Upload folder using huggingface_hub
Browse files- 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-36500/config.json +72 -0
- checkpoint-36500/model.safetensors +3 -0
- checkpoint-36500/optimizer.pt +3 -0
- checkpoint-36500/rng_state.pth +3 -0
- checkpoint-36500/scheduler.pt +3 -0
- checkpoint-36500/special_tokens_map.json +37 -0
- checkpoint-36500/tokenizer.json +0 -0
- checkpoint-36500/tokenizer_config.json +338 -0
- checkpoint-36500/trainer_state.json +1639 -0
- checkpoint-36500/training_args.bin +3 -0
- checkpoint-36500/vocab.txt +0 -0
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:fecf039de2f9f5c72decc0e08cb022d5b2100225a91f0dbc812616e079f1f367
|
| 3 |
+
size 540861516
|
checkpoint-35000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938ae5383860fff9063db6c40b0867f0e7926c996ebc358739fd3f498edb3e0f
|
| 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:d52d5173f4403a82614d6b66367c45df8570ad8a9a4230c2cb94e8a93f10b030
|
| 3 |
+
size 14645
|
checkpoint-35000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:812edc8765eafc7d48e5d526d28544d46657d6d84abe107147bc2050495c5575
|
| 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": 0.9472436482214578,
|
| 3 |
+
"best_model_checkpoint": "./arabert_author_model_full/checkpoint-35000",
|
| 4 |
+
"epoch": 3.80145541435864,
|
| 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": 0.054306505919409144,
|
| 13 |
+
"grad_norm": 14.85861587524414,
|
| 14 |
+
"learning_rate": 1.0795547108335597e-05,
|
| 15 |
+
"loss": 2.7396,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.054306505919409144,
|
| 20 |
+
"eval_accuracy": 0.5551075268817204,
|
| 21 |
+
"eval_f1_macro": 0.44528091004577197,
|
| 22 |
+
"eval_f1_micro": 0.5551075268817204,
|
| 23 |
+
"eval_loss": 2.086405038833618,
|
| 24 |
+
"eval_precision_macro": 0.5488362024601817,
|
| 25 |
+
"eval_precision_micro": 0.5551075268817204,
|
| 26 |
+
"eval_recall_macro": 0.5011249738249491,
|
| 27 |
+
"eval_recall_micro": 0.5551075268817204,
|
| 28 |
+
"eval_runtime": 1.5572,
|
| 29 |
+
"eval_samples_per_second": 477.769,
|
| 30 |
+
"eval_steps_per_second": 59.721,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.10861301183881829,
|
| 35 |
+
"grad_norm": 16.272708892822266,
|
| 36 |
+
"learning_rate": 2.1656258484930763e-05,
|
| 37 |
+
"loss": 1.584,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10861301183881829,
|
| 42 |
+
"eval_accuracy": 0.7190860215053764,
|
| 43 |
+
"eval_f1_macro": 0.6681343461862342,
|
| 44 |
+
"eval_f1_micro": 0.7190860215053764,
|
| 45 |
+
"eval_loss": 1.1402474641799927,
|
| 46 |
+
"eval_precision_macro": 0.7284168208592146,
|
| 47 |
+
"eval_precision_micro": 0.7190860215053764,
|
| 48 |
+
"eval_recall_macro": 0.6741017912193727,
|
| 49 |
+
"eval_recall_micro": 0.7190860215053764,
|
| 50 |
+
"eval_runtime": 1.5592,
|
| 51 |
+
"eval_samples_per_second": 477.171,
|
| 52 |
+
"eval_steps_per_second": 59.646,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.16291951775822744,
|
| 57 |
+
"grad_norm": 43.108097076416016,
|
| 58 |
+
"learning_rate": 3.2516969861525934e-05,
|
| 59 |
+
"loss": 1.0278,
|
| 60 |
+
"step": 1500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.16291951775822744,
|
| 64 |
+
"eval_accuracy": 0.6935483870967742,
|
| 65 |
+
"eval_f1_macro": 0.6694441122919238,
|
| 66 |
+
"eval_f1_micro": 0.6935483870967742,
|
| 67 |
+
"eval_loss": 0.9176589250564575,
|
| 68 |
+
"eval_precision_macro": 0.719370166471438,
|
| 69 |
+
"eval_precision_micro": 0.6935483870967742,
|
| 70 |
+
"eval_recall_macro": 0.700540634546637,
|
| 71 |
+
"eval_recall_micro": 0.6935483870967742,
|
| 72 |
+
"eval_runtime": 1.5614,
|
| 73 |
+
"eval_samples_per_second": 476.485,
|
| 74 |
+
"eval_steps_per_second": 59.561,
|
| 75 |
+
"step": 1500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.21722602367763658,
|
| 79 |
+
"grad_norm": 21.786911010742188,
|
| 80 |
+
"learning_rate": 4.33776812381211e-05,
|
| 81 |
+
"loss": 0.7819,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.21722602367763658,
|
| 86 |
+
"eval_accuracy": 0.7365591397849462,
|
| 87 |
+
"eval_f1_macro": 0.7225937916281533,
|
| 88 |
+
"eval_f1_micro": 0.7365591397849462,
|
| 89 |
+
"eval_loss": 0.9186232089996338,
|
| 90 |
+
"eval_precision_macro": 0.8090241740547917,
|
| 91 |
+
"eval_precision_micro": 0.7365591397849462,
|
| 92 |
+
"eval_recall_macro": 0.730498755334377,
|
| 93 |
+
"eval_recall_micro": 0.7365591397849462,
|
| 94 |
+
"eval_runtime": 1.7089,
|
| 95 |
+
"eval_samples_per_second": 435.367,
|
| 96 |
+
"eval_steps_per_second": 54.421,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.2715325295970457,
|
| 101 |
+
"grad_norm": 28.50157356262207,
|
| 102 |
+
"learning_rate": 5.4216671191963076e-05,
|
| 103 |
+
"loss": 0.7433,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.2715325295970457,
|
| 108 |
+
"eval_accuracy": 0.8091397849462365,
|
| 109 |
+
"eval_f1_macro": 0.7931780524032125,
|
| 110 |
+
"eval_f1_micro": 0.8091397849462365,
|
| 111 |
+
"eval_loss": 0.6774040460586548,
|
| 112 |
+
"eval_precision_macro": 0.8236755927756734,
|
| 113 |
+
"eval_precision_micro": 0.8091397849462365,
|
| 114 |
+
"eval_recall_macro": 0.8138164959150519,
|
| 115 |
+
"eval_recall_micro": 0.8091397849462365,
|
| 116 |
+
"eval_runtime": 1.5765,
|
| 117 |
+
"eval_samples_per_second": 471.94,
|
| 118 |
+
"eval_steps_per_second": 58.992,
|
| 119 |
+
"step": 2500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.3258390355164549,
|
| 123 |
+
"grad_norm": 23.32242774963379,
|
| 124 |
+
"learning_rate": 6.507738256855825e-05,
|
| 125 |
+
"loss": 0.7224,
|
| 126 |
+
"step": 3000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.3258390355164549,
|
| 130 |
+
"eval_accuracy": 0.7701612903225806,
|
| 131 |
+
"eval_f1_macro": 0.7568919015291462,
|
| 132 |
+
"eval_f1_micro": 0.7701612903225806,
|
| 133 |
+
"eval_loss": 0.726546585559845,
|
| 134 |
+
"eval_precision_macro": 0.8108640165896299,
|
| 135 |
+
"eval_precision_micro": 0.7701612903225806,
|
| 136 |
+
"eval_recall_macro": 0.7863245772318792,
|
| 137 |
+
"eval_recall_micro": 0.7701612903225806,
|
| 138 |
+
"eval_runtime": 1.5947,
|
| 139 |
+
"eval_samples_per_second": 466.552,
|
| 140 |
+
"eval_steps_per_second": 58.319,
|
| 141 |
+
"step": 3000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.38014554143586404,
|
| 145 |
+
"grad_norm": 38.11383056640625,
|
| 146 |
+
"learning_rate": 7.591637252240023e-05,
|
| 147 |
+
"loss": 0.7578,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.38014554143586404,
|
| 152 |
+
"eval_accuracy": 0.831989247311828,
|
| 153 |
+
"eval_f1_macro": 0.8113946213107872,
|
| 154 |
+
"eval_f1_micro": 0.831989247311828,
|
| 155 |
+
"eval_loss": 0.5666089653968811,
|
| 156 |
+
"eval_precision_macro": 0.8300071137831838,
|
| 157 |
+
"eval_precision_micro": 0.831989247311828,
|
| 158 |
+
"eval_recall_macro": 0.8277091616765468,
|
| 159 |
+
"eval_recall_micro": 0.831989247311828,
|
| 160 |
+
"eval_runtime": 1.5775,
|
| 161 |
+
"eval_samples_per_second": 471.647,
|
| 162 |
+
"eval_steps_per_second": 58.956,
|
| 163 |
+
"step": 3500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.43445204735527315,
|
| 167 |
+
"grad_norm": 27.02998161315918,
|
| 168 |
+
"learning_rate": 7.998262267095997e-05,
|
| 169 |
+
"loss": 0.7705,
|
| 170 |
+
"step": 4000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.43445204735527315,
|
| 174 |
+
"eval_accuracy": 0.793010752688172,
|
| 175 |
+
"eval_f1_macro": 0.7783295125154664,
|
| 176 |
+
"eval_f1_micro": 0.793010752688172,
|
| 177 |
+
"eval_loss": 0.7473301887512207,
|
| 178 |
+
"eval_precision_macro": 0.8365596188425319,
|
| 179 |
+
"eval_precision_micro": 0.793010752688172,
|
| 180 |
+
"eval_recall_macro": 0.7944564993024996,
|
| 181 |
+
"eval_recall_micro": 0.793010752688172,
|
| 182 |
+
"eval_runtime": 1.592,
|
| 183 |
+
"eval_samples_per_second": 467.348,
|
| 184 |
+
"eval_steps_per_second": 58.418,
|
| 185 |
+
"step": 4000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4887585532746823,
|
| 189 |
+
"grad_norm": 4.219649314880371,
|
| 190 |
+
"learning_rate": 7.988188051558617e-05,
|
| 191 |
+
"loss": 0.714,
|
| 192 |
+
"step": 4500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4887585532746823,
|
| 196 |
+
"eval_accuracy": 0.8615591397849462,
|
| 197 |
+
"eval_f1_macro": 0.8525941744256668,
|
| 198 |
+
"eval_f1_micro": 0.8615591397849462,
|
| 199 |
+
"eval_loss": 0.5411700010299683,
|
| 200 |
+
"eval_precision_macro": 0.8738317002846235,
|
| 201 |
+
"eval_precision_micro": 0.8615591397849462,
|
| 202 |
+
"eval_recall_macro": 0.857343934692196,
|
| 203 |
+
"eval_recall_micro": 0.8615591397849462,
|
| 204 |
+
"eval_runtime": 1.5935,
|
| 205 |
+
"eval_samples_per_second": 466.9,
|
| 206 |
+
"eval_steps_per_second": 58.363,
|
| 207 |
+
"step": 4500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5430650591940914,
|
| 211 |
+
"grad_norm": 2.9277937412261963,
|
| 212 |
+
"learning_rate": 7.969158166695609e-05,
|
| 213 |
+
"loss": 0.6781,
|
| 214 |
+
"step": 5000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.5430650591940914,
|
| 218 |
+
"eval_accuracy": 0.8440860215053764,
|
| 219 |
+
"eval_f1_macro": 0.8140189163428593,
|
| 220 |
+
"eval_f1_micro": 0.8440860215053764,
|
| 221 |
+
"eval_loss": 0.584912896156311,
|
| 222 |
+
"eval_precision_macro": 0.8304958001958954,
|
| 223 |
+
"eval_precision_micro": 0.8440860215053764,
|
| 224 |
+
"eval_recall_macro": 0.8277544733650097,
|
| 225 |
+
"eval_recall_micro": 0.8440860215053764,
|
| 226 |
+
"eval_runtime": 1.5664,
|
| 227 |
+
"eval_samples_per_second": 474.976,
|
| 228 |
+
"eval_steps_per_second": 59.372,
|
| 229 |
+
"step": 5000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5973715651135006,
|
| 233 |
+
"grad_norm": 2.422699213027954,
|
| 234 |
+
"learning_rate": 7.941215345034608e-05,
|
| 235 |
+
"loss": 0.6365,
|
| 236 |
+
"step": 5500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.5973715651135006,
|
| 240 |
+
"eval_accuracy": 0.8198924731182796,
|
| 241 |
+
"eval_f1_macro": 0.8098480937728665,
|
| 242 |
+
"eval_f1_micro": 0.8198924731182796,
|
| 243 |
+
"eval_loss": 0.6339462995529175,
|
| 244 |
+
"eval_precision_macro": 0.8511279803543597,
|
| 245 |
+
"eval_precision_micro": 0.8198924731182796,
|
| 246 |
+
"eval_recall_macro": 0.8376000571890804,
|
| 247 |
+
"eval_recall_micro": 0.8198924731182796,
|
| 248 |
+
"eval_runtime": 1.5714,
|
| 249 |
+
"eval_samples_per_second": 473.456,
|
| 250 |
+
"eval_steps_per_second": 59.182,
|
| 251 |
+
"step": 5500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.6516780710329098,
|
| 255 |
+
"grad_norm": 24.36614227294922,
|
| 256 |
+
"learning_rate": 7.90442233353428e-05,
|
| 257 |
+
"loss": 0.5609,
|
| 258 |
+
"step": 6000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.6516780710329098,
|
| 262 |
+
"eval_accuracy": 0.8803763440860215,
|
| 263 |
+
"eval_f1_macro": 0.8776901808589186,
|
| 264 |
+
"eval_f1_micro": 0.8803763440860215,
|
| 265 |
+
"eval_loss": 0.4191497564315796,
|
| 266 |
+
"eval_precision_macro": 0.9013592602931226,
|
| 267 |
+
"eval_precision_micro": 0.8803763440860215,
|
| 268 |
+
"eval_recall_macro": 0.8870337188867564,
|
| 269 |
+
"eval_recall_micro": 0.8803763440860215,
|
| 270 |
+
"eval_runtime": 1.5644,
|
| 271 |
+
"eval_samples_per_second": 475.586,
|
| 272 |
+
"eval_steps_per_second": 59.448,
|
| 273 |
+
"step": 6000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.7059845769523189,
|
| 277 |
+
"grad_norm": 7.382803440093994,
|
| 278 |
+
"learning_rate": 7.85896155913429e-05,
|
| 279 |
+
"loss": 0.557,
|
| 280 |
+
"step": 6500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7059845769523189,
|
| 284 |
+
"eval_accuracy": 0.8870967741935484,
|
| 285 |
+
"eval_f1_macro": 0.873257230355725,
|
| 286 |
+
"eval_f1_micro": 0.8870967741935484,
|
| 287 |
+
"eval_loss": 0.43305835127830505,
|
| 288 |
+
"eval_precision_macro": 0.9066583526088271,
|
| 289 |
+
"eval_precision_micro": 0.8870967741935484,
|
| 290 |
+
"eval_recall_macro": 0.8813447066604991,
|
| 291 |
+
"eval_recall_micro": 0.8870967741935484,
|
| 292 |
+
"eval_runtime": 1.572,
|
| 293 |
+
"eval_samples_per_second": 473.271,
|
| 294 |
+
"eval_steps_per_second": 59.159,
|
| 295 |
+
"step": 6500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.7602910828717281,
|
| 299 |
+
"grad_norm": 40.95680618286133,
|
| 300 |
+
"learning_rate": 7.804752932863711e-05,
|
| 301 |
+
"loss": 0.5581,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.7602910828717281,
|
| 306 |
+
"eval_accuracy": 0.8400537634408602,
|
| 307 |
+
"eval_f1_macro": 0.832080514333091,
|
| 308 |
+
"eval_f1_micro": 0.8400537634408602,
|
| 309 |
+
"eval_loss": 0.6264011263847351,
|
| 310 |
+
"eval_precision_macro": 0.8486272179160291,
|
| 311 |
+
"eval_precision_micro": 0.8400537634408602,
|
| 312 |
+
"eval_recall_macro": 0.8385309495501778,
|
| 313 |
+
"eval_recall_micro": 0.8400537634408602,
|
| 314 |
+
"eval_runtime": 1.5709,
|
| 315 |
+
"eval_samples_per_second": 473.61,
|
| 316 |
+
"eval_steps_per_second": 59.201,
|
| 317 |
+
"step": 7000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8145975887911372,
|
| 321 |
+
"grad_norm": 1.4635225534439087,
|
| 322 |
+
"learning_rate": 7.74200054970606e-05,
|
| 323 |
+
"loss": 0.6216,
|
| 324 |
+
"step": 7500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8145975887911372,
|
| 328 |
+
"eval_accuracy": 0.8790322580645161,
|
| 329 |
+
"eval_f1_macro": 0.8733027369549773,
|
| 330 |
+
"eval_f1_micro": 0.8790322580645161,
|
| 331 |
+
"eval_loss": 0.409856379032135,
|
| 332 |
+
"eval_precision_macro": 0.8884912266604943,
|
| 333 |
+
"eval_precision_micro": 0.8790322580645161,
|
| 334 |
+
"eval_recall_macro": 0.8755203032263899,
|
| 335 |
+
"eval_recall_micro": 0.8790322580645161,
|
| 336 |
+
"eval_runtime": 1.5605,
|
| 337 |
+
"eval_samples_per_second": 476.783,
|
| 338 |
+
"eval_steps_per_second": 59.598,
|
| 339 |
+
"step": 7500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8689040947105463,
|
| 343 |
+
"grad_norm": 45.099891662597656,
|
| 344 |
+
"learning_rate": 7.670845323175364e-05,
|
| 345 |
+
"loss": 0.5329,
|
| 346 |
+
"step": 8000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8689040947105463,
|
| 350 |
+
"eval_accuracy": 0.8494623655913979,
|
| 351 |
+
"eval_f1_macro": 0.8493612714696808,
|
| 352 |
+
"eval_f1_micro": 0.8494623655913979,
|
| 353 |
+
"eval_loss": 0.4563172161579132,
|
| 354 |
+
"eval_precision_macro": 0.893910479148947,
|
| 355 |
+
"eval_precision_micro": 0.8494623655913979,
|
| 356 |
+
"eval_recall_macro": 0.8604223349122991,
|
| 357 |
+
"eval_recall_micro": 0.8494623655913979,
|
| 358 |
+
"eval_runtime": 1.5627,
|
| 359 |
+
"eval_samples_per_second": 476.104,
|
| 360 |
+
"eval_steps_per_second": 59.513,
|
| 361 |
+
"step": 8000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.9232106006299554,
|
| 365 |
+
"grad_norm": 144.00657653808594,
|
| 366 |
+
"learning_rate": 7.591447035777205e-05,
|
| 367 |
+
"loss": 0.5361,
|
| 368 |
+
"step": 8500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.9232106006299554,
|
| 372 |
+
"eval_accuracy": 0.8655913978494624,
|
| 373 |
+
"eval_f1_macro": 0.8441067821828483,
|
| 374 |
+
"eval_f1_micro": 0.8655913978494624,
|
| 375 |
+
"eval_loss": 0.6785014867782593,
|
| 376 |
+
"eval_precision_macro": 0.8860824516800835,
|
| 377 |
+
"eval_precision_micro": 0.8655913978494624,
|
| 378 |
+
"eval_recall_macro": 0.8499754697649283,
|
| 379 |
+
"eval_recall_micro": 0.8655913978494624,
|
| 380 |
+
"eval_runtime": 1.7462,
|
| 381 |
+
"eval_samples_per_second": 426.057,
|
| 382 |
+
"eval_steps_per_second": 53.257,
|
| 383 |
+
"step": 8500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.9775171065493646,
|
| 387 |
+
"grad_norm": 51.59966278076172,
|
| 388 |
+
"learning_rate": 7.50398398020936e-05,
|
| 389 |
+
"loss": 0.5004,
|
| 390 |
+
"step": 9000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.9775171065493646,
|
| 394 |
+
"eval_accuracy": 0.8830645161290323,
|
| 395 |
+
"eval_f1_macro": 0.8700101159667029,
|
| 396 |
+
"eval_f1_micro": 0.8830645161290323,
|
| 397 |
+
"eval_loss": 0.5261440277099609,
|
| 398 |
+
"eval_precision_macro": 0.9053295147781684,
|
| 399 |
+
"eval_precision_micro": 0.8830645161290323,
|
| 400 |
+
"eval_recall_macro": 0.8611036436092915,
|
| 401 |
+
"eval_recall_micro": 0.8830645161290323,
|
| 402 |
+
"eval_runtime": 1.5897,
|
| 403 |
+
"eval_samples_per_second": 468.018,
|
| 404 |
+
"eval_steps_per_second": 58.502,
|
| 405 |
+
"step": 9000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0318236124687739,
|
| 409 |
+
"grad_norm": 1.6247466802597046,
|
| 410 |
+
"learning_rate": 7.408850935077056e-05,
|
| 411 |
+
"loss": 0.4548,
|
| 412 |
+
"step": 9500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.0318236124687739,
|
| 416 |
+
"eval_accuracy": 0.885752688172043,
|
| 417 |
+
"eval_f1_macro": 0.8771175055624273,
|
| 418 |
+
"eval_f1_micro": 0.885752688172043,
|
| 419 |
+
"eval_loss": 0.47863149642944336,
|
| 420 |
+
"eval_precision_macro": 0.9058069553824752,
|
| 421 |
+
"eval_precision_micro": 0.885752688172043,
|
| 422 |
+
"eval_recall_macro": 0.8766787609951181,
|
| 423 |
+
"eval_recall_micro": 0.885752688172043,
|
| 424 |
+
"eval_runtime": 1.5934,
|
| 425 |
+
"eval_samples_per_second": 466.926,
|
| 426 |
+
"eval_steps_per_second": 58.366,
|
| 427 |
+
"step": 9500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.0861301183881829,
|
| 431 |
+
"grad_norm": 0.7039883732795715,
|
| 432 |
+
"learning_rate": 7.305880302978226e-05,
|
| 433 |
+
"loss": 0.3634,
|
| 434 |
+
"step": 10000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0861301183881829,
|
| 438 |
+
"eval_accuracy": 0.8454301075268817,
|
| 439 |
+
"eval_f1_macro": 0.8355409368806581,
|
| 440 |
+
"eval_f1_micro": 0.8454301075268817,
|
| 441 |
+
"eval_loss": 0.584094226360321,
|
| 442 |
+
"eval_precision_macro": 0.8637046558195853,
|
| 443 |
+
"eval_precision_micro": 0.8454301075268817,
|
| 444 |
+
"eval_recall_macro": 0.8620713017041678,
|
| 445 |
+
"eval_recall_micro": 0.8454301075268817,
|
| 446 |
+
"eval_runtime": 1.5924,
|
| 447 |
+
"eval_samples_per_second": 467.211,
|
| 448 |
+
"eval_steps_per_second": 58.401,
|
| 449 |
+
"step": 10000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.140436624307592,
|
| 453 |
+
"grad_norm": 18.514562606811523,
|
| 454 |
+
"learning_rate": 7.195486156631612e-05,
|
| 455 |
+
"loss": 0.38,
|
| 456 |
+
"step": 10500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.140436624307592,
|
| 460 |
+
"eval_accuracy": 0.8736559139784946,
|
| 461 |
+
"eval_f1_macro": 0.8650283345776192,
|
| 462 |
+
"eval_f1_micro": 0.8736559139784946,
|
| 463 |
+
"eval_loss": 0.609620213508606,
|
| 464 |
+
"eval_precision_macro": 0.8846991890947015,
|
| 465 |
+
"eval_precision_micro": 0.8736559139784946,
|
| 466 |
+
"eval_recall_macro": 0.8788120484876811,
|
| 467 |
+
"eval_recall_micro": 0.8736559139784946,
|
| 468 |
+
"eval_runtime": 1.596,
|
| 469 |
+
"eval_samples_per_second": 466.176,
|
| 470 |
+
"eval_steps_per_second": 58.272,
|
| 471 |
+
"step": 10500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.194743130227001,
|
| 475 |
+
"grad_norm": 33.06956481933594,
|
| 476 |
+
"learning_rate": 7.077916391436673e-05,
|
| 477 |
+
"loss": 0.4346,
|
| 478 |
+
"step": 11000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.194743130227001,
|
| 482 |
+
"eval_accuracy": 0.8588709677419355,
|
| 483 |
+
"eval_f1_macro": 0.8369609828838035,
|
| 484 |
+
"eval_f1_micro": 0.8588709677419355,
|
| 485 |
+
"eval_loss": 0.6567370891571045,
|
| 486 |
+
"eval_precision_macro": 0.8596584963088156,
|
| 487 |
+
"eval_precision_micro": 0.8588709677419355,
|
| 488 |
+
"eval_recall_macro": 0.8553630932096153,
|
| 489 |
+
"eval_recall_micro": 0.8588709677419355,
|
| 490 |
+
"eval_runtime": 1.5912,
|
| 491 |
+
"eval_samples_per_second": 467.56,
|
| 492 |
+
"eval_steps_per_second": 58.445,
|
| 493 |
+
"step": 11000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.2490496361464103,
|
| 497 |
+
"grad_norm": 5.124754428863525,
|
| 498 |
+
"learning_rate": 6.953690693258913e-05,
|
| 499 |
+
"loss": 0.4048,
|
| 500 |
+
"step": 11500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.2490496361464103,
|
| 504 |
+
"eval_accuracy": 0.8185483870967742,
|
| 505 |
+
"eval_f1_macro": 0.8138708613483465,
|
| 506 |
+
"eval_f1_micro": 0.8185483870967742,
|
| 507 |
+
"eval_loss": 0.8613069653511047,
|
| 508 |
+
"eval_precision_macro": 0.8751078398440778,
|
| 509 |
+
"eval_precision_micro": 0.8185483870967742,
|
| 510 |
+
"eval_recall_macro": 0.8210231918764864,
|
| 511 |
+
"eval_recall_micro": 0.8185483870967742,
|
| 512 |
+
"eval_runtime": 1.5897,
|
| 513 |
+
"eval_samples_per_second": 468.009,
|
| 514 |
+
"eval_steps_per_second": 58.501,
|
| 515 |
+
"step": 11500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.3033561420658195,
|
| 519 |
+
"grad_norm": 5.379746437072754,
|
| 520 |
+
"learning_rate": 6.822590211705641e-05,
|
| 521 |
+
"loss": 0.4131,
|
| 522 |
+
"step": 12000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.3033561420658195,
|
| 526 |
+
"eval_accuracy": 0.907258064516129,
|
| 527 |
+
"eval_f1_macro": 0.9064546460371958,
|
| 528 |
+
"eval_f1_micro": 0.907258064516129,
|
| 529 |
+
"eval_loss": 0.383698046207428,
|
| 530 |
+
"eval_precision_macro": 0.9285092418542091,
|
| 531 |
+
"eval_precision_micro": 0.907258064516129,
|
| 532 |
+
"eval_recall_macro": 0.9084149302207563,
|
| 533 |
+
"eval_recall_micro": 0.907258064516129,
|
| 534 |
+
"eval_runtime": 1.6383,
|
| 535 |
+
"eval_samples_per_second": 454.138,
|
| 536 |
+
"eval_steps_per_second": 56.767,
|
| 537 |
+
"step": 12000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.3576626479852285,
|
| 541 |
+
"grad_norm": 21.04884910583496,
|
| 542 |
+
"learning_rate": 6.685432467442772e-05,
|
| 543 |
+
"loss": 0.3744,
|
| 544 |
+
"step": 12500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.3576626479852285,
|
| 548 |
+
"eval_accuracy": 0.8884408602150538,
|
| 549 |
+
"eval_f1_macro": 0.903985402366871,
|
| 550 |
+
"eval_f1_micro": 0.8884408602150538,
|
| 551 |
+
"eval_loss": 0.33839282393455505,
|
| 552 |
+
"eval_precision_macro": 0.9202041810282631,
|
| 553 |
+
"eval_precision_micro": 0.8884408602150538,
|
| 554 |
+
"eval_recall_macro": 0.9167129841156823,
|
| 555 |
+
"eval_recall_micro": 0.8884408602150538,
|
| 556 |
+
"eval_runtime": 1.5684,
|
| 557 |
+
"eval_samples_per_second": 474.375,
|
| 558 |
+
"eval_steps_per_second": 59.297,
|
| 559 |
+
"step": 12500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.4119691539046377,
|
| 563 |
+
"grad_norm": 2.0264995098114014,
|
| 564 |
+
"learning_rate": 6.541975827485887e-05,
|
| 565 |
+
"loss": 0.3789,
|
| 566 |
+
"step": 13000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.4119691539046377,
|
| 570 |
+
"eval_accuracy": 0.8548387096774194,
|
| 571 |
+
"eval_f1_macro": 0.8568056198138125,
|
| 572 |
+
"eval_f1_micro": 0.8548387096774194,
|
| 573 |
+
"eval_loss": 0.5327471494674683,
|
| 574 |
+
"eval_precision_macro": 0.8878810831304436,
|
| 575 |
+
"eval_precision_micro": 0.8548387096774194,
|
| 576 |
+
"eval_recall_macro": 0.8739629853819976,
|
| 577 |
+
"eval_recall_micro": 0.8548387096774194,
|
| 578 |
+
"eval_runtime": 1.5511,
|
| 579 |
+
"eval_samples_per_second": 479.662,
|
| 580 |
+
"eval_steps_per_second": 59.958,
|
| 581 |
+
"step": 13000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.466275659824047,
|
| 585 |
+
"grad_norm": 3.5367252826690674,
|
| 586 |
+
"learning_rate": 6.392811057759191e-05,
|
| 587 |
+
"loss": 0.3494,
|
| 588 |
+
"step": 13500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.466275659824047,
|
| 592 |
+
"eval_accuracy": 0.9005376344086021,
|
| 593 |
+
"eval_f1_macro": 0.8873317559394204,
|
| 594 |
+
"eval_f1_micro": 0.9005376344086021,
|
| 595 |
+
"eval_loss": 0.38247689604759216,
|
| 596 |
+
"eval_precision_macro": 0.8991156587188684,
|
| 597 |
+
"eval_precision_micro": 0.9005376344086021,
|
| 598 |
+
"eval_recall_macro": 0.8980828267359259,
|
| 599 |
+
"eval_recall_micro": 0.9005376344086021,
|
| 600 |
+
"eval_runtime": 1.545,
|
| 601 |
+
"eval_samples_per_second": 481.563,
|
| 602 |
+
"eval_steps_per_second": 60.195,
|
| 603 |
+
"step": 13500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.520582165743456,
|
| 607 |
+
"grad_norm": 0.7285934090614319,
|
| 608 |
+
"learning_rate": 6.238273114973711e-05,
|
| 609 |
+
"loss": 0.3942,
|
| 610 |
+
"step": 14000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.520582165743456,
|
| 614 |
+
"eval_accuracy": 0.9045698924731183,
|
| 615 |
+
"eval_f1_macro": 0.8961888882643896,
|
| 616 |
+
"eval_f1_micro": 0.9045698924731183,
|
| 617 |
+
"eval_loss": 0.45909252762794495,
|
| 618 |
+
"eval_precision_macro": 0.9132890481201191,
|
| 619 |
+
"eval_precision_micro": 0.9045698924731183,
|
| 620 |
+
"eval_recall_macro": 0.896670735624709,
|
| 621 |
+
"eval_recall_micro": 0.9045698924731183,
|
| 622 |
+
"eval_runtime": 1.5463,
|
| 623 |
+
"eval_samples_per_second": 481.142,
|
| 624 |
+
"eval_steps_per_second": 60.143,
|
| 625 |
+
"step": 14000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.5748886716628652,
|
| 629 |
+
"grad_norm": 2.59505295753479,
|
| 630 |
+
"learning_rate": 6.078709021560674e-05,
|
| 631 |
+
"loss": 0.3023,
|
| 632 |
+
"step": 14500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.5748886716628652,
|
| 636 |
+
"eval_accuracy": 0.8978494623655914,
|
| 637 |
+
"eval_f1_macro": 0.8915991372968476,
|
| 638 |
+
"eval_f1_micro": 0.8978494623655914,
|
| 639 |
+
"eval_loss": 0.5516388416290283,
|
| 640 |
+
"eval_precision_macro": 0.9068635931933978,
|
| 641 |
+
"eval_precision_micro": 0.8978494623655914,
|
| 642 |
+
"eval_recall_macro": 0.8942451339148669,
|
| 643 |
+
"eval_recall_micro": 0.8978494623655914,
|
| 644 |
+
"eval_runtime": 1.5446,
|
| 645 |
+
"eval_samples_per_second": 481.685,
|
| 646 |
+
"eval_steps_per_second": 60.211,
|
| 647 |
+
"step": 14500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.6291951775822744,
|
| 651 |
+
"grad_norm": 2.187466859817505,
|
| 652 |
+
"learning_rate": 5.9144770864158464e-05,
|
| 653 |
+
"loss": 0.3757,
|
| 654 |
+
"step": 15000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.6291951775822744,
|
| 658 |
+
"eval_accuracy": 0.8951612903225806,
|
| 659 |
+
"eval_f1_macro": 0.8833952116973107,
|
| 660 |
+
"eval_f1_micro": 0.8951612903225806,
|
| 661 |
+
"eval_loss": 0.4487917423248291,
|
| 662 |
+
"eval_precision_macro": 0.9141733968196161,
|
| 663 |
+
"eval_precision_micro": 0.8951612903225806,
|
| 664 |
+
"eval_recall_macro": 0.8813523748993086,
|
| 665 |
+
"eval_recall_micro": 0.8951612903225806,
|
| 666 |
+
"eval_runtime": 1.5598,
|
| 667 |
+
"eval_samples_per_second": 476.976,
|
| 668 |
+
"eval_steps_per_second": 59.622,
|
| 669 |
+
"step": 15000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.6835016835016834,
|
| 673 |
+
"grad_norm": 0.7013949751853943,
|
| 674 |
+
"learning_rate": 5.745946100299554e-05,
|
| 675 |
+
"loss": 0.3241,
|
| 676 |
+
"step": 15500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.6835016835016834,
|
| 680 |
+
"eval_accuracy": 0.8817204301075269,
|
| 681 |
+
"eval_f1_macro": 0.8941666527754931,
|
| 682 |
+
"eval_f1_micro": 0.8817204301075269,
|
| 683 |
+
"eval_loss": 0.39030957221984863,
|
| 684 |
+
"eval_precision_macro": 0.9229567222513297,
|
| 685 |
+
"eval_precision_micro": 0.8817204301075269,
|
| 686 |
+
"eval_recall_macro": 0.9032318624546449,
|
| 687 |
+
"eval_recall_micro": 0.8817204301075269,
|
| 688 |
+
"eval_runtime": 1.5563,
|
| 689 |
+
"eval_samples_per_second": 478.06,
|
| 690 |
+
"eval_steps_per_second": 59.757,
|
| 691 |
+
"step": 15500
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.7378081894210926,
|
| 695 |
+
"grad_norm": 28.38803482055664,
|
| 696 |
+
"learning_rate": 5.573494507699185e-05,
|
| 697 |
+
"loss": 0.349,
|
| 698 |
+
"step": 16000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.7378081894210926,
|
| 702 |
+
"eval_accuracy": 0.9126344086021505,
|
| 703 |
+
"eval_f1_macro": 0.9078743168203657,
|
| 704 |
+
"eval_f1_micro": 0.9126344086021505,
|
| 705 |
+
"eval_loss": 0.26589375734329224,
|
| 706 |
+
"eval_precision_macro": 0.9294672653448444,
|
| 707 |
+
"eval_precision_micro": 0.9126344086021505,
|
| 708 |
+
"eval_recall_macro": 0.9187759272246643,
|
| 709 |
+
"eval_recall_micro": 0.9126344086021505,
|
| 710 |
+
"eval_runtime": 1.5586,
|
| 711 |
+
"eval_samples_per_second": 477.346,
|
| 712 |
+
"eval_steps_per_second": 59.668,
|
| 713 |
+
"step": 16000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.7921146953405018,
|
| 717 |
+
"grad_norm": 119.5204086303711,
|
| 718 |
+
"learning_rate": 5.3975095570137725e-05,
|
| 719 |
+
"loss": 0.3292,
|
| 720 |
+
"step": 16500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.7921146953405018,
|
| 724 |
+
"eval_accuracy": 0.8776881720430108,
|
| 725 |
+
"eval_f1_macro": 0.8896563190824521,
|
| 726 |
+
"eval_f1_micro": 0.8776881720430108,
|
| 727 |
+
"eval_loss": 0.3458763062953949,
|
| 728 |
+
"eval_precision_macro": 0.9206080781097684,
|
| 729 |
+
"eval_precision_micro": 0.8776881720430108,
|
| 730 |
+
"eval_recall_macro": 0.8957695476343184,
|
| 731 |
+
"eval_recall_micro": 0.8776881720430108,
|
| 732 |
+
"eval_runtime": 1.6873,
|
| 733 |
+
"eval_samples_per_second": 440.949,
|
| 734 |
+
"eval_steps_per_second": 55.119,
|
| 735 |
+
"step": 16500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.8464212012599108,
|
| 739 |
+
"grad_norm": 0.7282613515853882,
|
| 740 |
+
"learning_rate": 5.21838643096897e-05,
|
| 741 |
+
"loss": 0.3063,
|
| 742 |
+
"step": 17000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.8464212012599108,
|
| 746 |
+
"eval_accuracy": 0.8991935483870968,
|
| 747 |
+
"eval_f1_macro": 0.8879891940359544,
|
| 748 |
+
"eval_f1_micro": 0.8991935483870968,
|
| 749 |
+
"eval_loss": 0.45412322878837585,
|
| 750 |
+
"eval_precision_macro": 0.9073381957613869,
|
| 751 |
+
"eval_precision_micro": 0.8991935483870968,
|
| 752 |
+
"eval_recall_macro": 0.901361453647893,
|
| 753 |
+
"eval_recall_micro": 0.8991935483870968,
|
| 754 |
+
"eval_runtime": 1.5907,
|
| 755 |
+
"eval_samples_per_second": 467.726,
|
| 756 |
+
"eval_steps_per_second": 58.466,
|
| 757 |
+
"step": 17000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.90072770717932,
|
| 761 |
+
"grad_norm": 22.810928344726562,
|
| 762 |
+
"learning_rate": 5.036527359215105e-05,
|
| 763 |
+
"loss": 0.2974,
|
| 764 |
+
"step": 17500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.90072770717932,
|
| 768 |
+
"eval_accuracy": 0.9139784946236559,
|
| 769 |
+
"eval_f1_macro": 0.9147040216841583,
|
| 770 |
+
"eval_f1_micro": 0.9139784946236559,
|
| 771 |
+
"eval_loss": 0.2588426470756531,
|
| 772 |
+
"eval_precision_macro": 0.9280953295150929,
|
| 773 |
+
"eval_precision_micro": 0.9139784946236559,
|
| 774 |
+
"eval_recall_macro": 0.9254419270814122,
|
| 775 |
+
"eval_recall_micro": 0.9139784946236559,
|
| 776 |
+
"eval_runtime": 1.5934,
|
| 777 |
+
"eval_samples_per_second": 466.917,
|
| 778 |
+
"eval_steps_per_second": 58.365,
|
| 779 |
+
"step": 17500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.9550342130987293,
|
| 783 |
+
"grad_norm": 0.9817183613777161,
|
| 784 |
+
"learning_rate": 4.8523407151010365e-05,
|
| 785 |
+
"loss": 0.2938,
|
| 786 |
+
"step": 18000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.9550342130987293,
|
| 790 |
+
"eval_accuracy": 0.875,
|
| 791 |
+
"eval_f1_macro": 0.8887166776365175,
|
| 792 |
+
"eval_f1_micro": 0.875,
|
| 793 |
+
"eval_loss": 0.45612600445747375,
|
| 794 |
+
"eval_precision_macro": 0.915931173623922,
|
| 795 |
+
"eval_precision_micro": 0.875,
|
| 796 |
+
"eval_recall_macro": 0.8997546027307288,
|
| 797 |
+
"eval_recall_micro": 0.875,
|
| 798 |
+
"eval_runtime": 1.6003,
|
| 799 |
+
"eval_samples_per_second": 464.907,
|
| 800 |
+
"eval_steps_per_second": 58.113,
|
| 801 |
+
"step": 18000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.0093407190181383,
|
| 805 |
+
"grad_norm": 85.74153137207031,
|
| 806 |
+
"learning_rate": 4.66624009865203e-05,
|
| 807 |
+
"loss": 0.3067,
|
| 808 |
+
"step": 18500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.0093407190181383,
|
| 812 |
+
"eval_accuracy": 0.8844086021505376,
|
| 813 |
+
"eval_f1_macro": 0.8921145619678118,
|
| 814 |
+
"eval_f1_micro": 0.8844086021505376,
|
| 815 |
+
"eval_loss": 0.3737676739692688,
|
| 816 |
+
"eval_precision_macro": 0.9173188296546068,
|
| 817 |
+
"eval_precision_micro": 0.8844086021505376,
|
| 818 |
+
"eval_recall_macro": 0.9047881017377212,
|
| 819 |
+
"eval_recall_micro": 0.8844086021505376,
|
| 820 |
+
"eval_runtime": 1.733,
|
| 821 |
+
"eval_samples_per_second": 429.309,
|
| 822 |
+
"eval_steps_per_second": 53.664,
|
| 823 |
+
"step": 18500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.0636472249375477,
|
| 827 |
+
"grad_norm": 4.293463706970215,
|
| 828 |
+
"learning_rate": 4.479019814743586e-05,
|
| 829 |
+
"loss": 0.1653,
|
| 830 |
+
"step": 19000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.0636472249375477,
|
| 834 |
+
"eval_accuracy": 0.9005376344086021,
|
| 835 |
+
"eval_f1_macro": 0.8930738638150588,
|
| 836 |
+
"eval_f1_micro": 0.9005376344086021,
|
| 837 |
+
"eval_loss": 0.5207958221435547,
|
| 838 |
+
"eval_precision_macro": 0.9287838810859212,
|
| 839 |
+
"eval_precision_micro": 0.9005376344086021,
|
| 840 |
+
"eval_recall_macro": 0.8936382765105635,
|
| 841 |
+
"eval_recall_micro": 0.9005376344086021,
|
| 842 |
+
"eval_runtime": 1.5912,
|
| 843 |
+
"eval_samples_per_second": 467.585,
|
| 844 |
+
"eval_steps_per_second": 58.448,
|
| 845 |
+
"step": 19000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.1179537308569567,
|
| 849 |
+
"grad_norm": 1.4437882900238037,
|
| 850 |
+
"learning_rate": 4.2907281661980334e-05,
|
| 851 |
+
"loss": 0.1901,
|
| 852 |
+
"step": 19500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.1179537308569567,
|
| 856 |
+
"eval_accuracy": 0.9206989247311828,
|
| 857 |
+
"eval_f1_macro": 0.9210532754724804,
|
| 858 |
+
"eval_f1_micro": 0.9206989247311828,
|
| 859 |
+
"eval_loss": 0.2993380129337311,
|
| 860 |
+
"eval_precision_macro": 0.9381153626922412,
|
| 861 |
+
"eval_precision_micro": 0.9206989247311828,
|
| 862 |
+
"eval_recall_macro": 0.9300212877722726,
|
| 863 |
+
"eval_recall_micro": 0.9206989247311828,
|
| 864 |
+
"eval_runtime": 1.7299,
|
| 865 |
+
"eval_samples_per_second": 430.073,
|
| 866 |
+
"eval_steps_per_second": 53.759,
|
| 867 |
+
"step": 19500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.1722602367763657,
|
| 871 |
+
"grad_norm": 764.3075561523438,
|
| 872 |
+
"learning_rate": 4.101407270852778e-05,
|
| 873 |
+
"loss": 0.2271,
|
| 874 |
+
"step": 20000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.1722602367763657,
|
| 878 |
+
"eval_accuracy": 0.9032258064516129,
|
| 879 |
+
"eval_f1_macro": 0.9205221777214502,
|
| 880 |
+
"eval_f1_micro": 0.9032258064516129,
|
| 881 |
+
"eval_loss": 0.27076366543769836,
|
| 882 |
+
"eval_precision_macro": 0.9497791884188832,
|
| 883 |
+
"eval_precision_micro": 0.9032258064516129,
|
| 884 |
+
"eval_recall_macro": 0.9297648445536885,
|
| 885 |
+
"eval_recall_micro": 0.9032258064516129,
|
| 886 |
+
"eval_runtime": 1.5754,
|
| 887 |
+
"eval_samples_per_second": 472.249,
|
| 888 |
+
"eval_steps_per_second": 59.031,
|
| 889 |
+
"step": 20000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.226566742695775,
|
| 893 |
+
"grad_norm": 8.108640670776367,
|
| 894 |
+
"learning_rate": 3.911858660572008e-05,
|
| 895 |
+
"loss": 0.2108,
|
| 896 |
+
"step": 20500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.226566742695775,
|
| 900 |
+
"eval_accuracy": 0.9220430107526881,
|
| 901 |
+
"eval_f1_macro": 0.9187239197738657,
|
| 902 |
+
"eval_f1_micro": 0.9220430107526881,
|
| 903 |
+
"eval_loss": 0.27602580189704895,
|
| 904 |
+
"eval_precision_macro": 0.9334752930289422,
|
| 905 |
+
"eval_precision_micro": 0.9220430107526881,
|
| 906 |
+
"eval_recall_macro": 0.9228409582632311,
|
| 907 |
+
"eval_recall_micro": 0.9220430107526881,
|
| 908 |
+
"eval_runtime": 1.5758,
|
| 909 |
+
"eval_samples_per_second": 472.143,
|
| 910 |
+
"eval_steps_per_second": 59.018,
|
| 911 |
+
"step": 20500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.280873248615184,
|
| 915 |
+
"grad_norm": 2.4227545261383057,
|
| 916 |
+
"learning_rate": 3.7225079759355747e-05,
|
| 917 |
+
"loss": 0.2068,
|
| 918 |
+
"step": 21000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.280873248615184,
|
| 922 |
+
"eval_accuracy": 0.9247311827956989,
|
| 923 |
+
"eval_f1_macro": 0.9260496184754449,
|
| 924 |
+
"eval_f1_micro": 0.9247311827956989,
|
| 925 |
+
"eval_loss": 0.25598055124282837,
|
| 926 |
+
"eval_precision_macro": 0.9394381557552136,
|
| 927 |
+
"eval_precision_micro": 0.9247311827956989,
|
| 928 |
+
"eval_recall_macro": 0.9349235944200235,
|
| 929 |
+
"eval_recall_micro": 0.9247311827956989,
|
| 930 |
+
"eval_runtime": 1.5558,
|
| 931 |
+
"eval_samples_per_second": 478.204,
|
| 932 |
+
"eval_steps_per_second": 59.776,
|
| 933 |
+
"step": 21000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.335179754534593,
|
| 937 |
+
"grad_norm": 1.4017307758331299,
|
| 938 |
+
"learning_rate": 3.5337804130717096e-05,
|
| 939 |
+
"loss": 0.2171,
|
| 940 |
+
"step": 21500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.335179754534593,
|
| 944 |
+
"eval_accuracy": 0.9166666666666666,
|
| 945 |
+
"eval_f1_macro": 0.9162826856619433,
|
| 946 |
+
"eval_f1_micro": 0.9166666666666666,
|
| 947 |
+
"eval_loss": 0.23610982298851013,
|
| 948 |
+
"eval_precision_macro": 0.9248109520591958,
|
| 949 |
+
"eval_precision_micro": 0.9166666666666666,
|
| 950 |
+
"eval_recall_macro": 0.9257832999982825,
|
| 951 |
+
"eval_recall_micro": 0.9166666666666666,
|
| 952 |
+
"eval_runtime": 1.6011,
|
| 953 |
+
"eval_samples_per_second": 464.685,
|
| 954 |
+
"eval_steps_per_second": 58.086,
|
| 955 |
+
"step": 21500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.389486260454002,
|
| 959 |
+
"grad_norm": 3.65702486038208,
|
| 960 |
+
"learning_rate": 3.34609976885854e-05,
|
| 961 |
+
"loss": 0.1544,
|
| 962 |
+
"step": 22000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.389486260454002,
|
| 966 |
+
"eval_accuracy": 0.8938172043010753,
|
| 967 |
+
"eval_f1_macro": 0.9112579615652996,
|
| 968 |
+
"eval_f1_micro": 0.8938172043010753,
|
| 969 |
+
"eval_loss": 0.31801822781562805,
|
| 970 |
+
"eval_precision_macro": 0.9257465643895157,
|
| 971 |
+
"eval_precision_micro": 0.8938172043010753,
|
| 972 |
+
"eval_recall_macro": 0.9157454548646736,
|
| 973 |
+
"eval_recall_micro": 0.8938172043010753,
|
| 974 |
+
"eval_runtime": 1.5901,
|
| 975 |
+
"eval_samples_per_second": 467.885,
|
| 976 |
+
"eval_steps_per_second": 58.486,
|
| 977 |
+
"step": 22000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.4437927663734116,
|
| 981 |
+
"grad_norm": 17.16629409790039,
|
| 982 |
+
"learning_rate": 3.15988748926769e-05,
|
| 983 |
+
"loss": 0.2244,
|
| 984 |
+
"step": 22500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.4437927663734116,
|
| 988 |
+
"eval_accuracy": 0.9274193548387096,
|
| 989 |
+
"eval_f1_macro": 0.929163688176975,
|
| 990 |
+
"eval_f1_micro": 0.9274193548387096,
|
| 991 |
+
"eval_loss": 0.2233731597661972,
|
| 992 |
+
"eval_precision_macro": 0.9488357724575086,
|
| 993 |
+
"eval_precision_micro": 0.9274193548387096,
|
| 994 |
+
"eval_recall_macro": 0.9373529300126245,
|
| 995 |
+
"eval_recall_micro": 0.9274193548387096,
|
| 996 |
+
"eval_runtime": 1.5811,
|
| 997 |
+
"eval_samples_per_second": 470.56,
|
| 998 |
+
"eval_steps_per_second": 58.82,
|
| 999 |
+
"step": 22500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.4980992722928206,
|
| 1003 |
+
"grad_norm": 0.002982610370963812,
|
| 1004 |
+
"learning_rate": 2.9755617229869363e-05,
|
| 1005 |
+
"loss": 0.1862,
|
| 1006 |
+
"step": 23000
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.4980992722928206,
|
| 1010 |
+
"eval_accuracy": 0.9233870967741935,
|
| 1011 |
+
"eval_f1_macro": 0.928924685412107,
|
| 1012 |
+
"eval_f1_micro": 0.9233870967741935,
|
| 1013 |
+
"eval_loss": 0.2193865180015564,
|
| 1014 |
+
"eval_precision_macro": 0.9530930478155653,
|
| 1015 |
+
"eval_precision_micro": 0.9233870967741935,
|
| 1016 |
+
"eval_recall_macro": 0.9284052780385081,
|
| 1017 |
+
"eval_recall_micro": 0.9233870967741935,
|
| 1018 |
+
"eval_runtime": 1.5911,
|
| 1019 |
+
"eval_samples_per_second": 467.594,
|
| 1020 |
+
"eval_steps_per_second": 58.449,
|
| 1021 |
+
"step": 23000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.55240577821223,
|
| 1025 |
+
"grad_norm": 0.005432271398603916,
|
| 1026 |
+
"learning_rate": 2.7942593577289413e-05,
|
| 1027 |
+
"loss": 0.1675,
|
| 1028 |
+
"step": 23500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.55240577821223,
|
| 1032 |
+
"eval_accuracy": 0.9032258064516129,
|
| 1033 |
+
"eval_f1_macro": 0.9171716939776399,
|
| 1034 |
+
"eval_f1_micro": 0.9032258064516129,
|
| 1035 |
+
"eval_loss": 0.28054481744766235,
|
| 1036 |
+
"eval_precision_macro": 0.9380595809537082,
|
| 1037 |
+
"eval_precision_micro": 0.9032258064516129,
|
| 1038 |
+
"eval_recall_macro": 0.9295445270488267,
|
| 1039 |
+
"eval_recall_micro": 0.9032258064516129,
|
| 1040 |
+
"eval_runtime": 1.5905,
|
| 1041 |
+
"eval_samples_per_second": 467.768,
|
| 1042 |
+
"eval_steps_per_second": 58.471,
|
| 1043 |
+
"step": 23500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.606712284131639,
|
| 1047 |
+
"grad_norm": 1.1801046133041382,
|
| 1048 |
+
"learning_rate": 2.6149315464903132e-05,
|
| 1049 |
+
"loss": 0.2154,
|
| 1050 |
+
"step": 24000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.606712284131639,
|
| 1054 |
+
"eval_accuracy": 0.9099462365591398,
|
| 1055 |
+
"eval_f1_macro": 0.9317358502662257,
|
| 1056 |
+
"eval_f1_micro": 0.9099462365591398,
|
| 1057 |
+
"eval_loss": 0.20521479845046997,
|
| 1058 |
+
"eval_precision_macro": 0.9532059136761886,
|
| 1059 |
+
"eval_precision_micro": 0.9099462365591398,
|
| 1060 |
+
"eval_recall_macro": 0.9443101546357744,
|
| 1061 |
+
"eval_recall_micro": 0.9099462365591398,
|
| 1062 |
+
"eval_runtime": 1.6188,
|
| 1063 |
+
"eval_samples_per_second": 459.613,
|
| 1064 |
+
"eval_steps_per_second": 57.452,
|
| 1065 |
+
"step": 24000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.661018790051048,
|
| 1069 |
+
"grad_norm": 2.6474785804748535,
|
| 1070 |
+
"learning_rate": 2.4387139735109228e-05,
|
| 1071 |
+
"loss": 0.1994,
|
| 1072 |
+
"step": 24500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.661018790051048,
|
| 1076 |
+
"eval_accuracy": 0.9206989247311828,
|
| 1077 |
+
"eval_f1_macro": 0.9285830674772237,
|
| 1078 |
+
"eval_f1_micro": 0.9206989247311828,
|
| 1079 |
+
"eval_loss": 0.3016538619995117,
|
| 1080 |
+
"eval_precision_macro": 0.9344600444511141,
|
| 1081 |
+
"eval_precision_micro": 0.9206989247311828,
|
| 1082 |
+
"eval_recall_macro": 0.9264637971148902,
|
| 1083 |
+
"eval_recall_micro": 0.9206989247311828,
|
| 1084 |
+
"eval_runtime": 1.5905,
|
| 1085 |
+
"eval_samples_per_second": 467.768,
|
| 1086 |
+
"eval_steps_per_second": 58.471,
|
| 1087 |
+
"step": 24500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.715325295970457,
|
| 1091 |
+
"grad_norm": 0.6192300319671631,
|
| 1092 |
+
"learning_rate": 2.266002343881043e-05,
|
| 1093 |
+
"loss": 0.1693,
|
| 1094 |
+
"step": 25000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.715325295970457,
|
| 1098 |
+
"eval_accuracy": 0.9247311827956989,
|
| 1099 |
+
"eval_f1_macro": 0.9264992560565771,
|
| 1100 |
+
"eval_f1_micro": 0.9247311827956989,
|
| 1101 |
+
"eval_loss": 0.2687015235424042,
|
| 1102 |
+
"eval_precision_macro": 0.9451846988558618,
|
| 1103 |
+
"eval_precision_micro": 0.9247311827956989,
|
| 1104 |
+
"eval_recall_macro": 0.931429635216938,
|
| 1105 |
+
"eval_recall_micro": 0.9247311827956989,
|
| 1106 |
+
"eval_runtime": 1.5613,
|
| 1107 |
+
"eval_samples_per_second": 476.521,
|
| 1108 |
+
"eval_steps_per_second": 59.565,
|
| 1109 |
+
"step": 25000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.7696318018898665,
|
| 1113 |
+
"grad_norm": 1.0121103525161743,
|
| 1114 |
+
"learning_rate": 2.0971844899254465e-05,
|
| 1115 |
+
"loss": 0.1455,
|
| 1116 |
+
"step": 25500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.7696318018898665,
|
| 1120 |
+
"eval_accuracy": 0.9301075268817204,
|
| 1121 |
+
"eval_f1_macro": 0.9355979987630854,
|
| 1122 |
+
"eval_f1_micro": 0.9301075268817204,
|
| 1123 |
+
"eval_loss": 0.1772308498620987,
|
| 1124 |
+
"eval_precision_macro": 0.9578394473984728,
|
| 1125 |
+
"eval_precision_micro": 0.9301075268817204,
|
| 1126 |
+
"eval_recall_macro": 0.9376020750294228,
|
| 1127 |
+
"eval_recall_micro": 0.9301075268817204,
|
| 1128 |
+
"eval_runtime": 1.5579,
|
| 1129 |
+
"eval_samples_per_second": 477.553,
|
| 1130 |
+
"eval_steps_per_second": 59.694,
|
| 1131 |
+
"step": 25500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.8239383078092755,
|
| 1135 |
+
"grad_norm": 7.186190605163574,
|
| 1136 |
+
"learning_rate": 1.9326395003071377e-05,
|
| 1137 |
+
"loss": 0.1483,
|
| 1138 |
+
"step": 26000
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.8239383078092755,
|
| 1142 |
+
"eval_accuracy": 0.9099462365591398,
|
| 1143 |
+
"eval_f1_macro": 0.9274305548763755,
|
| 1144 |
+
"eval_f1_micro": 0.9099462365591398,
|
| 1145 |
+
"eval_loss": 0.2263285517692566,
|
| 1146 |
+
"eval_precision_macro": 0.9497007612847732,
|
| 1147 |
+
"eval_precision_micro": 0.9099462365591398,
|
| 1148 |
+
"eval_recall_macro": 0.9370680110954468,
|
| 1149 |
+
"eval_recall_micro": 0.9099462365591398,
|
| 1150 |
+
"eval_runtime": 1.5569,
|
| 1151 |
+
"eval_samples_per_second": 477.873,
|
| 1152 |
+
"eval_steps_per_second": 59.734,
|
| 1153 |
+
"step": 26000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.878244813728685,
|
| 1157 |
+
"grad_norm": 0.7355983257293701,
|
| 1158 |
+
"learning_rate": 1.77273686876542e-05,
|
| 1159 |
+
"loss": 0.1228,
|
| 1160 |
+
"step": 26500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.878244813728685,
|
| 1164 |
+
"eval_accuracy": 0.9139784946236559,
|
| 1165 |
+
"eval_f1_macro": 0.9345990129995828,
|
| 1166 |
+
"eval_f1_micro": 0.9139784946236559,
|
| 1167 |
+
"eval_loss": 0.15667569637298584,
|
| 1168 |
+
"eval_precision_macro": 0.9546581752954356,
|
| 1169 |
+
"eval_precision_micro": 0.9139784946236559,
|
| 1170 |
+
"eval_recall_macro": 0.9451982881542952,
|
| 1171 |
+
"eval_recall_micro": 0.9139784946236559,
|
| 1172 |
+
"eval_runtime": 1.5563,
|
| 1173 |
+
"eval_samples_per_second": 478.061,
|
| 1174 |
+
"eval_steps_per_second": 59.758,
|
| 1175 |
+
"step": 26500
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.932551319648094,
|
| 1179 |
+
"grad_norm": 1.0231633186340332,
|
| 1180 |
+
"learning_rate": 1.617835664399812e-05,
|
| 1181 |
+
"loss": 0.1627,
|
| 1182 |
+
"step": 27000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.932551319648094,
|
| 1186 |
+
"eval_accuracy": 0.9112903225806451,
|
| 1187 |
+
"eval_f1_macro": 0.9300960898223695,
|
| 1188 |
+
"eval_f1_micro": 0.9112903225806451,
|
| 1189 |
+
"eval_loss": 0.19375352561473846,
|
| 1190 |
+
"eval_precision_macro": 0.9520703470166678,
|
| 1191 |
+
"eval_precision_micro": 0.9112903225806451,
|
| 1192 |
+
"eval_recall_macro": 0.9397685186488954,
|
| 1193 |
+
"eval_recall_micro": 0.9112903225806451,
|
| 1194 |
+
"eval_runtime": 1.5507,
|
| 1195 |
+
"eval_samples_per_second": 479.787,
|
| 1196 |
+
"eval_steps_per_second": 59.973,
|
| 1197 |
+
"step": 27000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.986857825567503,
|
| 1201 |
+
"grad_norm": 1.2636340856552124,
|
| 1202 |
+
"learning_rate": 1.4682837253630058e-05,
|
| 1203 |
+
"loss": 0.1106,
|
| 1204 |
+
"step": 27500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 2.986857825567503,
|
| 1208 |
+
"eval_accuracy": 0.9314516129032258,
|
| 1209 |
+
"eval_f1_macro": 0.9360611349608771,
|
| 1210 |
+
"eval_f1_micro": 0.9314516129032258,
|
| 1211 |
+
"eval_loss": 0.18830984830856323,
|
| 1212 |
+
"eval_precision_macro": 0.9530936916231376,
|
| 1213 |
+
"eval_precision_micro": 0.9314516129032258,
|
| 1214 |
+
"eval_recall_macro": 0.9396110759039699,
|
| 1215 |
+
"eval_recall_micro": 0.9314516129032258,
|
| 1216 |
+
"eval_runtime": 1.5429,
|
| 1217 |
+
"eval_samples_per_second": 482.224,
|
| 1218 |
+
"eval_steps_per_second": 60.278,
|
| 1219 |
+
"step": 27500
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 3.0411643314869123,
|
| 1223 |
+
"grad_norm": 1.0935313701629639,
|
| 1224 |
+
"learning_rate": 1.3244168777734551e-05,
|
| 1225 |
+
"loss": 0.1105,
|
| 1226 |
+
"step": 28000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.0411643314869123,
|
| 1230 |
+
"eval_accuracy": 0.9341397849462365,
|
| 1231 |
+
"eval_f1_macro": 0.9393547932119972,
|
| 1232 |
+
"eval_f1_micro": 0.9341397849462365,
|
| 1233 |
+
"eval_loss": 0.1898634135723114,
|
| 1234 |
+
"eval_precision_macro": 0.9593318319238684,
|
| 1235 |
+
"eval_precision_micro": 0.9341397849462365,
|
| 1236 |
+
"eval_recall_macro": 0.945290330511796,
|
| 1237 |
+
"eval_recall_micro": 0.9341397849462365,
|
| 1238 |
+
"eval_runtime": 1.5415,
|
| 1239 |
+
"eval_samples_per_second": 482.636,
|
| 1240 |
+
"eval_steps_per_second": 60.329,
|
| 1241 |
+
"step": 28000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.0954708374063213,
|
| 1245 |
+
"grad_norm": 1.7280462980270386,
|
| 1246 |
+
"learning_rate": 1.1865581816015724e-05,
|
| 1247 |
+
"loss": 0.0978,
|
| 1248 |
+
"step": 28500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.0954708374063213,
|
| 1252 |
+
"eval_accuracy": 0.9126344086021505,
|
| 1253 |
+
"eval_f1_macro": 0.932842505921675,
|
| 1254 |
+
"eval_f1_micro": 0.9126344086021505,
|
| 1255 |
+
"eval_loss": 0.1739678680896759,
|
| 1256 |
+
"eval_precision_macro": 0.9588560830865595,
|
| 1257 |
+
"eval_precision_micro": 0.9126344086021505,
|
| 1258 |
+
"eval_recall_macro": 0.9441396878334974,
|
| 1259 |
+
"eval_recall_micro": 0.9126344086021505,
|
| 1260 |
+
"eval_runtime": 1.5969,
|
| 1261 |
+
"eval_samples_per_second": 465.902,
|
| 1262 |
+
"eval_steps_per_second": 58.238,
|
| 1263 |
+
"step": 28500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.1497773433257303,
|
| 1267 |
+
"grad_norm": 4.298096656799316,
|
| 1268 |
+
"learning_rate": 1.055017205222924e-05,
|
| 1269 |
+
"loss": 0.0847,
|
| 1270 |
+
"step": 29000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.1497773433257303,
|
| 1274 |
+
"eval_accuracy": 0.907258064516129,
|
| 1275 |
+
"eval_f1_macro": 0.9287242305872121,
|
| 1276 |
+
"eval_f1_micro": 0.907258064516129,
|
| 1277 |
+
"eval_loss": 0.18464291095733643,
|
| 1278 |
+
"eval_precision_macro": 0.9485674275338388,
|
| 1279 |
+
"eval_precision_micro": 0.907258064516129,
|
| 1280 |
+
"eval_recall_macro": 0.9397129171252141,
|
| 1281 |
+
"eval_recall_micro": 0.907258064516129,
|
| 1282 |
+
"eval_runtime": 1.5931,
|
| 1283 |
+
"eval_samples_per_second": 467.028,
|
| 1284 |
+
"eval_steps_per_second": 58.378,
|
| 1285 |
+
"step": 29000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 3.20408384924514,
|
| 1289 |
+
"grad_norm": 2.599429130554199,
|
| 1290 |
+
"learning_rate": 9.30332397145231e-06,
|
| 1291 |
+
"loss": 0.0929,
|
| 1292 |
+
"step": 29500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.20408384924514,
|
| 1296 |
+
"eval_accuracy": 0.928763440860215,
|
| 1297 |
+
"eval_f1_macro": 0.9319260758161285,
|
| 1298 |
+
"eval_f1_micro": 0.928763440860215,
|
| 1299 |
+
"eval_loss": 0.2623588442802429,
|
| 1300 |
+
"eval_precision_macro": 0.9522632308119076,
|
| 1301 |
+
"eval_precision_micro": 0.928763440860215,
|
| 1302 |
+
"eval_recall_macro": 0.9354531905275971,
|
| 1303 |
+
"eval_recall_micro": 0.928763440860215,
|
| 1304 |
+
"eval_runtime": 1.5913,
|
| 1305 |
+
"eval_samples_per_second": 467.542,
|
| 1306 |
+
"eval_steps_per_second": 58.443,
|
| 1307 |
+
"step": 29500
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.258390355164549,
|
| 1311 |
+
"grad_norm": 1.0820720195770264,
|
| 1312 |
+
"learning_rate": 8.122840981545725e-06,
|
| 1313 |
+
"loss": 0.0861,
|
| 1314 |
+
"step": 30000
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.258390355164549,
|
| 1318 |
+
"eval_accuracy": 0.9274193548387096,
|
| 1319 |
+
"eval_f1_macro": 0.9276130625845173,
|
| 1320 |
+
"eval_f1_micro": 0.9274193548387096,
|
| 1321 |
+
"eval_loss": 0.26659145951271057,
|
| 1322 |
+
"eval_precision_macro": 0.9482101341581514,
|
| 1323 |
+
"eval_precision_micro": 0.9274193548387096,
|
| 1324 |
+
"eval_recall_macro": 0.9313633323621086,
|
| 1325 |
+
"eval_recall_micro": 0.9274193548387096,
|
| 1326 |
+
"eval_runtime": 1.5883,
|
| 1327 |
+
"eval_samples_per_second": 468.419,
|
| 1328 |
+
"eval_steps_per_second": 58.552,
|
| 1329 |
+
"step": 30000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.3126968610839578,
|
| 1333 |
+
"grad_norm": 0.9298611283302307,
|
| 1334 |
+
"learning_rate": 7.016084376904304e-06,
|
| 1335 |
+
"loss": 0.1159,
|
| 1336 |
+
"step": 30500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.3126968610839578,
|
| 1340 |
+
"eval_accuracy": 0.9086021505376344,
|
| 1341 |
+
"eval_f1_macro": 0.9269507193451398,
|
| 1342 |
+
"eval_f1_micro": 0.9086021505376344,
|
| 1343 |
+
"eval_loss": 0.2247731238603592,
|
| 1344 |
+
"eval_precision_macro": 0.9537479338140438,
|
| 1345 |
+
"eval_precision_micro": 0.9086021505376344,
|
| 1346 |
+
"eval_recall_macro": 0.9375578499701469,
|
| 1347 |
+
"eval_recall_micro": 0.9086021505376344,
|
| 1348 |
+
"eval_runtime": 1.5934,
|
| 1349 |
+
"eval_samples_per_second": 466.925,
|
| 1350 |
+
"eval_steps_per_second": 58.366,
|
| 1351 |
+
"step": 30500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 3.3670033670033668,
|
| 1355 |
+
"grad_norm": 1.2038335800170898,
|
| 1356 |
+
"learning_rate": 5.981104366775459e-06,
|
| 1357 |
+
"loss": 0.0983,
|
| 1358 |
+
"step": 31000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 3.3670033670033668,
|
| 1362 |
+
"eval_accuracy": 0.9112903225806451,
|
| 1363 |
+
"eval_f1_macro": 0.929673894660028,
|
| 1364 |
+
"eval_f1_micro": 0.9112903225806451,
|
| 1365 |
+
"eval_loss": 0.21170715987682343,
|
| 1366 |
+
"eval_precision_macro": 0.9562636570844839,
|
| 1367 |
+
"eval_precision_micro": 0.9112903225806451,
|
| 1368 |
+
"eval_recall_macro": 0.9408174871583557,
|
| 1369 |
+
"eval_recall_micro": 0.9112903225806451,
|
| 1370 |
+
"eval_runtime": 1.592,
|
| 1371 |
+
"eval_samples_per_second": 467.328,
|
| 1372 |
+
"eval_steps_per_second": 58.416,
|
| 1373 |
+
"step": 31000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 3.421309872922776,
|
| 1377 |
+
"grad_norm": 14.01207447052002,
|
| 1378 |
+
"learning_rate": 5.022515433540584e-06,
|
| 1379 |
+
"loss": 0.1093,
|
| 1380 |
+
"step": 31500
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 3.421309872922776,
|
| 1384 |
+
"eval_accuracy": 0.9341397849462365,
|
| 1385 |
+
"eval_f1_macro": 0.9384885883048681,
|
| 1386 |
+
"eval_f1_micro": 0.9341397849462365,
|
| 1387 |
+
"eval_loss": 0.21036885678768158,
|
| 1388 |
+
"eval_precision_macro": 0.9544129085177095,
|
| 1389 |
+
"eval_precision_micro": 0.9341397849462365,
|
| 1390 |
+
"eval_recall_macro": 0.9426855279069932,
|
| 1391 |
+
"eval_recall_micro": 0.9341397849462365,
|
| 1392 |
+
"eval_runtime": 1.5897,
|
| 1393 |
+
"eval_samples_per_second": 468.025,
|
| 1394 |
+
"eval_steps_per_second": 58.503,
|
| 1395 |
+
"step": 31500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.475616378842185,
|
| 1399 |
+
"grad_norm": 0.0029710547532886267,
|
| 1400 |
+
"learning_rate": 4.142470135051615e-06,
|
| 1401 |
+
"loss": 0.0892,
|
| 1402 |
+
"step": 32000
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 3.475616378842185,
|
| 1406 |
+
"eval_accuracy": 0.9126344086021505,
|
| 1407 |
+
"eval_f1_macro": 0.933263998404932,
|
| 1408 |
+
"eval_f1_micro": 0.9126344086021505,
|
| 1409 |
+
"eval_loss": 0.21525545418262482,
|
| 1410 |
+
"eval_precision_macro": 0.9471592585609407,
|
| 1411 |
+
"eval_precision_micro": 0.9126344086021505,
|
| 1412 |
+
"eval_recall_macro": 0.9420731137871163,
|
| 1413 |
+
"eval_recall_micro": 0.9126344086021505,
|
| 1414 |
+
"eval_runtime": 1.5909,
|
| 1415 |
+
"eval_samples_per_second": 467.651,
|
| 1416 |
+
"eval_steps_per_second": 58.456,
|
| 1417 |
+
"step": 32000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.5299228847615947,
|
| 1421 |
+
"grad_norm": 0.0014916452346369624,
|
| 1422 |
+
"learning_rate": 3.3429446556265453e-06,
|
| 1423 |
+
"loss": 0.0921,
|
| 1424 |
+
"step": 32500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.5299228847615947,
|
| 1428 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1429 |
+
"eval_f1_macro": 0.9403174227850596,
|
| 1430 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1431 |
+
"eval_loss": 0.20182642340660095,
|
| 1432 |
+
"eval_precision_macro": 0.9610729151777162,
|
| 1433 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1434 |
+
"eval_recall_macro": 0.9450761984609293,
|
| 1435 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1436 |
+
"eval_runtime": 1.5911,
|
| 1437 |
+
"eval_samples_per_second": 467.608,
|
| 1438 |
+
"eval_steps_per_second": 58.451,
|
| 1439 |
+
"step": 32500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 3.5842293906810037,
|
| 1443 |
+
"grad_norm": 0.028313804417848587,
|
| 1444 |
+
"learning_rate": 2.625734368431996e-06,
|
| 1445 |
+
"loss": 0.1112,
|
| 1446 |
+
"step": 33000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 3.5842293906810037,
|
| 1450 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1451 |
+
"eval_f1_macro": 0.9403174227850596,
|
| 1452 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1453 |
+
"eval_loss": 0.19140255451202393,
|
| 1454 |
+
"eval_precision_macro": 0.9610729151777162,
|
| 1455 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1456 |
+
"eval_recall_macro": 0.9450761984609293,
|
| 1457 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1458 |
+
"eval_runtime": 1.5433,
|
| 1459 |
+
"eval_samples_per_second": 482.098,
|
| 1460 |
+
"eval_steps_per_second": 60.262,
|
| 1461 |
+
"step": 33000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 3.6385358966004127,
|
| 1465 |
+
"grad_norm": 0.7935597896575928,
|
| 1466 |
+
"learning_rate": 1.992449803885794e-06,
|
| 1467 |
+
"loss": 0.0781,
|
| 1468 |
+
"step": 33500
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 3.6385358966004127,
|
| 1472 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1473 |
+
"eval_f1_macro": 0.9431465250491902,
|
| 1474 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1475 |
+
"eval_loss": 0.18505831062793732,
|
| 1476 |
+
"eval_precision_macro": 0.9605281751371779,
|
| 1477 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1478 |
+
"eval_recall_macro": 0.9482532934747587,
|
| 1479 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1480 |
+
"eval_runtime": 1.5588,
|
| 1481 |
+
"eval_samples_per_second": 477.296,
|
| 1482 |
+
"eval_steps_per_second": 59.662,
|
| 1483 |
+
"step": 33500
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 3.6928424025198217,
|
| 1487 |
+
"grad_norm": 3.4242069721221924,
|
| 1488 |
+
"learning_rate": 1.444513033132977e-06,
|
| 1489 |
+
"loss": 0.104,
|
| 1490 |
+
"step": 34000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 3.6928424025198217,
|
| 1494 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1495 |
+
"eval_f1_macro": 0.9436897074728228,
|
| 1496 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1497 |
+
"eval_loss": 0.1714259684085846,
|
| 1498 |
+
"eval_precision_macro": 0.9618566197941735,
|
| 1499 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1500 |
+
"eval_recall_macro": 0.9478564680779333,
|
| 1501 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1502 |
+
"eval_runtime": 1.5565,
|
| 1503 |
+
"eval_samples_per_second": 478.008,
|
| 1504 |
+
"eval_steps_per_second": 59.751,
|
| 1505 |
+
"step": 34000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.747148908439231,
|
| 1509 |
+
"grad_norm": 0.5764946341514587,
|
| 1510 |
+
"learning_rate": 9.839900655621303e-07,
|
| 1511 |
+
"loss": 0.0771,
|
| 1512 |
+
"step": 34500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 3.747148908439231,
|
| 1516 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1517 |
+
"eval_f1_macro": 0.9453734182306841,
|
| 1518 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1519 |
+
"eval_loss": 0.17406800389289856,
|
| 1520 |
+
"eval_precision_macro": 0.9558439949105471,
|
| 1521 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1522 |
+
"eval_recall_macro": 0.9474835754951718,
|
| 1523 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1524 |
+
"eval_runtime": 1.5564,
|
| 1525 |
+
"eval_samples_per_second": 478.012,
|
| 1526 |
+
"eval_steps_per_second": 59.752,
|
| 1527 |
+
"step": 34500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 3.80145541435864,
|
| 1531 |
+
"grad_norm": 1.5720099210739136,
|
| 1532 |
+
"learning_rate": 6.100695905203458e-07,
|
| 1533 |
+
"loss": 0.0916,
|
| 1534 |
+
"step": 35000
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 3.80145541435864,
|
| 1538 |
+
"eval_accuracy": 0.9341397849462365,
|
| 1539 |
+
"eval_f1_macro": 0.9472436482214578,
|
| 1540 |
+
"eval_f1_micro": 0.9341397849462365,
|
| 1541 |
+
"eval_loss": 0.17374970018863678,
|
| 1542 |
+
"eval_precision_macro": 0.9499695730366108,
|
| 1543 |
+
"eval_precision_micro": 0.9341397849462365,
|
| 1544 |
+
"eval_recall_macro": 0.9488576574662688,
|
| 1545 |
+
"eval_recall_micro": 0.9341397849462365,
|
| 1546 |
+
"eval_runtime": 1.5561,
|
| 1547 |
+
"eval_samples_per_second": 478.114,
|
| 1548 |
+
"eval_steps_per_second": 59.764,
|
| 1549 |
+
"step": 35000
|
| 1550 |
+
}
|
| 1551 |
+
],
|
| 1552 |
+
"logging_steps": 500,
|
| 1553 |
+
"max_steps": 36828,
|
| 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": 7.368129489509683e+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 sha256:0b99ccaf60fb3d3d3654ec7ad7c6c81e3cadbbcacaebb9454d1deec6f2192d5d
|
| 3 |
+
size 5521
|
checkpoint-35000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-36500/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-36500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c3bed4176c90416cf0a5b3050bad602012207228d165b60ebef6791cb665b2a
|
| 3 |
+
size 540861516
|
checkpoint-36500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85cffe64fde81f44326f06c8c7e7b6cc8a7915f39c3a1f556f2d28155e79dd03
|
| 3 |
+
size 1081844491
|
checkpoint-36500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1832f8148b53b9c6b2031f9143cdcdebdaf12ad45d6457ef2320d51af77e2083
|
| 3 |
+
size 14645
|
checkpoint-36500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5b8f2774e4550a5314bf9773bfcb7ff21db377815bbec00d9b9473e499ec4b5
|
| 3 |
+
size 1465
|
checkpoint-36500/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-36500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-36500/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-36500/trainer_state.json
ADDED
|
@@ -0,0 +1,1639 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9472436482214578,
|
| 3 |
+
"best_model_checkpoint": "./arabert_author_model_full/checkpoint-35000",
|
| 4 |
+
"epoch": 3.9643749321168675,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 36500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.054306505919409144,
|
| 13 |
+
"grad_norm": 14.85861587524414,
|
| 14 |
+
"learning_rate": 1.0795547108335597e-05,
|
| 15 |
+
"loss": 2.7396,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.054306505919409144,
|
| 20 |
+
"eval_accuracy": 0.5551075268817204,
|
| 21 |
+
"eval_f1_macro": 0.44528091004577197,
|
| 22 |
+
"eval_f1_micro": 0.5551075268817204,
|
| 23 |
+
"eval_loss": 2.086405038833618,
|
| 24 |
+
"eval_precision_macro": 0.5488362024601817,
|
| 25 |
+
"eval_precision_micro": 0.5551075268817204,
|
| 26 |
+
"eval_recall_macro": 0.5011249738249491,
|
| 27 |
+
"eval_recall_micro": 0.5551075268817204,
|
| 28 |
+
"eval_runtime": 1.5572,
|
| 29 |
+
"eval_samples_per_second": 477.769,
|
| 30 |
+
"eval_steps_per_second": 59.721,
|
| 31 |
+
"step": 500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.10861301183881829,
|
| 35 |
+
"grad_norm": 16.272708892822266,
|
| 36 |
+
"learning_rate": 2.1656258484930763e-05,
|
| 37 |
+
"loss": 1.584,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10861301183881829,
|
| 42 |
+
"eval_accuracy": 0.7190860215053764,
|
| 43 |
+
"eval_f1_macro": 0.6681343461862342,
|
| 44 |
+
"eval_f1_micro": 0.7190860215053764,
|
| 45 |
+
"eval_loss": 1.1402474641799927,
|
| 46 |
+
"eval_precision_macro": 0.7284168208592146,
|
| 47 |
+
"eval_precision_micro": 0.7190860215053764,
|
| 48 |
+
"eval_recall_macro": 0.6741017912193727,
|
| 49 |
+
"eval_recall_micro": 0.7190860215053764,
|
| 50 |
+
"eval_runtime": 1.5592,
|
| 51 |
+
"eval_samples_per_second": 477.171,
|
| 52 |
+
"eval_steps_per_second": 59.646,
|
| 53 |
+
"step": 1000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.16291951775822744,
|
| 57 |
+
"grad_norm": 43.108097076416016,
|
| 58 |
+
"learning_rate": 3.2516969861525934e-05,
|
| 59 |
+
"loss": 1.0278,
|
| 60 |
+
"step": 1500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.16291951775822744,
|
| 64 |
+
"eval_accuracy": 0.6935483870967742,
|
| 65 |
+
"eval_f1_macro": 0.6694441122919238,
|
| 66 |
+
"eval_f1_micro": 0.6935483870967742,
|
| 67 |
+
"eval_loss": 0.9176589250564575,
|
| 68 |
+
"eval_precision_macro": 0.719370166471438,
|
| 69 |
+
"eval_precision_micro": 0.6935483870967742,
|
| 70 |
+
"eval_recall_macro": 0.700540634546637,
|
| 71 |
+
"eval_recall_micro": 0.6935483870967742,
|
| 72 |
+
"eval_runtime": 1.5614,
|
| 73 |
+
"eval_samples_per_second": 476.485,
|
| 74 |
+
"eval_steps_per_second": 59.561,
|
| 75 |
+
"step": 1500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.21722602367763658,
|
| 79 |
+
"grad_norm": 21.786911010742188,
|
| 80 |
+
"learning_rate": 4.33776812381211e-05,
|
| 81 |
+
"loss": 0.7819,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.21722602367763658,
|
| 86 |
+
"eval_accuracy": 0.7365591397849462,
|
| 87 |
+
"eval_f1_macro": 0.7225937916281533,
|
| 88 |
+
"eval_f1_micro": 0.7365591397849462,
|
| 89 |
+
"eval_loss": 0.9186232089996338,
|
| 90 |
+
"eval_precision_macro": 0.8090241740547917,
|
| 91 |
+
"eval_precision_micro": 0.7365591397849462,
|
| 92 |
+
"eval_recall_macro": 0.730498755334377,
|
| 93 |
+
"eval_recall_micro": 0.7365591397849462,
|
| 94 |
+
"eval_runtime": 1.7089,
|
| 95 |
+
"eval_samples_per_second": 435.367,
|
| 96 |
+
"eval_steps_per_second": 54.421,
|
| 97 |
+
"step": 2000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.2715325295970457,
|
| 101 |
+
"grad_norm": 28.50157356262207,
|
| 102 |
+
"learning_rate": 5.4216671191963076e-05,
|
| 103 |
+
"loss": 0.7433,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.2715325295970457,
|
| 108 |
+
"eval_accuracy": 0.8091397849462365,
|
| 109 |
+
"eval_f1_macro": 0.7931780524032125,
|
| 110 |
+
"eval_f1_micro": 0.8091397849462365,
|
| 111 |
+
"eval_loss": 0.6774040460586548,
|
| 112 |
+
"eval_precision_macro": 0.8236755927756734,
|
| 113 |
+
"eval_precision_micro": 0.8091397849462365,
|
| 114 |
+
"eval_recall_macro": 0.8138164959150519,
|
| 115 |
+
"eval_recall_micro": 0.8091397849462365,
|
| 116 |
+
"eval_runtime": 1.5765,
|
| 117 |
+
"eval_samples_per_second": 471.94,
|
| 118 |
+
"eval_steps_per_second": 58.992,
|
| 119 |
+
"step": 2500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.3258390355164549,
|
| 123 |
+
"grad_norm": 23.32242774963379,
|
| 124 |
+
"learning_rate": 6.507738256855825e-05,
|
| 125 |
+
"loss": 0.7224,
|
| 126 |
+
"step": 3000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.3258390355164549,
|
| 130 |
+
"eval_accuracy": 0.7701612903225806,
|
| 131 |
+
"eval_f1_macro": 0.7568919015291462,
|
| 132 |
+
"eval_f1_micro": 0.7701612903225806,
|
| 133 |
+
"eval_loss": 0.726546585559845,
|
| 134 |
+
"eval_precision_macro": 0.8108640165896299,
|
| 135 |
+
"eval_precision_micro": 0.7701612903225806,
|
| 136 |
+
"eval_recall_macro": 0.7863245772318792,
|
| 137 |
+
"eval_recall_micro": 0.7701612903225806,
|
| 138 |
+
"eval_runtime": 1.5947,
|
| 139 |
+
"eval_samples_per_second": 466.552,
|
| 140 |
+
"eval_steps_per_second": 58.319,
|
| 141 |
+
"step": 3000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.38014554143586404,
|
| 145 |
+
"grad_norm": 38.11383056640625,
|
| 146 |
+
"learning_rate": 7.591637252240023e-05,
|
| 147 |
+
"loss": 0.7578,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.38014554143586404,
|
| 152 |
+
"eval_accuracy": 0.831989247311828,
|
| 153 |
+
"eval_f1_macro": 0.8113946213107872,
|
| 154 |
+
"eval_f1_micro": 0.831989247311828,
|
| 155 |
+
"eval_loss": 0.5666089653968811,
|
| 156 |
+
"eval_precision_macro": 0.8300071137831838,
|
| 157 |
+
"eval_precision_micro": 0.831989247311828,
|
| 158 |
+
"eval_recall_macro": 0.8277091616765468,
|
| 159 |
+
"eval_recall_micro": 0.831989247311828,
|
| 160 |
+
"eval_runtime": 1.5775,
|
| 161 |
+
"eval_samples_per_second": 471.647,
|
| 162 |
+
"eval_steps_per_second": 58.956,
|
| 163 |
+
"step": 3500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.43445204735527315,
|
| 167 |
+
"grad_norm": 27.02998161315918,
|
| 168 |
+
"learning_rate": 7.998262267095997e-05,
|
| 169 |
+
"loss": 0.7705,
|
| 170 |
+
"step": 4000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.43445204735527315,
|
| 174 |
+
"eval_accuracy": 0.793010752688172,
|
| 175 |
+
"eval_f1_macro": 0.7783295125154664,
|
| 176 |
+
"eval_f1_micro": 0.793010752688172,
|
| 177 |
+
"eval_loss": 0.7473301887512207,
|
| 178 |
+
"eval_precision_macro": 0.8365596188425319,
|
| 179 |
+
"eval_precision_micro": 0.793010752688172,
|
| 180 |
+
"eval_recall_macro": 0.7944564993024996,
|
| 181 |
+
"eval_recall_micro": 0.793010752688172,
|
| 182 |
+
"eval_runtime": 1.592,
|
| 183 |
+
"eval_samples_per_second": 467.348,
|
| 184 |
+
"eval_steps_per_second": 58.418,
|
| 185 |
+
"step": 4000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4887585532746823,
|
| 189 |
+
"grad_norm": 4.219649314880371,
|
| 190 |
+
"learning_rate": 7.988188051558617e-05,
|
| 191 |
+
"loss": 0.714,
|
| 192 |
+
"step": 4500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.4887585532746823,
|
| 196 |
+
"eval_accuracy": 0.8615591397849462,
|
| 197 |
+
"eval_f1_macro": 0.8525941744256668,
|
| 198 |
+
"eval_f1_micro": 0.8615591397849462,
|
| 199 |
+
"eval_loss": 0.5411700010299683,
|
| 200 |
+
"eval_precision_macro": 0.8738317002846235,
|
| 201 |
+
"eval_precision_micro": 0.8615591397849462,
|
| 202 |
+
"eval_recall_macro": 0.857343934692196,
|
| 203 |
+
"eval_recall_micro": 0.8615591397849462,
|
| 204 |
+
"eval_runtime": 1.5935,
|
| 205 |
+
"eval_samples_per_second": 466.9,
|
| 206 |
+
"eval_steps_per_second": 58.363,
|
| 207 |
+
"step": 4500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.5430650591940914,
|
| 211 |
+
"grad_norm": 2.9277937412261963,
|
| 212 |
+
"learning_rate": 7.969158166695609e-05,
|
| 213 |
+
"loss": 0.6781,
|
| 214 |
+
"step": 5000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.5430650591940914,
|
| 218 |
+
"eval_accuracy": 0.8440860215053764,
|
| 219 |
+
"eval_f1_macro": 0.8140189163428593,
|
| 220 |
+
"eval_f1_micro": 0.8440860215053764,
|
| 221 |
+
"eval_loss": 0.584912896156311,
|
| 222 |
+
"eval_precision_macro": 0.8304958001958954,
|
| 223 |
+
"eval_precision_micro": 0.8440860215053764,
|
| 224 |
+
"eval_recall_macro": 0.8277544733650097,
|
| 225 |
+
"eval_recall_micro": 0.8440860215053764,
|
| 226 |
+
"eval_runtime": 1.5664,
|
| 227 |
+
"eval_samples_per_second": 474.976,
|
| 228 |
+
"eval_steps_per_second": 59.372,
|
| 229 |
+
"step": 5000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.5973715651135006,
|
| 233 |
+
"grad_norm": 2.422699213027954,
|
| 234 |
+
"learning_rate": 7.941215345034608e-05,
|
| 235 |
+
"loss": 0.6365,
|
| 236 |
+
"step": 5500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.5973715651135006,
|
| 240 |
+
"eval_accuracy": 0.8198924731182796,
|
| 241 |
+
"eval_f1_macro": 0.8098480937728665,
|
| 242 |
+
"eval_f1_micro": 0.8198924731182796,
|
| 243 |
+
"eval_loss": 0.6339462995529175,
|
| 244 |
+
"eval_precision_macro": 0.8511279803543597,
|
| 245 |
+
"eval_precision_micro": 0.8198924731182796,
|
| 246 |
+
"eval_recall_macro": 0.8376000571890804,
|
| 247 |
+
"eval_recall_micro": 0.8198924731182796,
|
| 248 |
+
"eval_runtime": 1.5714,
|
| 249 |
+
"eval_samples_per_second": 473.456,
|
| 250 |
+
"eval_steps_per_second": 59.182,
|
| 251 |
+
"step": 5500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.6516780710329098,
|
| 255 |
+
"grad_norm": 24.36614227294922,
|
| 256 |
+
"learning_rate": 7.90442233353428e-05,
|
| 257 |
+
"loss": 0.5609,
|
| 258 |
+
"step": 6000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.6516780710329098,
|
| 262 |
+
"eval_accuracy": 0.8803763440860215,
|
| 263 |
+
"eval_f1_macro": 0.8776901808589186,
|
| 264 |
+
"eval_f1_micro": 0.8803763440860215,
|
| 265 |
+
"eval_loss": 0.4191497564315796,
|
| 266 |
+
"eval_precision_macro": 0.9013592602931226,
|
| 267 |
+
"eval_precision_micro": 0.8803763440860215,
|
| 268 |
+
"eval_recall_macro": 0.8870337188867564,
|
| 269 |
+
"eval_recall_micro": 0.8803763440860215,
|
| 270 |
+
"eval_runtime": 1.5644,
|
| 271 |
+
"eval_samples_per_second": 475.586,
|
| 272 |
+
"eval_steps_per_second": 59.448,
|
| 273 |
+
"step": 6000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.7059845769523189,
|
| 277 |
+
"grad_norm": 7.382803440093994,
|
| 278 |
+
"learning_rate": 7.85896155913429e-05,
|
| 279 |
+
"loss": 0.557,
|
| 280 |
+
"step": 6500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.7059845769523189,
|
| 284 |
+
"eval_accuracy": 0.8870967741935484,
|
| 285 |
+
"eval_f1_macro": 0.873257230355725,
|
| 286 |
+
"eval_f1_micro": 0.8870967741935484,
|
| 287 |
+
"eval_loss": 0.43305835127830505,
|
| 288 |
+
"eval_precision_macro": 0.9066583526088271,
|
| 289 |
+
"eval_precision_micro": 0.8870967741935484,
|
| 290 |
+
"eval_recall_macro": 0.8813447066604991,
|
| 291 |
+
"eval_recall_micro": 0.8870967741935484,
|
| 292 |
+
"eval_runtime": 1.572,
|
| 293 |
+
"eval_samples_per_second": 473.271,
|
| 294 |
+
"eval_steps_per_second": 59.159,
|
| 295 |
+
"step": 6500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.7602910828717281,
|
| 299 |
+
"grad_norm": 40.95680618286133,
|
| 300 |
+
"learning_rate": 7.804752932863711e-05,
|
| 301 |
+
"loss": 0.5581,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.7602910828717281,
|
| 306 |
+
"eval_accuracy": 0.8400537634408602,
|
| 307 |
+
"eval_f1_macro": 0.832080514333091,
|
| 308 |
+
"eval_f1_micro": 0.8400537634408602,
|
| 309 |
+
"eval_loss": 0.6264011263847351,
|
| 310 |
+
"eval_precision_macro": 0.8486272179160291,
|
| 311 |
+
"eval_precision_micro": 0.8400537634408602,
|
| 312 |
+
"eval_recall_macro": 0.8385309495501778,
|
| 313 |
+
"eval_recall_micro": 0.8400537634408602,
|
| 314 |
+
"eval_runtime": 1.5709,
|
| 315 |
+
"eval_samples_per_second": 473.61,
|
| 316 |
+
"eval_steps_per_second": 59.201,
|
| 317 |
+
"step": 7000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.8145975887911372,
|
| 321 |
+
"grad_norm": 1.4635225534439087,
|
| 322 |
+
"learning_rate": 7.74200054970606e-05,
|
| 323 |
+
"loss": 0.6216,
|
| 324 |
+
"step": 7500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8145975887911372,
|
| 328 |
+
"eval_accuracy": 0.8790322580645161,
|
| 329 |
+
"eval_f1_macro": 0.8733027369549773,
|
| 330 |
+
"eval_f1_micro": 0.8790322580645161,
|
| 331 |
+
"eval_loss": 0.409856379032135,
|
| 332 |
+
"eval_precision_macro": 0.8884912266604943,
|
| 333 |
+
"eval_precision_micro": 0.8790322580645161,
|
| 334 |
+
"eval_recall_macro": 0.8755203032263899,
|
| 335 |
+
"eval_recall_micro": 0.8790322580645161,
|
| 336 |
+
"eval_runtime": 1.5605,
|
| 337 |
+
"eval_samples_per_second": 476.783,
|
| 338 |
+
"eval_steps_per_second": 59.598,
|
| 339 |
+
"step": 7500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8689040947105463,
|
| 343 |
+
"grad_norm": 45.099891662597656,
|
| 344 |
+
"learning_rate": 7.670845323175364e-05,
|
| 345 |
+
"loss": 0.5329,
|
| 346 |
+
"step": 8000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8689040947105463,
|
| 350 |
+
"eval_accuracy": 0.8494623655913979,
|
| 351 |
+
"eval_f1_macro": 0.8493612714696808,
|
| 352 |
+
"eval_f1_micro": 0.8494623655913979,
|
| 353 |
+
"eval_loss": 0.4563172161579132,
|
| 354 |
+
"eval_precision_macro": 0.893910479148947,
|
| 355 |
+
"eval_precision_micro": 0.8494623655913979,
|
| 356 |
+
"eval_recall_macro": 0.8604223349122991,
|
| 357 |
+
"eval_recall_micro": 0.8494623655913979,
|
| 358 |
+
"eval_runtime": 1.5627,
|
| 359 |
+
"eval_samples_per_second": 476.104,
|
| 360 |
+
"eval_steps_per_second": 59.513,
|
| 361 |
+
"step": 8000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.9232106006299554,
|
| 365 |
+
"grad_norm": 144.00657653808594,
|
| 366 |
+
"learning_rate": 7.591447035777205e-05,
|
| 367 |
+
"loss": 0.5361,
|
| 368 |
+
"step": 8500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.9232106006299554,
|
| 372 |
+
"eval_accuracy": 0.8655913978494624,
|
| 373 |
+
"eval_f1_macro": 0.8441067821828483,
|
| 374 |
+
"eval_f1_micro": 0.8655913978494624,
|
| 375 |
+
"eval_loss": 0.6785014867782593,
|
| 376 |
+
"eval_precision_macro": 0.8860824516800835,
|
| 377 |
+
"eval_precision_micro": 0.8655913978494624,
|
| 378 |
+
"eval_recall_macro": 0.8499754697649283,
|
| 379 |
+
"eval_recall_micro": 0.8655913978494624,
|
| 380 |
+
"eval_runtime": 1.7462,
|
| 381 |
+
"eval_samples_per_second": 426.057,
|
| 382 |
+
"eval_steps_per_second": 53.257,
|
| 383 |
+
"step": 8500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.9775171065493646,
|
| 387 |
+
"grad_norm": 51.59966278076172,
|
| 388 |
+
"learning_rate": 7.50398398020936e-05,
|
| 389 |
+
"loss": 0.5004,
|
| 390 |
+
"step": 9000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.9775171065493646,
|
| 394 |
+
"eval_accuracy": 0.8830645161290323,
|
| 395 |
+
"eval_f1_macro": 0.8700101159667029,
|
| 396 |
+
"eval_f1_micro": 0.8830645161290323,
|
| 397 |
+
"eval_loss": 0.5261440277099609,
|
| 398 |
+
"eval_precision_macro": 0.9053295147781684,
|
| 399 |
+
"eval_precision_micro": 0.8830645161290323,
|
| 400 |
+
"eval_recall_macro": 0.8611036436092915,
|
| 401 |
+
"eval_recall_micro": 0.8830645161290323,
|
| 402 |
+
"eval_runtime": 1.5897,
|
| 403 |
+
"eval_samples_per_second": 468.018,
|
| 404 |
+
"eval_steps_per_second": 58.502,
|
| 405 |
+
"step": 9000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.0318236124687739,
|
| 409 |
+
"grad_norm": 1.6247466802597046,
|
| 410 |
+
"learning_rate": 7.408850935077056e-05,
|
| 411 |
+
"loss": 0.4548,
|
| 412 |
+
"step": 9500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.0318236124687739,
|
| 416 |
+
"eval_accuracy": 0.885752688172043,
|
| 417 |
+
"eval_f1_macro": 0.8771175055624273,
|
| 418 |
+
"eval_f1_micro": 0.885752688172043,
|
| 419 |
+
"eval_loss": 0.47863149642944336,
|
| 420 |
+
"eval_precision_macro": 0.9058069553824752,
|
| 421 |
+
"eval_precision_micro": 0.885752688172043,
|
| 422 |
+
"eval_recall_macro": 0.8766787609951181,
|
| 423 |
+
"eval_recall_micro": 0.885752688172043,
|
| 424 |
+
"eval_runtime": 1.5934,
|
| 425 |
+
"eval_samples_per_second": 466.926,
|
| 426 |
+
"eval_steps_per_second": 58.366,
|
| 427 |
+
"step": 9500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.0861301183881829,
|
| 431 |
+
"grad_norm": 0.7039883732795715,
|
| 432 |
+
"learning_rate": 7.305880302978226e-05,
|
| 433 |
+
"loss": 0.3634,
|
| 434 |
+
"step": 10000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.0861301183881829,
|
| 438 |
+
"eval_accuracy": 0.8454301075268817,
|
| 439 |
+
"eval_f1_macro": 0.8355409368806581,
|
| 440 |
+
"eval_f1_micro": 0.8454301075268817,
|
| 441 |
+
"eval_loss": 0.584094226360321,
|
| 442 |
+
"eval_precision_macro": 0.8637046558195853,
|
| 443 |
+
"eval_precision_micro": 0.8454301075268817,
|
| 444 |
+
"eval_recall_macro": 0.8620713017041678,
|
| 445 |
+
"eval_recall_micro": 0.8454301075268817,
|
| 446 |
+
"eval_runtime": 1.5924,
|
| 447 |
+
"eval_samples_per_second": 467.211,
|
| 448 |
+
"eval_steps_per_second": 58.401,
|
| 449 |
+
"step": 10000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.140436624307592,
|
| 453 |
+
"grad_norm": 18.514562606811523,
|
| 454 |
+
"learning_rate": 7.195486156631612e-05,
|
| 455 |
+
"loss": 0.38,
|
| 456 |
+
"step": 10500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.140436624307592,
|
| 460 |
+
"eval_accuracy": 0.8736559139784946,
|
| 461 |
+
"eval_f1_macro": 0.8650283345776192,
|
| 462 |
+
"eval_f1_micro": 0.8736559139784946,
|
| 463 |
+
"eval_loss": 0.609620213508606,
|
| 464 |
+
"eval_precision_macro": 0.8846991890947015,
|
| 465 |
+
"eval_precision_micro": 0.8736559139784946,
|
| 466 |
+
"eval_recall_macro": 0.8788120484876811,
|
| 467 |
+
"eval_recall_micro": 0.8736559139784946,
|
| 468 |
+
"eval_runtime": 1.596,
|
| 469 |
+
"eval_samples_per_second": 466.176,
|
| 470 |
+
"eval_steps_per_second": 58.272,
|
| 471 |
+
"step": 10500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.194743130227001,
|
| 475 |
+
"grad_norm": 33.06956481933594,
|
| 476 |
+
"learning_rate": 7.077916391436673e-05,
|
| 477 |
+
"loss": 0.4346,
|
| 478 |
+
"step": 11000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.194743130227001,
|
| 482 |
+
"eval_accuracy": 0.8588709677419355,
|
| 483 |
+
"eval_f1_macro": 0.8369609828838035,
|
| 484 |
+
"eval_f1_micro": 0.8588709677419355,
|
| 485 |
+
"eval_loss": 0.6567370891571045,
|
| 486 |
+
"eval_precision_macro": 0.8596584963088156,
|
| 487 |
+
"eval_precision_micro": 0.8588709677419355,
|
| 488 |
+
"eval_recall_macro": 0.8553630932096153,
|
| 489 |
+
"eval_recall_micro": 0.8588709677419355,
|
| 490 |
+
"eval_runtime": 1.5912,
|
| 491 |
+
"eval_samples_per_second": 467.56,
|
| 492 |
+
"eval_steps_per_second": 58.445,
|
| 493 |
+
"step": 11000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.2490496361464103,
|
| 497 |
+
"grad_norm": 5.124754428863525,
|
| 498 |
+
"learning_rate": 6.953690693258913e-05,
|
| 499 |
+
"loss": 0.4048,
|
| 500 |
+
"step": 11500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.2490496361464103,
|
| 504 |
+
"eval_accuracy": 0.8185483870967742,
|
| 505 |
+
"eval_f1_macro": 0.8138708613483465,
|
| 506 |
+
"eval_f1_micro": 0.8185483870967742,
|
| 507 |
+
"eval_loss": 0.8613069653511047,
|
| 508 |
+
"eval_precision_macro": 0.8751078398440778,
|
| 509 |
+
"eval_precision_micro": 0.8185483870967742,
|
| 510 |
+
"eval_recall_macro": 0.8210231918764864,
|
| 511 |
+
"eval_recall_micro": 0.8185483870967742,
|
| 512 |
+
"eval_runtime": 1.5897,
|
| 513 |
+
"eval_samples_per_second": 468.009,
|
| 514 |
+
"eval_steps_per_second": 58.501,
|
| 515 |
+
"step": 11500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.3033561420658195,
|
| 519 |
+
"grad_norm": 5.379746437072754,
|
| 520 |
+
"learning_rate": 6.822590211705641e-05,
|
| 521 |
+
"loss": 0.4131,
|
| 522 |
+
"step": 12000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.3033561420658195,
|
| 526 |
+
"eval_accuracy": 0.907258064516129,
|
| 527 |
+
"eval_f1_macro": 0.9064546460371958,
|
| 528 |
+
"eval_f1_micro": 0.907258064516129,
|
| 529 |
+
"eval_loss": 0.383698046207428,
|
| 530 |
+
"eval_precision_macro": 0.9285092418542091,
|
| 531 |
+
"eval_precision_micro": 0.907258064516129,
|
| 532 |
+
"eval_recall_macro": 0.9084149302207563,
|
| 533 |
+
"eval_recall_micro": 0.907258064516129,
|
| 534 |
+
"eval_runtime": 1.6383,
|
| 535 |
+
"eval_samples_per_second": 454.138,
|
| 536 |
+
"eval_steps_per_second": 56.767,
|
| 537 |
+
"step": 12000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.3576626479852285,
|
| 541 |
+
"grad_norm": 21.04884910583496,
|
| 542 |
+
"learning_rate": 6.685432467442772e-05,
|
| 543 |
+
"loss": 0.3744,
|
| 544 |
+
"step": 12500
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.3576626479852285,
|
| 548 |
+
"eval_accuracy": 0.8884408602150538,
|
| 549 |
+
"eval_f1_macro": 0.903985402366871,
|
| 550 |
+
"eval_f1_micro": 0.8884408602150538,
|
| 551 |
+
"eval_loss": 0.33839282393455505,
|
| 552 |
+
"eval_precision_macro": 0.9202041810282631,
|
| 553 |
+
"eval_precision_micro": 0.8884408602150538,
|
| 554 |
+
"eval_recall_macro": 0.9167129841156823,
|
| 555 |
+
"eval_recall_micro": 0.8884408602150538,
|
| 556 |
+
"eval_runtime": 1.5684,
|
| 557 |
+
"eval_samples_per_second": 474.375,
|
| 558 |
+
"eval_steps_per_second": 59.297,
|
| 559 |
+
"step": 12500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.4119691539046377,
|
| 563 |
+
"grad_norm": 2.0264995098114014,
|
| 564 |
+
"learning_rate": 6.541975827485887e-05,
|
| 565 |
+
"loss": 0.3789,
|
| 566 |
+
"step": 13000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.4119691539046377,
|
| 570 |
+
"eval_accuracy": 0.8548387096774194,
|
| 571 |
+
"eval_f1_macro": 0.8568056198138125,
|
| 572 |
+
"eval_f1_micro": 0.8548387096774194,
|
| 573 |
+
"eval_loss": 0.5327471494674683,
|
| 574 |
+
"eval_precision_macro": 0.8878810831304436,
|
| 575 |
+
"eval_precision_micro": 0.8548387096774194,
|
| 576 |
+
"eval_recall_macro": 0.8739629853819976,
|
| 577 |
+
"eval_recall_micro": 0.8548387096774194,
|
| 578 |
+
"eval_runtime": 1.5511,
|
| 579 |
+
"eval_samples_per_second": 479.662,
|
| 580 |
+
"eval_steps_per_second": 59.958,
|
| 581 |
+
"step": 13000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.466275659824047,
|
| 585 |
+
"grad_norm": 3.5367252826690674,
|
| 586 |
+
"learning_rate": 6.392811057759191e-05,
|
| 587 |
+
"loss": 0.3494,
|
| 588 |
+
"step": 13500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.466275659824047,
|
| 592 |
+
"eval_accuracy": 0.9005376344086021,
|
| 593 |
+
"eval_f1_macro": 0.8873317559394204,
|
| 594 |
+
"eval_f1_micro": 0.9005376344086021,
|
| 595 |
+
"eval_loss": 0.38247689604759216,
|
| 596 |
+
"eval_precision_macro": 0.8991156587188684,
|
| 597 |
+
"eval_precision_micro": 0.9005376344086021,
|
| 598 |
+
"eval_recall_macro": 0.8980828267359259,
|
| 599 |
+
"eval_recall_micro": 0.9005376344086021,
|
| 600 |
+
"eval_runtime": 1.545,
|
| 601 |
+
"eval_samples_per_second": 481.563,
|
| 602 |
+
"eval_steps_per_second": 60.195,
|
| 603 |
+
"step": 13500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.520582165743456,
|
| 607 |
+
"grad_norm": 0.7285934090614319,
|
| 608 |
+
"learning_rate": 6.238273114973711e-05,
|
| 609 |
+
"loss": 0.3942,
|
| 610 |
+
"step": 14000
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.520582165743456,
|
| 614 |
+
"eval_accuracy": 0.9045698924731183,
|
| 615 |
+
"eval_f1_macro": 0.8961888882643896,
|
| 616 |
+
"eval_f1_micro": 0.9045698924731183,
|
| 617 |
+
"eval_loss": 0.45909252762794495,
|
| 618 |
+
"eval_precision_macro": 0.9132890481201191,
|
| 619 |
+
"eval_precision_micro": 0.9045698924731183,
|
| 620 |
+
"eval_recall_macro": 0.896670735624709,
|
| 621 |
+
"eval_recall_micro": 0.9045698924731183,
|
| 622 |
+
"eval_runtime": 1.5463,
|
| 623 |
+
"eval_samples_per_second": 481.142,
|
| 624 |
+
"eval_steps_per_second": 60.143,
|
| 625 |
+
"step": 14000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.5748886716628652,
|
| 629 |
+
"grad_norm": 2.59505295753479,
|
| 630 |
+
"learning_rate": 6.078709021560674e-05,
|
| 631 |
+
"loss": 0.3023,
|
| 632 |
+
"step": 14500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.5748886716628652,
|
| 636 |
+
"eval_accuracy": 0.8978494623655914,
|
| 637 |
+
"eval_f1_macro": 0.8915991372968476,
|
| 638 |
+
"eval_f1_micro": 0.8978494623655914,
|
| 639 |
+
"eval_loss": 0.5516388416290283,
|
| 640 |
+
"eval_precision_macro": 0.9068635931933978,
|
| 641 |
+
"eval_precision_micro": 0.8978494623655914,
|
| 642 |
+
"eval_recall_macro": 0.8942451339148669,
|
| 643 |
+
"eval_recall_micro": 0.8978494623655914,
|
| 644 |
+
"eval_runtime": 1.5446,
|
| 645 |
+
"eval_samples_per_second": 481.685,
|
| 646 |
+
"eval_steps_per_second": 60.211,
|
| 647 |
+
"step": 14500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.6291951775822744,
|
| 651 |
+
"grad_norm": 2.187466859817505,
|
| 652 |
+
"learning_rate": 5.9144770864158464e-05,
|
| 653 |
+
"loss": 0.3757,
|
| 654 |
+
"step": 15000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.6291951775822744,
|
| 658 |
+
"eval_accuracy": 0.8951612903225806,
|
| 659 |
+
"eval_f1_macro": 0.8833952116973107,
|
| 660 |
+
"eval_f1_micro": 0.8951612903225806,
|
| 661 |
+
"eval_loss": 0.4487917423248291,
|
| 662 |
+
"eval_precision_macro": 0.9141733968196161,
|
| 663 |
+
"eval_precision_micro": 0.8951612903225806,
|
| 664 |
+
"eval_recall_macro": 0.8813523748993086,
|
| 665 |
+
"eval_recall_micro": 0.8951612903225806,
|
| 666 |
+
"eval_runtime": 1.5598,
|
| 667 |
+
"eval_samples_per_second": 476.976,
|
| 668 |
+
"eval_steps_per_second": 59.622,
|
| 669 |
+
"step": 15000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.6835016835016834,
|
| 673 |
+
"grad_norm": 0.7013949751853943,
|
| 674 |
+
"learning_rate": 5.745946100299554e-05,
|
| 675 |
+
"loss": 0.3241,
|
| 676 |
+
"step": 15500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.6835016835016834,
|
| 680 |
+
"eval_accuracy": 0.8817204301075269,
|
| 681 |
+
"eval_f1_macro": 0.8941666527754931,
|
| 682 |
+
"eval_f1_micro": 0.8817204301075269,
|
| 683 |
+
"eval_loss": 0.39030957221984863,
|
| 684 |
+
"eval_precision_macro": 0.9229567222513297,
|
| 685 |
+
"eval_precision_micro": 0.8817204301075269,
|
| 686 |
+
"eval_recall_macro": 0.9032318624546449,
|
| 687 |
+
"eval_recall_micro": 0.8817204301075269,
|
| 688 |
+
"eval_runtime": 1.5563,
|
| 689 |
+
"eval_samples_per_second": 478.06,
|
| 690 |
+
"eval_steps_per_second": 59.757,
|
| 691 |
+
"step": 15500
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 1.7378081894210926,
|
| 695 |
+
"grad_norm": 28.38803482055664,
|
| 696 |
+
"learning_rate": 5.573494507699185e-05,
|
| 697 |
+
"loss": 0.349,
|
| 698 |
+
"step": 16000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.7378081894210926,
|
| 702 |
+
"eval_accuracy": 0.9126344086021505,
|
| 703 |
+
"eval_f1_macro": 0.9078743168203657,
|
| 704 |
+
"eval_f1_micro": 0.9126344086021505,
|
| 705 |
+
"eval_loss": 0.26589375734329224,
|
| 706 |
+
"eval_precision_macro": 0.9294672653448444,
|
| 707 |
+
"eval_precision_micro": 0.9126344086021505,
|
| 708 |
+
"eval_recall_macro": 0.9187759272246643,
|
| 709 |
+
"eval_recall_micro": 0.9126344086021505,
|
| 710 |
+
"eval_runtime": 1.5586,
|
| 711 |
+
"eval_samples_per_second": 477.346,
|
| 712 |
+
"eval_steps_per_second": 59.668,
|
| 713 |
+
"step": 16000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.7921146953405018,
|
| 717 |
+
"grad_norm": 119.5204086303711,
|
| 718 |
+
"learning_rate": 5.3975095570137725e-05,
|
| 719 |
+
"loss": 0.3292,
|
| 720 |
+
"step": 16500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.7921146953405018,
|
| 724 |
+
"eval_accuracy": 0.8776881720430108,
|
| 725 |
+
"eval_f1_macro": 0.8896563190824521,
|
| 726 |
+
"eval_f1_micro": 0.8776881720430108,
|
| 727 |
+
"eval_loss": 0.3458763062953949,
|
| 728 |
+
"eval_precision_macro": 0.9206080781097684,
|
| 729 |
+
"eval_precision_micro": 0.8776881720430108,
|
| 730 |
+
"eval_recall_macro": 0.8957695476343184,
|
| 731 |
+
"eval_recall_micro": 0.8776881720430108,
|
| 732 |
+
"eval_runtime": 1.6873,
|
| 733 |
+
"eval_samples_per_second": 440.949,
|
| 734 |
+
"eval_steps_per_second": 55.119,
|
| 735 |
+
"step": 16500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.8464212012599108,
|
| 739 |
+
"grad_norm": 0.7282613515853882,
|
| 740 |
+
"learning_rate": 5.21838643096897e-05,
|
| 741 |
+
"loss": 0.3063,
|
| 742 |
+
"step": 17000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.8464212012599108,
|
| 746 |
+
"eval_accuracy": 0.8991935483870968,
|
| 747 |
+
"eval_f1_macro": 0.8879891940359544,
|
| 748 |
+
"eval_f1_micro": 0.8991935483870968,
|
| 749 |
+
"eval_loss": 0.45412322878837585,
|
| 750 |
+
"eval_precision_macro": 0.9073381957613869,
|
| 751 |
+
"eval_precision_micro": 0.8991935483870968,
|
| 752 |
+
"eval_recall_macro": 0.901361453647893,
|
| 753 |
+
"eval_recall_micro": 0.8991935483870968,
|
| 754 |
+
"eval_runtime": 1.5907,
|
| 755 |
+
"eval_samples_per_second": 467.726,
|
| 756 |
+
"eval_steps_per_second": 58.466,
|
| 757 |
+
"step": 17000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 1.90072770717932,
|
| 761 |
+
"grad_norm": 22.810928344726562,
|
| 762 |
+
"learning_rate": 5.036527359215105e-05,
|
| 763 |
+
"loss": 0.2974,
|
| 764 |
+
"step": 17500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.90072770717932,
|
| 768 |
+
"eval_accuracy": 0.9139784946236559,
|
| 769 |
+
"eval_f1_macro": 0.9147040216841583,
|
| 770 |
+
"eval_f1_micro": 0.9139784946236559,
|
| 771 |
+
"eval_loss": 0.2588426470756531,
|
| 772 |
+
"eval_precision_macro": 0.9280953295150929,
|
| 773 |
+
"eval_precision_micro": 0.9139784946236559,
|
| 774 |
+
"eval_recall_macro": 0.9254419270814122,
|
| 775 |
+
"eval_recall_micro": 0.9139784946236559,
|
| 776 |
+
"eval_runtime": 1.5934,
|
| 777 |
+
"eval_samples_per_second": 466.917,
|
| 778 |
+
"eval_steps_per_second": 58.365,
|
| 779 |
+
"step": 17500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.9550342130987293,
|
| 783 |
+
"grad_norm": 0.9817183613777161,
|
| 784 |
+
"learning_rate": 4.8523407151010365e-05,
|
| 785 |
+
"loss": 0.2938,
|
| 786 |
+
"step": 18000
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.9550342130987293,
|
| 790 |
+
"eval_accuracy": 0.875,
|
| 791 |
+
"eval_f1_macro": 0.8887166776365175,
|
| 792 |
+
"eval_f1_micro": 0.875,
|
| 793 |
+
"eval_loss": 0.45612600445747375,
|
| 794 |
+
"eval_precision_macro": 0.915931173623922,
|
| 795 |
+
"eval_precision_micro": 0.875,
|
| 796 |
+
"eval_recall_macro": 0.8997546027307288,
|
| 797 |
+
"eval_recall_micro": 0.875,
|
| 798 |
+
"eval_runtime": 1.6003,
|
| 799 |
+
"eval_samples_per_second": 464.907,
|
| 800 |
+
"eval_steps_per_second": 58.113,
|
| 801 |
+
"step": 18000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.0093407190181383,
|
| 805 |
+
"grad_norm": 85.74153137207031,
|
| 806 |
+
"learning_rate": 4.66624009865203e-05,
|
| 807 |
+
"loss": 0.3067,
|
| 808 |
+
"step": 18500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.0093407190181383,
|
| 812 |
+
"eval_accuracy": 0.8844086021505376,
|
| 813 |
+
"eval_f1_macro": 0.8921145619678118,
|
| 814 |
+
"eval_f1_micro": 0.8844086021505376,
|
| 815 |
+
"eval_loss": 0.3737676739692688,
|
| 816 |
+
"eval_precision_macro": 0.9173188296546068,
|
| 817 |
+
"eval_precision_micro": 0.8844086021505376,
|
| 818 |
+
"eval_recall_macro": 0.9047881017377212,
|
| 819 |
+
"eval_recall_micro": 0.8844086021505376,
|
| 820 |
+
"eval_runtime": 1.733,
|
| 821 |
+
"eval_samples_per_second": 429.309,
|
| 822 |
+
"eval_steps_per_second": 53.664,
|
| 823 |
+
"step": 18500
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.0636472249375477,
|
| 827 |
+
"grad_norm": 4.293463706970215,
|
| 828 |
+
"learning_rate": 4.479019814743586e-05,
|
| 829 |
+
"loss": 0.1653,
|
| 830 |
+
"step": 19000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.0636472249375477,
|
| 834 |
+
"eval_accuracy": 0.9005376344086021,
|
| 835 |
+
"eval_f1_macro": 0.8930738638150588,
|
| 836 |
+
"eval_f1_micro": 0.9005376344086021,
|
| 837 |
+
"eval_loss": 0.5207958221435547,
|
| 838 |
+
"eval_precision_macro": 0.9287838810859212,
|
| 839 |
+
"eval_precision_micro": 0.9005376344086021,
|
| 840 |
+
"eval_recall_macro": 0.8936382765105635,
|
| 841 |
+
"eval_recall_micro": 0.9005376344086021,
|
| 842 |
+
"eval_runtime": 1.5912,
|
| 843 |
+
"eval_samples_per_second": 467.585,
|
| 844 |
+
"eval_steps_per_second": 58.448,
|
| 845 |
+
"step": 19000
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.1179537308569567,
|
| 849 |
+
"grad_norm": 1.4437882900238037,
|
| 850 |
+
"learning_rate": 4.2907281661980334e-05,
|
| 851 |
+
"loss": 0.1901,
|
| 852 |
+
"step": 19500
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.1179537308569567,
|
| 856 |
+
"eval_accuracy": 0.9206989247311828,
|
| 857 |
+
"eval_f1_macro": 0.9210532754724804,
|
| 858 |
+
"eval_f1_micro": 0.9206989247311828,
|
| 859 |
+
"eval_loss": 0.2993380129337311,
|
| 860 |
+
"eval_precision_macro": 0.9381153626922412,
|
| 861 |
+
"eval_precision_micro": 0.9206989247311828,
|
| 862 |
+
"eval_recall_macro": 0.9300212877722726,
|
| 863 |
+
"eval_recall_micro": 0.9206989247311828,
|
| 864 |
+
"eval_runtime": 1.7299,
|
| 865 |
+
"eval_samples_per_second": 430.073,
|
| 866 |
+
"eval_steps_per_second": 53.759,
|
| 867 |
+
"step": 19500
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.1722602367763657,
|
| 871 |
+
"grad_norm": 764.3075561523438,
|
| 872 |
+
"learning_rate": 4.101407270852778e-05,
|
| 873 |
+
"loss": 0.2271,
|
| 874 |
+
"step": 20000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.1722602367763657,
|
| 878 |
+
"eval_accuracy": 0.9032258064516129,
|
| 879 |
+
"eval_f1_macro": 0.9205221777214502,
|
| 880 |
+
"eval_f1_micro": 0.9032258064516129,
|
| 881 |
+
"eval_loss": 0.27076366543769836,
|
| 882 |
+
"eval_precision_macro": 0.9497791884188832,
|
| 883 |
+
"eval_precision_micro": 0.9032258064516129,
|
| 884 |
+
"eval_recall_macro": 0.9297648445536885,
|
| 885 |
+
"eval_recall_micro": 0.9032258064516129,
|
| 886 |
+
"eval_runtime": 1.5754,
|
| 887 |
+
"eval_samples_per_second": 472.249,
|
| 888 |
+
"eval_steps_per_second": 59.031,
|
| 889 |
+
"step": 20000
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 2.226566742695775,
|
| 893 |
+
"grad_norm": 8.108640670776367,
|
| 894 |
+
"learning_rate": 3.911858660572008e-05,
|
| 895 |
+
"loss": 0.2108,
|
| 896 |
+
"step": 20500
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.226566742695775,
|
| 900 |
+
"eval_accuracy": 0.9220430107526881,
|
| 901 |
+
"eval_f1_macro": 0.9187239197738657,
|
| 902 |
+
"eval_f1_micro": 0.9220430107526881,
|
| 903 |
+
"eval_loss": 0.27602580189704895,
|
| 904 |
+
"eval_precision_macro": 0.9334752930289422,
|
| 905 |
+
"eval_precision_micro": 0.9220430107526881,
|
| 906 |
+
"eval_recall_macro": 0.9228409582632311,
|
| 907 |
+
"eval_recall_micro": 0.9220430107526881,
|
| 908 |
+
"eval_runtime": 1.5758,
|
| 909 |
+
"eval_samples_per_second": 472.143,
|
| 910 |
+
"eval_steps_per_second": 59.018,
|
| 911 |
+
"step": 20500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 2.280873248615184,
|
| 915 |
+
"grad_norm": 2.4227545261383057,
|
| 916 |
+
"learning_rate": 3.7225079759355747e-05,
|
| 917 |
+
"loss": 0.2068,
|
| 918 |
+
"step": 21000
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.280873248615184,
|
| 922 |
+
"eval_accuracy": 0.9247311827956989,
|
| 923 |
+
"eval_f1_macro": 0.9260496184754449,
|
| 924 |
+
"eval_f1_micro": 0.9247311827956989,
|
| 925 |
+
"eval_loss": 0.25598055124282837,
|
| 926 |
+
"eval_precision_macro": 0.9394381557552136,
|
| 927 |
+
"eval_precision_micro": 0.9247311827956989,
|
| 928 |
+
"eval_recall_macro": 0.9349235944200235,
|
| 929 |
+
"eval_recall_micro": 0.9247311827956989,
|
| 930 |
+
"eval_runtime": 1.5558,
|
| 931 |
+
"eval_samples_per_second": 478.204,
|
| 932 |
+
"eval_steps_per_second": 59.776,
|
| 933 |
+
"step": 21000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.335179754534593,
|
| 937 |
+
"grad_norm": 1.4017307758331299,
|
| 938 |
+
"learning_rate": 3.5337804130717096e-05,
|
| 939 |
+
"loss": 0.2171,
|
| 940 |
+
"step": 21500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.335179754534593,
|
| 944 |
+
"eval_accuracy": 0.9166666666666666,
|
| 945 |
+
"eval_f1_macro": 0.9162826856619433,
|
| 946 |
+
"eval_f1_micro": 0.9166666666666666,
|
| 947 |
+
"eval_loss": 0.23610982298851013,
|
| 948 |
+
"eval_precision_macro": 0.9248109520591958,
|
| 949 |
+
"eval_precision_micro": 0.9166666666666666,
|
| 950 |
+
"eval_recall_macro": 0.9257832999982825,
|
| 951 |
+
"eval_recall_micro": 0.9166666666666666,
|
| 952 |
+
"eval_runtime": 1.6011,
|
| 953 |
+
"eval_samples_per_second": 464.685,
|
| 954 |
+
"eval_steps_per_second": 58.086,
|
| 955 |
+
"step": 21500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.389486260454002,
|
| 959 |
+
"grad_norm": 3.65702486038208,
|
| 960 |
+
"learning_rate": 3.34609976885854e-05,
|
| 961 |
+
"loss": 0.1544,
|
| 962 |
+
"step": 22000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.389486260454002,
|
| 966 |
+
"eval_accuracy": 0.8938172043010753,
|
| 967 |
+
"eval_f1_macro": 0.9112579615652996,
|
| 968 |
+
"eval_f1_micro": 0.8938172043010753,
|
| 969 |
+
"eval_loss": 0.31801822781562805,
|
| 970 |
+
"eval_precision_macro": 0.9257465643895157,
|
| 971 |
+
"eval_precision_micro": 0.8938172043010753,
|
| 972 |
+
"eval_recall_macro": 0.9157454548646736,
|
| 973 |
+
"eval_recall_micro": 0.8938172043010753,
|
| 974 |
+
"eval_runtime": 1.5901,
|
| 975 |
+
"eval_samples_per_second": 467.885,
|
| 976 |
+
"eval_steps_per_second": 58.486,
|
| 977 |
+
"step": 22000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.4437927663734116,
|
| 981 |
+
"grad_norm": 17.16629409790039,
|
| 982 |
+
"learning_rate": 3.15988748926769e-05,
|
| 983 |
+
"loss": 0.2244,
|
| 984 |
+
"step": 22500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.4437927663734116,
|
| 988 |
+
"eval_accuracy": 0.9274193548387096,
|
| 989 |
+
"eval_f1_macro": 0.929163688176975,
|
| 990 |
+
"eval_f1_micro": 0.9274193548387096,
|
| 991 |
+
"eval_loss": 0.2233731597661972,
|
| 992 |
+
"eval_precision_macro": 0.9488357724575086,
|
| 993 |
+
"eval_precision_micro": 0.9274193548387096,
|
| 994 |
+
"eval_recall_macro": 0.9373529300126245,
|
| 995 |
+
"eval_recall_micro": 0.9274193548387096,
|
| 996 |
+
"eval_runtime": 1.5811,
|
| 997 |
+
"eval_samples_per_second": 470.56,
|
| 998 |
+
"eval_steps_per_second": 58.82,
|
| 999 |
+
"step": 22500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.4980992722928206,
|
| 1003 |
+
"grad_norm": 0.002982610370963812,
|
| 1004 |
+
"learning_rate": 2.9755617229869363e-05,
|
| 1005 |
+
"loss": 0.1862,
|
| 1006 |
+
"step": 23000
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.4980992722928206,
|
| 1010 |
+
"eval_accuracy": 0.9233870967741935,
|
| 1011 |
+
"eval_f1_macro": 0.928924685412107,
|
| 1012 |
+
"eval_f1_micro": 0.9233870967741935,
|
| 1013 |
+
"eval_loss": 0.2193865180015564,
|
| 1014 |
+
"eval_precision_macro": 0.9530930478155653,
|
| 1015 |
+
"eval_precision_micro": 0.9233870967741935,
|
| 1016 |
+
"eval_recall_macro": 0.9284052780385081,
|
| 1017 |
+
"eval_recall_micro": 0.9233870967741935,
|
| 1018 |
+
"eval_runtime": 1.5911,
|
| 1019 |
+
"eval_samples_per_second": 467.594,
|
| 1020 |
+
"eval_steps_per_second": 58.449,
|
| 1021 |
+
"step": 23000
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 2.55240577821223,
|
| 1025 |
+
"grad_norm": 0.005432271398603916,
|
| 1026 |
+
"learning_rate": 2.7942593577289413e-05,
|
| 1027 |
+
"loss": 0.1675,
|
| 1028 |
+
"step": 23500
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.55240577821223,
|
| 1032 |
+
"eval_accuracy": 0.9032258064516129,
|
| 1033 |
+
"eval_f1_macro": 0.9171716939776399,
|
| 1034 |
+
"eval_f1_micro": 0.9032258064516129,
|
| 1035 |
+
"eval_loss": 0.28054481744766235,
|
| 1036 |
+
"eval_precision_macro": 0.9380595809537082,
|
| 1037 |
+
"eval_precision_micro": 0.9032258064516129,
|
| 1038 |
+
"eval_recall_macro": 0.9295445270488267,
|
| 1039 |
+
"eval_recall_micro": 0.9032258064516129,
|
| 1040 |
+
"eval_runtime": 1.5905,
|
| 1041 |
+
"eval_samples_per_second": 467.768,
|
| 1042 |
+
"eval_steps_per_second": 58.471,
|
| 1043 |
+
"step": 23500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.606712284131639,
|
| 1047 |
+
"grad_norm": 1.1801046133041382,
|
| 1048 |
+
"learning_rate": 2.6149315464903132e-05,
|
| 1049 |
+
"loss": 0.2154,
|
| 1050 |
+
"step": 24000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 2.606712284131639,
|
| 1054 |
+
"eval_accuracy": 0.9099462365591398,
|
| 1055 |
+
"eval_f1_macro": 0.9317358502662257,
|
| 1056 |
+
"eval_f1_micro": 0.9099462365591398,
|
| 1057 |
+
"eval_loss": 0.20521479845046997,
|
| 1058 |
+
"eval_precision_macro": 0.9532059136761886,
|
| 1059 |
+
"eval_precision_micro": 0.9099462365591398,
|
| 1060 |
+
"eval_recall_macro": 0.9443101546357744,
|
| 1061 |
+
"eval_recall_micro": 0.9099462365591398,
|
| 1062 |
+
"eval_runtime": 1.6188,
|
| 1063 |
+
"eval_samples_per_second": 459.613,
|
| 1064 |
+
"eval_steps_per_second": 57.452,
|
| 1065 |
+
"step": 24000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 2.661018790051048,
|
| 1069 |
+
"grad_norm": 2.6474785804748535,
|
| 1070 |
+
"learning_rate": 2.4387139735109228e-05,
|
| 1071 |
+
"loss": 0.1994,
|
| 1072 |
+
"step": 24500
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 2.661018790051048,
|
| 1076 |
+
"eval_accuracy": 0.9206989247311828,
|
| 1077 |
+
"eval_f1_macro": 0.9285830674772237,
|
| 1078 |
+
"eval_f1_micro": 0.9206989247311828,
|
| 1079 |
+
"eval_loss": 0.3016538619995117,
|
| 1080 |
+
"eval_precision_macro": 0.9344600444511141,
|
| 1081 |
+
"eval_precision_micro": 0.9206989247311828,
|
| 1082 |
+
"eval_recall_macro": 0.9264637971148902,
|
| 1083 |
+
"eval_recall_micro": 0.9206989247311828,
|
| 1084 |
+
"eval_runtime": 1.5905,
|
| 1085 |
+
"eval_samples_per_second": 467.768,
|
| 1086 |
+
"eval_steps_per_second": 58.471,
|
| 1087 |
+
"step": 24500
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 2.715325295970457,
|
| 1091 |
+
"grad_norm": 0.6192300319671631,
|
| 1092 |
+
"learning_rate": 2.266002343881043e-05,
|
| 1093 |
+
"loss": 0.1693,
|
| 1094 |
+
"step": 25000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.715325295970457,
|
| 1098 |
+
"eval_accuracy": 0.9247311827956989,
|
| 1099 |
+
"eval_f1_macro": 0.9264992560565771,
|
| 1100 |
+
"eval_f1_micro": 0.9247311827956989,
|
| 1101 |
+
"eval_loss": 0.2687015235424042,
|
| 1102 |
+
"eval_precision_macro": 0.9451846988558618,
|
| 1103 |
+
"eval_precision_micro": 0.9247311827956989,
|
| 1104 |
+
"eval_recall_macro": 0.931429635216938,
|
| 1105 |
+
"eval_recall_micro": 0.9247311827956989,
|
| 1106 |
+
"eval_runtime": 1.5613,
|
| 1107 |
+
"eval_samples_per_second": 476.521,
|
| 1108 |
+
"eval_steps_per_second": 59.565,
|
| 1109 |
+
"step": 25000
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.7696318018898665,
|
| 1113 |
+
"grad_norm": 1.0121103525161743,
|
| 1114 |
+
"learning_rate": 2.0971844899254465e-05,
|
| 1115 |
+
"loss": 0.1455,
|
| 1116 |
+
"step": 25500
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.7696318018898665,
|
| 1120 |
+
"eval_accuracy": 0.9301075268817204,
|
| 1121 |
+
"eval_f1_macro": 0.9355979987630854,
|
| 1122 |
+
"eval_f1_micro": 0.9301075268817204,
|
| 1123 |
+
"eval_loss": 0.1772308498620987,
|
| 1124 |
+
"eval_precision_macro": 0.9578394473984728,
|
| 1125 |
+
"eval_precision_micro": 0.9301075268817204,
|
| 1126 |
+
"eval_recall_macro": 0.9376020750294228,
|
| 1127 |
+
"eval_recall_micro": 0.9301075268817204,
|
| 1128 |
+
"eval_runtime": 1.5579,
|
| 1129 |
+
"eval_samples_per_second": 477.553,
|
| 1130 |
+
"eval_steps_per_second": 59.694,
|
| 1131 |
+
"step": 25500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.8239383078092755,
|
| 1135 |
+
"grad_norm": 7.186190605163574,
|
| 1136 |
+
"learning_rate": 1.9326395003071377e-05,
|
| 1137 |
+
"loss": 0.1483,
|
| 1138 |
+
"step": 26000
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.8239383078092755,
|
| 1142 |
+
"eval_accuracy": 0.9099462365591398,
|
| 1143 |
+
"eval_f1_macro": 0.9274305548763755,
|
| 1144 |
+
"eval_f1_micro": 0.9099462365591398,
|
| 1145 |
+
"eval_loss": 0.2263285517692566,
|
| 1146 |
+
"eval_precision_macro": 0.9497007612847732,
|
| 1147 |
+
"eval_precision_micro": 0.9099462365591398,
|
| 1148 |
+
"eval_recall_macro": 0.9370680110954468,
|
| 1149 |
+
"eval_recall_micro": 0.9099462365591398,
|
| 1150 |
+
"eval_runtime": 1.5569,
|
| 1151 |
+
"eval_samples_per_second": 477.873,
|
| 1152 |
+
"eval_steps_per_second": 59.734,
|
| 1153 |
+
"step": 26000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.878244813728685,
|
| 1157 |
+
"grad_norm": 0.7355983257293701,
|
| 1158 |
+
"learning_rate": 1.77273686876542e-05,
|
| 1159 |
+
"loss": 0.1228,
|
| 1160 |
+
"step": 26500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 2.878244813728685,
|
| 1164 |
+
"eval_accuracy": 0.9139784946236559,
|
| 1165 |
+
"eval_f1_macro": 0.9345990129995828,
|
| 1166 |
+
"eval_f1_micro": 0.9139784946236559,
|
| 1167 |
+
"eval_loss": 0.15667569637298584,
|
| 1168 |
+
"eval_precision_macro": 0.9546581752954356,
|
| 1169 |
+
"eval_precision_micro": 0.9139784946236559,
|
| 1170 |
+
"eval_recall_macro": 0.9451982881542952,
|
| 1171 |
+
"eval_recall_micro": 0.9139784946236559,
|
| 1172 |
+
"eval_runtime": 1.5563,
|
| 1173 |
+
"eval_samples_per_second": 478.061,
|
| 1174 |
+
"eval_steps_per_second": 59.758,
|
| 1175 |
+
"step": 26500
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.932551319648094,
|
| 1179 |
+
"grad_norm": 1.0231633186340332,
|
| 1180 |
+
"learning_rate": 1.617835664399812e-05,
|
| 1181 |
+
"loss": 0.1627,
|
| 1182 |
+
"step": 27000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.932551319648094,
|
| 1186 |
+
"eval_accuracy": 0.9112903225806451,
|
| 1187 |
+
"eval_f1_macro": 0.9300960898223695,
|
| 1188 |
+
"eval_f1_micro": 0.9112903225806451,
|
| 1189 |
+
"eval_loss": 0.19375352561473846,
|
| 1190 |
+
"eval_precision_macro": 0.9520703470166678,
|
| 1191 |
+
"eval_precision_micro": 0.9112903225806451,
|
| 1192 |
+
"eval_recall_macro": 0.9397685186488954,
|
| 1193 |
+
"eval_recall_micro": 0.9112903225806451,
|
| 1194 |
+
"eval_runtime": 1.5507,
|
| 1195 |
+
"eval_samples_per_second": 479.787,
|
| 1196 |
+
"eval_steps_per_second": 59.973,
|
| 1197 |
+
"step": 27000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 2.986857825567503,
|
| 1201 |
+
"grad_norm": 1.2636340856552124,
|
| 1202 |
+
"learning_rate": 1.4682837253630058e-05,
|
| 1203 |
+
"loss": 0.1106,
|
| 1204 |
+
"step": 27500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 2.986857825567503,
|
| 1208 |
+
"eval_accuracy": 0.9314516129032258,
|
| 1209 |
+
"eval_f1_macro": 0.9360611349608771,
|
| 1210 |
+
"eval_f1_micro": 0.9314516129032258,
|
| 1211 |
+
"eval_loss": 0.18830984830856323,
|
| 1212 |
+
"eval_precision_macro": 0.9530936916231376,
|
| 1213 |
+
"eval_precision_micro": 0.9314516129032258,
|
| 1214 |
+
"eval_recall_macro": 0.9396110759039699,
|
| 1215 |
+
"eval_recall_micro": 0.9314516129032258,
|
| 1216 |
+
"eval_runtime": 1.5429,
|
| 1217 |
+
"eval_samples_per_second": 482.224,
|
| 1218 |
+
"eval_steps_per_second": 60.278,
|
| 1219 |
+
"step": 27500
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 3.0411643314869123,
|
| 1223 |
+
"grad_norm": 1.0935313701629639,
|
| 1224 |
+
"learning_rate": 1.3244168777734551e-05,
|
| 1225 |
+
"loss": 0.1105,
|
| 1226 |
+
"step": 28000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 3.0411643314869123,
|
| 1230 |
+
"eval_accuracy": 0.9341397849462365,
|
| 1231 |
+
"eval_f1_macro": 0.9393547932119972,
|
| 1232 |
+
"eval_f1_micro": 0.9341397849462365,
|
| 1233 |
+
"eval_loss": 0.1898634135723114,
|
| 1234 |
+
"eval_precision_macro": 0.9593318319238684,
|
| 1235 |
+
"eval_precision_micro": 0.9341397849462365,
|
| 1236 |
+
"eval_recall_macro": 0.945290330511796,
|
| 1237 |
+
"eval_recall_micro": 0.9341397849462365,
|
| 1238 |
+
"eval_runtime": 1.5415,
|
| 1239 |
+
"eval_samples_per_second": 482.636,
|
| 1240 |
+
"eval_steps_per_second": 60.329,
|
| 1241 |
+
"step": 28000
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 3.0954708374063213,
|
| 1245 |
+
"grad_norm": 1.7280462980270386,
|
| 1246 |
+
"learning_rate": 1.1865581816015724e-05,
|
| 1247 |
+
"loss": 0.0978,
|
| 1248 |
+
"step": 28500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 3.0954708374063213,
|
| 1252 |
+
"eval_accuracy": 0.9126344086021505,
|
| 1253 |
+
"eval_f1_macro": 0.932842505921675,
|
| 1254 |
+
"eval_f1_micro": 0.9126344086021505,
|
| 1255 |
+
"eval_loss": 0.1739678680896759,
|
| 1256 |
+
"eval_precision_macro": 0.9588560830865595,
|
| 1257 |
+
"eval_precision_micro": 0.9126344086021505,
|
| 1258 |
+
"eval_recall_macro": 0.9441396878334974,
|
| 1259 |
+
"eval_recall_micro": 0.9126344086021505,
|
| 1260 |
+
"eval_runtime": 1.5969,
|
| 1261 |
+
"eval_samples_per_second": 465.902,
|
| 1262 |
+
"eval_steps_per_second": 58.238,
|
| 1263 |
+
"step": 28500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 3.1497773433257303,
|
| 1267 |
+
"grad_norm": 4.298096656799316,
|
| 1268 |
+
"learning_rate": 1.055017205222924e-05,
|
| 1269 |
+
"loss": 0.0847,
|
| 1270 |
+
"step": 29000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 3.1497773433257303,
|
| 1274 |
+
"eval_accuracy": 0.907258064516129,
|
| 1275 |
+
"eval_f1_macro": 0.9287242305872121,
|
| 1276 |
+
"eval_f1_micro": 0.907258064516129,
|
| 1277 |
+
"eval_loss": 0.18464291095733643,
|
| 1278 |
+
"eval_precision_macro": 0.9485674275338388,
|
| 1279 |
+
"eval_precision_micro": 0.907258064516129,
|
| 1280 |
+
"eval_recall_macro": 0.9397129171252141,
|
| 1281 |
+
"eval_recall_micro": 0.907258064516129,
|
| 1282 |
+
"eval_runtime": 1.5931,
|
| 1283 |
+
"eval_samples_per_second": 467.028,
|
| 1284 |
+
"eval_steps_per_second": 58.378,
|
| 1285 |
+
"step": 29000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 3.20408384924514,
|
| 1289 |
+
"grad_norm": 2.599429130554199,
|
| 1290 |
+
"learning_rate": 9.30332397145231e-06,
|
| 1291 |
+
"loss": 0.0929,
|
| 1292 |
+
"step": 29500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 3.20408384924514,
|
| 1296 |
+
"eval_accuracy": 0.928763440860215,
|
| 1297 |
+
"eval_f1_macro": 0.9319260758161285,
|
| 1298 |
+
"eval_f1_micro": 0.928763440860215,
|
| 1299 |
+
"eval_loss": 0.2623588442802429,
|
| 1300 |
+
"eval_precision_macro": 0.9522632308119076,
|
| 1301 |
+
"eval_precision_micro": 0.928763440860215,
|
| 1302 |
+
"eval_recall_macro": 0.9354531905275971,
|
| 1303 |
+
"eval_recall_micro": 0.928763440860215,
|
| 1304 |
+
"eval_runtime": 1.5913,
|
| 1305 |
+
"eval_samples_per_second": 467.542,
|
| 1306 |
+
"eval_steps_per_second": 58.443,
|
| 1307 |
+
"step": 29500
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 3.258390355164549,
|
| 1311 |
+
"grad_norm": 1.0820720195770264,
|
| 1312 |
+
"learning_rate": 8.122840981545725e-06,
|
| 1313 |
+
"loss": 0.0861,
|
| 1314 |
+
"step": 30000
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 3.258390355164549,
|
| 1318 |
+
"eval_accuracy": 0.9274193548387096,
|
| 1319 |
+
"eval_f1_macro": 0.9276130625845173,
|
| 1320 |
+
"eval_f1_micro": 0.9274193548387096,
|
| 1321 |
+
"eval_loss": 0.26659145951271057,
|
| 1322 |
+
"eval_precision_macro": 0.9482101341581514,
|
| 1323 |
+
"eval_precision_micro": 0.9274193548387096,
|
| 1324 |
+
"eval_recall_macro": 0.9313633323621086,
|
| 1325 |
+
"eval_recall_micro": 0.9274193548387096,
|
| 1326 |
+
"eval_runtime": 1.5883,
|
| 1327 |
+
"eval_samples_per_second": 468.419,
|
| 1328 |
+
"eval_steps_per_second": 58.552,
|
| 1329 |
+
"step": 30000
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 3.3126968610839578,
|
| 1333 |
+
"grad_norm": 0.9298611283302307,
|
| 1334 |
+
"learning_rate": 7.016084376904304e-06,
|
| 1335 |
+
"loss": 0.1159,
|
| 1336 |
+
"step": 30500
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 3.3126968610839578,
|
| 1340 |
+
"eval_accuracy": 0.9086021505376344,
|
| 1341 |
+
"eval_f1_macro": 0.9269507193451398,
|
| 1342 |
+
"eval_f1_micro": 0.9086021505376344,
|
| 1343 |
+
"eval_loss": 0.2247731238603592,
|
| 1344 |
+
"eval_precision_macro": 0.9537479338140438,
|
| 1345 |
+
"eval_precision_micro": 0.9086021505376344,
|
| 1346 |
+
"eval_recall_macro": 0.9375578499701469,
|
| 1347 |
+
"eval_recall_micro": 0.9086021505376344,
|
| 1348 |
+
"eval_runtime": 1.5934,
|
| 1349 |
+
"eval_samples_per_second": 466.925,
|
| 1350 |
+
"eval_steps_per_second": 58.366,
|
| 1351 |
+
"step": 30500
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 3.3670033670033668,
|
| 1355 |
+
"grad_norm": 1.2038335800170898,
|
| 1356 |
+
"learning_rate": 5.981104366775459e-06,
|
| 1357 |
+
"loss": 0.0983,
|
| 1358 |
+
"step": 31000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 3.3670033670033668,
|
| 1362 |
+
"eval_accuracy": 0.9112903225806451,
|
| 1363 |
+
"eval_f1_macro": 0.929673894660028,
|
| 1364 |
+
"eval_f1_micro": 0.9112903225806451,
|
| 1365 |
+
"eval_loss": 0.21170715987682343,
|
| 1366 |
+
"eval_precision_macro": 0.9562636570844839,
|
| 1367 |
+
"eval_precision_micro": 0.9112903225806451,
|
| 1368 |
+
"eval_recall_macro": 0.9408174871583557,
|
| 1369 |
+
"eval_recall_micro": 0.9112903225806451,
|
| 1370 |
+
"eval_runtime": 1.592,
|
| 1371 |
+
"eval_samples_per_second": 467.328,
|
| 1372 |
+
"eval_steps_per_second": 58.416,
|
| 1373 |
+
"step": 31000
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 3.421309872922776,
|
| 1377 |
+
"grad_norm": 14.01207447052002,
|
| 1378 |
+
"learning_rate": 5.022515433540584e-06,
|
| 1379 |
+
"loss": 0.1093,
|
| 1380 |
+
"step": 31500
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 3.421309872922776,
|
| 1384 |
+
"eval_accuracy": 0.9341397849462365,
|
| 1385 |
+
"eval_f1_macro": 0.9384885883048681,
|
| 1386 |
+
"eval_f1_micro": 0.9341397849462365,
|
| 1387 |
+
"eval_loss": 0.21036885678768158,
|
| 1388 |
+
"eval_precision_macro": 0.9544129085177095,
|
| 1389 |
+
"eval_precision_micro": 0.9341397849462365,
|
| 1390 |
+
"eval_recall_macro": 0.9426855279069932,
|
| 1391 |
+
"eval_recall_micro": 0.9341397849462365,
|
| 1392 |
+
"eval_runtime": 1.5897,
|
| 1393 |
+
"eval_samples_per_second": 468.025,
|
| 1394 |
+
"eval_steps_per_second": 58.503,
|
| 1395 |
+
"step": 31500
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 3.475616378842185,
|
| 1399 |
+
"grad_norm": 0.0029710547532886267,
|
| 1400 |
+
"learning_rate": 4.142470135051615e-06,
|
| 1401 |
+
"loss": 0.0892,
|
| 1402 |
+
"step": 32000
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 3.475616378842185,
|
| 1406 |
+
"eval_accuracy": 0.9126344086021505,
|
| 1407 |
+
"eval_f1_macro": 0.933263998404932,
|
| 1408 |
+
"eval_f1_micro": 0.9126344086021505,
|
| 1409 |
+
"eval_loss": 0.21525545418262482,
|
| 1410 |
+
"eval_precision_macro": 0.9471592585609407,
|
| 1411 |
+
"eval_precision_micro": 0.9126344086021505,
|
| 1412 |
+
"eval_recall_macro": 0.9420731137871163,
|
| 1413 |
+
"eval_recall_micro": 0.9126344086021505,
|
| 1414 |
+
"eval_runtime": 1.5909,
|
| 1415 |
+
"eval_samples_per_second": 467.651,
|
| 1416 |
+
"eval_steps_per_second": 58.456,
|
| 1417 |
+
"step": 32000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.5299228847615947,
|
| 1421 |
+
"grad_norm": 0.0014916452346369624,
|
| 1422 |
+
"learning_rate": 3.3429446556265453e-06,
|
| 1423 |
+
"loss": 0.0921,
|
| 1424 |
+
"step": 32500
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.5299228847615947,
|
| 1428 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1429 |
+
"eval_f1_macro": 0.9403174227850596,
|
| 1430 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1431 |
+
"eval_loss": 0.20182642340660095,
|
| 1432 |
+
"eval_precision_macro": 0.9610729151777162,
|
| 1433 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1434 |
+
"eval_recall_macro": 0.9450761984609293,
|
| 1435 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1436 |
+
"eval_runtime": 1.5911,
|
| 1437 |
+
"eval_samples_per_second": 467.608,
|
| 1438 |
+
"eval_steps_per_second": 58.451,
|
| 1439 |
+
"step": 32500
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 3.5842293906810037,
|
| 1443 |
+
"grad_norm": 0.028313804417848587,
|
| 1444 |
+
"learning_rate": 2.625734368431996e-06,
|
| 1445 |
+
"loss": 0.1112,
|
| 1446 |
+
"step": 33000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 3.5842293906810037,
|
| 1450 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1451 |
+
"eval_f1_macro": 0.9403174227850596,
|
| 1452 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1453 |
+
"eval_loss": 0.19140255451202393,
|
| 1454 |
+
"eval_precision_macro": 0.9610729151777162,
|
| 1455 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1456 |
+
"eval_recall_macro": 0.9450761984609293,
|
| 1457 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1458 |
+
"eval_runtime": 1.5433,
|
| 1459 |
+
"eval_samples_per_second": 482.098,
|
| 1460 |
+
"eval_steps_per_second": 60.262,
|
| 1461 |
+
"step": 33000
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 3.6385358966004127,
|
| 1465 |
+
"grad_norm": 0.7935597896575928,
|
| 1466 |
+
"learning_rate": 1.992449803885794e-06,
|
| 1467 |
+
"loss": 0.0781,
|
| 1468 |
+
"step": 33500
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 3.6385358966004127,
|
| 1472 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1473 |
+
"eval_f1_macro": 0.9431465250491902,
|
| 1474 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1475 |
+
"eval_loss": 0.18505831062793732,
|
| 1476 |
+
"eval_precision_macro": 0.9605281751371779,
|
| 1477 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1478 |
+
"eval_recall_macro": 0.9482532934747587,
|
| 1479 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1480 |
+
"eval_runtime": 1.5588,
|
| 1481 |
+
"eval_samples_per_second": 477.296,
|
| 1482 |
+
"eval_steps_per_second": 59.662,
|
| 1483 |
+
"step": 33500
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 3.6928424025198217,
|
| 1487 |
+
"grad_norm": 3.4242069721221924,
|
| 1488 |
+
"learning_rate": 1.444513033132977e-06,
|
| 1489 |
+
"loss": 0.104,
|
| 1490 |
+
"step": 34000
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 3.6928424025198217,
|
| 1494 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1495 |
+
"eval_f1_macro": 0.9436897074728228,
|
| 1496 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1497 |
+
"eval_loss": 0.1714259684085846,
|
| 1498 |
+
"eval_precision_macro": 0.9618566197941735,
|
| 1499 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1500 |
+
"eval_recall_macro": 0.9478564680779333,
|
| 1501 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1502 |
+
"eval_runtime": 1.5565,
|
| 1503 |
+
"eval_samples_per_second": 478.008,
|
| 1504 |
+
"eval_steps_per_second": 59.751,
|
| 1505 |
+
"step": 34000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.747148908439231,
|
| 1509 |
+
"grad_norm": 0.5764946341514587,
|
| 1510 |
+
"learning_rate": 9.839900655621303e-07,
|
| 1511 |
+
"loss": 0.0771,
|
| 1512 |
+
"step": 34500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 3.747148908439231,
|
| 1516 |
+
"eval_accuracy": 0.9368279569892473,
|
| 1517 |
+
"eval_f1_macro": 0.9453734182306841,
|
| 1518 |
+
"eval_f1_micro": 0.9368279569892473,
|
| 1519 |
+
"eval_loss": 0.17406800389289856,
|
| 1520 |
+
"eval_precision_macro": 0.9558439949105471,
|
| 1521 |
+
"eval_precision_micro": 0.9368279569892473,
|
| 1522 |
+
"eval_recall_macro": 0.9474835754951718,
|
| 1523 |
+
"eval_recall_micro": 0.9368279569892473,
|
| 1524 |
+
"eval_runtime": 1.5564,
|
| 1525 |
+
"eval_samples_per_second": 478.012,
|
| 1526 |
+
"eval_steps_per_second": 59.752,
|
| 1527 |
+
"step": 34500
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 3.80145541435864,
|
| 1531 |
+
"grad_norm": 1.5720099210739136,
|
| 1532 |
+
"learning_rate": 6.100695905203458e-07,
|
| 1533 |
+
"loss": 0.0916,
|
| 1534 |
+
"step": 35000
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 3.80145541435864,
|
| 1538 |
+
"eval_accuracy": 0.9341397849462365,
|
| 1539 |
+
"eval_f1_macro": 0.9472436482214578,
|
| 1540 |
+
"eval_f1_micro": 0.9341397849462365,
|
| 1541 |
+
"eval_loss": 0.17374970018863678,
|
| 1542 |
+
"eval_precision_macro": 0.9499695730366108,
|
| 1543 |
+
"eval_precision_micro": 0.9341397849462365,
|
| 1544 |
+
"eval_recall_macro": 0.9488576574662688,
|
| 1545 |
+
"eval_recall_micro": 0.9341397849462365,
|
| 1546 |
+
"eval_runtime": 1.5561,
|
| 1547 |
+
"eval_samples_per_second": 478.114,
|
| 1548 |
+
"eval_steps_per_second": 59.764,
|
| 1549 |
+
"step": 35000
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 3.8557619202780495,
|
| 1553 |
+
"grad_norm": 1.1937015056610107,
|
| 1554 |
+
"learning_rate": 3.2460111095780954e-07,
|
| 1555 |
+
"loss": 0.0871,
|
| 1556 |
+
"step": 35500
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 3.8557619202780495,
|
| 1560 |
+
"eval_accuracy": 0.9153225806451613,
|
| 1561 |
+
"eval_f1_macro": 0.9355623635453241,
|
| 1562 |
+
"eval_f1_micro": 0.9153225806451613,
|
| 1563 |
+
"eval_loss": 0.17309460043907166,
|
| 1564 |
+
"eval_precision_macro": 0.9566935705253509,
|
| 1565 |
+
"eval_precision_micro": 0.9153225806451613,
|
| 1566 |
+
"eval_recall_macro": 0.9470660204134378,
|
| 1567 |
+
"eval_recall_micro": 0.9153225806451613,
|
| 1568 |
+
"eval_runtime": 1.5563,
|
| 1569 |
+
"eval_samples_per_second": 478.07,
|
| 1570 |
+
"eval_steps_per_second": 59.759,
|
| 1571 |
+
"step": 35500
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.9100684261974585,
|
| 1575 |
+
"grad_norm": 0.0013589151203632355,
|
| 1576 |
+
"learning_rate": 1.2822566016402971e-07,
|
| 1577 |
+
"loss": 0.1047,
|
| 1578 |
+
"step": 36000
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.9100684261974585,
|
| 1582 |
+
"eval_accuracy": 0.9153225806451613,
|
| 1583 |
+
"eval_f1_macro": 0.9355623635453241,
|
| 1584 |
+
"eval_f1_micro": 0.9153225806451613,
|
| 1585 |
+
"eval_loss": 0.17508365213871002,
|
| 1586 |
+
"eval_precision_macro": 0.9566935705253509,
|
| 1587 |
+
"eval_precision_micro": 0.9153225806451613,
|
| 1588 |
+
"eval_recall_macro": 0.9470660204134378,
|
| 1589 |
+
"eval_recall_micro": 0.9153225806451613,
|
| 1590 |
+
"eval_runtime": 1.5895,
|
| 1591 |
+
"eval_samples_per_second": 468.068,
|
| 1592 |
+
"eval_steps_per_second": 58.509,
|
| 1593 |
+
"step": 36000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 3.9643749321168675,
|
| 1597 |
+
"grad_norm": 0.9162406325340271,
|
| 1598 |
+
"learning_rate": 2.1384208719683607e-08,
|
| 1599 |
+
"loss": 0.0845,
|
| 1600 |
+
"step": 36500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 3.9643749321168675,
|
| 1604 |
+
"eval_accuracy": 0.9153225806451613,
|
| 1605 |
+
"eval_f1_macro": 0.9355623635453241,
|
| 1606 |
+
"eval_f1_micro": 0.9153225806451613,
|
| 1607 |
+
"eval_loss": 0.17528513073921204,
|
| 1608 |
+
"eval_precision_macro": 0.9566935705253509,
|
| 1609 |
+
"eval_precision_micro": 0.9153225806451613,
|
| 1610 |
+
"eval_recall_macro": 0.9470660204134378,
|
| 1611 |
+
"eval_recall_micro": 0.9153225806451613,
|
| 1612 |
+
"eval_runtime": 1.5895,
|
| 1613 |
+
"eval_samples_per_second": 468.083,
|
| 1614 |
+
"eval_steps_per_second": 58.51,
|
| 1615 |
+
"step": 36500
|
| 1616 |
+
}
|
| 1617 |
+
],
|
| 1618 |
+
"logging_steps": 500,
|
| 1619 |
+
"max_steps": 36828,
|
| 1620 |
+
"num_input_tokens_seen": 0,
|
| 1621 |
+
"num_train_epochs": 4,
|
| 1622 |
+
"save_steps": 500,
|
| 1623 |
+
"stateful_callbacks": {
|
| 1624 |
+
"TrainerControl": {
|
| 1625 |
+
"args": {
|
| 1626 |
+
"should_epoch_stop": false,
|
| 1627 |
+
"should_evaluate": false,
|
| 1628 |
+
"should_log": false,
|
| 1629 |
+
"should_save": true,
|
| 1630 |
+
"should_training_stop": false
|
| 1631 |
+
},
|
| 1632 |
+
"attributes": {}
|
| 1633 |
+
}
|
| 1634 |
+
},
|
| 1635 |
+
"total_flos": 7.683916617932083e+16,
|
| 1636 |
+
"train_batch_size": 8,
|
| 1637 |
+
"trial_name": null,
|
| 1638 |
+
"trial_params": null
|
| 1639 |
+
}
|
checkpoint-36500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b99ccaf60fb3d3d3654ec7ad7c6c81e3cadbbcacaebb9454d1deec6f2192d5d
|
| 3 |
+
size 5521
|
checkpoint-36500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|