Upload folder using huggingface_hub
Browse files- checkpoint-14500/config.json +70 -0
- checkpoint-14500/model.safetensors +3 -0
- checkpoint-14500/optimizer.pt +3 -0
- checkpoint-14500/rng_state.pth +3 -0
- checkpoint-14500/scaler.pt +3 -0
- checkpoint-14500/scheduler.pt +3 -0
- checkpoint-14500/special_tokens_map.json +37 -0
- checkpoint-14500/tokenizer.json +0 -0
- checkpoint-14500/tokenizer_config.json +339 -0
- checkpoint-14500/trainer_state.json +672 -0
- checkpoint-14500/training_args.bin +3 -0
- checkpoint-14500/vocab.txt +0 -0
- checkpoint-16472/config.json +70 -0
- checkpoint-16472/model.safetensors +3 -0
- checkpoint-16472/optimizer.pt +3 -0
- checkpoint-16472/rng_state.pth +3 -0
- checkpoint-16472/scaler.pt +3 -0
- checkpoint-16472/scheduler.pt +3 -0
- checkpoint-16472/special_tokens_map.json +37 -0
- checkpoint-16472/tokenizer.json +0 -0
- checkpoint-16472/tokenizer_config.json +339 -0
- checkpoint-16472/trainer_state.json +738 -0
- checkpoint-16472/training_args.bin +3 -0
- checkpoint-16472/vocab.txt +0 -0
checkpoint-14500/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CustomAraBERTClassifier"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4",
|
| 16 |
+
"5": "LABEL_5",
|
| 17 |
+
"6": "LABEL_6",
|
| 18 |
+
"7": "LABEL_7",
|
| 19 |
+
"8": "LABEL_8",
|
| 20 |
+
"9": "LABEL_9",
|
| 21 |
+
"10": "LABEL_10",
|
| 22 |
+
"11": "LABEL_11",
|
| 23 |
+
"12": "LABEL_12",
|
| 24 |
+
"13": "LABEL_13",
|
| 25 |
+
"14": "LABEL_14",
|
| 26 |
+
"15": "LABEL_15",
|
| 27 |
+
"16": "LABEL_16",
|
| 28 |
+
"17": "LABEL_17",
|
| 29 |
+
"18": "LABEL_18",
|
| 30 |
+
"19": "LABEL_19",
|
| 31 |
+
"20": "LABEL_20"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_10": 10,
|
| 39 |
+
"LABEL_11": 11,
|
| 40 |
+
"LABEL_12": 12,
|
| 41 |
+
"LABEL_13": 13,
|
| 42 |
+
"LABEL_14": 14,
|
| 43 |
+
"LABEL_15": 15,
|
| 44 |
+
"LABEL_16": 16,
|
| 45 |
+
"LABEL_17": 17,
|
| 46 |
+
"LABEL_18": 18,
|
| 47 |
+
"LABEL_19": 19,
|
| 48 |
+
"LABEL_2": 2,
|
| 49 |
+
"LABEL_20": 20,
|
| 50 |
+
"LABEL_3": 3,
|
| 51 |
+
"LABEL_4": 4,
|
| 52 |
+
"LABEL_5": 5,
|
| 53 |
+
"LABEL_6": 6,
|
| 54 |
+
"LABEL_7": 7,
|
| 55 |
+
"LABEL_8": 8,
|
| 56 |
+
"LABEL_9": 9
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-12,
|
| 59 |
+
"max_position_embeddings": 512,
|
| 60 |
+
"model_type": "bert",
|
| 61 |
+
"num_attention_heads": 12,
|
| 62 |
+
"num_hidden_layers": 12,
|
| 63 |
+
"pad_token_id": 0,
|
| 64 |
+
"position_embedding_type": "absolute",
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.53.3",
|
| 67 |
+
"type_vocab_size": 2,
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"vocab_size": 64000
|
| 70 |
+
}
|
checkpoint-14500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4470dc94accd060571e750a863502e60870c09920999e9ea04c40d359cb9d6a6
|
| 3 |
+
size 542010628
|
checkpoint-14500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf0a6feb3b5d17c156566a824187ff67fdae51bd51f35e8678ac4cb4b98e8f5b
|
| 3 |
+
size 1084144011
|
checkpoint-14500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae7f7e3bbe4609f13c9a4e4b3de4aa64c140187e8deeb23e9ad265afd6822d16
|
| 3 |
+
size 14645
|
checkpoint-14500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d2bdac9bf4b40495acb1dae760d920b4e9a2ecffe48d4efe1a22c61b3566a5a
|
| 3 |
+
size 1383
|
checkpoint-14500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18ac965a7790faade764f57b93e56cac781190e2e837cd74775199b715be40ab
|
| 3 |
+
size 1465
|
checkpoint-14500/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-14500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-14500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "+ا",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "+ك",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "ب+",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "+هم",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "+ات",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "+ي",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "ل+",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "+هما",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "+نا",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "+ن",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "+ها",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "+كما",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "+ة",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "ف+",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "+كم",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "+كن",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "+ت",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[بريد]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[مستخدم]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "لل+",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "ال+",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[رابط]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "س+",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "+ان",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "+وا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "+ه",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "+ون",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "+هن",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "+ين",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": true,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "��+",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": true,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "ك+",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": true,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[UNK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[CLS]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[SEP]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[MASK]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": false,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"extra_special_tokens": {},
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ك",
|
| 302 |
+
"+كما",
|
| 303 |
+
"ك+",
|
| 304 |
+
"+وا",
|
| 305 |
+
"+ين",
|
| 306 |
+
"و+",
|
| 307 |
+
"+كن",
|
| 308 |
+
"+ان",
|
| 309 |
+
"+هم",
|
| 310 |
+
"+ة",
|
| 311 |
+
"[بريد]",
|
| 312 |
+
"لل+",
|
| 313 |
+
"+ي",
|
| 314 |
+
"+ت",
|
| 315 |
+
"+ن",
|
| 316 |
+
"س+",
|
| 317 |
+
"ل+",
|
| 318 |
+
"[مستخدم]",
|
| 319 |
+
"+كم",
|
| 320 |
+
"+ا",
|
| 321 |
+
"ب+",
|
| 322 |
+
"ف+",
|
| 323 |
+
"+نا",
|
| 324 |
+
"+ها",
|
| 325 |
+
"+ون",
|
| 326 |
+
"+هما",
|
| 327 |
+
"ال+",
|
| 328 |
+
"+ه",
|
| 329 |
+
"+هن",
|
| 330 |
+
"+ات",
|
| 331 |
+
"[رابط]"
|
| 332 |
+
],
|
| 333 |
+
"pad_token": "[PAD]",
|
| 334 |
+
"sep_token": "[SEP]",
|
| 335 |
+
"strip_accents": null,
|
| 336 |
+
"tokenize_chinese_chars": true,
|
| 337 |
+
"tokenizer_class": "BertTokenizer",
|
| 338 |
+
"unk_token": "[UNK]"
|
| 339 |
+
}
|
checkpoint-14500/trainer_state.json
ADDED
|
@@ -0,0 +1,672 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 14500,
|
| 3 |
+
"best_metric": 0.8339685375452801,
|
| 4 |
+
"best_model_checkpoint": "./arabert_author_model/checkpoint-14500",
|
| 5 |
+
"epoch": 3.52112676056338,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 14500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.12141816415735794,
|
| 14 |
+
"grad_norm": 29.529987335205078,
|
| 15 |
+
"learning_rate": 2.393203883495146e-05,
|
| 16 |
+
"loss": 2.8696,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12141816415735794,
|
| 21 |
+
"eval_accuracy": 0.3425547269665624,
|
| 22 |
+
"eval_f1_macro": 0.25445032746487084,
|
| 23 |
+
"eval_f1_micro": 0.3425547269665624,
|
| 24 |
+
"eval_loss": 2.5629944801330566,
|
| 25 |
+
"eval_precision_macro": 0.3403621440266495,
|
| 26 |
+
"eval_precision_micro": 0.3425547269665624,
|
| 27 |
+
"eval_recall_macro": 0.3478089407512695,
|
| 28 |
+
"eval_recall_micro": 0.3425547269665624,
|
| 29 |
+
"eval_runtime": 27.2244,
|
| 30 |
+
"eval_samples_per_second": 152.694,
|
| 31 |
+
"eval_steps_per_second": 19.101,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.24283632831471588,
|
| 36 |
+
"grad_norm": 9.098995208740234,
|
| 37 |
+
"learning_rate": 4.8155339805825245e-05,
|
| 38 |
+
"loss": 1.9602,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.24283632831471588,
|
| 43 |
+
"eval_accuracy": 0.6454173682944431,
|
| 44 |
+
"eval_f1_macro": 0.5286934521513375,
|
| 45 |
+
"eval_f1_micro": 0.6454173682944431,
|
| 46 |
+
"eval_loss": 1.4127496480941772,
|
| 47 |
+
"eval_precision_macro": 0.5385051007277866,
|
| 48 |
+
"eval_precision_micro": 0.6454173682944431,
|
| 49 |
+
"eval_recall_macro": 0.5857769176935503,
|
| 50 |
+
"eval_recall_micro": 0.6454173682944431,
|
| 51 |
+
"eval_runtime": 27.2734,
|
| 52 |
+
"eval_samples_per_second": 152.42,
|
| 53 |
+
"eval_steps_per_second": 19.066,
|
| 54 |
+
"step": 1000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.3642544924720738,
|
| 58 |
+
"grad_norm": 12.638616561889648,
|
| 59 |
+
"learning_rate": 7.242718446601942e-05,
|
| 60 |
+
"loss": 1.3183,
|
| 61 |
+
"step": 1500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.3642544924720738,
|
| 65 |
+
"eval_accuracy": 0.65215299494828,
|
| 66 |
+
"eval_f1_macro": 0.5540919349082173,
|
| 67 |
+
"eval_f1_micro": 0.65215299494828,
|
| 68 |
+
"eval_loss": 1.239192247390747,
|
| 69 |
+
"eval_precision_macro": 0.6120898590926472,
|
| 70 |
+
"eval_precision_micro": 0.65215299494828,
|
| 71 |
+
"eval_recall_macro": 0.6092527387773333,
|
| 72 |
+
"eval_recall_micro": 0.65215299494828,
|
| 73 |
+
"eval_runtime": 27.2704,
|
| 74 |
+
"eval_samples_per_second": 152.437,
|
| 75 |
+
"eval_steps_per_second": 19.068,
|
| 76 |
+
"step": 1500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.48567265662943176,
|
| 80 |
+
"grad_norm": 30.778980255126953,
|
| 81 |
+
"learning_rate": 7.989375134121083e-05,
|
| 82 |
+
"loss": 1.0436,
|
| 83 |
+
"step": 2000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.48567265662943176,
|
| 87 |
+
"eval_accuracy": 0.7310560500360838,
|
| 88 |
+
"eval_f1_macro": 0.6287971185064818,
|
| 89 |
+
"eval_f1_micro": 0.7310560500360838,
|
| 90 |
+
"eval_loss": 0.9975479245185852,
|
| 91 |
+
"eval_precision_macro": 0.6542445683571894,
|
| 92 |
+
"eval_precision_micro": 0.7310560500360838,
|
| 93 |
+
"eval_recall_macro": 0.6428366638693614,
|
| 94 |
+
"eval_recall_micro": 0.7310560500360838,
|
| 95 |
+
"eval_runtime": 27.2787,
|
| 96 |
+
"eval_samples_per_second": 152.39,
|
| 97 |
+
"eval_steps_per_second": 19.062,
|
| 98 |
+
"step": 2000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.6070908207867897,
|
| 102 |
+
"grad_norm": 19.659687042236328,
|
| 103 |
+
"learning_rate": 7.936184577251333e-05,
|
| 104 |
+
"loss": 0.8937,
|
| 105 |
+
"step": 2500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.6070908207867897,
|
| 109 |
+
"eval_accuracy": 0.6634592254029348,
|
| 110 |
+
"eval_f1_macro": 0.5881193362986468,
|
| 111 |
+
"eval_f1_micro": 0.6634592254029348,
|
| 112 |
+
"eval_loss": 1.2966861724853516,
|
| 113 |
+
"eval_precision_macro": 0.6346376229831586,
|
| 114 |
+
"eval_precision_micro": 0.6634592254029348,
|
| 115 |
+
"eval_recall_macro": 0.6216328795839745,
|
| 116 |
+
"eval_recall_micro": 0.6634592254029348,
|
| 117 |
+
"eval_runtime": 27.2772,
|
| 118 |
+
"eval_samples_per_second": 152.398,
|
| 119 |
+
"eval_steps_per_second": 19.064,
|
| 120 |
+
"step": 2500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.7285089849441476,
|
| 124 |
+
"grad_norm": 52.43323516845703,
|
| 125 |
+
"learning_rate": 7.838839212672895e-05,
|
| 126 |
+
"loss": 0.7939,
|
| 127 |
+
"step": 3000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.7285089849441476,
|
| 131 |
+
"eval_accuracy": 0.7363483281212413,
|
| 132 |
+
"eval_f1_macro": 0.6401725490543624,
|
| 133 |
+
"eval_f1_micro": 0.7363483281212413,
|
| 134 |
+
"eval_loss": 1.0666863918304443,
|
| 135 |
+
"eval_precision_macro": 0.6944496519079535,
|
| 136 |
+
"eval_precision_micro": 0.7363483281212413,
|
| 137 |
+
"eval_recall_macro": 0.6587226907421574,
|
| 138 |
+
"eval_recall_micro": 0.7363483281212413,
|
| 139 |
+
"eval_runtime": 27.2761,
|
| 140 |
+
"eval_samples_per_second": 152.404,
|
| 141 |
+
"eval_steps_per_second": 19.064,
|
| 142 |
+
"step": 3000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8499271491015056,
|
| 146 |
+
"grad_norm": 11.124955177307129,
|
| 147 |
+
"learning_rate": 7.698753853285741e-05,
|
| 148 |
+
"loss": 0.6947,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8499271491015056,
|
| 153 |
+
"eval_accuracy": 0.797931200384893,
|
| 154 |
+
"eval_f1_macro": 0.7157099044978049,
|
| 155 |
+
"eval_f1_micro": 0.797931200384893,
|
| 156 |
+
"eval_loss": 0.8941665291786194,
|
| 157 |
+
"eval_precision_macro": 0.7316892204440334,
|
| 158 |
+
"eval_precision_micro": 0.797931200384893,
|
| 159 |
+
"eval_recall_macro": 0.7416061573455679,
|
| 160 |
+
"eval_recall_micro": 0.797931200384893,
|
| 161 |
+
"eval_runtime": 27.2726,
|
| 162 |
+
"eval_samples_per_second": 152.424,
|
| 163 |
+
"eval_steps_per_second": 19.067,
|
| 164 |
+
"step": 3500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9713453132588635,
|
| 168 |
+
"grad_norm": 16.576419830322266,
|
| 169 |
+
"learning_rate": 7.516938992131817e-05,
|
| 170 |
+
"loss": 0.5841,
|
| 171 |
+
"step": 4000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.9713453132588635,
|
| 175 |
+
"eval_accuracy": 0.769545345200866,
|
| 176 |
+
"eval_f1_macro": 0.7080092768138256,
|
| 177 |
+
"eval_f1_micro": 0.769545345200866,
|
| 178 |
+
"eval_loss": 1.0479093790054321,
|
| 179 |
+
"eval_precision_macro": 0.7402406037514909,
|
| 180 |
+
"eval_precision_micro": 0.769545345200866,
|
| 181 |
+
"eval_recall_macro": 0.7084186724135678,
|
| 182 |
+
"eval_recall_micro": 0.769545345200866,
|
| 183 |
+
"eval_runtime": 27.2399,
|
| 184 |
+
"eval_samples_per_second": 152.607,
|
| 185 |
+
"eval_steps_per_second": 19.09,
|
| 186 |
+
"step": 4000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.0927634774162214,
|
| 190 |
+
"grad_norm": 94.69003295898438,
|
| 191 |
+
"learning_rate": 7.295672280620509e-05,
|
| 192 |
+
"loss": 0.5537,
|
| 193 |
+
"step": 4500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.0927634774162214,
|
| 197 |
+
"eval_accuracy": 0.8123646860716863,
|
| 198 |
+
"eval_f1_macro": 0.708482661435726,
|
| 199 |
+
"eval_f1_micro": 0.8123646860716863,
|
| 200 |
+
"eval_loss": 0.9393090009689331,
|
| 201 |
+
"eval_precision_macro": 0.7317184546335789,
|
| 202 |
+
"eval_precision_micro": 0.8123646860716863,
|
| 203 |
+
"eval_recall_macro": 0.7488908271016358,
|
| 204 |
+
"eval_recall_micro": 0.8123646860716863,
|
| 205 |
+
"eval_runtime": 27.2362,
|
| 206 |
+
"eval_samples_per_second": 152.628,
|
| 207 |
+
"eval_steps_per_second": 19.092,
|
| 208 |
+
"step": 4500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.2141816415735793,
|
| 212 |
+
"grad_norm": 0.39278239011764526,
|
| 213 |
+
"learning_rate": 7.037435815032454e-05,
|
| 214 |
+
"loss": 0.4486,
|
| 215 |
+
"step": 5000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.2141816415735793,
|
| 219 |
+
"eval_accuracy": 0.7700264613904257,
|
| 220 |
+
"eval_f1_macro": 0.6920667410628023,
|
| 221 |
+
"eval_f1_micro": 0.7700264613904257,
|
| 222 |
+
"eval_loss": 1.3262685537338257,
|
| 223 |
+
"eval_precision_macro": 0.7077529941590818,
|
| 224 |
+
"eval_precision_micro": 0.7700264613904257,
|
| 225 |
+
"eval_recall_macro": 0.7242769813758809,
|
| 226 |
+
"eval_recall_micro": 0.7700264613904257,
|
| 227 |
+
"eval_runtime": 27.269,
|
| 228 |
+
"eval_samples_per_second": 152.444,
|
| 229 |
+
"eval_steps_per_second": 19.069,
|
| 230 |
+
"step": 5000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3355998057309373,
|
| 234 |
+
"grad_norm": 71.1628646850586,
|
| 235 |
+
"learning_rate": 6.74512640603739e-05,
|
| 236 |
+
"loss": 0.4811,
|
| 237 |
+
"step": 5500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.3355998057309373,
|
| 241 |
+
"eval_accuracy": 0.7813326918450806,
|
| 242 |
+
"eval_f1_macro": 0.6798745973269448,
|
| 243 |
+
"eval_f1_micro": 0.7813326918450806,
|
| 244 |
+
"eval_loss": 1.250918984413147,
|
| 245 |
+
"eval_precision_macro": 0.696314210159468,
|
| 246 |
+
"eval_precision_micro": 0.7813326918450806,
|
| 247 |
+
"eval_recall_macro": 0.7168696022753556,
|
| 248 |
+
"eval_recall_micro": 0.7813326918450806,
|
| 249 |
+
"eval_runtime": 27.283,
|
| 250 |
+
"eval_samples_per_second": 152.366,
|
| 251 |
+
"eval_steps_per_second": 19.059,
|
| 252 |
+
"step": 5500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.4570179698882952,
|
| 256 |
+
"grad_norm": 34.226558685302734,
|
| 257 |
+
"learning_rate": 6.42202308323677e-05,
|
| 258 |
+
"loss": 0.4389,
|
| 259 |
+
"step": 6000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.4570179698882952,
|
| 263 |
+
"eval_accuracy": 0.8395477507818138,
|
| 264 |
+
"eval_f1_macro": 0.7822529958429223,
|
| 265 |
+
"eval_f1_micro": 0.8395477507818138,
|
| 266 |
+
"eval_loss": 0.8688516616821289,
|
| 267 |
+
"eval_precision_macro": 0.7886529357301303,
|
| 268 |
+
"eval_precision_micro": 0.8395477507818138,
|
| 269 |
+
"eval_recall_macro": 0.8010892695635744,
|
| 270 |
+
"eval_recall_micro": 0.8395477507818138,
|
| 271 |
+
"eval_runtime": 27.2551,
|
| 272 |
+
"eval_samples_per_second": 152.522,
|
| 273 |
+
"eval_steps_per_second": 19.079,
|
| 274 |
+
"step": 6000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.5784361340456532,
|
| 278 |
+
"grad_norm": 10.712166786193848,
|
| 279 |
+
"learning_rate": 6.0717503121017445e-05,
|
| 280 |
+
"loss": 0.3433,
|
| 281 |
+
"step": 6500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.5784361340456532,
|
| 285 |
+
"eval_accuracy": 0.7988934327640125,
|
| 286 |
+
"eval_f1_macro": 0.7185328451214701,
|
| 287 |
+
"eval_f1_micro": 0.7988934327640125,
|
| 288 |
+
"eval_loss": 1.2528094053268433,
|
| 289 |
+
"eval_precision_macro": 0.762570014575197,
|
| 290 |
+
"eval_precision_micro": 0.7988934327640125,
|
| 291 |
+
"eval_recall_macro": 0.7402242917897641,
|
| 292 |
+
"eval_recall_micro": 0.7988934327640125,
|
| 293 |
+
"eval_runtime": 27.2805,
|
| 294 |
+
"eval_samples_per_second": 152.38,
|
| 295 |
+
"eval_steps_per_second": 19.061,
|
| 296 |
+
"step": 6500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6998542982030111,
|
| 300 |
+
"grad_norm": 3.9133920669555664,
|
| 301 |
+
"learning_rate": 5.69823733592655e-05,
|
| 302 |
+
"loss": 0.471,
|
| 303 |
+
"step": 7000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6998542982030111,
|
| 307 |
+
"eval_accuracy": 0.828241520327159,
|
| 308 |
+
"eval_f1_macro": 0.7419223686901416,
|
| 309 |
+
"eval_f1_micro": 0.828241520327159,
|
| 310 |
+
"eval_loss": 1.075687289237976,
|
| 311 |
+
"eval_precision_macro": 0.7752437424626774,
|
| 312 |
+
"eval_precision_micro": 0.828241520327159,
|
| 313 |
+
"eval_recall_macro": 0.7580751864014141,
|
| 314 |
+
"eval_recall_micro": 0.828241520327159,
|
| 315 |
+
"eval_runtime": 27.2851,
|
| 316 |
+
"eval_samples_per_second": 152.354,
|
| 317 |
+
"eval_steps_per_second": 19.058,
|
| 318 |
+
"step": 7000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.821272462360369,
|
| 322 |
+
"grad_norm": 0.013289747759699821,
|
| 323 |
+
"learning_rate": 5.305674098885817e-05,
|
| 324 |
+
"loss": 0.2998,
|
| 325 |
+
"step": 7500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.821272462360369,
|
| 329 |
+
"eval_accuracy": 0.8611979793120038,
|
| 330 |
+
"eval_f1_macro": 0.7904181392650506,
|
| 331 |
+
"eval_f1_micro": 0.8611979793120038,
|
| 332 |
+
"eval_loss": 0.8718775510787964,
|
| 333 |
+
"eval_precision_macro": 0.7956296769713385,
|
| 334 |
+
"eval_precision_micro": 0.8611979793120038,
|
| 335 |
+
"eval_recall_macro": 0.80418966707122,
|
| 336 |
+
"eval_recall_micro": 0.8611979793120038,
|
| 337 |
+
"eval_runtime": 27.2544,
|
| 338 |
+
"eval_samples_per_second": 152.526,
|
| 339 |
+
"eval_steps_per_second": 19.079,
|
| 340 |
+
"step": 7500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.942690626517727,
|
| 344 |
+
"grad_norm": 0.021947728469967842,
|
| 345 |
+
"learning_rate": 4.8984642446361996e-05,
|
| 346 |
+
"loss": 0.3576,
|
| 347 |
+
"step": 8000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.942690626517727,
|
| 351 |
+
"eval_accuracy": 0.8381044022131344,
|
| 352 |
+
"eval_f1_macro": 0.7345862755143372,
|
| 353 |
+
"eval_f1_micro": 0.8381044022131344,
|
| 354 |
+
"eval_loss": 1.0301835536956787,
|
| 355 |
+
"eval_precision_macro": 0.7639396507763108,
|
| 356 |
+
"eval_precision_micro": 0.8381044022131344,
|
| 357 |
+
"eval_recall_macro": 0.7583287896739785,
|
| 358 |
+
"eval_recall_micro": 0.8381044022131344,
|
| 359 |
+
"eval_runtime": 27.2522,
|
| 360 |
+
"eval_samples_per_second": 152.538,
|
| 361 |
+
"eval_steps_per_second": 19.081,
|
| 362 |
+
"step": 8000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.064108790675085,
|
| 366 |
+
"grad_norm": 0.008582094684243202,
|
| 367 |
+
"learning_rate": 4.481175717708393e-05,
|
| 368 |
+
"loss": 0.2684,
|
| 369 |
+
"step": 8500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.064108790675085,
|
| 373 |
+
"eval_accuracy": 0.8255953812845802,
|
| 374 |
+
"eval_f1_macro": 0.741469099618401,
|
| 375 |
+
"eval_f1_micro": 0.8255953812845802,
|
| 376 |
+
"eval_loss": 1.1655328273773193,
|
| 377 |
+
"eval_precision_macro": 0.7756252943895736,
|
| 378 |
+
"eval_precision_micro": 0.8255953812845802,
|
| 379 |
+
"eval_recall_macro": 0.7550220015299758,
|
| 380 |
+
"eval_recall_micro": 0.8255953812845802,
|
| 381 |
+
"eval_runtime": 27.2757,
|
| 382 |
+
"eval_samples_per_second": 152.407,
|
| 383 |
+
"eval_steps_per_second": 19.065,
|
| 384 |
+
"step": 8500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.1855269548324427,
|
| 388 |
+
"grad_norm": 0.6862893104553223,
|
| 389 |
+
"learning_rate": 4.058489521826674e-05,
|
| 390 |
+
"loss": 0.1725,
|
| 391 |
+
"step": 9000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.1855269548324427,
|
| 395 |
+
"eval_accuracy": 0.8275198460428194,
|
| 396 |
+
"eval_f1_macro": 0.764400269732795,
|
| 397 |
+
"eval_f1_micro": 0.8275198460428194,
|
| 398 |
+
"eval_loss": 1.2364674806594849,
|
| 399 |
+
"eval_precision_macro": 0.7823463486710002,
|
| 400 |
+
"eval_precision_micro": 0.8275198460428194,
|
| 401 |
+
"eval_recall_macro": 0.7824155097281223,
|
| 402 |
+
"eval_recall_micro": 0.8275198460428194,
|
| 403 |
+
"eval_runtime": 27.2782,
|
| 404 |
+
"eval_samples_per_second": 152.393,
|
| 405 |
+
"eval_steps_per_second": 19.063,
|
| 406 |
+
"step": 9000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.306945118989801,
|
| 410 |
+
"grad_norm": 0.025181420147418976,
|
| 411 |
+
"learning_rate": 3.6376797956022654e-05,
|
| 412 |
+
"loss": 0.2397,
|
| 413 |
+
"step": 9500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.306945118989801,
|
| 417 |
+
"eval_accuracy": 0.8604763050276641,
|
| 418 |
+
"eval_f1_macro": 0.7877572256817134,
|
| 419 |
+
"eval_f1_micro": 0.8604763050276641,
|
| 420 |
+
"eval_loss": 0.9292256832122803,
|
| 421 |
+
"eval_precision_macro": 0.7918673462927787,
|
| 422 |
+
"eval_precision_micro": 0.8604763050276641,
|
| 423 |
+
"eval_recall_macro": 0.8180582399792742,
|
| 424 |
+
"eval_recall_micro": 0.8604763050276641,
|
| 425 |
+
"eval_runtime": 27.2846,
|
| 426 |
+
"eval_samples_per_second": 152.357,
|
| 427 |
+
"eval_steps_per_second": 19.058,
|
| 428 |
+
"step": 9500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.4283632831471587,
|
| 432 |
+
"grad_norm": 0.018914269283413887,
|
| 433 |
+
"learning_rate": 3.218391627330709e-05,
|
| 434 |
+
"loss": 0.1292,
|
| 435 |
+
"step": 10000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.4283632831471587,
|
| 439 |
+
"eval_accuracy": 0.8400288669713736,
|
| 440 |
+
"eval_f1_macro": 0.7578353273109111,
|
| 441 |
+
"eval_f1_micro": 0.8400288669713736,
|
| 442 |
+
"eval_loss": 1.1471483707427979,
|
| 443 |
+
"eval_precision_macro": 0.7859915664713247,
|
| 444 |
+
"eval_precision_micro": 0.8400288669713736,
|
| 445 |
+
"eval_recall_macro": 0.7586324294579785,
|
| 446 |
+
"eval_recall_micro": 0.8400288669713736,
|
| 447 |
+
"eval_runtime": 27.283,
|
| 448 |
+
"eval_samples_per_second": 152.366,
|
| 449 |
+
"eval_steps_per_second": 19.059,
|
| 450 |
+
"step": 10000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.549781447304517,
|
| 454 |
+
"grad_norm": 0.0191049687564373,
|
| 455 |
+
"learning_rate": 2.8078712814824657e-05,
|
| 456 |
+
"loss": 0.1677,
|
| 457 |
+
"step": 10500
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.549781447304517,
|
| 461 |
+
"eval_accuracy": 0.8328121241279769,
|
| 462 |
+
"eval_f1_macro": 0.7690561159084898,
|
| 463 |
+
"eval_f1_micro": 0.8328121241279769,
|
| 464 |
+
"eval_loss": 1.0550189018249512,
|
| 465 |
+
"eval_precision_macro": 0.7884069469380799,
|
| 466 |
+
"eval_precision_micro": 0.8328121241279769,
|
| 467 |
+
"eval_recall_macro": 0.773349971413203,
|
| 468 |
+
"eval_recall_micro": 0.8328121241279769,
|
| 469 |
+
"eval_runtime": 27.2869,
|
| 470 |
+
"eval_samples_per_second": 152.344,
|
| 471 |
+
"eval_steps_per_second": 19.057,
|
| 472 |
+
"step": 10500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.6711996114618746,
|
| 476 |
+
"grad_norm": 0.3478395342826843,
|
| 477 |
+
"learning_rate": 2.410723838580481e-05,
|
| 478 |
+
"loss": 0.1714,
|
| 479 |
+
"step": 11000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.6711996114618746,
|
| 483 |
+
"eval_accuracy": 0.854462352658167,
|
| 484 |
+
"eval_f1_macro": 0.7910976498287203,
|
| 485 |
+
"eval_f1_micro": 0.854462352658167,
|
| 486 |
+
"eval_loss": 0.9365512728691101,
|
| 487 |
+
"eval_precision_macro": 0.8109094372488469,
|
| 488 |
+
"eval_precision_micro": 0.854462352658167,
|
| 489 |
+
"eval_recall_macro": 0.7994690071665942,
|
| 490 |
+
"eval_recall_micro": 0.854462352658167,
|
| 491 |
+
"eval_runtime": 27.2665,
|
| 492 |
+
"eval_samples_per_second": 152.458,
|
| 493 |
+
"eval_steps_per_second": 19.071,
|
| 494 |
+
"step": 11000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.7926177756192327,
|
| 498 |
+
"grad_norm": 0.018084919080138206,
|
| 499 |
+
"learning_rate": 2.0314043663760713e-05,
|
| 500 |
+
"loss": 0.1543,
|
| 501 |
+
"step": 11500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.7926177756192327,
|
| 505 |
+
"eval_accuracy": 0.8756314649987972,
|
| 506 |
+
"eval_f1_macro": 0.8158862362390574,
|
| 507 |
+
"eval_f1_micro": 0.8756314649987972,
|
| 508 |
+
"eval_loss": 0.9110000729560852,
|
| 509 |
+
"eval_precision_macro": 0.8343727376865201,
|
| 510 |
+
"eval_precision_micro": 0.8756314649987972,
|
| 511 |
+
"eval_recall_macro": 0.8210414008872133,
|
| 512 |
+
"eval_recall_micro": 0.8756314649987972,
|
| 513 |
+
"eval_runtime": 27.2652,
|
| 514 |
+
"eval_samples_per_second": 152.465,
|
| 515 |
+
"eval_steps_per_second": 19.072,
|
| 516 |
+
"step": 11500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.9140359397765905,
|
| 520 |
+
"grad_norm": 0.013514680787920952,
|
| 521 |
+
"learning_rate": 1.6741679443825673e-05,
|
| 522 |
+
"loss": 0.1027,
|
| 523 |
+
"step": 12000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.9140359397765905,
|
| 527 |
+
"eval_accuracy": 0.8655280250180418,
|
| 528 |
+
"eval_f1_macro": 0.814236769671234,
|
| 529 |
+
"eval_f1_micro": 0.8655280250180418,
|
| 530 |
+
"eval_loss": 1.0340354442596436,
|
| 531 |
+
"eval_precision_macro": 0.8211316713081322,
|
| 532 |
+
"eval_precision_micro": 0.8655280250180418,
|
| 533 |
+
"eval_recall_macro": 0.8190728220384627,
|
| 534 |
+
"eval_recall_micro": 0.8655280250180418,
|
| 535 |
+
"eval_runtime": 27.2801,
|
| 536 |
+
"eval_samples_per_second": 152.382,
|
| 537 |
+
"eval_steps_per_second": 19.062,
|
| 538 |
+
"step": 12000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.0354541039339487,
|
| 542 |
+
"grad_norm": 0.06883151084184647,
|
| 543 |
+
"learning_rate": 1.34302193181041e-05,
|
| 544 |
+
"loss": 0.1368,
|
| 545 |
+
"step": 12500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.0354541039339487,
|
| 549 |
+
"eval_accuracy": 0.8737070002405581,
|
| 550 |
+
"eval_f1_macro": 0.8142391346531119,
|
| 551 |
+
"eval_f1_micro": 0.8737070002405581,
|
| 552 |
+
"eval_loss": 0.8788183927536011,
|
| 553 |
+
"eval_precision_macro": 0.8186147346918103,
|
| 554 |
+
"eval_precision_micro": 0.8737070002405581,
|
| 555 |
+
"eval_recall_macro": 0.8331902702603373,
|
| 556 |
+
"eval_recall_micro": 0.8737070002405581,
|
| 557 |
+
"eval_runtime": 27.2538,
|
| 558 |
+
"eval_samples_per_second": 152.529,
|
| 559 |
+
"eval_steps_per_second": 19.08,
|
| 560 |
+
"step": 12500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.1568722680913064,
|
| 564 |
+
"grad_norm": 0.007450424134731293,
|
| 565 |
+
"learning_rate": 1.0416810143461263e-05,
|
| 566 |
+
"loss": 0.0501,
|
| 567 |
+
"step": 13000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.1568722680913064,
|
| 571 |
+
"eval_accuracy": 0.8866971373586722,
|
| 572 |
+
"eval_f1_macro": 0.8306324981784764,
|
| 573 |
+
"eval_f1_micro": 0.8866971373586722,
|
| 574 |
+
"eval_loss": 0.8202418088912964,
|
| 575 |
+
"eval_precision_macro": 0.8476975671689575,
|
| 576 |
+
"eval_precision_micro": 0.8866971373586722,
|
| 577 |
+
"eval_recall_macro": 0.8296071466526088,
|
| 578 |
+
"eval_recall_micro": 0.8866971373586722,
|
| 579 |
+
"eval_runtime": 27.2733,
|
| 580 |
+
"eval_samples_per_second": 152.42,
|
| 581 |
+
"eval_steps_per_second": 19.066,
|
| 582 |
+
"step": 13000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.2782904322486646,
|
| 586 |
+
"grad_norm": 0.006428878754377365,
|
| 587 |
+
"learning_rate": 7.73525534045391e-06,
|
| 588 |
+
"loss": 0.0556,
|
| 589 |
+
"step": 13500
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.2782904322486646,
|
| 593 |
+
"eval_accuracy": 0.8773153716622565,
|
| 594 |
+
"eval_f1_macro": 0.8187172181232656,
|
| 595 |
+
"eval_f1_micro": 0.8773153716622565,
|
| 596 |
+
"eval_loss": 0.9218270182609558,
|
| 597 |
+
"eval_precision_macro": 0.8355184291729084,
|
| 598 |
+
"eval_precision_micro": 0.8773153716622565,
|
| 599 |
+
"eval_recall_macro": 0.8247427107635721,
|
| 600 |
+
"eval_recall_micro": 0.8773153716622565,
|
| 601 |
+
"eval_runtime": 27.275,
|
| 602 |
+
"eval_samples_per_second": 152.411,
|
| 603 |
+
"eval_steps_per_second": 19.065,
|
| 604 |
+
"step": 13500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.3997085964060223,
|
| 608 |
+
"grad_norm": 0.0064325109124183655,
|
| 609 |
+
"learning_rate": 5.415635697816259e-06,
|
| 610 |
+
"loss": 0.0468,
|
| 611 |
+
"step": 14000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.3997085964060223,
|
| 615 |
+
"eval_accuracy": 0.8744286745248978,
|
| 616 |
+
"eval_f1_macro": 0.8190467137701445,
|
| 617 |
+
"eval_f1_micro": 0.8744286745248978,
|
| 618 |
+
"eval_loss": 0.8941731452941895,
|
| 619 |
+
"eval_precision_macro": 0.817939746546661,
|
| 620 |
+
"eval_precision_micro": 0.8744286745248978,
|
| 621 |
+
"eval_recall_macro": 0.8276624213993112,
|
| 622 |
+
"eval_recall_micro": 0.8744286745248978,
|
| 623 |
+
"eval_runtime": 27.261,
|
| 624 |
+
"eval_samples_per_second": 152.489,
|
| 625 |
+
"eval_steps_per_second": 19.075,
|
| 626 |
+
"step": 14000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.52112676056338,
|
| 630 |
+
"grad_norm": 0.004375011660158634,
|
| 631 |
+
"learning_rate": 3.4839719361897852e-06,
|
| 632 |
+
"loss": 0.0665,
|
| 633 |
+
"step": 14500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.52112676056338,
|
| 637 |
+
"eval_accuracy": 0.8915082992542699,
|
| 638 |
+
"eval_f1_macro": 0.8339685375452801,
|
| 639 |
+
"eval_f1_micro": 0.8915082992542699,
|
| 640 |
+
"eval_loss": 0.7931458950042725,
|
| 641 |
+
"eval_precision_macro": 0.8462712956558062,
|
| 642 |
+
"eval_precision_micro": 0.8915082992542699,
|
| 643 |
+
"eval_recall_macro": 0.8342943619225055,
|
| 644 |
+
"eval_recall_micro": 0.8915082992542699,
|
| 645 |
+
"eval_runtime": 27.2445,
|
| 646 |
+
"eval_samples_per_second": 152.581,
|
| 647 |
+
"eval_steps_per_second": 19.086,
|
| 648 |
+
"step": 14500
|
| 649 |
+
}
|
| 650 |
+
],
|
| 651 |
+
"logging_steps": 500,
|
| 652 |
+
"max_steps": 16472,
|
| 653 |
+
"num_input_tokens_seen": 0,
|
| 654 |
+
"num_train_epochs": 4,
|
| 655 |
+
"save_steps": 500,
|
| 656 |
+
"stateful_callbacks": {
|
| 657 |
+
"TrainerControl": {
|
| 658 |
+
"args": {
|
| 659 |
+
"should_epoch_stop": false,
|
| 660 |
+
"should_evaluate": false,
|
| 661 |
+
"should_log": false,
|
| 662 |
+
"should_save": true,
|
| 663 |
+
"should_training_stop": false
|
| 664 |
+
},
|
| 665 |
+
"attributes": {}
|
| 666 |
+
}
|
| 667 |
+
},
|
| 668 |
+
"total_flos": 3.0626068433642496e+16,
|
| 669 |
+
"train_batch_size": 8,
|
| 670 |
+
"trial_name": null,
|
| 671 |
+
"trial_params": null
|
| 672 |
+
}
|
checkpoint-14500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e92bf6666684fb5efaf90782737fab17e97c478b9d9b32d6e2b07dd4345ae13
|
| 3 |
+
size 5713
|
checkpoint-14500/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16472/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CustomAraBERTClassifier"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "LABEL_0",
|
| 12 |
+
"1": "LABEL_1",
|
| 13 |
+
"2": "LABEL_2",
|
| 14 |
+
"3": "LABEL_3",
|
| 15 |
+
"4": "LABEL_4",
|
| 16 |
+
"5": "LABEL_5",
|
| 17 |
+
"6": "LABEL_6",
|
| 18 |
+
"7": "LABEL_7",
|
| 19 |
+
"8": "LABEL_8",
|
| 20 |
+
"9": "LABEL_9",
|
| 21 |
+
"10": "LABEL_10",
|
| 22 |
+
"11": "LABEL_11",
|
| 23 |
+
"12": "LABEL_12",
|
| 24 |
+
"13": "LABEL_13",
|
| 25 |
+
"14": "LABEL_14",
|
| 26 |
+
"15": "LABEL_15",
|
| 27 |
+
"16": "LABEL_16",
|
| 28 |
+
"17": "LABEL_17",
|
| 29 |
+
"18": "LABEL_18",
|
| 30 |
+
"19": "LABEL_19",
|
| 31 |
+
"20": "LABEL_20"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 3072,
|
| 35 |
+
"label2id": {
|
| 36 |
+
"LABEL_0": 0,
|
| 37 |
+
"LABEL_1": 1,
|
| 38 |
+
"LABEL_10": 10,
|
| 39 |
+
"LABEL_11": 11,
|
| 40 |
+
"LABEL_12": 12,
|
| 41 |
+
"LABEL_13": 13,
|
| 42 |
+
"LABEL_14": 14,
|
| 43 |
+
"LABEL_15": 15,
|
| 44 |
+
"LABEL_16": 16,
|
| 45 |
+
"LABEL_17": 17,
|
| 46 |
+
"LABEL_18": 18,
|
| 47 |
+
"LABEL_19": 19,
|
| 48 |
+
"LABEL_2": 2,
|
| 49 |
+
"LABEL_20": 20,
|
| 50 |
+
"LABEL_3": 3,
|
| 51 |
+
"LABEL_4": 4,
|
| 52 |
+
"LABEL_5": 5,
|
| 53 |
+
"LABEL_6": 6,
|
| 54 |
+
"LABEL_7": 7,
|
| 55 |
+
"LABEL_8": 8,
|
| 56 |
+
"LABEL_9": 9
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-12,
|
| 59 |
+
"max_position_embeddings": 512,
|
| 60 |
+
"model_type": "bert",
|
| 61 |
+
"num_attention_heads": 12,
|
| 62 |
+
"num_hidden_layers": 12,
|
| 63 |
+
"pad_token_id": 0,
|
| 64 |
+
"position_embedding_type": "absolute",
|
| 65 |
+
"torch_dtype": "float32",
|
| 66 |
+
"transformers_version": "4.53.3",
|
| 67 |
+
"type_vocab_size": 2,
|
| 68 |
+
"use_cache": true,
|
| 69 |
+
"vocab_size": 64000
|
| 70 |
+
}
|
checkpoint-16472/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2398d1a0653eea1591d4b1c753ca4b7c279d8b7a220e5407fe1a4c3d9058d94
|
| 3 |
+
size 542010628
|
checkpoint-16472/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8487ebfbea12ea091925fa2f3bc066898092ca1f01fb17fc5f84796dcc6634c
|
| 3 |
+
size 1084144011
|
checkpoint-16472/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0d2ab663d81d3221a8e31be1f7659d5f23c2b1d8964f3d4bf7cceef63104150
|
| 3 |
+
size 14645
|
checkpoint-16472/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1607e7c183120ca17dc96e16ddeedbe047d56885fcb4541f65e20e85d138124f
|
| 3 |
+
size 1383
|
checkpoint-16472/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b3d7f8e7d240acd0b69140807523f5f3689ad5dc47bdbdc66da735019a3419b
|
| 3 |
+
size 1465
|
checkpoint-16472/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-16472/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-16472/tokenizer_config.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "+ا",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": true,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "+ك",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": true,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "ب+",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": true,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "+هم",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": true,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "+ات",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": true,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "+ي",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": true,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "ل+",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": true,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "+هما",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": true,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "+نا",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": true,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "+ن",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": true,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "+ها",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": true,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "+كما",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": true,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "+ة",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": true,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "ف+",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": true,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "+كم",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": true,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "+كن",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": true,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "+ت",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": true,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[بريد]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": true,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[مستخدم]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": true,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "لل+",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": true,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "ال+",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": true,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[رابط]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": true,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "س+",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": true,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "+ان",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": true,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "+وا",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": true,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "+ه",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": true,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "+ون",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": true,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "+هن",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": true,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": true,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "+ين",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": true,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": true,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "��+",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": true,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": true,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "ك+",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": true,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": true,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[UNK]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[CLS]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[SEP]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[MASK]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"clean_up_tokenization_spaces": false,
|
| 293 |
+
"cls_token": "[CLS]",
|
| 294 |
+
"do_basic_tokenize": true,
|
| 295 |
+
"do_lower_case": false,
|
| 296 |
+
"extra_special_tokens": {},
|
| 297 |
+
"mask_token": "[MASK]",
|
| 298 |
+
"max_len": 512,
|
| 299 |
+
"model_max_length": 512,
|
| 300 |
+
"never_split": [
|
| 301 |
+
"+ك",
|
| 302 |
+
"+كما",
|
| 303 |
+
"ك+",
|
| 304 |
+
"+وا",
|
| 305 |
+
"+ين",
|
| 306 |
+
"و+",
|
| 307 |
+
"+كن",
|
| 308 |
+
"+ان",
|
| 309 |
+
"+هم",
|
| 310 |
+
"+ة",
|
| 311 |
+
"[بريد]",
|
| 312 |
+
"لل+",
|
| 313 |
+
"+ي",
|
| 314 |
+
"+ت",
|
| 315 |
+
"+ن",
|
| 316 |
+
"س+",
|
| 317 |
+
"ل+",
|
| 318 |
+
"[مستخدم]",
|
| 319 |
+
"+كم",
|
| 320 |
+
"+ا",
|
| 321 |
+
"ب+",
|
| 322 |
+
"ف+",
|
| 323 |
+
"+نا",
|
| 324 |
+
"+ها",
|
| 325 |
+
"+ون",
|
| 326 |
+
"+هما",
|
| 327 |
+
"ال+",
|
| 328 |
+
"+ه",
|
| 329 |
+
"+هن",
|
| 330 |
+
"+ات",
|
| 331 |
+
"[رابط]"
|
| 332 |
+
],
|
| 333 |
+
"pad_token": "[PAD]",
|
| 334 |
+
"sep_token": "[SEP]",
|
| 335 |
+
"strip_accents": null,
|
| 336 |
+
"tokenize_chinese_chars": true,
|
| 337 |
+
"tokenizer_class": "BertTokenizer",
|
| 338 |
+
"unk_token": "[UNK]"
|
| 339 |
+
}
|
checkpoint-16472/trainer_state.json
ADDED
|
@@ -0,0 +1,738 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 14500,
|
| 3 |
+
"best_metric": 0.8339685375452801,
|
| 4 |
+
"best_model_checkpoint": "./arabert_author_model/checkpoint-14500",
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 16472,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.12141816415735794,
|
| 14 |
+
"grad_norm": 29.529987335205078,
|
| 15 |
+
"learning_rate": 2.393203883495146e-05,
|
| 16 |
+
"loss": 2.8696,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12141816415735794,
|
| 21 |
+
"eval_accuracy": 0.3425547269665624,
|
| 22 |
+
"eval_f1_macro": 0.25445032746487084,
|
| 23 |
+
"eval_f1_micro": 0.3425547269665624,
|
| 24 |
+
"eval_loss": 2.5629944801330566,
|
| 25 |
+
"eval_precision_macro": 0.3403621440266495,
|
| 26 |
+
"eval_precision_micro": 0.3425547269665624,
|
| 27 |
+
"eval_recall_macro": 0.3478089407512695,
|
| 28 |
+
"eval_recall_micro": 0.3425547269665624,
|
| 29 |
+
"eval_runtime": 27.2244,
|
| 30 |
+
"eval_samples_per_second": 152.694,
|
| 31 |
+
"eval_steps_per_second": 19.101,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.24283632831471588,
|
| 36 |
+
"grad_norm": 9.098995208740234,
|
| 37 |
+
"learning_rate": 4.8155339805825245e-05,
|
| 38 |
+
"loss": 1.9602,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.24283632831471588,
|
| 43 |
+
"eval_accuracy": 0.6454173682944431,
|
| 44 |
+
"eval_f1_macro": 0.5286934521513375,
|
| 45 |
+
"eval_f1_micro": 0.6454173682944431,
|
| 46 |
+
"eval_loss": 1.4127496480941772,
|
| 47 |
+
"eval_precision_macro": 0.5385051007277866,
|
| 48 |
+
"eval_precision_micro": 0.6454173682944431,
|
| 49 |
+
"eval_recall_macro": 0.5857769176935503,
|
| 50 |
+
"eval_recall_micro": 0.6454173682944431,
|
| 51 |
+
"eval_runtime": 27.2734,
|
| 52 |
+
"eval_samples_per_second": 152.42,
|
| 53 |
+
"eval_steps_per_second": 19.066,
|
| 54 |
+
"step": 1000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.3642544924720738,
|
| 58 |
+
"grad_norm": 12.638616561889648,
|
| 59 |
+
"learning_rate": 7.242718446601942e-05,
|
| 60 |
+
"loss": 1.3183,
|
| 61 |
+
"step": 1500
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.3642544924720738,
|
| 65 |
+
"eval_accuracy": 0.65215299494828,
|
| 66 |
+
"eval_f1_macro": 0.5540919349082173,
|
| 67 |
+
"eval_f1_micro": 0.65215299494828,
|
| 68 |
+
"eval_loss": 1.239192247390747,
|
| 69 |
+
"eval_precision_macro": 0.6120898590926472,
|
| 70 |
+
"eval_precision_micro": 0.65215299494828,
|
| 71 |
+
"eval_recall_macro": 0.6092527387773333,
|
| 72 |
+
"eval_recall_micro": 0.65215299494828,
|
| 73 |
+
"eval_runtime": 27.2704,
|
| 74 |
+
"eval_samples_per_second": 152.437,
|
| 75 |
+
"eval_steps_per_second": 19.068,
|
| 76 |
+
"step": 1500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.48567265662943176,
|
| 80 |
+
"grad_norm": 30.778980255126953,
|
| 81 |
+
"learning_rate": 7.989375134121083e-05,
|
| 82 |
+
"loss": 1.0436,
|
| 83 |
+
"step": 2000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.48567265662943176,
|
| 87 |
+
"eval_accuracy": 0.7310560500360838,
|
| 88 |
+
"eval_f1_macro": 0.6287971185064818,
|
| 89 |
+
"eval_f1_micro": 0.7310560500360838,
|
| 90 |
+
"eval_loss": 0.9975479245185852,
|
| 91 |
+
"eval_precision_macro": 0.6542445683571894,
|
| 92 |
+
"eval_precision_micro": 0.7310560500360838,
|
| 93 |
+
"eval_recall_macro": 0.6428366638693614,
|
| 94 |
+
"eval_recall_micro": 0.7310560500360838,
|
| 95 |
+
"eval_runtime": 27.2787,
|
| 96 |
+
"eval_samples_per_second": 152.39,
|
| 97 |
+
"eval_steps_per_second": 19.062,
|
| 98 |
+
"step": 2000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.6070908207867897,
|
| 102 |
+
"grad_norm": 19.659687042236328,
|
| 103 |
+
"learning_rate": 7.936184577251333e-05,
|
| 104 |
+
"loss": 0.8937,
|
| 105 |
+
"step": 2500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.6070908207867897,
|
| 109 |
+
"eval_accuracy": 0.6634592254029348,
|
| 110 |
+
"eval_f1_macro": 0.5881193362986468,
|
| 111 |
+
"eval_f1_micro": 0.6634592254029348,
|
| 112 |
+
"eval_loss": 1.2966861724853516,
|
| 113 |
+
"eval_precision_macro": 0.6346376229831586,
|
| 114 |
+
"eval_precision_micro": 0.6634592254029348,
|
| 115 |
+
"eval_recall_macro": 0.6216328795839745,
|
| 116 |
+
"eval_recall_micro": 0.6634592254029348,
|
| 117 |
+
"eval_runtime": 27.2772,
|
| 118 |
+
"eval_samples_per_second": 152.398,
|
| 119 |
+
"eval_steps_per_second": 19.064,
|
| 120 |
+
"step": 2500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.7285089849441476,
|
| 124 |
+
"grad_norm": 52.43323516845703,
|
| 125 |
+
"learning_rate": 7.838839212672895e-05,
|
| 126 |
+
"loss": 0.7939,
|
| 127 |
+
"step": 3000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.7285089849441476,
|
| 131 |
+
"eval_accuracy": 0.7363483281212413,
|
| 132 |
+
"eval_f1_macro": 0.6401725490543624,
|
| 133 |
+
"eval_f1_micro": 0.7363483281212413,
|
| 134 |
+
"eval_loss": 1.0666863918304443,
|
| 135 |
+
"eval_precision_macro": 0.6944496519079535,
|
| 136 |
+
"eval_precision_micro": 0.7363483281212413,
|
| 137 |
+
"eval_recall_macro": 0.6587226907421574,
|
| 138 |
+
"eval_recall_micro": 0.7363483281212413,
|
| 139 |
+
"eval_runtime": 27.2761,
|
| 140 |
+
"eval_samples_per_second": 152.404,
|
| 141 |
+
"eval_steps_per_second": 19.064,
|
| 142 |
+
"step": 3000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8499271491015056,
|
| 146 |
+
"grad_norm": 11.124955177307129,
|
| 147 |
+
"learning_rate": 7.698753853285741e-05,
|
| 148 |
+
"loss": 0.6947,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8499271491015056,
|
| 153 |
+
"eval_accuracy": 0.797931200384893,
|
| 154 |
+
"eval_f1_macro": 0.7157099044978049,
|
| 155 |
+
"eval_f1_micro": 0.797931200384893,
|
| 156 |
+
"eval_loss": 0.8941665291786194,
|
| 157 |
+
"eval_precision_macro": 0.7316892204440334,
|
| 158 |
+
"eval_precision_micro": 0.797931200384893,
|
| 159 |
+
"eval_recall_macro": 0.7416061573455679,
|
| 160 |
+
"eval_recall_micro": 0.797931200384893,
|
| 161 |
+
"eval_runtime": 27.2726,
|
| 162 |
+
"eval_samples_per_second": 152.424,
|
| 163 |
+
"eval_steps_per_second": 19.067,
|
| 164 |
+
"step": 3500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9713453132588635,
|
| 168 |
+
"grad_norm": 16.576419830322266,
|
| 169 |
+
"learning_rate": 7.516938992131817e-05,
|
| 170 |
+
"loss": 0.5841,
|
| 171 |
+
"step": 4000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.9713453132588635,
|
| 175 |
+
"eval_accuracy": 0.769545345200866,
|
| 176 |
+
"eval_f1_macro": 0.7080092768138256,
|
| 177 |
+
"eval_f1_micro": 0.769545345200866,
|
| 178 |
+
"eval_loss": 1.0479093790054321,
|
| 179 |
+
"eval_precision_macro": 0.7402406037514909,
|
| 180 |
+
"eval_precision_micro": 0.769545345200866,
|
| 181 |
+
"eval_recall_macro": 0.7084186724135678,
|
| 182 |
+
"eval_recall_micro": 0.769545345200866,
|
| 183 |
+
"eval_runtime": 27.2399,
|
| 184 |
+
"eval_samples_per_second": 152.607,
|
| 185 |
+
"eval_steps_per_second": 19.09,
|
| 186 |
+
"step": 4000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.0927634774162214,
|
| 190 |
+
"grad_norm": 94.69003295898438,
|
| 191 |
+
"learning_rate": 7.295672280620509e-05,
|
| 192 |
+
"loss": 0.5537,
|
| 193 |
+
"step": 4500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.0927634774162214,
|
| 197 |
+
"eval_accuracy": 0.8123646860716863,
|
| 198 |
+
"eval_f1_macro": 0.708482661435726,
|
| 199 |
+
"eval_f1_micro": 0.8123646860716863,
|
| 200 |
+
"eval_loss": 0.9393090009689331,
|
| 201 |
+
"eval_precision_macro": 0.7317184546335789,
|
| 202 |
+
"eval_precision_micro": 0.8123646860716863,
|
| 203 |
+
"eval_recall_macro": 0.7488908271016358,
|
| 204 |
+
"eval_recall_micro": 0.8123646860716863,
|
| 205 |
+
"eval_runtime": 27.2362,
|
| 206 |
+
"eval_samples_per_second": 152.628,
|
| 207 |
+
"eval_steps_per_second": 19.092,
|
| 208 |
+
"step": 4500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.2141816415735793,
|
| 212 |
+
"grad_norm": 0.39278239011764526,
|
| 213 |
+
"learning_rate": 7.037435815032454e-05,
|
| 214 |
+
"loss": 0.4486,
|
| 215 |
+
"step": 5000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.2141816415735793,
|
| 219 |
+
"eval_accuracy": 0.7700264613904257,
|
| 220 |
+
"eval_f1_macro": 0.6920667410628023,
|
| 221 |
+
"eval_f1_micro": 0.7700264613904257,
|
| 222 |
+
"eval_loss": 1.3262685537338257,
|
| 223 |
+
"eval_precision_macro": 0.7077529941590818,
|
| 224 |
+
"eval_precision_micro": 0.7700264613904257,
|
| 225 |
+
"eval_recall_macro": 0.7242769813758809,
|
| 226 |
+
"eval_recall_micro": 0.7700264613904257,
|
| 227 |
+
"eval_runtime": 27.269,
|
| 228 |
+
"eval_samples_per_second": 152.444,
|
| 229 |
+
"eval_steps_per_second": 19.069,
|
| 230 |
+
"step": 5000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3355998057309373,
|
| 234 |
+
"grad_norm": 71.1628646850586,
|
| 235 |
+
"learning_rate": 6.74512640603739e-05,
|
| 236 |
+
"loss": 0.4811,
|
| 237 |
+
"step": 5500
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.3355998057309373,
|
| 241 |
+
"eval_accuracy": 0.7813326918450806,
|
| 242 |
+
"eval_f1_macro": 0.6798745973269448,
|
| 243 |
+
"eval_f1_micro": 0.7813326918450806,
|
| 244 |
+
"eval_loss": 1.250918984413147,
|
| 245 |
+
"eval_precision_macro": 0.696314210159468,
|
| 246 |
+
"eval_precision_micro": 0.7813326918450806,
|
| 247 |
+
"eval_recall_macro": 0.7168696022753556,
|
| 248 |
+
"eval_recall_micro": 0.7813326918450806,
|
| 249 |
+
"eval_runtime": 27.283,
|
| 250 |
+
"eval_samples_per_second": 152.366,
|
| 251 |
+
"eval_steps_per_second": 19.059,
|
| 252 |
+
"step": 5500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.4570179698882952,
|
| 256 |
+
"grad_norm": 34.226558685302734,
|
| 257 |
+
"learning_rate": 6.42202308323677e-05,
|
| 258 |
+
"loss": 0.4389,
|
| 259 |
+
"step": 6000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.4570179698882952,
|
| 263 |
+
"eval_accuracy": 0.8395477507818138,
|
| 264 |
+
"eval_f1_macro": 0.7822529958429223,
|
| 265 |
+
"eval_f1_micro": 0.8395477507818138,
|
| 266 |
+
"eval_loss": 0.8688516616821289,
|
| 267 |
+
"eval_precision_macro": 0.7886529357301303,
|
| 268 |
+
"eval_precision_micro": 0.8395477507818138,
|
| 269 |
+
"eval_recall_macro": 0.8010892695635744,
|
| 270 |
+
"eval_recall_micro": 0.8395477507818138,
|
| 271 |
+
"eval_runtime": 27.2551,
|
| 272 |
+
"eval_samples_per_second": 152.522,
|
| 273 |
+
"eval_steps_per_second": 19.079,
|
| 274 |
+
"step": 6000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.5784361340456532,
|
| 278 |
+
"grad_norm": 10.712166786193848,
|
| 279 |
+
"learning_rate": 6.0717503121017445e-05,
|
| 280 |
+
"loss": 0.3433,
|
| 281 |
+
"step": 6500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.5784361340456532,
|
| 285 |
+
"eval_accuracy": 0.7988934327640125,
|
| 286 |
+
"eval_f1_macro": 0.7185328451214701,
|
| 287 |
+
"eval_f1_micro": 0.7988934327640125,
|
| 288 |
+
"eval_loss": 1.2528094053268433,
|
| 289 |
+
"eval_precision_macro": 0.762570014575197,
|
| 290 |
+
"eval_precision_micro": 0.7988934327640125,
|
| 291 |
+
"eval_recall_macro": 0.7402242917897641,
|
| 292 |
+
"eval_recall_micro": 0.7988934327640125,
|
| 293 |
+
"eval_runtime": 27.2805,
|
| 294 |
+
"eval_samples_per_second": 152.38,
|
| 295 |
+
"eval_steps_per_second": 19.061,
|
| 296 |
+
"step": 6500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6998542982030111,
|
| 300 |
+
"grad_norm": 3.9133920669555664,
|
| 301 |
+
"learning_rate": 5.69823733592655e-05,
|
| 302 |
+
"loss": 0.471,
|
| 303 |
+
"step": 7000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6998542982030111,
|
| 307 |
+
"eval_accuracy": 0.828241520327159,
|
| 308 |
+
"eval_f1_macro": 0.7419223686901416,
|
| 309 |
+
"eval_f1_micro": 0.828241520327159,
|
| 310 |
+
"eval_loss": 1.075687289237976,
|
| 311 |
+
"eval_precision_macro": 0.7752437424626774,
|
| 312 |
+
"eval_precision_micro": 0.828241520327159,
|
| 313 |
+
"eval_recall_macro": 0.7580751864014141,
|
| 314 |
+
"eval_recall_micro": 0.828241520327159,
|
| 315 |
+
"eval_runtime": 27.2851,
|
| 316 |
+
"eval_samples_per_second": 152.354,
|
| 317 |
+
"eval_steps_per_second": 19.058,
|
| 318 |
+
"step": 7000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.821272462360369,
|
| 322 |
+
"grad_norm": 0.013289747759699821,
|
| 323 |
+
"learning_rate": 5.305674098885817e-05,
|
| 324 |
+
"loss": 0.2998,
|
| 325 |
+
"step": 7500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.821272462360369,
|
| 329 |
+
"eval_accuracy": 0.8611979793120038,
|
| 330 |
+
"eval_f1_macro": 0.7904181392650506,
|
| 331 |
+
"eval_f1_micro": 0.8611979793120038,
|
| 332 |
+
"eval_loss": 0.8718775510787964,
|
| 333 |
+
"eval_precision_macro": 0.7956296769713385,
|
| 334 |
+
"eval_precision_micro": 0.8611979793120038,
|
| 335 |
+
"eval_recall_macro": 0.80418966707122,
|
| 336 |
+
"eval_recall_micro": 0.8611979793120038,
|
| 337 |
+
"eval_runtime": 27.2544,
|
| 338 |
+
"eval_samples_per_second": 152.526,
|
| 339 |
+
"eval_steps_per_second": 19.079,
|
| 340 |
+
"step": 7500
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.942690626517727,
|
| 344 |
+
"grad_norm": 0.021947728469967842,
|
| 345 |
+
"learning_rate": 4.8984642446361996e-05,
|
| 346 |
+
"loss": 0.3576,
|
| 347 |
+
"step": 8000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.942690626517727,
|
| 351 |
+
"eval_accuracy": 0.8381044022131344,
|
| 352 |
+
"eval_f1_macro": 0.7345862755143372,
|
| 353 |
+
"eval_f1_micro": 0.8381044022131344,
|
| 354 |
+
"eval_loss": 1.0301835536956787,
|
| 355 |
+
"eval_precision_macro": 0.7639396507763108,
|
| 356 |
+
"eval_precision_micro": 0.8381044022131344,
|
| 357 |
+
"eval_recall_macro": 0.7583287896739785,
|
| 358 |
+
"eval_recall_micro": 0.8381044022131344,
|
| 359 |
+
"eval_runtime": 27.2522,
|
| 360 |
+
"eval_samples_per_second": 152.538,
|
| 361 |
+
"eval_steps_per_second": 19.081,
|
| 362 |
+
"step": 8000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.064108790675085,
|
| 366 |
+
"grad_norm": 0.008582094684243202,
|
| 367 |
+
"learning_rate": 4.481175717708393e-05,
|
| 368 |
+
"loss": 0.2684,
|
| 369 |
+
"step": 8500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.064108790675085,
|
| 373 |
+
"eval_accuracy": 0.8255953812845802,
|
| 374 |
+
"eval_f1_macro": 0.741469099618401,
|
| 375 |
+
"eval_f1_micro": 0.8255953812845802,
|
| 376 |
+
"eval_loss": 1.1655328273773193,
|
| 377 |
+
"eval_precision_macro": 0.7756252943895736,
|
| 378 |
+
"eval_precision_micro": 0.8255953812845802,
|
| 379 |
+
"eval_recall_macro": 0.7550220015299758,
|
| 380 |
+
"eval_recall_micro": 0.8255953812845802,
|
| 381 |
+
"eval_runtime": 27.2757,
|
| 382 |
+
"eval_samples_per_second": 152.407,
|
| 383 |
+
"eval_steps_per_second": 19.065,
|
| 384 |
+
"step": 8500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.1855269548324427,
|
| 388 |
+
"grad_norm": 0.6862893104553223,
|
| 389 |
+
"learning_rate": 4.058489521826674e-05,
|
| 390 |
+
"loss": 0.1725,
|
| 391 |
+
"step": 9000
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.1855269548324427,
|
| 395 |
+
"eval_accuracy": 0.8275198460428194,
|
| 396 |
+
"eval_f1_macro": 0.764400269732795,
|
| 397 |
+
"eval_f1_micro": 0.8275198460428194,
|
| 398 |
+
"eval_loss": 1.2364674806594849,
|
| 399 |
+
"eval_precision_macro": 0.7823463486710002,
|
| 400 |
+
"eval_precision_micro": 0.8275198460428194,
|
| 401 |
+
"eval_recall_macro": 0.7824155097281223,
|
| 402 |
+
"eval_recall_micro": 0.8275198460428194,
|
| 403 |
+
"eval_runtime": 27.2782,
|
| 404 |
+
"eval_samples_per_second": 152.393,
|
| 405 |
+
"eval_steps_per_second": 19.063,
|
| 406 |
+
"step": 9000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.306945118989801,
|
| 410 |
+
"grad_norm": 0.025181420147418976,
|
| 411 |
+
"learning_rate": 3.6376797956022654e-05,
|
| 412 |
+
"loss": 0.2397,
|
| 413 |
+
"step": 9500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.306945118989801,
|
| 417 |
+
"eval_accuracy": 0.8604763050276641,
|
| 418 |
+
"eval_f1_macro": 0.7877572256817134,
|
| 419 |
+
"eval_f1_micro": 0.8604763050276641,
|
| 420 |
+
"eval_loss": 0.9292256832122803,
|
| 421 |
+
"eval_precision_macro": 0.7918673462927787,
|
| 422 |
+
"eval_precision_micro": 0.8604763050276641,
|
| 423 |
+
"eval_recall_macro": 0.8180582399792742,
|
| 424 |
+
"eval_recall_micro": 0.8604763050276641,
|
| 425 |
+
"eval_runtime": 27.2846,
|
| 426 |
+
"eval_samples_per_second": 152.357,
|
| 427 |
+
"eval_steps_per_second": 19.058,
|
| 428 |
+
"step": 9500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.4283632831471587,
|
| 432 |
+
"grad_norm": 0.018914269283413887,
|
| 433 |
+
"learning_rate": 3.218391627330709e-05,
|
| 434 |
+
"loss": 0.1292,
|
| 435 |
+
"step": 10000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.4283632831471587,
|
| 439 |
+
"eval_accuracy": 0.8400288669713736,
|
| 440 |
+
"eval_f1_macro": 0.7578353273109111,
|
| 441 |
+
"eval_f1_micro": 0.8400288669713736,
|
| 442 |
+
"eval_loss": 1.1471483707427979,
|
| 443 |
+
"eval_precision_macro": 0.7859915664713247,
|
| 444 |
+
"eval_precision_micro": 0.8400288669713736,
|
| 445 |
+
"eval_recall_macro": 0.7586324294579785,
|
| 446 |
+
"eval_recall_micro": 0.8400288669713736,
|
| 447 |
+
"eval_runtime": 27.283,
|
| 448 |
+
"eval_samples_per_second": 152.366,
|
| 449 |
+
"eval_steps_per_second": 19.059,
|
| 450 |
+
"step": 10000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.549781447304517,
|
| 454 |
+
"grad_norm": 0.0191049687564373,
|
| 455 |
+
"learning_rate": 2.8078712814824657e-05,
|
| 456 |
+
"loss": 0.1677,
|
| 457 |
+
"step": 10500
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.549781447304517,
|
| 461 |
+
"eval_accuracy": 0.8328121241279769,
|
| 462 |
+
"eval_f1_macro": 0.7690561159084898,
|
| 463 |
+
"eval_f1_micro": 0.8328121241279769,
|
| 464 |
+
"eval_loss": 1.0550189018249512,
|
| 465 |
+
"eval_precision_macro": 0.7884069469380799,
|
| 466 |
+
"eval_precision_micro": 0.8328121241279769,
|
| 467 |
+
"eval_recall_macro": 0.773349971413203,
|
| 468 |
+
"eval_recall_micro": 0.8328121241279769,
|
| 469 |
+
"eval_runtime": 27.2869,
|
| 470 |
+
"eval_samples_per_second": 152.344,
|
| 471 |
+
"eval_steps_per_second": 19.057,
|
| 472 |
+
"step": 10500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.6711996114618746,
|
| 476 |
+
"grad_norm": 0.3478395342826843,
|
| 477 |
+
"learning_rate": 2.410723838580481e-05,
|
| 478 |
+
"loss": 0.1714,
|
| 479 |
+
"step": 11000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.6711996114618746,
|
| 483 |
+
"eval_accuracy": 0.854462352658167,
|
| 484 |
+
"eval_f1_macro": 0.7910976498287203,
|
| 485 |
+
"eval_f1_micro": 0.854462352658167,
|
| 486 |
+
"eval_loss": 0.9365512728691101,
|
| 487 |
+
"eval_precision_macro": 0.8109094372488469,
|
| 488 |
+
"eval_precision_micro": 0.854462352658167,
|
| 489 |
+
"eval_recall_macro": 0.7994690071665942,
|
| 490 |
+
"eval_recall_micro": 0.854462352658167,
|
| 491 |
+
"eval_runtime": 27.2665,
|
| 492 |
+
"eval_samples_per_second": 152.458,
|
| 493 |
+
"eval_steps_per_second": 19.071,
|
| 494 |
+
"step": 11000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.7926177756192327,
|
| 498 |
+
"grad_norm": 0.018084919080138206,
|
| 499 |
+
"learning_rate": 2.0314043663760713e-05,
|
| 500 |
+
"loss": 0.1543,
|
| 501 |
+
"step": 11500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.7926177756192327,
|
| 505 |
+
"eval_accuracy": 0.8756314649987972,
|
| 506 |
+
"eval_f1_macro": 0.8158862362390574,
|
| 507 |
+
"eval_f1_micro": 0.8756314649987972,
|
| 508 |
+
"eval_loss": 0.9110000729560852,
|
| 509 |
+
"eval_precision_macro": 0.8343727376865201,
|
| 510 |
+
"eval_precision_micro": 0.8756314649987972,
|
| 511 |
+
"eval_recall_macro": 0.8210414008872133,
|
| 512 |
+
"eval_recall_micro": 0.8756314649987972,
|
| 513 |
+
"eval_runtime": 27.2652,
|
| 514 |
+
"eval_samples_per_second": 152.465,
|
| 515 |
+
"eval_steps_per_second": 19.072,
|
| 516 |
+
"step": 11500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.9140359397765905,
|
| 520 |
+
"grad_norm": 0.013514680787920952,
|
| 521 |
+
"learning_rate": 1.6741679443825673e-05,
|
| 522 |
+
"loss": 0.1027,
|
| 523 |
+
"step": 12000
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.9140359397765905,
|
| 527 |
+
"eval_accuracy": 0.8655280250180418,
|
| 528 |
+
"eval_f1_macro": 0.814236769671234,
|
| 529 |
+
"eval_f1_micro": 0.8655280250180418,
|
| 530 |
+
"eval_loss": 1.0340354442596436,
|
| 531 |
+
"eval_precision_macro": 0.8211316713081322,
|
| 532 |
+
"eval_precision_micro": 0.8655280250180418,
|
| 533 |
+
"eval_recall_macro": 0.8190728220384627,
|
| 534 |
+
"eval_recall_micro": 0.8655280250180418,
|
| 535 |
+
"eval_runtime": 27.2801,
|
| 536 |
+
"eval_samples_per_second": 152.382,
|
| 537 |
+
"eval_steps_per_second": 19.062,
|
| 538 |
+
"step": 12000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.0354541039339487,
|
| 542 |
+
"grad_norm": 0.06883151084184647,
|
| 543 |
+
"learning_rate": 1.34302193181041e-05,
|
| 544 |
+
"loss": 0.1368,
|
| 545 |
+
"step": 12500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.0354541039339487,
|
| 549 |
+
"eval_accuracy": 0.8737070002405581,
|
| 550 |
+
"eval_f1_macro": 0.8142391346531119,
|
| 551 |
+
"eval_f1_micro": 0.8737070002405581,
|
| 552 |
+
"eval_loss": 0.8788183927536011,
|
| 553 |
+
"eval_precision_macro": 0.8186147346918103,
|
| 554 |
+
"eval_precision_micro": 0.8737070002405581,
|
| 555 |
+
"eval_recall_macro": 0.8331902702603373,
|
| 556 |
+
"eval_recall_micro": 0.8737070002405581,
|
| 557 |
+
"eval_runtime": 27.2538,
|
| 558 |
+
"eval_samples_per_second": 152.529,
|
| 559 |
+
"eval_steps_per_second": 19.08,
|
| 560 |
+
"step": 12500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.1568722680913064,
|
| 564 |
+
"grad_norm": 0.007450424134731293,
|
| 565 |
+
"learning_rate": 1.0416810143461263e-05,
|
| 566 |
+
"loss": 0.0501,
|
| 567 |
+
"step": 13000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.1568722680913064,
|
| 571 |
+
"eval_accuracy": 0.8866971373586722,
|
| 572 |
+
"eval_f1_macro": 0.8306324981784764,
|
| 573 |
+
"eval_f1_micro": 0.8866971373586722,
|
| 574 |
+
"eval_loss": 0.8202418088912964,
|
| 575 |
+
"eval_precision_macro": 0.8476975671689575,
|
| 576 |
+
"eval_precision_micro": 0.8866971373586722,
|
| 577 |
+
"eval_recall_macro": 0.8296071466526088,
|
| 578 |
+
"eval_recall_micro": 0.8866971373586722,
|
| 579 |
+
"eval_runtime": 27.2733,
|
| 580 |
+
"eval_samples_per_second": 152.42,
|
| 581 |
+
"eval_steps_per_second": 19.066,
|
| 582 |
+
"step": 13000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.2782904322486646,
|
| 586 |
+
"grad_norm": 0.006428878754377365,
|
| 587 |
+
"learning_rate": 7.73525534045391e-06,
|
| 588 |
+
"loss": 0.0556,
|
| 589 |
+
"step": 13500
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 3.2782904322486646,
|
| 593 |
+
"eval_accuracy": 0.8773153716622565,
|
| 594 |
+
"eval_f1_macro": 0.8187172181232656,
|
| 595 |
+
"eval_f1_micro": 0.8773153716622565,
|
| 596 |
+
"eval_loss": 0.9218270182609558,
|
| 597 |
+
"eval_precision_macro": 0.8355184291729084,
|
| 598 |
+
"eval_precision_micro": 0.8773153716622565,
|
| 599 |
+
"eval_recall_macro": 0.8247427107635721,
|
| 600 |
+
"eval_recall_micro": 0.8773153716622565,
|
| 601 |
+
"eval_runtime": 27.275,
|
| 602 |
+
"eval_samples_per_second": 152.411,
|
| 603 |
+
"eval_steps_per_second": 19.065,
|
| 604 |
+
"step": 13500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.3997085964060223,
|
| 608 |
+
"grad_norm": 0.0064325109124183655,
|
| 609 |
+
"learning_rate": 5.415635697816259e-06,
|
| 610 |
+
"loss": 0.0468,
|
| 611 |
+
"step": 14000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.3997085964060223,
|
| 615 |
+
"eval_accuracy": 0.8744286745248978,
|
| 616 |
+
"eval_f1_macro": 0.8190467137701445,
|
| 617 |
+
"eval_f1_micro": 0.8744286745248978,
|
| 618 |
+
"eval_loss": 0.8941731452941895,
|
| 619 |
+
"eval_precision_macro": 0.817939746546661,
|
| 620 |
+
"eval_precision_micro": 0.8744286745248978,
|
| 621 |
+
"eval_recall_macro": 0.8276624213993112,
|
| 622 |
+
"eval_recall_micro": 0.8744286745248978,
|
| 623 |
+
"eval_runtime": 27.261,
|
| 624 |
+
"eval_samples_per_second": 152.489,
|
| 625 |
+
"eval_steps_per_second": 19.075,
|
| 626 |
+
"step": 14000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.52112676056338,
|
| 630 |
+
"grad_norm": 0.004375011660158634,
|
| 631 |
+
"learning_rate": 3.4839719361897852e-06,
|
| 632 |
+
"loss": 0.0665,
|
| 633 |
+
"step": 14500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 3.52112676056338,
|
| 637 |
+
"eval_accuracy": 0.8915082992542699,
|
| 638 |
+
"eval_f1_macro": 0.8339685375452801,
|
| 639 |
+
"eval_f1_micro": 0.8915082992542699,
|
| 640 |
+
"eval_loss": 0.7931458950042725,
|
| 641 |
+
"eval_precision_macro": 0.8462712956558062,
|
| 642 |
+
"eval_precision_micro": 0.8915082992542699,
|
| 643 |
+
"eval_recall_macro": 0.8342943619225055,
|
| 644 |
+
"eval_recall_micro": 0.8915082992542699,
|
| 645 |
+
"eval_runtime": 27.2445,
|
| 646 |
+
"eval_samples_per_second": 152.581,
|
| 647 |
+
"eval_steps_per_second": 19.086,
|
| 648 |
+
"step": 14500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.642544924720738,
|
| 652 |
+
"grad_norm": 0.001833868445828557,
|
| 653 |
+
"learning_rate": 1.9619328163448515e-06,
|
| 654 |
+
"loss": 0.0501,
|
| 655 |
+
"step": 15000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.642544924720738,
|
| 659 |
+
"eval_accuracy": 0.8874188116430118,
|
| 660 |
+
"eval_f1_macro": 0.8310772401939998,
|
| 661 |
+
"eval_f1_micro": 0.8874188116430118,
|
| 662 |
+
"eval_loss": 0.836759626865387,
|
| 663 |
+
"eval_precision_macro": 0.8466657132643576,
|
| 664 |
+
"eval_precision_micro": 0.8874188116430118,
|
| 665 |
+
"eval_recall_macro": 0.8343787872890429,
|
| 666 |
+
"eval_recall_micro": 0.8874188116430118,
|
| 667 |
+
"eval_runtime": 27.2674,
|
| 668 |
+
"eval_samples_per_second": 152.453,
|
| 669 |
+
"eval_steps_per_second": 19.07,
|
| 670 |
+
"step": 15000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 3.7639630888780964,
|
| 674 |
+
"grad_norm": 0.0033753265161067247,
|
| 675 |
+
"learning_rate": 8.665920662387894e-07,
|
| 676 |
+
"loss": 0.0484,
|
| 677 |
+
"step": 15500
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.7639630888780964,
|
| 681 |
+
"eval_accuracy": 0.8871782535482319,
|
| 682 |
+
"eval_f1_macro": 0.8297898341377807,
|
| 683 |
+
"eval_f1_micro": 0.8871782535482319,
|
| 684 |
+
"eval_loss": 0.8264660835266113,
|
| 685 |
+
"eval_precision_macro": 0.8376058490993101,
|
| 686 |
+
"eval_precision_micro": 0.8871782535482319,
|
| 687 |
+
"eval_recall_macro": 0.8371349644182987,
|
| 688 |
+
"eval_recall_micro": 0.8871782535482319,
|
| 689 |
+
"eval_runtime": 27.2745,
|
| 690 |
+
"eval_samples_per_second": 152.413,
|
| 691 |
+
"eval_steps_per_second": 19.065,
|
| 692 |
+
"step": 15500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.885381253035454,
|
| 696 |
+
"grad_norm": 0.00866024848073721,
|
| 697 |
+
"learning_rate": 2.1023685362179913e-07,
|
| 698 |
+
"loss": 0.0454,
|
| 699 |
+
"step": 16000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 3.885381253035454,
|
| 703 |
+
"eval_accuracy": 0.8850132306952129,
|
| 704 |
+
"eval_f1_macro": 0.8261753135901729,
|
| 705 |
+
"eval_f1_micro": 0.8850132306952129,
|
| 706 |
+
"eval_loss": 0.8282179236412048,
|
| 707 |
+
"eval_precision_macro": 0.8341202183391875,
|
| 708 |
+
"eval_precision_micro": 0.8850132306952129,
|
| 709 |
+
"eval_recall_macro": 0.8329926466265877,
|
| 710 |
+
"eval_recall_micro": 0.8850132306952129,
|
| 711 |
+
"eval_runtime": 27.255,
|
| 712 |
+
"eval_samples_per_second": 152.522,
|
| 713 |
+
"eval_steps_per_second": 19.079,
|
| 714 |
+
"step": 16000
|
| 715 |
+
}
|
| 716 |
+
],
|
| 717 |
+
"logging_steps": 500,
|
| 718 |
+
"max_steps": 16472,
|
| 719 |
+
"num_input_tokens_seen": 0,
|
| 720 |
+
"num_train_epochs": 4,
|
| 721 |
+
"save_steps": 500,
|
| 722 |
+
"stateful_callbacks": {
|
| 723 |
+
"TrainerControl": {
|
| 724 |
+
"args": {
|
| 725 |
+
"should_epoch_stop": false,
|
| 726 |
+
"should_evaluate": false,
|
| 727 |
+
"should_log": false,
|
| 728 |
+
"should_save": true,
|
| 729 |
+
"should_training_stop": true
|
| 730 |
+
},
|
| 731 |
+
"attributes": {}
|
| 732 |
+
}
|
| 733 |
+
},
|
| 734 |
+
"total_flos": 3.4790744808566784e+16,
|
| 735 |
+
"train_batch_size": 8,
|
| 736 |
+
"trial_name": null,
|
| 737 |
+
"trial_params": null
|
| 738 |
+
}
|
checkpoint-16472/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e92bf6666684fb5efaf90782737fab17e97c478b9d9b32d6e2b07dd4345ae13
|
| 3 |
+
size 5713
|
checkpoint-16472/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|