eval_runtime": 8.4196,
|
| 1525 |
+
"eval_samples_per_second": 493.73,
|
| 1526 |
+
"eval_steps_per_second": 61.761,
|
| 1527 |
+
"step": 34500
|
| 1528 |
+
}
|
| 1529 |
+
],
|
| 1530 |
+
"logging_steps": 500,
|
| 1531 |
+
"max_steps": 35120,
|
| 1532 |
+
"num_input_tokens_seen": 0,
|
| 1533 |
+
"num_train_epochs": 4,
|
| 1534 |
+
"save_steps": 500,
|
| 1535 |
+
"stateful_callbacks": {
|
| 1536 |
+
"TrainerControl": {
|
| 1537 |
+
"args": {
|
| 1538 |
+
"should_epoch_stop": false,
|
| 1539 |
+
"should_evaluate": false,
|
| 1540 |
+
"should_log": false,
|
| 1541 |
+
"should_save": true,
|
| 1542 |
+
"should_training_stop": false
|
| 1543 |
+
},
|
| 1544 |
+
"attributes": {}
|
| 1545 |
+
}
|
| 1546 |
+
},
|
| 1547 |
+
"total_flos": 7.2631039537152e+16,
|
| 1548 |
+
"train_batch_size": 8,
|
| 1549 |
+
"trial_name": null,
|
| 1550 |
+
"trial_params": null
|
| 1551 |
+
}
|
checkpoint-34500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49538db7a2ace12c7d89de1c0011d0ddc0ea3c0b5d2b68c5a1982e226b28b01b
|
| 3 |
+
size 5521
|
checkpoint-34500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-35000/config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "aubmindlab/bert-base-arabertv2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_10": 10,
|
| 40 |
+
"LABEL_11": 11,
|
| 41 |
+
"LABEL_12": 12,
|
| 42 |
+
"LABEL_13": 13,
|
| 43 |
+
"LABEL_14": 14,
|
| 44 |
+
"LABEL_15": 15,
|
| 45 |
+
"LABEL_16": 16,
|
| 46 |
+
"LABEL_17": 17,
|
| 47 |
+
"LABEL_18": 18,
|
| 48 |
+
"LABEL_19": 19,
|
| 49 |
+
"LABEL_2": 2,
|
| 50 |
+
"LABEL_20": 20,
|
| 51 |
+
"LABEL_3": 3,
|
| 52 |
+
"LABEL_4": 4,
|
| 53 |
+
"LABEL_5": 5,
|
| 54 |
+
"LABEL_6": 6,
|
| 55 |
+
"LABEL_7": 7,
|
| 56 |
+
"LABEL_8": 8,
|
| 57 |
+
"LABEL_9": 9
|
| 58 |
+
},
|
| 59 |
+
"layer_norm_eps": 1e-12,
|
| 60 |
+
"max_position_embeddings": 512,
|
| 61 |
+
"model_type": "bert",
|
| 62 |
+
"num_attention_heads": 12,
|
| 63 |
+
"num_hidden_layers": 12,
|
| 64 |
+
"pad_token_id": 0,
|
| 65 |
+
"position_embedding_type": "absolute",
|
| 66 |
+
"problem_type": "single_label_classification",
|
| 67 |
+
"torch_dtype": "float32",
|
| 68 |
+
"transformers_version": "4.41.2",
|
| 69 |
+
"type_vocab_size": 2,
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 64000
|
| 72 |
+
}
|
checkpoint-35000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0419677be86f5d3b8b35bd2c3eeea72d44383a7c098d48d53b431977dce17386
|
| 3 |
+
size 540861516
|
checkpoint-35000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40bcd6ab7feec46bf51689f0fc6d14cc968b9a88db2e25eb20df3c7c1cc614e8
|
| 3 |
+
size 1081844491
|
checkpoint-35000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:345eb6e8452b31abbac6144b0c26773de44be68c383b6ce8e6ba48780ab49676
|
| 3 |
+
size 14645
|
checkpoint-35000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f2e385a3c01a688d341c79647a06ab2e6ce2c1d0f306eb20f5f7610ebf9fb43
|
| 3 |
+
size 1465
|
checkpoint-35000/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 |
+
}
|
checkpoint-35000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-35000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"mask_token": "[MASK]",
|
| 297 |
+
"max_len": 512,
|
| 298 |
+
"model_max_length": 512,
|
| 299 |
+
"never_split": [
|
| 300 |
+
"+ك",
|
| 301 |
+
"+كما",
|
| 302 |
+
"ك+",
|
| 303 |
+
"+وا",
|
| 304 |
+
"+ين",
|
| 305 |
+
"و+",
|
| 306 |
+
"+كن",
|
| 307 |
+
"+ان",
|
| 308 |
+
"+هم",
|
| 309 |
+
"+ة",
|
| 310 |
+
"[بريد]",
|
| 311 |
+
"لل+",
|
| 312 |
+
"+ي",
|
| 313 |
+
"+ت",
|
| 314 |
+
"+ن",
|
| 315 |
+
"س+",
|
| 316 |
+
"ل+",
|
| 317 |
+
"[مستخدم]",
|
| 318 |
+
"+كم",
|
| 319 |
+
"+ا",
|
| 320 |
+
"ب+",
|
| 321 |
+
"ف+",
|
| 322 |
+
"+نا",
|
| 323 |
+
"+ها",
|
| 324 |
+
"+ون",
|
| 325 |
+
"+هما",
|
| 326 |
+
"ال+",
|
| 327 |
+
"+ه",
|
| 328 |
+
"+هن",
|
| 329 |
+
"+ات",
|
| 330 |
+
"[رابط]"
|
| 331 |
+
],
|
| 332 |
+
"pad_token": "[PAD]",
|
| 333 |
+
"sep_token": "[SEP]",
|
| 334 |
+
"strip_accents": null,
|
| 335 |
+
"tokenize_chinese_chars": true,
|
| 336 |
+
"tokenizer_class": "BertTokenizer",
|
| 337 |
+
"unk_token": "[UNK]"
|
| 338 |
+
}
|
checkpoint-35000/trainer_state.json
ADDED
|
@@ -0,0 +1,1573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8982632597992836,
|
| 3 |
+
"best_model_checkpoint": "./arabert_author_model/checkpoint-34500",
|
| 4 |
+
"epoch": 3.9863325740318905,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 35000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05694760820045558,
|
| 13 |
+
"grad_norm": 15.19107437133789,
|
| 14 |
+
"learning_rate": 1.1343963553530753e-05,
|
| 15 |
+
"loss": 2.7205,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05694760820045558,
|
| 20 |
+
"eval_accuracy": 0.3750300697618475,
|
| 21 |
+
"eval_f1_macro": 0.28596660166175775,
|
| 22 |
+
"eval_f1_micro": 0.3750300697618475,
|
| 23 |
+
"eval_loss": 2.32218337059021,
|
| 24 |
+
"eval_precision_macro": 0.3865217733215992,
|
| 25 |
+
"eval_precision_micro": 0.3750300697618475,
|
| 26 |
+
"eval_recall_macro": 0.3672924033460141,
|
| 27 |
+
"eval_recall_micro": 0.3750300697618475,
|
| 28 |
+
"eval_runtime": 9.1613,
|
| 29 |
+
"eval_samples_per_second": 453.755,
|
| 30 |
+
"eval_steps_per_second": 56.76,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11389521640091116,
|
| 35 |
+
"grad_norm": 21.725738525390625,
|
| 36 |
+
"learning_rate": 2.2710706150341686e-05,
|
| 37 |
+
"loss": 1.6025,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11389521640091116,
|
| 42 |
+
"eval_accuracy": 0.4892951647822949,
|
| 43 |
+
"eval_f1_macro": 0.4406771878616986,
|
| 44 |
+
"eval_f1_micro": 0.4892951647822949,
|
| 45 |
+
"eval_loss": 1.6631975173950195,
|
| 46 |
+
"eval_precision_macro": 0.56733686366756,
|
| 47 |
+
"eval_precision_micro": 0.4892951647822949,
|
| 48 |
+
"eval_recall_macro": 0.48704653807602066,
|
| 49 |
+
"eval_recall_micro": 0.4892951647822949,
|
| 50 |
+
"eval_runtime": 8.477,
|
| 51 |
+
"eval_samples_per_second": 490.385,
|
| 52 |
+
"eval_steps_per_second": 61.342,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.17084282460136674,
|
| 57 |
+
"grad_norm": 13.716214179992676,
|
| 58 |
+
"learning_rate": 3.4100227790432806e-05,
|
| 59 |
+
"loss": 1.0328,
|
| 60 |
+
"step": 1500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.17084282460136674,
|
| 64 |
+
"eval_accuracy": 0.6615347606446957,
|
| 65 |
+
"eval_f1_macro": 0.5830637518928246,
|
| 66 |
+
"eval_f1_micro": 0.6615347606446957,
|
| 67 |
+
"eval_loss": 1.1024270057678223,
|
| 68 |
+
"eval_precision_macro": 0.697472543022928,
|
| 69 |
+
"eval_precision_micro": 0.6615347606446957,
|
| 70 |
+
"eval_recall_macro": 0.6033302465966366,
|
| 71 |
+
"eval_recall_micro": 0.6615347606446957,
|
| 72 |
+
"eval_runtime": 8.4612,
|
| 73 |
+
"eval_samples_per_second": 491.299,
|
| 74 |
+
"eval_steps_per_second": 61.457,
|
| 75 |
+
"step": 1500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.22779043280182232,
|
| 79 |
+
"grad_norm": 17.078737258911133,
|
| 80 |
+
"learning_rate": 4.548974943052392e-05,
|
| 81 |
+
"loss": 0.8504,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.22779043280182232,
|
| 86 |
+
"eval_accuracy": 0.639162857830166,
|
| 87 |
+
"eval_f1_macro": 0.5476482518700577,
|
| 88 |
+
"eval_f1_micro": 0.639162857830166,
|
| 89 |
+
"eval_loss": 1.2488256692886353,
|
| 90 |
+
"eval_precision_macro": 0.668531963924838,
|
| 91 |
+
"eval_precision_micro": 0.639162857830166,
|
| 92 |
+
"eval_recall_macro": 0.5729925283587635,
|
| 93 |
+
"eval_recall_micro": 0.639162857830166,
|
| 94 |
+
"eval_runtime": 8.6485,
|
| 95 |
+
"eval_samples_per_second": 480.664,
|
| 96 |
+
"eval_steps_per_second": 60.126,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.2847380410022779,
|
| 101 |
+
"grad_norm": 45.41240692138672,
|
| 102 |
+
"learning_rate": 5.6856492027334856e-05,
|
| 103 |
+
"loss": 0.7882,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.2847380410022779,
|
| 108 |
+
"eval_accuracy": 0.6523935530430599,
|
| 109 |
+
"eval_f1_macro": 0.5994264876841328,
|
| 110 |
+
"eval_f1_micro": 0.6523935530430599,
|
| 111 |
+
"eval_loss": 1.2463157176971436,
|
| 112 |
+
"eval_precision_macro": 0.6529647074997418,
|
| 113 |
+
"eval_precision_micro": 0.6523935530430599,
|
| 114 |
+
"eval_recall_macro": 0.6436371671271747,
|
| 115 |
+
"eval_recall_micro": 0.6523935530430599,
|
| 116 |
+
"eval_runtime": 8.4613,
|
| 117 |
+
"eval_samples_per_second": 491.293,
|
| 118 |
+
"eval_steps_per_second": 61.456,
|
| 119 |
+
"step": 2500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.3416856492027335,
|
| 123 |
+
"grad_norm": 17.272947311401367,
|
| 124 |
+
"learning_rate": 6.824601366742597e-05,
|
| 125 |
+
"loss": 0.8087,
|
| 126 |
+
"step": 3000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.3416856492027335,
|
| 130 |
+
"eval_accuracy": 0.7055568919894154,
|
| 131 |
+
"eval_f1_macro": 0.6265017927625092,
|
| 132 |
+
"eval_f1_micro": 0.7055568919894154,
|
| 133 |
+
"eval_loss": 1.2766073942184448,
|
| 134 |
+
"eval_precision_macro": 0.6878658131219406,
|
| 135 |
+
"eval_precision_micro": 0.7055568919894154,
|
| 136 |
+
"eval_recall_macro": 0.6658140911489481,
|
| 137 |
+
"eval_recall_micro": 0.7055568919894154,
|
| 138 |
+
"eval_runtime": 8.9536,
|
| 139 |
+
"eval_samples_per_second": 464.281,
|
| 140 |
+
"eval_steps_per_second": 58.077,
|
| 141 |
+
"step": 3000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.39863325740318906,
|
| 145 |
+
"grad_norm": 36.27668380737305,
|
| 146 |
+
"learning_rate": 7.96355353075171e-05,
|
| 147 |
+
"loss": 0.7887,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.39863325740318906,
|
| 152 |
+
"eval_accuracy": 0.7149386576858311,
|
| 153 |
+
"eval_f1_macro": 0.6616726950770662,
|
| 154 |
+
"eval_f1_micro": 0.7149386576858311,
|
| 155 |
+
"eval_loss": 1.1627144813537598,
|
| 156 |
+
"eval_precision_macro": 0.7514554135519156,
|
| 157 |
+
"eval_precision_micro": 0.7149386576858311,
|
| 158 |
+
"eval_recall_macro": 0.6834968200252539,
|
| 159 |
+
"eval_recall_micro": 0.7149386576858311,
|
| 160 |
+
"eval_runtime": 8.4816,
|
| 161 |
+
"eval_samples_per_second": 490.118,
|
| 162 |
+
"eval_steps_per_second": 61.309,
|
| 163 |
+
"step": 3500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.45558086560364464,
|
| 167 |
+
"grad_norm": 3.0386502742767334,
|
| 168 |
+
"learning_rate": 7.995372539966228e-05,
|
| 169 |
+
"loss": 0.7357,
|
| 170 |
+
"step": 4000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.45558086560364464,
|
| 174 |
+
"eval_accuracy": 0.7611258118835699,
|
| 175 |
+
"eval_f1_macro": 0.6745353046335729,
|
| 176 |
+
"eval_f1_micro": 0.7611258118835699,
|
| 177 |
+
"eval_loss": 0.9807717800140381,
|
| 178 |
+
"eval_precision_macro": 0.7007756446431578,
|
| 179 |
+
"eval_precision_micro": 0.7611258118835699,
|
| 180 |
+
"eval_recall_macro": 0.7425048520300992,
|
| 181 |
+
"eval_recall_micro": 0.7611258118835699,
|
| 182 |
+
"eval_runtime": 8.4828,
|
| 183 |
+
"eval_samples_per_second": 490.05,
|
| 184 |
+
"eval_steps_per_second": 61.3,
|
| 185 |
+
"step": 4000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5125284738041003,
|
| 189 |
+
"grad_norm": 2.7381744384765625,
|
| 190 |
+
"learning_rate": 7.980884762455173e-05,
|
| 191 |
+
"loss": 0.7022,
|
| 192 |
+
"step": 4500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.5125284738041003,
|
| 196 |
+
"eval_accuracy": 0.76088525378879,
|
| 197 |
+
"eval_f1_macro": 0.6871238458955197,
|
| 198 |
+
"eval_f1_micro": 0.76088525378879,
|
| 199 |
+
"eval_loss": 1.1158560514450073,
|
| 200 |
+
"eval_precision_macro": 0.7591168248124284,
|
| 201 |
+
"eval_precision_micro": 0.76088525378879,
|
| 202 |
+
"eval_recall_macro": 0.7099914791461782,
|
| 203 |
+
"eval_recall_micro": 0.76088525378879,
|
| 204 |
+
"eval_runtime": 9.0538,
|
| 205 |
+
"eval_samples_per_second": 459.145,
|
| 206 |
+
"eval_steps_per_second": 57.435,
|
| 207 |
+
"step": 4500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5694760820045558,
|
| 211 |
+
"grad_norm": 32.207054138183594,
|
| 212 |
+
"learning_rate": 7.956625791551662e-05,
|
| 213 |
+
"loss": 0.6587,
|
| 214 |
+
"step": 5000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.5694760820045558,
|
| 218 |
+
"eval_accuracy": 0.8008178975222516,
|
| 219 |
+
"eval_f1_macro": 0.76243086871798,
|
| 220 |
+
"eval_f1_micro": 0.8008178975222516,
|
| 221 |
+
"eval_loss": 0.8932181000709534,
|
| 222 |
+
"eval_precision_macro": 0.7876270109291943,
|
| 223 |
+
"eval_precision_micro": 0.8008178975222516,
|
| 224 |
+
"eval_recall_macro": 0.7876260076814952,
|
| 225 |
+
"eval_recall_micro": 0.8008178975222516,
|
| 226 |
+
"eval_runtime": 8.5148,
|
| 227 |
+
"eval_samples_per_second": 488.207,
|
| 228 |
+
"eval_steps_per_second": 61.07,
|
| 229 |
+
"step": 5000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.6264236902050114,
|
| 233 |
+
"grad_norm": 0.29054978489875793,
|
| 234 |
+
"learning_rate": 7.922558317223566e-05,
|
| 235 |
+
"loss": 0.5719,
|
| 236 |
+
"step": 5500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.6264236902050114,
|
| 240 |
+
"eval_accuracy": 0.773875390906904,
|
| 241 |
+
"eval_f1_macro": 0.7249768597960354,
|
| 242 |
+
"eval_f1_micro": 0.773875390906904,
|
| 243 |
+
"eval_loss": 0.9966481328010559,
|
| 244 |
+
"eval_precision_macro": 0.7358501532705917,
|
| 245 |
+
"eval_precision_micro": 0.773875390906904,
|
| 246 |
+
"eval_recall_macro": 0.7614420126439011,
|
| 247 |
+
"eval_recall_micro": 0.773875390906904,
|
| 248 |
+
"eval_runtime": 8.4793,
|
| 249 |
+
"eval_samples_per_second": 490.251,
|
| 250 |
+
"eval_steps_per_second": 61.326,
|
| 251 |
+
"step": 5500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.683371298405467,
|
| 255 |
+
"grad_norm": 1.0872896909713745,
|
| 256 |
+
"learning_rate": 7.878805260363261e-05,
|
| 257 |
+
"loss": 0.6425,
|
| 258 |
+
"step": 6000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.683371298405467,
|
| 262 |
+
"eval_accuracy": 0.771710368053885,
|
| 263 |
+
"eval_f1_macro": 0.7254677224325083,
|
| 264 |
+
"eval_f1_micro": 0.771710368053885,
|
| 265 |
+
"eval_loss": 0.9605371952056885,
|
| 266 |
+
"eval_precision_macro": 0.8005336996598393,
|
| 267 |
+
"eval_precision_micro": 0.771710368053885,
|
| 268 |
+
"eval_recall_macro": 0.7547512504988463,
|
| 269 |
+
"eval_recall_micro": 0.771710368053885,
|
| 270 |
+
"eval_runtime": 8.4743,
|
| 271 |
+
"eval_samples_per_second": 490.54,
|
| 272 |
+
"eval_steps_per_second": 61.362,
|
| 273 |
+
"step": 6000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.7403189066059226,
|
| 277 |
+
"grad_norm": 189.1195068359375,
|
| 278 |
+
"learning_rate": 7.82547465603587e-05,
|
| 279 |
+
"loss": 0.5433,
|
| 280 |
+
"step": 6500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7403189066059226,
|
| 284 |
+
"eval_accuracy": 0.7700264613904257,
|
| 285 |
+
"eval_f1_macro": 0.740451647791416,
|
| 286 |
+
"eval_f1_micro": 0.7700264613904257,
|
| 287 |
+
"eval_loss": 1.0783036947250366,
|
| 288 |
+
"eval_precision_macro": 0.769666104173451,
|
| 289 |
+
"eval_precision_micro": 0.7700264613904257,
|
| 290 |
+
"eval_recall_macro": 0.7659213860833466,
|
| 291 |
+
"eval_recall_micro": 0.7700264613904257,
|
| 292 |
+
"eval_runtime": 8.4608,
|
| 293 |
+
"eval_samples_per_second": 491.328,
|
| 294 |
+
"eval_steps_per_second": 61.46,
|
| 295 |
+
"step": 6500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.7972665148063781,
|
| 299 |
+
"grad_norm": 0.5625237822532654,
|
| 300 |
+
"learning_rate": 7.762833068916386e-05,
|
| 301 |
+
"loss": 0.5736,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.7972665148063781,
|
| 306 |
+
"eval_accuracy": 0.7782054366129421,
|
| 307 |
+
"eval_f1_macro": 0.6779030343365783,
|
| 308 |
+
"eval_f1_micro": 0.7782054366129421,
|
| 309 |
+
"eval_loss": 1.0509027242660522,
|
| 310 |
+
"eval_precision_macro": 0.7339555194909612,
|
| 311 |
+
"eval_precision_micro": 0.7782054366129421,
|
| 312 |
+
"eval_recall_macro": 0.6828886626680506,
|
| 313 |
+
"eval_recall_micro": 0.7782054366129421,
|
| 314 |
+
"eval_runtime": 8.481,
|
| 315 |
+
"eval_samples_per_second": 490.156,
|
| 316 |
+
"eval_steps_per_second": 61.314,
|
| 317 |
+
"step": 7000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8542141230068337,
|
| 321 |
+
"grad_norm": 64.8875503540039,
|
| 322 |
+
"learning_rate": 7.690784156928418e-05,
|
| 323 |
+
"loss": 0.5273,
|
| 324 |
+
"step": 7500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8542141230068337,
|
| 328 |
+
"eval_accuracy": 0.7774837623286024,
|
| 329 |
+
"eval_f1_macro": 0.7006759117702724,
|
| 330 |
+
"eval_f1_micro": 0.7774837623286024,
|
| 331 |
+
"eval_loss": 1.083090901374817,
|
| 332 |
+
"eval_precision_macro": 0.7615638623524419,
|
| 333 |
+
"eval_precision_micro": 0.7774837623286024,
|
| 334 |
+
"eval_recall_macro": 0.7385809772355115,
|
| 335 |
+
"eval_recall_micro": 0.7774837623286024,
|
| 336 |
+
"eval_runtime": 8.4704,
|
| 337 |
+
"eval_samples_per_second": 490.769,
|
| 338 |
+
"eval_steps_per_second": 61.39,
|
| 339 |
+
"step": 7500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9111617312072893,
|
| 343 |
+
"grad_norm": 0.9078112840652466,
|
| 344 |
+
"learning_rate": 7.609621959255558e-05,
|
| 345 |
+
"loss": 0.5268,
|
| 346 |
+
"step": 8000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9111617312072893,
|
| 350 |
+
"eval_accuracy": 0.7445273033437575,
|
| 351 |
+
"eval_f1_macro": 0.699580887402278,
|
| 352 |
+
"eval_f1_micro": 0.7445273033437575,
|
| 353 |
+
"eval_loss": 1.3979923725128174,
|
| 354 |
+
"eval_precision_macro": 0.7001048011829232,
|
| 355 |
+
"eval_precision_micro": 0.7445273033437575,
|
| 356 |
+
"eval_recall_macro": 0.7726266308290096,
|
| 357 |
+
"eval_recall_micro": 0.7445273033437575,
|
| 358 |
+
"eval_runtime": 8.4384,
|
| 359 |
+
"eval_samples_per_second": 492.631,
|
| 360 |
+
"eval_steps_per_second": 61.623,
|
| 361 |
+
"step": 8000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.9681093394077449,
|
| 365 |
+
"grad_norm": 42.65549850463867,
|
| 366 |
+
"learning_rate": 7.519735782617663e-05,
|
| 367 |
+
"loss": 0.5462,
|
| 368 |
+
"step": 8500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.9681093394077449,
|
| 372 |
+
"eval_accuracy": 0.8287226365167187,
|
| 373 |
+
"eval_f1_macro": 0.7785313462283256,
|
| 374 |
+
"eval_f1_micro": 0.8287226365167187,
|
| 375 |
+
"eval_loss": 0.9026873111724854,
|
| 376 |
+
"eval_precision_macro": 0.7868255645583773,
|
| 377 |
+
"eval_precision_micro": 0.8287226365167187,
|
| 378 |
+
"eval_recall_macro": 0.8024053906273642,
|
| 379 |
+
"eval_recall_micro": 0.8287226365167187,
|
| 380 |
+
"eval_runtime": 8.4335,
|
| 381 |
+
"eval_samples_per_second": 492.916,
|
| 382 |
+
"eval_steps_per_second": 61.659,
|
| 383 |
+
"step": 8500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.0250569476082005,
|
| 387 |
+
"grad_norm": 0.9462873935699463,
|
| 388 |
+
"learning_rate": 7.420987383057407e-05,
|
| 389 |
+
"loss": 0.486,
|
| 390 |
+
"step": 9000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.0250569476082005,
|
| 394 |
+
"eval_accuracy": 0.7211931681501083,
|
| 395 |
+
"eval_f1_macro": 0.6932948143152837,
|
| 396 |
+
"eval_f1_micro": 0.7211931681501083,
|
| 397 |
+
"eval_loss": 1.7263842821121216,
|
| 398 |
+
"eval_precision_macro": 0.7360552900892146,
|
| 399 |
+
"eval_precision_micro": 0.7211931681501083,
|
| 400 |
+
"eval_recall_macro": 0.7409941847523269,
|
| 401 |
+
"eval_recall_micro": 0.7211931681501083,
|
| 402 |
+
"eval_runtime": 8.473,
|
| 403 |
+
"eval_samples_per_second": 490.615,
|
| 404 |
+
"eval_steps_per_second": 61.371,
|
| 405 |
+
"step": 9000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.082004555808656,
|
| 409 |
+
"grad_norm": 0.8366897106170654,
|
| 410 |
+
"learning_rate": 7.314014528807089e-05,
|
| 411 |
+
"loss": 0.4458,
|
| 412 |
+
"step": 9500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.082004555808656,
|
| 416 |
+
"eval_accuracy": 0.8186191965359635,
|
| 417 |
+
"eval_f1_macro": 0.7675006381723768,
|
| 418 |
+
"eval_f1_micro": 0.8186191965359635,
|
| 419 |
+
"eval_loss": 0.9773014783859253,
|
| 420 |
+
"eval_precision_macro": 0.7844621076644617,
|
| 421 |
+
"eval_precision_micro": 0.8186191965359635,
|
| 422 |
+
"eval_recall_macro": 0.8041851318048103,
|
| 423 |
+
"eval_recall_micro": 0.8186191965359635,
|
| 424 |
+
"eval_runtime": 8.4706,
|
| 425 |
+
"eval_samples_per_second": 490.754,
|
| 426 |
+
"eval_steps_per_second": 61.389,
|
| 427 |
+
"step": 9500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.1389521640091116,
|
| 431 |
+
"grad_norm": 2.115098237991333,
|
| 432 |
+
"learning_rate": 7.198652696785955e-05,
|
| 433 |
+
"loss": 0.4102,
|
| 434 |
+
"step": 10000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.1389521640091116,
|
| 438 |
+
"eval_accuracy": 0.8316093336540774,
|
| 439 |
+
"eval_f1_macro": 0.7933624073358755,
|
| 440 |
+
"eval_f1_micro": 0.8316093336540774,
|
| 441 |
+
"eval_loss": 0.967036247253418,
|
| 442 |
+
"eval_precision_macro": 0.7949251475033909,
|
| 443 |
+
"eval_precision_micro": 0.8316093336540774,
|
| 444 |
+
"eval_recall_macro": 0.8274655786829063,
|
| 445 |
+
"eval_recall_micro": 0.8316093336540774,
|
| 446 |
+
"eval_runtime": 8.4509,
|
| 447 |
+
"eval_samples_per_second": 491.9,
|
| 448 |
+
"eval_steps_per_second": 61.532,
|
| 449 |
+
"step": 10000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.1958997722095672,
|
| 453 |
+
"grad_norm": 1.0413740873336792,
|
| 454 |
+
"learning_rate": 7.075392750273938e-05,
|
| 455 |
+
"loss": 0.3773,
|
| 456 |
+
"step": 10500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.1958997722095672,
|
| 460 |
+
"eval_accuracy": 0.8171758479672842,
|
| 461 |
+
"eval_f1_macro": 0.7981622962245145,
|
| 462 |
+
"eval_f1_micro": 0.8171758479672842,
|
| 463 |
+
"eval_loss": 0.9198176860809326,
|
| 464 |
+
"eval_precision_macro": 0.819291401144176,
|
| 465 |
+
"eval_precision_micro": 0.8171758479672842,
|
| 466 |
+
"eval_recall_macro": 0.8245482183363974,
|
| 467 |
+
"eval_recall_micro": 0.8171758479672842,
|
| 468 |
+
"eval_runtime": 8.4577,
|
| 469 |
+
"eval_samples_per_second": 491.505,
|
| 470 |
+
"eval_steps_per_second": 61.482,
|
| 471 |
+
"step": 10500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.2528473804100229,
|
| 475 |
+
"grad_norm": 7.1126203536987305,
|
| 476 |
+
"learning_rate": 6.94453904277921e-05,
|
| 477 |
+
"loss": 0.3796,
|
| 478 |
+
"step": 11000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.2528473804100229,
|
| 482 |
+
"eval_accuracy": 0.7741159490016839,
|
| 483 |
+
"eval_f1_macro": 0.7334267874337288,
|
| 484 |
+
"eval_f1_micro": 0.7741159490016839,
|
| 485 |
+
"eval_loss": 1.324471116065979,
|
| 486 |
+
"eval_precision_macro": 0.7554977548108798,
|
| 487 |
+
"eval_precision_micro": 0.7741159490016839,
|
| 488 |
+
"eval_recall_macro": 0.7865189643712818,
|
| 489 |
+
"eval_recall_micro": 0.7741159490016839,
|
| 490 |
+
"eval_runtime": 8.4546,
|
| 491 |
+
"eval_samples_per_second": 491.688,
|
| 492 |
+
"eval_steps_per_second": 61.505,
|
| 493 |
+
"step": 11000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.3097949886104785,
|
| 497 |
+
"grad_norm": 85.53689575195312,
|
| 498 |
+
"learning_rate": 6.806414678327537e-05,
|
| 499 |
+
"loss": 0.4432,
|
| 500 |
+
"step": 11500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.3097949886104785,
|
| 504 |
+
"eval_accuracy": 0.8092374308395478,
|
| 505 |
+
"eval_f1_macro": 0.7438442519057924,
|
| 506 |
+
"eval_f1_micro": 0.8092374308395478,
|
| 507 |
+
"eval_loss": 1.1105079650878906,
|
| 508 |
+
"eval_precision_macro": 0.7748012629794462,
|
| 509 |
+
"eval_precision_micro": 0.8092374308395478,
|
| 510 |
+
"eval_recall_macro": 0.7783932685192183,
|
| 511 |
+
"eval_recall_micro": 0.8092374308395478,
|
| 512 |
+
"eval_runtime": 8.4968,
|
| 513 |
+
"eval_samples_per_second": 489.244,
|
| 514 |
+
"eval_steps_per_second": 61.2,
|
| 515 |
+
"step": 11500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.366742596810934,
|
| 519 |
+
"grad_norm": 1.0569897890090942,
|
| 520 |
+
"learning_rate": 6.661360713653681e-05,
|
| 521 |
+
"loss": 0.389,
|
| 522 |
+
"step": 12000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.366742596810934,
|
| 526 |
+
"eval_accuracy": 0.8128458022612461,
|
| 527 |
+
"eval_f1_macro": 0.7595338289100665,
|
| 528 |
+
"eval_f1_micro": 0.8128458022612461,
|
| 529 |
+
"eval_loss": 1.0267034769058228,
|
| 530 |
+
"eval_precision_macro": 0.7590761169934961,
|
| 531 |
+
"eval_precision_micro": 0.8128458022612461,
|
| 532 |
+
"eval_recall_macro": 0.8036606747506161,
|
| 533 |
+
"eval_recall_micro": 0.8128458022612461,
|
| 534 |
+
"eval_runtime": 8.4648,
|
| 535 |
+
"eval_samples_per_second": 491.09,
|
| 536 |
+
"eval_steps_per_second": 61.431,
|
| 537 |
+
"step": 12000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.4236902050113895,
|
| 541 |
+
"grad_norm": 14.686357498168945,
|
| 542 |
+
"learning_rate": 6.509735316063996e-05,
|
| 543 |
+
"loss": 0.6087,
|
| 544 |
+
"step": 12500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.4236902050113895,
|
| 548 |
+
"eval_accuracy": 0.8443589126774116,
|
| 549 |
+
"eval_f1_macro": 0.7997974993396904,
|
| 550 |
+
"eval_f1_micro": 0.8443589126774116,
|
| 551 |
+
"eval_loss": 0.9193519353866577,
|
| 552 |
+
"eval_precision_macro": 0.7894219117254144,
|
| 553 |
+
"eval_precision_micro": 0.8443589126774116,
|
| 554 |
+
"eval_recall_macro": 0.833108777347993,
|
| 555 |
+
"eval_recall_micro": 0.8443589126774116,
|
| 556 |
+
"eval_runtime": 8.4379,
|
| 557 |
+
"eval_samples_per_second": 492.657,
|
| 558 |
+
"eval_steps_per_second": 61.627,
|
| 559 |
+
"step": 12500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.4806378132118452,
|
| 563 |
+
"grad_norm": 0.05014890432357788,
|
| 564 |
+
"learning_rate": 6.352234452003862e-05,
|
| 565 |
+
"loss": 0.4803,
|
| 566 |
+
"step": 13000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.4806378132118452,
|
| 570 |
+
"eval_accuracy": 0.8535001202790474,
|
| 571 |
+
"eval_f1_macro": 0.8265458036830905,
|
| 572 |
+
"eval_f1_micro": 0.8535001202790474,
|
| 573 |
+
"eval_loss": 0.879317581653595,
|
| 574 |
+
"eval_precision_macro": 0.8329036145166532,
|
| 575 |
+
"eval_precision_micro": 0.8535001202790474,
|
| 576 |
+
"eval_recall_macro": 0.8340628674797995,
|
| 577 |
+
"eval_recall_micro": 0.8535001202790474,
|
| 578 |
+
"eval_runtime": 8.4157,
|
| 579 |
+
"eval_samples_per_second": 493.96,
|
| 580 |
+
"eval_steps_per_second": 61.79,
|
| 581 |
+
"step": 13000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.5375854214123006,
|
| 585 |
+
"grad_norm": 40.28041076660156,
|
| 586 |
+
"learning_rate": 6.188948654276723e-05,
|
| 587 |
+
"loss": 0.5513,
|
| 588 |
+
"step": 13500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.5375854214123006,
|
| 592 |
+
"eval_accuracy": 0.7782054366129421,
|
| 593 |
+
"eval_f1_macro": 0.7066835334217871,
|
| 594 |
+
"eval_f1_micro": 0.7782054366129421,
|
| 595 |
+
"eval_loss": 1.1909141540527344,
|
| 596 |
+
"eval_precision_macro": 0.7255202837659691,
|
| 597 |
+
"eval_precision_micro": 0.7782054366129421,
|
| 598 |
+
"eval_recall_macro": 0.7402758652568006,
|
| 599 |
+
"eval_recall_micro": 0.7782054366129421,
|
| 600 |
+
"eval_runtime": 8.4835,
|
| 601 |
+
"eval_samples_per_second": 490.012,
|
| 602 |
+
"eval_steps_per_second": 61.296,
|
| 603 |
+
"step": 13500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.5945330296127562,
|
| 607 |
+
"grad_norm": 8.929847717285156,
|
| 608 |
+
"learning_rate": 6.019936353958699e-05,
|
| 609 |
+
"loss": 0.693,
|
| 610 |
+
"step": 14000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.5945330296127562,
|
| 614 |
+
"eval_accuracy": 0.2460909309598268,
|
| 615 |
+
"eval_f1_macro": 0.20336556842910194,
|
| 616 |
+
"eval_f1_micro": 0.2460909309598268,
|
| 617 |
+
"eval_loss": 2.8277578353881836,
|
| 618 |
+
"eval_precision_macro": 0.5226671539146224,
|
| 619 |
+
"eval_precision_micro": 0.2460909309598268,
|
| 620 |
+
"eval_recall_macro": 0.1936798727163823,
|
| 621 |
+
"eval_recall_micro": 0.2460909309598268,
|
| 622 |
+
"eval_runtime": 8.4782,
|
| 623 |
+
"eval_samples_per_second": 490.315,
|
| 624 |
+
"eval_steps_per_second": 61.334,
|
| 625 |
+
"step": 14000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.6514806378132119,
|
| 629 |
+
"grad_norm": 28.1862735748291,
|
| 630 |
+
"learning_rate": 5.8459364260048594e-05,
|
| 631 |
+
"loss": 0.9646,
|
| 632 |
+
"step": 14500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.6514806378132119,
|
| 636 |
+
"eval_accuracy": 0.8246331489054607,
|
| 637 |
+
"eval_f1_macro": 0.7913907456133474,
|
| 638 |
+
"eval_f1_micro": 0.8246331489054607,
|
| 639 |
+
"eval_loss": 0.948131799697876,
|
| 640 |
+
"eval_precision_macro": 0.799701208597097,
|
| 641 |
+
"eval_precision_micro": 0.8246331489054607,
|
| 642 |
+
"eval_recall_macro": 0.8123299807423895,
|
| 643 |
+
"eval_recall_micro": 0.8246331489054607,
|
| 644 |
+
"eval_runtime": 8.4643,
|
| 645 |
+
"eval_samples_per_second": 491.124,
|
| 646 |
+
"eval_steps_per_second": 61.435,
|
| 647 |
+
"step": 14500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.7084282460136673,
|
| 651 |
+
"grad_norm": 7.083284854888916,
|
| 652 |
+
"learning_rate": 5.6673785111054136e-05,
|
| 653 |
+
"loss": 0.462,
|
| 654 |
+
"step": 15000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.7084282460136673,
|
| 658 |
+
"eval_accuracy": 0.8472456098147703,
|
| 659 |
+
"eval_f1_macro": 0.8091993297668394,
|
| 660 |
+
"eval_f1_micro": 0.8472456098147703,
|
| 661 |
+
"eval_loss": 0.8667464256286621,
|
| 662 |
+
"eval_precision_macro": 0.8198322314440802,
|
| 663 |
+
"eval_precision_micro": 0.8472456098147703,
|
| 664 |
+
"eval_recall_macro": 0.8266325847969769,
|
| 665 |
+
"eval_recall_micro": 0.8472456098147703,
|
| 666 |
+
"eval_runtime": 8.4589,
|
| 667 |
+
"eval_samples_per_second": 491.435,
|
| 668 |
+
"eval_steps_per_second": 61.474,
|
| 669 |
+
"step": 15000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.7653758542141231,
|
| 673 |
+
"grad_norm": 65.16443634033203,
|
| 674 |
+
"learning_rate": 5.484703504533721e-05,
|
| 675 |
+
"loss": 0.4093,
|
| 676 |
+
"step": 15500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.7653758542141231,
|
| 680 |
+
"eval_accuracy": 0.8116430117873467,
|
| 681 |
+
"eval_f1_macro": 0.7700885656504642,
|
| 682 |
+
"eval_f1_micro": 0.8116430117873467,
|
| 683 |
+
"eval_loss": 1.1932649612426758,
|
| 684 |
+
"eval_precision_macro": 0.8232095109547221,
|
| 685 |
+
"eval_precision_micro": 0.8116430117873467,
|
| 686 |
+
"eval_recall_macro": 0.775800293436143,
|
| 687 |
+
"eval_recall_micro": 0.8116430117873467,
|
| 688 |
+
"eval_runtime": 8.4735,
|
| 689 |
+
"eval_samples_per_second": 490.589,
|
| 690 |
+
"eval_steps_per_second": 61.368,
|
| 691 |
+
"step": 15500
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.8223234624145785,
|
| 695 |
+
"grad_norm": 15.238636016845703,
|
| 696 |
+
"learning_rate": 5.2983624674875084e-05,
|
| 697 |
+
"loss": 0.349,
|
| 698 |
+
"step": 16000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.8223234624145785,
|
| 702 |
+
"eval_accuracy": 0.8799615107048352,
|
| 703 |
+
"eval_f1_macro": 0.8377281287378512,
|
| 704 |
+
"eval_f1_micro": 0.8799615107048352,
|
| 705 |
+
"eval_loss": 0.7749123573303223,
|
| 706 |
+
"eval_precision_macro": 0.8358272736538074,
|
| 707 |
+
"eval_precision_micro": 0.8799615107048352,
|
| 708 |
+
"eval_recall_macro": 0.8723899950094214,
|
| 709 |
+
"eval_recall_micro": 0.8799615107048352,
|
| 710 |
+
"eval_runtime": 8.4617,
|
| 711 |
+
"eval_samples_per_second": 491.272,
|
| 712 |
+
"eval_steps_per_second": 61.453,
|
| 713 |
+
"step": 16000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.8792710706150342,
|
| 717 |
+
"grad_norm": 1.931815505027771,
|
| 718 |
+
"learning_rate": 5.108815513328386e-05,
|
| 719 |
+
"loss": 0.3333,
|
| 720 |
+
"step": 16500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.8792710706150342,
|
| 724 |
+
"eval_accuracy": 0.8799615107048352,
|
| 725 |
+
"eval_f1_macro": 0.851689807067872,
|
| 726 |
+
"eval_f1_micro": 0.8799615107048352,
|
| 727 |
+
"eval_loss": 0.6482954025268555,
|
| 728 |
+
"eval_precision_macro": 0.8439980638748368,
|
| 729 |
+
"eval_precision_micro": 0.8799615107048352,
|
| 730 |
+
"eval_recall_macro": 0.8709009740944947,
|
| 731 |
+
"eval_recall_micro": 0.8799615107048352,
|
| 732 |
+
"eval_runtime": 8.4707,
|
| 733 |
+
"eval_samples_per_second": 490.751,
|
| 734 |
+
"eval_steps_per_second": 61.388,
|
| 735 |
+
"step": 16500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.9362186788154898,
|
| 739 |
+
"grad_norm": 14.734030723571777,
|
| 740 |
+
"learning_rate": 4.916530671469754e-05,
|
| 741 |
+
"loss": 0.3449,
|
| 742 |
+
"step": 17000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.9362186788154898,
|
| 746 |
+
"eval_accuracy": 0.7890305508780371,
|
| 747 |
+
"eval_f1_macro": 0.7375164837600725,
|
| 748 |
+
"eval_f1_micro": 0.7890305508780371,
|
| 749 |
+
"eval_loss": 1.2130000591278076,
|
| 750 |
+
"eval_precision_macro": 0.7696829158091395,
|
| 751 |
+
"eval_precision_micro": 0.7890305508780371,
|
| 752 |
+
"eval_recall_macro": 0.7545432686041814,
|
| 753 |
+
"eval_recall_micro": 0.7890305508780371,
|
| 754 |
+
"eval_runtime": 8.448,
|
| 755 |
+
"eval_samples_per_second": 492.07,
|
| 756 |
+
"eval_steps_per_second": 61.553,
|
| 757 |
+
"step": 17000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.9931662870159452,
|
| 761 |
+
"grad_norm": 4.0362091064453125,
|
| 762 |
+
"learning_rate": 4.7219827317183907e-05,
|
| 763 |
+
"loss": 0.2982,
|
| 764 |
+
"step": 17500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.9931662870159452,
|
| 768 |
+
"eval_accuracy": 0.8599951888381044,
|
| 769 |
+
"eval_f1_macro": 0.8354955249556116,
|
| 770 |
+
"eval_f1_micro": 0.8599951888381044,
|
| 771 |
+
"eval_loss": 0.8803524374961853,
|
| 772 |
+
"eval_precision_macro": 0.8342493543222153,
|
| 773 |
+
"eval_precision_micro": 0.8599951888381044,
|
| 774 |
+
"eval_recall_macro": 0.8556466165427711,
|
| 775 |
+
"eval_recall_micro": 0.8599951888381044,
|
| 776 |
+
"eval_runtime": 8.4723,
|
| 777 |
+
"eval_samples_per_second": 490.66,
|
| 778 |
+
"eval_steps_per_second": 61.377,
|
| 779 |
+
"step": 17500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.050113895216401,
|
| 783 |
+
"grad_norm": 0.7534123659133911,
|
| 784 |
+
"learning_rate": 4.525652071923279e-05,
|
| 785 |
+
"loss": 0.2348,
|
| 786 |
+
"step": 18000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.050113895216401,
|
| 790 |
+
"eval_accuracy": 0.8448400288669714,
|
| 791 |
+
"eval_f1_macro": 0.8190720986060728,
|
| 792 |
+
"eval_f1_micro": 0.8448400288669714,
|
| 793 |
+
"eval_loss": 1.1245763301849365,
|
| 794 |
+
"eval_precision_macro": 0.8337767355676724,
|
| 795 |
+
"eval_precision_micro": 0.8448400288669714,
|
| 796 |
+
"eval_recall_macro": 0.8557743090961959,
|
| 797 |
+
"eval_recall_micro": 0.8448400288669714,
|
| 798 |
+
"eval_runtime": 8.4721,
|
| 799 |
+
"eval_samples_per_second": 490.667,
|
| 800 |
+
"eval_steps_per_second": 61.378,
|
| 801 |
+
"step": 18000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.1070615034168565,
|
| 805 |
+
"grad_norm": 1.4927374124526978,
|
| 806 |
+
"learning_rate": 4.328023471826429e-05,
|
| 807 |
+
"loss": 0.2299,
|
| 808 |
+
"step": 18500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.1070615034168565,
|
| 812 |
+
"eval_accuracy": 0.8708203031031995,
|
| 813 |
+
"eval_f1_macro": 0.8303241771039817,
|
| 814 |
+
"eval_f1_micro": 0.8708203031031995,
|
| 815 |
+
"eval_loss": 0.8329204320907593,
|
| 816 |
+
"eval_precision_macro": 0.83267401976066,
|
| 817 |
+
"eval_precision_micro": 0.8708203031031995,
|
| 818 |
+
"eval_recall_macro": 0.8610797711013763,
|
| 819 |
+
"eval_recall_micro": 0.8708203031031995,
|
| 820 |
+
"eval_runtime": 8.4578,
|
| 821 |
+
"eval_samples_per_second": 491.498,
|
| 822 |
+
"eval_steps_per_second": 61.482,
|
| 823 |
+
"step": 18500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.164009111617312,
|
| 827 |
+
"grad_norm": 1.7383619546890259,
|
| 828 |
+
"learning_rate": 4.129584916044555e-05,
|
| 829 |
+
"loss": 0.2468,
|
| 830 |
+
"step": 19000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.164009111617312,
|
| 834 |
+
"eval_accuracy": 0.8773153716622565,
|
| 835 |
+
"eval_f1_macro": 0.846177762458016,
|
| 836 |
+
"eval_f1_micro": 0.8773153716622565,
|
| 837 |
+
"eval_loss": 0.7664415836334229,
|
| 838 |
+
"eval_precision_macro": 0.8368864405451267,
|
| 839 |
+
"eval_precision_micro": 0.8773153716622565,
|
| 840 |
+
"eval_recall_macro": 0.8780489137762446,
|
| 841 |
+
"eval_recall_micro": 0.8773153716622565,
|
| 842 |
+
"eval_runtime": 8.4381,
|
| 843 |
+
"eval_samples_per_second": 492.645,
|
| 844 |
+
"eval_steps_per_second": 61.625,
|
| 845 |
+
"step": 19000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.2209567198177678,
|
| 849 |
+
"grad_norm": 400.013916015625,
|
| 850 |
+
"learning_rate": 3.930826389137262e-05,
|
| 851 |
+
"loss": 0.1899,
|
| 852 |
+
"step": 19500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.2209567198177678,
|
| 856 |
+
"eval_accuracy": 0.8862160211691124,
|
| 857 |
+
"eval_f1_macro": 0.8558563382552302,
|
| 858 |
+
"eval_f1_micro": 0.8862160211691124,
|
| 859 |
+
"eval_loss": 0.7495226263999939,
|
| 860 |
+
"eval_precision_macro": 0.8555231307289006,
|
| 861 |
+
"eval_precision_micro": 0.8862160211691124,
|
| 862 |
+
"eval_recall_macro": 0.8758801511510593,
|
| 863 |
+
"eval_recall_micro": 0.8862160211691124,
|
| 864 |
+
"eval_runtime": 8.4445,
|
| 865 |
+
"eval_samples_per_second": 492.274,
|
| 866 |
+
"eval_steps_per_second": 61.579,
|
| 867 |
+
"step": 19500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.277904328018223,
|
| 871 |
+
"grad_norm": 2.0449647903442383,
|
| 872 |
+
"learning_rate": 3.732635344608829e-05,
|
| 873 |
+
"loss": 0.1977,
|
| 874 |
+
"step": 20000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.277904328018223,
|
| 878 |
+
"eval_accuracy": 0.8551840269425066,
|
| 879 |
+
"eval_f1_macro": 0.8198359165864053,
|
| 880 |
+
"eval_f1_micro": 0.8551840269425066,
|
| 881 |
+
"eval_loss": 1.0149922370910645,
|
| 882 |
+
"eval_precision_macro": 0.8328051392132652,
|
| 883 |
+
"eval_precision_micro": 0.8551840269425066,
|
| 884 |
+
"eval_recall_macro": 0.853902169918103,
|
| 885 |
+
"eval_recall_micro": 0.8551840269425066,
|
| 886 |
+
"eval_runtime": 8.4355,
|
| 887 |
+
"eval_samples_per_second": 492.798,
|
| 888 |
+
"eval_steps_per_second": 61.644,
|
| 889 |
+
"step": 20000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.334851936218679,
|
| 893 |
+
"grad_norm": 0.7749654650688171,
|
| 894 |
+
"learning_rate": 3.534706966798757e-05,
|
| 895 |
+
"loss": 0.2314,
|
| 896 |
+
"step": 20500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.334851936218679,
|
| 900 |
+
"eval_accuracy": 0.8948761125811884,
|
| 901 |
+
"eval_f1_macro": 0.8659539030629905,
|
| 902 |
+
"eval_f1_micro": 0.8948761125811884,
|
| 903 |
+
"eval_loss": 0.6898870468139648,
|
| 904 |
+
"eval_precision_macro": 0.8564830162508421,
|
| 905 |
+
"eval_precision_micro": 0.8948761125811884,
|
| 906 |
+
"eval_recall_macro": 0.8978688795664334,
|
| 907 |
+
"eval_recall_micro": 0.8948761125811884,
|
| 908 |
+
"eval_runtime": 8.4412,
|
| 909 |
+
"eval_samples_per_second": 492.466,
|
| 910 |
+
"eval_steps_per_second": 61.603,
|
| 911 |
+
"step": 20500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.3917995444191344,
|
| 915 |
+
"grad_norm": 0.007438243832439184,
|
| 916 |
+
"learning_rate": 3.337927490728384e-05,
|
| 917 |
+
"loss": 0.203,
|
| 918 |
+
"step": 21000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.3917995444191344,
|
| 922 |
+
"eval_accuracy": 0.8984844840028867,
|
| 923 |
+
"eval_f1_macro": 0.8654367599963082,
|
| 924 |
+
"eval_f1_micro": 0.8984844840028867,
|
| 925 |
+
"eval_loss": 0.6225568652153015,
|
| 926 |
+
"eval_precision_macro": 0.8710584795534867,
|
| 927 |
+
"eval_precision_micro": 0.8984844840028867,
|
| 928 |
+
"eval_recall_macro": 0.8907316535034207,
|
| 929 |
+
"eval_recall_micro": 0.8984844840028867,
|
| 930 |
+
"eval_runtime": 8.4582,
|
| 931 |
+
"eval_samples_per_second": 491.477,
|
| 932 |
+
"eval_steps_per_second": 61.479,
|
| 933 |
+
"step": 21000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.44874715261959,
|
| 937 |
+
"grad_norm": 1.0429240465164185,
|
| 938 |
+
"learning_rate": 3.142782804357047e-05,
|
| 939 |
+
"loss": 0.1784,
|
| 940 |
+
"step": 21500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.44874715261959,
|
| 944 |
+
"eval_accuracy": 0.8806831849891749,
|
| 945 |
+
"eval_f1_macro": 0.8516903935082014,
|
| 946 |
+
"eval_f1_micro": 0.8806831849891749,
|
| 947 |
+
"eval_loss": 0.8446455001831055,
|
| 948 |
+
"eval_precision_macro": 0.86002376045135,
|
| 949 |
+
"eval_precision_micro": 0.8806831849891749,
|
| 950 |
+
"eval_recall_macro": 0.8768325982997476,
|
| 951 |
+
"eval_recall_micro": 0.8806831849891749,
|
| 952 |
+
"eval_runtime": 8.4659,
|
| 953 |
+
"eval_samples_per_second": 491.026,
|
| 954 |
+
"eval_steps_per_second": 61.423,
|
| 955 |
+
"step": 21500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.5056947608200457,
|
| 959 |
+
"grad_norm": 89.87359619140625,
|
| 960 |
+
"learning_rate": 2.9497547590207118e-05,
|
| 961 |
+
"loss": 0.2044,
|
| 962 |
+
"step": 22000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.5056947608200457,
|
| 966 |
+
"eval_accuracy": 0.8556651431320664,
|
| 967 |
+
"eval_f1_macro": 0.8466413367690651,
|
| 968 |
+
"eval_f1_micro": 0.8556651431320664,
|
| 969 |
+
"eval_loss": 0.9901952743530273,
|
| 970 |
+
"eval_precision_macro": 0.8512325160929325,
|
| 971 |
+
"eval_precision_micro": 0.8556651431320664,
|
| 972 |
+
"eval_recall_macro": 0.875509109034969,
|
| 973 |
+
"eval_recall_micro": 0.8556651431320664,
|
| 974 |
+
"eval_runtime": 8.5077,
|
| 975 |
+
"eval_samples_per_second": 488.617,
|
| 976 |
+
"eval_steps_per_second": 61.121,
|
| 977 |
+
"step": 22000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.562642369020501,
|
| 981 |
+
"grad_norm": 0.013815644197165966,
|
| 982 |
+
"learning_rate": 2.759319979644478e-05,
|
| 983 |
+
"loss": 0.1914,
|
| 984 |
+
"step": 22500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.562642369020501,
|
| 988 |
+
"eval_accuracy": 0.8927110897281694,
|
| 989 |
+
"eval_f1_macro": 0.8644517343056812,
|
| 990 |
+
"eval_f1_micro": 0.8927110897281694,
|
| 991 |
+
"eval_loss": 0.7158553004264832,
|
| 992 |
+
"eval_precision_macro": 0.8493787111870335,
|
| 993 |
+
"eval_precision_micro": 0.8927110897281694,
|
| 994 |
+
"eval_recall_macro": 0.898066885887026,
|
| 995 |
+
"eval_recall_micro": 0.8927110897281694,
|
| 996 |
+
"eval_runtime": 8.4749,
|
| 997 |
+
"eval_samples_per_second": 490.509,
|
| 998 |
+
"eval_steps_per_second": 61.358,
|
| 999 |
+
"step": 22500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.619589977220957,
|
| 1003 |
+
"grad_norm": 4.245390892028809,
|
| 1004 |
+
"learning_rate": 2.5719486878601176e-05,
|
| 1005 |
+
"loss": 0.1639,
|
| 1006 |
+
"step": 23000
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.619589977220957,
|
| 1010 |
+
"eval_accuracy": 0.8864565792638922,
|
| 1011 |
+
"eval_f1_macro": 0.8458899447458572,
|
| 1012 |
+
"eval_f1_micro": 0.8864565792638922,
|
| 1013 |
+
"eval_loss": 0.729199230670929,
|
| 1014 |
+
"eval_precision_macro": 0.8401968974647541,
|
| 1015 |
+
"eval_precision_micro": 0.8864565792638922,
|
| 1016 |
+
"eval_recall_macro": 0.8805776786360812,
|
| 1017 |
+
"eval_recall_micro": 0.8864565792638922,
|
| 1018 |
+
"eval_runtime": 8.4586,
|
| 1019 |
+
"eval_samples_per_second": 491.451,
|
| 1020 |
+
"eval_steps_per_second": 61.476,
|
| 1021 |
+
"step": 23000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.6765375854214124,
|
| 1025 |
+
"grad_norm": 1.427230715751648,
|
| 1026 |
+
"learning_rate": 2.3881035409346452e-05,
|
| 1027 |
+
"loss": 0.218,
|
| 1028 |
+
"step": 23500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.6765375854214124,
|
| 1032 |
+
"eval_accuracy": 0.8965600192446476,
|
| 1033 |
+
"eval_f1_macro": 0.8710100150868682,
|
| 1034 |
+
"eval_f1_micro": 0.8965600192446476,
|
| 1035 |
+
"eval_loss": 0.6507639288902283,
|
| 1036 |
+
"eval_precision_macro": 0.8627987859589317,
|
| 1037 |
+
"eval_precision_micro": 0.8965600192446476,
|
| 1038 |
+
"eval_recall_macro": 0.8951286903819264,
|
| 1039 |
+
"eval_recall_micro": 0.8965600192446476,
|
| 1040 |
+
"eval_runtime": 8.4672,
|
| 1041 |
+
"eval_samples_per_second": 490.955,
|
| 1042 |
+
"eval_steps_per_second": 61.414,
|
| 1043 |
+
"step": 23500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.733485193621868,
|
| 1047 |
+
"grad_norm": 0.07296980172395706,
|
| 1048 |
+
"learning_rate": 2.208238489376805e-05,
|
| 1049 |
+
"loss": 0.1723,
|
| 1050 |
+
"step": 24000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.733485193621868,
|
| 1054 |
+
"eval_accuracy": 0.9023334135193649,
|
| 1055 |
+
"eval_f1_macro": 0.8816239296246752,
|
| 1056 |
+
"eval_f1_micro": 0.9023334135193649,
|
| 1057 |
+
"eval_loss": 0.6424487233161926,
|
| 1058 |
+
"eval_precision_macro": 0.8835852425011356,
|
| 1059 |
+
"eval_precision_micro": 0.9023334135193649,
|
| 1060 |
+
"eval_recall_macro": 0.8920920740693067,
|
| 1061 |
+
"eval_recall_micro": 0.9023334135193649,
|
| 1062 |
+
"eval_runtime": 8.4613,
|
| 1063 |
+
"eval_samples_per_second": 491.296,
|
| 1064 |
+
"eval_steps_per_second": 61.456,
|
| 1065 |
+
"step": 24000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.7904328018223232,
|
| 1069 |
+
"grad_norm": 125.23475646972656,
|
| 1070 |
+
"learning_rate": 2.0331438324793375e-05,
|
| 1071 |
+
"loss": 0.1682,
|
| 1072 |
+
"step": 24500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.7904328018223232,
|
| 1076 |
+
"eval_accuracy": 0.8972816935289872,
|
| 1077 |
+
"eval_f1_macro": 0.8822737330613647,
|
| 1078 |
+
"eval_f1_micro": 0.8972816935289872,
|
| 1079 |
+
"eval_loss": 0.6842340230941772,
|
| 1080 |
+
"eval_precision_macro": 0.8827282408108892,
|
| 1081 |
+
"eval_precision_micro": 0.8972816935289872,
|
| 1082 |
+
"eval_recall_macro": 0.8944889961638287,
|
| 1083 |
+
"eval_recall_micro": 0.8972816935289872,
|
| 1084 |
+
"eval_runtime": 8.4764,
|
| 1085 |
+
"eval_samples_per_second": 490.419,
|
| 1086 |
+
"eval_steps_per_second": 61.347,
|
| 1087 |
+
"step": 24500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.847380410022779,
|
| 1091 |
+
"grad_norm": 0.5098503828048706,
|
| 1092 |
+
"learning_rate": 1.8628863347570347e-05,
|
| 1093 |
+
"loss": 0.1441,
|
| 1094 |
+
"step": 25000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.847380410022779,
|
| 1098 |
+
"eval_accuracy": 0.8948761125811884,
|
| 1099 |
+
"eval_f1_macro": 0.8736085811230334,
|
| 1100 |
+
"eval_f1_micro": 0.8948761125811884,
|
| 1101 |
+
"eval_loss": 0.7110973596572876,
|
| 1102 |
+
"eval_precision_macro": 0.8674915707955687,
|
| 1103 |
+
"eval_precision_micro": 0.8948761125811884,
|
| 1104 |
+
"eval_recall_macro": 0.901699859992757,
|
| 1105 |
+
"eval_recall_micro": 0.8948761125811884,
|
| 1106 |
+
"eval_runtime": 8.4537,
|
| 1107 |
+
"eval_samples_per_second": 491.739,
|
| 1108 |
+
"eval_steps_per_second": 61.512,
|
| 1109 |
+
"step": 25000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.9043280182232345,
|
| 1113 |
+
"grad_norm": 0.8350435495376587,
|
| 1114 |
+
"learning_rate": 1.6975596030661532e-05,
|
| 1115 |
+
"loss": 0.1625,
|
| 1116 |
+
"step": 25500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.9043280182232345,
|
| 1120 |
+
"eval_accuracy": 0.9030550878037046,
|
| 1121 |
+
"eval_f1_macro": 0.8779275841497265,
|
| 1122 |
+
"eval_f1_micro": 0.9030550878037046,
|
| 1123 |
+
"eval_loss": 0.6505866050720215,
|
| 1124 |
+
"eval_precision_macro": 0.8690908487688577,
|
| 1125 |
+
"eval_precision_micro": 0.9030550878037046,
|
| 1126 |
+
"eval_recall_macro": 0.9045801541095179,
|
| 1127 |
+
"eval_recall_micro": 0.9030550878037046,
|
| 1128 |
+
"eval_runtime": 8.4694,
|
| 1129 |
+
"eval_samples_per_second": 490.823,
|
| 1130 |
+
"eval_steps_per_second": 61.397,
|
| 1131 |
+
"step": 25500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.9612756264236904,
|
| 1135 |
+
"grad_norm": 0.08747211843729019,
|
| 1136 |
+
"learning_rate": 1.537918058104578e-05,
|
| 1137 |
+
"loss": 0.1494,
|
| 1138 |
+
"step": 26000
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.9612756264236904,
|
| 1142 |
+
"eval_accuracy": 0.9090690401732018,
|
| 1143 |
+
"eval_f1_macro": 0.8830141025055214,
|
| 1144 |
+
"eval_f1_micro": 0.9090690401732018,
|
| 1145 |
+
"eval_loss": 0.5693129301071167,
|
| 1146 |
+
"eval_precision_macro": 0.8816974949312945,
|
| 1147 |
+
"eval_precision_micro": 0.9090690401732018,
|
| 1148 |
+
"eval_recall_macro": 0.9015040014659215,
|
| 1149 |
+
"eval_recall_micro": 0.9090690401732018,
|
| 1150 |
+
"eval_runtime": 8.5221,
|
| 1151 |
+
"eval_samples_per_second": 487.793,
|
| 1152 |
+
"eval_steps_per_second": 61.018,
|
| 1153 |
+
"step": 26000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.0182232346241458,
|
| 1157 |
+
"grad_norm": 2.089958906173706,
|
| 1158 |
+
"learning_rate": 1.3843558868376073e-05,
|
| 1159 |
+
"loss": 0.1306,
|
| 1160 |
+
"step": 26500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.0182232346241458,
|
| 1164 |
+
"eval_accuracy": 0.9179696896800578,
|
| 1165 |
+
"eval_f1_macro": 0.8947539710239703,
|
| 1166 |
+
"eval_f1_micro": 0.9179696896800578,
|
| 1167 |
+
"eval_loss": 0.534771203994751,
|
| 1168 |
+
"eval_precision_macro": 0.8923066730381018,
|
| 1169 |
+
"eval_precision_micro": 0.9179696896800578,
|
| 1170 |
+
"eval_recall_macro": 0.9121332598176911,
|
| 1171 |
+
"eval_recall_micro": 0.9179696896800578,
|
| 1172 |
+
"eval_runtime": 8.5905,
|
| 1173 |
+
"eval_samples_per_second": 483.909,
|
| 1174 |
+
"eval_steps_per_second": 60.532,
|
| 1175 |
+
"step": 26500
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 3.075170842824601,
|
| 1179 |
+
"grad_norm": 0.0017847216222435236,
|
| 1180 |
+
"learning_rate": 1.2372522650386443e-05,
|
| 1181 |
+
"loss": 0.0929,
|
| 1182 |
+
"step": 27000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 3.075170842824601,
|
| 1186 |
+
"eval_accuracy": 0.9162857830165985,
|
| 1187 |
+
"eval_f1_macro": 0.8899287169854497,
|
| 1188 |
+
"eval_f1_micro": 0.9162857830165985,
|
| 1189 |
+
"eval_loss": 0.5843378305435181,
|
| 1190 |
+
"eval_precision_macro": 0.8796301981250076,
|
| 1191 |
+
"eval_precision_micro": 0.9162857830165985,
|
| 1192 |
+
"eval_recall_macro": 0.9152639619070458,
|
| 1193 |
+
"eval_recall_micro": 0.9162857830165985,
|
| 1194 |
+
"eval_runtime": 8.4184,
|
| 1195 |
+
"eval_samples_per_second": 493.798,
|
| 1196 |
+
"eval_steps_per_second": 61.769,
|
| 1197 |
+
"step": 27000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.132118451025057,
|
| 1201 |
+
"grad_norm": 0.7512030601501465,
|
| 1202 |
+
"learning_rate": 1.096970421028209e-05,
|
| 1203 |
+
"loss": 0.1351,
|
| 1204 |
+
"step": 27500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 3.132118451025057,
|
| 1208 |
+
"eval_accuracy": 0.9023334135193649,
|
| 1209 |
+
"eval_f1_macro": 0.8733006387364801,
|
| 1210 |
+
"eval_f1_micro": 0.9023334135193649,
|
| 1211 |
+
"eval_loss": 0.6913191080093384,
|
| 1212 |
+
"eval_precision_macro": 0.8611014409270759,
|
| 1213 |
+
"eval_precision_micro": 0.9023334135193649,
|
| 1214 |
+
"eval_recall_macro": 0.9038150903313851,
|
| 1215 |
+
"eval_recall_micro": 0.9023334135193649,
|
| 1216 |
+
"eval_runtime": 8.4379,
|
| 1217 |
+
"eval_samples_per_second": 492.656,
|
| 1218 |
+
"eval_steps_per_second": 61.626,
|
| 1219 |
+
"step": 27500
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 3.1890660592255125,
|
| 1223 |
+
"grad_norm": 0.005041371565312147,
|
| 1224 |
+
"learning_rate": 9.638567387904402e-06,
|
| 1225 |
+
"loss": 0.0907,
|
| 1226 |
+
"step": 28000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.1890660592255125,
|
| 1230 |
+
"eval_accuracy": 0.9206158287226365,
|
| 1231 |
+
"eval_f1_macro": 0.8974407788451421,
|
| 1232 |
+
"eval_f1_micro": 0.9206158287226365,
|
| 1233 |
+
"eval_loss": 0.5801523327827454,
|
| 1234 |
+
"eval_precision_macro": 0.8882950671220116,
|
| 1235 |
+
"eval_precision_micro": 0.9206158287226365,
|
| 1236 |
+
"eval_recall_macro": 0.9136820970599899,
|
| 1237 |
+
"eval_recall_micro": 0.9206158287226365,
|
| 1238 |
+
"eval_runtime": 8.4725,
|
| 1239 |
+
"eval_samples_per_second": 490.649,
|
| 1240 |
+
"eval_steps_per_second": 61.375,
|
| 1241 |
+
"step": 28000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.2460136674259683,
|
| 1245 |
+
"grad_norm": 0.6128404140472412,
|
| 1246 |
+
"learning_rate": 8.382399026816216e-06,
|
| 1247 |
+
"loss": 0.117,
|
| 1248 |
+
"step": 28500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.2460136674259683,
|
| 1252 |
+
"eval_accuracy": 0.9105123887418811,
|
| 1253 |
+
"eval_f1_macro": 0.8877368293575257,
|
| 1254 |
+
"eval_f1_micro": 0.9105123887418811,
|
| 1255 |
+
"eval_loss": 0.6602935791015625,
|
| 1256 |
+
"eval_precision_macro": 0.8839485939859522,
|
| 1257 |
+
"eval_precision_micro": 0.9105123887418811,
|
| 1258 |
+
"eval_recall_macro": 0.905732720534913,
|
| 1259 |
+
"eval_recall_micro": 0.9105123887418811,
|
| 1260 |
+
"eval_runtime": 8.482,
|
| 1261 |
+
"eval_samples_per_second": 490.097,
|
| 1262 |
+
"eval_steps_per_second": 61.306,
|
| 1263 |
+
"step": 28500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.3029612756264237,
|
| 1267 |
+
"grad_norm": 0.0018906695768237114,
|
| 1268 |
+
"learning_rate": 7.2065771743884275e-06,
|
| 1269 |
+
"loss": 0.0986,
|
| 1270 |
+
"step": 29000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.3029612756264237,
|
| 1274 |
+
"eval_accuracy": 0.9105123887418811,
|
| 1275 |
+
"eval_f1_macro": 0.887646044144043,
|
| 1276 |
+
"eval_f1_micro": 0.9105123887418811,
|
| 1277 |
+
"eval_loss": 0.6138319969177246,
|
| 1278 |
+
"eval_precision_macro": 0.887907584612917,
|
| 1279 |
+
"eval_precision_micro": 0.9105123887418811,
|
| 1280 |
+
"eval_recall_macro": 0.9029879731406512,
|
| 1281 |
+
"eval_recall_micro": 0.9105123887418811,
|
| 1282 |
+
"eval_runtime": 8.4603,
|
| 1283 |
+
"eval_samples_per_second": 491.355,
|
| 1284 |
+
"eval_steps_per_second": 61.464,
|
| 1285 |
+
"step": 29000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 3.359908883826879,
|
| 1289 |
+
"grad_norm": 1.5009195804595947,
|
| 1290 |
+
"learning_rate": 6.109293429462298e-06,
|
| 1291 |
+
"loss": 0.1196,
|
| 1292 |
+
"step": 29500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.359908883826879,
|
| 1296 |
+
"eval_accuracy": 0.9131585277844599,
|
| 1297 |
+
"eval_f1_macro": 0.8922838073892356,
|
| 1298 |
+
"eval_f1_micro": 0.9131585277844599,
|
| 1299 |
+
"eval_loss": 0.6528560519218445,
|
| 1300 |
+
"eval_precision_macro": 0.8910787251464412,
|
| 1301 |
+
"eval_precision_micro": 0.9131585277844599,
|
| 1302 |
+
"eval_recall_macro": 0.9099849910959319,
|
| 1303 |
+
"eval_recall_micro": 0.9131585277844599,
|
| 1304 |
+
"eval_runtime": 8.4579,
|
| 1305 |
+
"eval_samples_per_second": 491.492,
|
| 1306 |
+
"eval_steps_per_second": 61.481,
|
| 1307 |
+
"step": 29500
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.416856492027335,
|
| 1311 |
+
"grad_norm": 2.331648349761963,
|
| 1312 |
+
"learning_rate": 5.0956926304652455e-06,
|
| 1313 |
+
"loss": 0.1056,
|
| 1314 |
+
"step": 30000
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.416856492027335,
|
| 1318 |
+
"eval_accuracy": 0.9131585277844599,
|
| 1319 |
+
"eval_f1_macro": 0.8919235957427174,
|
| 1320 |
+
"eval_f1_micro": 0.9131585277844599,
|
| 1321 |
+
"eval_loss": 0.6215759515762329,
|
| 1322 |
+
"eval_precision_macro": 0.884609220404625,
|
| 1323 |
+
"eval_precision_micro": 0.9131585277844599,
|
| 1324 |
+
"eval_recall_macro": 0.9135941017288176,
|
| 1325 |
+
"eval_recall_micro": 0.9131585277844599,
|
| 1326 |
+
"eval_runtime": 8.4442,
|
| 1327 |
+
"eval_samples_per_second": 492.29,
|
| 1328 |
+
"eval_steps_per_second": 61.581,
|
| 1329 |
+
"step": 30000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.4738041002277904,
|
| 1333 |
+
"grad_norm": 148.2794189453125,
|
| 1334 |
+
"learning_rate": 4.168277560886878e-06,
|
| 1335 |
+
"loss": 0.1106,
|
| 1336 |
+
"step": 30500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.4738041002277904,
|
| 1340 |
+
"eval_accuracy": 0.9201347125330768,
|
| 1341 |
+
"eval_f1_macro": 0.891345440347701,
|
| 1342 |
+
"eval_f1_micro": 0.9201347125330768,
|
| 1343 |
+
"eval_loss": 0.5669803023338318,
|
| 1344 |
+
"eval_precision_macro": 0.8817511779041877,
|
| 1345 |
+
"eval_precision_micro": 0.9201347125330768,
|
| 1346 |
+
"eval_recall_macro": 0.9129521474780394,
|
| 1347 |
+
"eval_recall_micro": 0.9201347125330768,
|
| 1348 |
+
"eval_runtime": 8.4316,
|
| 1349 |
+
"eval_samples_per_second": 493.024,
|
| 1350 |
+
"eval_steps_per_second": 61.672,
|
| 1351 |
+
"step": 30500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 3.5307517084282463,
|
| 1355 |
+
"grad_norm": 4.748849868774414,
|
| 1356 |
+
"learning_rate": 3.3293381943799983e-06,
|
| 1357 |
+
"loss": 0.0953,
|
| 1358 |
+
"step": 31000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 3.5307517084282463,
|
| 1362 |
+
"eval_accuracy": 0.9189319220591773,
|
| 1363 |
+
"eval_f1_macro": 0.8934567988898604,
|
| 1364 |
+
"eval_f1_micro": 0.9189319220591773,
|
| 1365 |
+
"eval_loss": 0.569622278213501,
|
| 1366 |
+
"eval_precision_macro": 0.8825638399763271,
|
| 1367 |
+
"eval_precision_micro": 0.9189319220591773,
|
| 1368 |
+
"eval_recall_macro": 0.9187150647269768,
|
| 1369 |
+
"eval_recall_micro": 0.9189319220591773,
|
| 1370 |
+
"eval_runtime": 8.4421,
|
| 1371 |
+
"eval_samples_per_second": 492.411,
|
| 1372 |
+
"eval_steps_per_second": 61.596,
|
| 1373 |
+
"step": 31000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 3.5876993166287017,
|
| 1377 |
+
"grad_norm": 1.284857153892517,
|
| 1378 |
+
"learning_rate": 2.580946040356764e-06,
|
| 1379 |
+
"loss": 0.0989,
|
| 1380 |
+
"step": 31500
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 3.5876993166287017,
|
| 1384 |
+
"eval_accuracy": 0.9194130382487371,
|
| 1385 |
+
"eval_f1_macro": 0.8981523298720768,
|
| 1386 |
+
"eval_f1_micro": 0.9194130382487371,
|
| 1387 |
+
"eval_loss": 0.5652771592140198,
|
| 1388 |
+
"eval_precision_macro": 0.8854580096444836,
|
| 1389 |
+
"eval_precision_micro": 0.9194130382487371,
|
| 1390 |
+
"eval_recall_macro": 0.9219999897271275,
|
| 1391 |
+
"eval_recall_micro": 0.9194130382487371,
|
| 1392 |
+
"eval_runtime": 8.43,
|
| 1393 |
+
"eval_samples_per_second": 493.122,
|
| 1394 |
+
"eval_steps_per_second": 61.685,
|
| 1395 |
+
"step": 31500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.644646924829157,
|
| 1399 |
+
"grad_norm": 1.4339042901992798,
|
| 1400 |
+
"learning_rate": 1.9249490290167914e-06,
|
| 1401 |
+
"loss": 0.0989,
|
| 1402 |
+
"step": 32000
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 3.644646924829157,
|
| 1406 |
+
"eval_accuracy": 0.9138802020687996,
|
| 1407 |
+
"eval_f1_macro": 0.89412218234686,
|
| 1408 |
+
"eval_f1_micro": 0.9138802020687996,
|
| 1409 |
+
"eval_loss": 0.6019502282142639,
|
| 1410 |
+
"eval_precision_macro": 0.882568682117879,
|
| 1411 |
+
"eval_precision_micro": 0.9138802020687996,
|
| 1412 |
+
"eval_recall_macro": 0.9175339639156622,
|
| 1413 |
+
"eval_recall_micro": 0.9138802020687996,
|
| 1414 |
+
"eval_runtime": 8.4297,
|
| 1415 |
+
"eval_samples_per_second": 493.138,
|
| 1416 |
+
"eval_steps_per_second": 61.687,
|
| 1417 |
+
"step": 32000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.7015945330296125,
|
| 1421 |
+
"grad_norm": 0.7662363648414612,
|
| 1422 |
+
"learning_rate": 1.3629669484372722e-06,
|
| 1423 |
+
"loss": 0.0876,
|
| 1424 |
+
"step": 32500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.7015945330296125,
|
| 1428 |
+
"eval_accuracy": 0.9167668992061583,
|
| 1429 |
+
"eval_f1_macro": 0.8960433945398601,
|
| 1430 |
+
"eval_f1_micro": 0.9167668992061583,
|
| 1431 |
+
"eval_loss": 0.578229546546936,
|
| 1432 |
+
"eval_precision_macro": 0.8823539415499122,
|
| 1433 |
+
"eval_precision_micro": 0.9167668992061583,
|
| 1434 |
+
"eval_recall_macro": 0.9211442367709737,
|
| 1435 |
+
"eval_recall_micro": 0.9167668992061583,
|
| 1436 |
+
"eval_runtime": 8.4419,
|
| 1437 |
+
"eval_samples_per_second": 492.426,
|
| 1438 |
+
"eval_steps_per_second": 61.598,
|
| 1439 |
+
"step": 32500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 3.7585421412300684,
|
| 1443 |
+
"grad_norm": 0.8838233947753906,
|
| 1444 |
+
"learning_rate": 8.963874449915156e-07,
|
| 1445 |
+
"loss": 0.1004,
|
| 1446 |
+
"step": 33000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 3.7585421412300684,
|
| 1450 |
+
"eval_accuracy": 0.9186913639643974,
|
| 1451 |
+
"eval_f1_macro": 0.8974164477796313,
|
| 1452 |
+
"eval_f1_micro": 0.9186913639643974,
|
| 1453 |
+
"eval_loss": 0.5638399720191956,
|
| 1454 |
+
"eval_precision_macro": 0.8850042534249818,
|
| 1455 |
+
"eval_precision_micro": 0.9186913639643974,
|
| 1456 |
+
"eval_recall_macro": 0.9204573653096998,
|
| 1457 |
+
"eval_recall_micro": 0.9186913639643974,
|
| 1458 |
+
"eval_runtime": 8.4287,
|
| 1459 |
+
"eval_samples_per_second": 493.198,
|
| 1460 |
+
"eval_steps_per_second": 61.694,
|
| 1461 |
+
"step": 33000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 3.8154897494305238,
|
| 1465 |
+
"grad_norm": 0.8862270712852478,
|
| 1466 |
+
"learning_rate": 5.263625969720654e-07,
|
| 1467 |
+
"loss": 0.1163,
|
| 1468 |
+
"step": 33500
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 3.8154897494305238,
|
| 1472 |
+
"eval_accuracy": 0.9189319220591773,
|
| 1473 |
+
"eval_f1_macro": 0.8978554181419179,
|
| 1474 |
+
"eval_f1_micro": 0.9189319220591773,
|
| 1475 |
+
"eval_loss": 0.5575982332229614,
|
| 1476 |
+
"eval_precision_macro": 0.8842809438001717,
|
| 1477 |
+
"eval_precision_micro": 0.9189319220591773,
|
| 1478 |
+
"eval_recall_macro": 0.9207880969765441,
|
| 1479 |
+
"eval_recall_micro": 0.9189319220591773,
|
| 1480 |
+
"eval_runtime": 8.4411,
|
| 1481 |
+
"eval_samples_per_second": 492.47,
|
| 1482 |
+
"eval_steps_per_second": 61.603,
|
| 1483 |
+
"step": 33500
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 3.8724373576309796,
|
| 1487 |
+
"grad_norm": 0.0018380646361038089,
|
| 1488 |
+
"learning_rate": 2.5380606987847725e-07,
|
| 1489 |
+
"loss": 0.1014,
|
| 1490 |
+
"step": 34000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 3.8724373576309796,
|
| 1494 |
+
"eval_accuracy": 0.9184508058696175,
|
| 1495 |
+
"eval_f1_macro": 0.8970972466165426,
|
| 1496 |
+
"eval_f1_micro": 0.9184508058696175,
|
| 1497 |
+
"eval_loss": 0.5561444759368896,
|
| 1498 |
+
"eval_precision_macro": 0.8836350789167062,
|
| 1499 |
+
"eval_precision_micro": 0.9184508058696175,
|
| 1500 |
+
"eval_recall_macro": 0.9206973516595941,
|
| 1501 |
+
"eval_recall_micro": 0.9184508058696175,
|
| 1502 |
+
"eval_runtime": 8.432,
|
| 1503 |
+
"eval_samples_per_second": 493.002,
|
| 1504 |
+
"eval_steps_per_second": 61.67,
|
| 1505 |
+
"step": 34000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.929384965831435,
|
| 1509 |
+
"grad_norm": 1.3534623384475708,
|
| 1510 |
+
"learning_rate": 7.939086039413291e-08,
|
| 1511 |
+
"loss": 0.0948,
|
| 1512 |
+
"step": 34500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 3.929384965831435,
|
| 1516 |
+
"eval_accuracy": 0.9191724801539571,
|
| 1517 |
+
"eval_f1_macro": 0.8982632597992836,
|
| 1518 |
+
"eval_f1_micro": 0.9191724801539571,
|
| 1519 |
+
"eval_loss": 0.5567488074302673,
|
| 1520 |
+
"eval_precision_macro": 0.8854065999210586,
|
| 1521 |
+
"eval_precision_micro": 0.9191724801539571,
|
| 1522 |
+
"eval_recall_macro": 0.9212323971384597,
|
| 1523 |
+
"eval_recall_micro": 0.9191724801539571,
|
| 1524 |
+
"eval_runtime": 8.4196,
|
| 1525 |
+
"eval_samples_per_second": 493.73,
|
| 1526 |
+
"eval_steps_per_second": 61.761,
|
| 1527 |
+
"step": 34500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 3.9863325740318905,
|
| 1531 |
+
"grad_norm": 0.00499533349648118,
|
| 1532 |
+
"learning_rate": 3.6007811694149795e-09,
|
| 1533 |
+
"loss": 0.0915,
|
| 1534 |
+
"step": 35000
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 3.9863325740318905,
|
| 1538 |
+
"eval_accuracy": 0.9189319220591773,
|
| 1539 |
+
"eval_f1_macro": 0.8979067522497397,
|
| 1540 |
+
"eval_f1_micro": 0.9189319220591773,
|
| 1541 |
+
"eval_loss": 0.5568965673446655,
|
| 1542 |
+
"eval_precision_macro": 0.8849842519873105,
|
| 1543 |
+
"eval_precision_micro": 0.9189319220591773,
|
| 1544 |
+
"eval_recall_macro": 0.9210492469553095,
|
| 1545 |
+
"eval_recall_micro": 0.9189319220591773,
|
| 1546 |
+
"eval_runtime": 8.4437,
|
| 1547 |
+
"eval_samples_per_second": 492.321,
|
| 1548 |
+
"eval_steps_per_second": 61.585,
|
| 1549 |
+
"step": 35000
|
| 1550 |
+
}
|
| 1551 |
+
],
|
| 1552 |
+
"logging_steps": 500,
|
| 1553 |
+
"max_steps": 35120,
|
| 1554 |
+
"num_input_tokens_seen": 0,
|
| 1555 |
+
"num_train_epochs": 4,
|
| 1556 |
+
"save_steps": 500,
|
| 1557 |
+
"stateful_callbacks": {
|
| 1558 |
+
"TrainerControl": {
|
| 1559 |
+
"args": {
|
| 1560 |
+
"should_epoch_stop": false,
|
| 1561 |
+
"should_evaluate": false,
|
| 1562 |
+
"should_log": false,
|
| 1563 |
+
"should_save": true,
|
| 1564 |
+
"should_training_stop": false
|
| 1565 |
+
},
|
| 1566 |
+
"attributes": {}
|
| 1567 |
+
}
|
| 1568 |
+
},
|
| 1569 |
+
"total_flos": 7.368366329856e+16,
|
| 1570 |
+
"train_batch_size": 8,
|
| 1571 |
+
"trial_name": null,
|
| 1572 |
+
"trial_params": null
|
| 1573 |
+
}
|
checkpoint-35000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49538db7a2ace12c7d89de1c0011d0ddc0ea3c0b5d2b68c5a1982e226b28b01b
|
| 3 |
+
size 5521
|
checkpoint-35000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|