Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-10605/config.json +136 -0
- checkpoint-10605/model.safetensors +3 -0
- checkpoint-10605/optimizer.pt +3 -0
- checkpoint-10605/rng_state.pth +3 -0
- checkpoint-10605/scheduler.pt +3 -0
- checkpoint-10605/trainer_state.json +3046 -0
- checkpoint-10605/training_args.bin +3 -0
- config.json +136 -0
- model.safetensors +3 -0
- runs/Oct24_07-27-25_r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq/events.out.tfevents.1761290846.r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq.90.0 +2 -2
- runs/Oct24_07-27-25_r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq/events.out.tfevents.1761295429.r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq.90.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- training_args.bin +3 -0
- training_params.json +30 -0
README.md
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- autotrain
|
| 6 |
+
- token-classification
|
| 7 |
+
base_model: answerdotai/ModernBERT-large
|
| 8 |
+
widget:
|
| 9 |
+
- text: "I love AutoTrain"
|
| 10 |
+
datasets:
|
| 11 |
+
- juanmcristobal/ner-ioc-dataset3
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Trained Using AutoTrain
|
| 15 |
+
|
| 16 |
+
- Problem type: Token Classification
|
| 17 |
+
|
| 18 |
+
## Validation Metrics
|
| 19 |
+
loss: 0.080692358314991
|
| 20 |
+
|
| 21 |
+
precision: 0.8956920811279763
|
| 22 |
+
|
| 23 |
+
recall: 0.9126250733540829
|
| 24 |
+
|
| 25 |
+
f1: 0.9040792973909716
|
| 26 |
+
|
| 27 |
+
accuracy: 0.9731636716504077
|
checkpoint-10605/config.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-large",
|
| 3 |
+
"_num_labels": 42,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ModernBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 50281,
|
| 10 |
+
"classifier_activation": "gelu",
|
| 11 |
+
"classifier_bias": false,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"classifier_pooling": "mean",
|
| 14 |
+
"cls_token_id": 50281,
|
| 15 |
+
"decoder_bias": true,
|
| 16 |
+
"deterministic_flash_attn": false,
|
| 17 |
+
"embedding_dropout": 0.0,
|
| 18 |
+
"eos_token_id": 50282,
|
| 19 |
+
"global_attn_every_n_layers": 3,
|
| 20 |
+
"global_rope_theta": 160000.0,
|
| 21 |
+
"gradient_checkpointing": false,
|
| 22 |
+
"hidden_activation": "gelu",
|
| 23 |
+
"hidden_size": 1024,
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "B-URL",
|
| 26 |
+
"1": "I-URL",
|
| 27 |
+
"2": "O",
|
| 28 |
+
"3": "B-ORG",
|
| 29 |
+
"4": "B-SERVICE",
|
| 30 |
+
"5": "I-ORG",
|
| 31 |
+
"6": "B-SECTOR",
|
| 32 |
+
"7": "I-SECTOR",
|
| 33 |
+
"8": "B-FILEPATH",
|
| 34 |
+
"9": "I-FILEPATH",
|
| 35 |
+
"10": "I-DOMAIN",
|
| 36 |
+
"11": "B-PLATFORM",
|
| 37 |
+
"12": "I-SERVICE",
|
| 38 |
+
"13": "I-PLATFORM",
|
| 39 |
+
"14": "B-THREAT-ACTOR",
|
| 40 |
+
"15": "I-THREAT-ACTOR",
|
| 41 |
+
"16": "B-PRODUCT",
|
| 42 |
+
"17": "B-MALWARE",
|
| 43 |
+
"18": "I-MALWARE",
|
| 44 |
+
"19": "B-LOC",
|
| 45 |
+
"20": "B-CVE",
|
| 46 |
+
"21": "I-CVE",
|
| 47 |
+
"22": "B-TOOL",
|
| 48 |
+
"23": "I-PRODUCT",
|
| 49 |
+
"24": "B-IPV4",
|
| 50 |
+
"25": "I-IPV4",
|
| 51 |
+
"26": "B-MITRE-TACTIC",
|
| 52 |
+
"27": "I-MITRE-TACTIC",
|
| 53 |
+
"28": "B-DOMAIN",
|
| 54 |
+
"29": "I-TOOL",
|
| 55 |
+
"30": "B-MD5",
|
| 56 |
+
"31": "I-LOC",
|
| 57 |
+
"32": "B-CAMPAIGN",
|
| 58 |
+
"33": "I-CAMPAIGN",
|
| 59 |
+
"34": "B-SHA1",
|
| 60 |
+
"35": "B-SHA256",
|
| 61 |
+
"36": "B-EMAIL",
|
| 62 |
+
"37": "I-EMAIL",
|
| 63 |
+
"38": "B-IPV6",
|
| 64 |
+
"39": "I-IPV6",
|
| 65 |
+
"40": "B-REGISTRY-KEYS",
|
| 66 |
+
"41": "I-REGISTRY-KEYS"
|
| 67 |
+
},
|
| 68 |
+
"initializer_cutoff_factor": 2.0,
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 2624,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"B-CAMPAIGN": 32,
|
| 73 |
+
"B-CVE": 20,
|
| 74 |
+
"B-DOMAIN": 28,
|
| 75 |
+
"B-EMAIL": 36,
|
| 76 |
+
"B-FILEPATH": 8,
|
| 77 |
+
"B-IPV4": 24,
|
| 78 |
+
"B-IPV6": 38,
|
| 79 |
+
"B-LOC": 19,
|
| 80 |
+
"B-MALWARE": 17,
|
| 81 |
+
"B-MD5": 30,
|
| 82 |
+
"B-MITRE-TACTIC": 26,
|
| 83 |
+
"B-ORG": 3,
|
| 84 |
+
"B-PLATFORM": 11,
|
| 85 |
+
"B-PRODUCT": 16,
|
| 86 |
+
"B-REGISTRY-KEYS": 40,
|
| 87 |
+
"B-SECTOR": 6,
|
| 88 |
+
"B-SERVICE": 4,
|
| 89 |
+
"B-SHA1": 34,
|
| 90 |
+
"B-SHA256": 35,
|
| 91 |
+
"B-THREAT-ACTOR": 14,
|
| 92 |
+
"B-TOOL": 22,
|
| 93 |
+
"B-URL": 0,
|
| 94 |
+
"I-CAMPAIGN": 33,
|
| 95 |
+
"I-CVE": 21,
|
| 96 |
+
"I-DOMAIN": 10,
|
| 97 |
+
"I-EMAIL": 37,
|
| 98 |
+
"I-FILEPATH": 9,
|
| 99 |
+
"I-IPV4": 25,
|
| 100 |
+
"I-IPV6": 39,
|
| 101 |
+
"I-LOC": 31,
|
| 102 |
+
"I-MALWARE": 18,
|
| 103 |
+
"I-MITRE-TACTIC": 27,
|
| 104 |
+
"I-ORG": 5,
|
| 105 |
+
"I-PLATFORM": 13,
|
| 106 |
+
"I-PRODUCT": 23,
|
| 107 |
+
"I-REGISTRY-KEYS": 41,
|
| 108 |
+
"I-SECTOR": 7,
|
| 109 |
+
"I-SERVICE": 12,
|
| 110 |
+
"I-THREAT-ACTOR": 15,
|
| 111 |
+
"I-TOOL": 29,
|
| 112 |
+
"I-URL": 1,
|
| 113 |
+
"O": 2
|
| 114 |
+
},
|
| 115 |
+
"layer_norm_eps": 1e-05,
|
| 116 |
+
"local_attention": 128,
|
| 117 |
+
"local_rope_theta": 10000.0,
|
| 118 |
+
"max_position_embeddings": 8192,
|
| 119 |
+
"mlp_bias": false,
|
| 120 |
+
"mlp_dropout": 0.0,
|
| 121 |
+
"model_type": "modernbert",
|
| 122 |
+
"norm_bias": false,
|
| 123 |
+
"norm_eps": 1e-05,
|
| 124 |
+
"num_attention_heads": 16,
|
| 125 |
+
"num_hidden_layers": 28,
|
| 126 |
+
"pad_token_id": 50283,
|
| 127 |
+
"position_embedding_type": "absolute",
|
| 128 |
+
"reference_compile": true,
|
| 129 |
+
"repad_logits_with_grad": false,
|
| 130 |
+
"sep_token_id": 50282,
|
| 131 |
+
"sparse_pred_ignore_index": -100,
|
| 132 |
+
"sparse_prediction": false,
|
| 133 |
+
"torch_dtype": "float32",
|
| 134 |
+
"transformers_version": "4.48.0",
|
| 135 |
+
"vocab_size": 50368
|
| 136 |
+
}
|
checkpoint-10605/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52fe43effd7557bea8056246926a2cc952953b1facb01c2c020f0b8fa5e7927f
|
| 3 |
+
size 1583515640
|
checkpoint-10605/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:355db5828e53dad3fb07dfb9d1e869ab4a33eaa748de5119b7f93eef9127cfb5
|
| 3 |
+
size 3167141114
|
checkpoint-10605/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
|
| 3 |
+
size 14244
|
checkpoint-10605/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c39fecfbb20dafe4de628b038dfd9b1c411f754cb08db3057f17717acae14f13
|
| 3 |
+
size 1064
|
checkpoint-10605/trainer_state.json
ADDED
|
@@ -0,0 +1,3046 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.080692358314991,
|
| 3 |
+
"best_model_checkpoint": "autotrain-sec4/checkpoint-10605",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 10605,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.007072135785007072,
|
| 13 |
+
"grad_norm": 75.34838104248047,
|
| 14 |
+
"learning_rate": 6.504524886877829e-07,
|
| 15 |
+
"loss": 3.7557,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.014144271570014143,
|
| 20 |
+
"grad_norm": 15.420210838317871,
|
| 21 |
+
"learning_rate": 1.3574660633484164e-06,
|
| 22 |
+
"loss": 2.4958,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.021216407355021217,
|
| 27 |
+
"grad_norm": 4.017354965209961,
|
| 28 |
+
"learning_rate": 2.0361990950226245e-06,
|
| 29 |
+
"loss": 1.1167,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.028288543140028287,
|
| 34 |
+
"grad_norm": 3.0722529888153076,
|
| 35 |
+
"learning_rate": 2.743212669683258e-06,
|
| 36 |
+
"loss": 0.7577,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03536067892503536,
|
| 41 |
+
"grad_norm": 4.105304718017578,
|
| 42 |
+
"learning_rate": 3.450226244343892e-06,
|
| 43 |
+
"loss": 0.6,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.042432814710042434,
|
| 48 |
+
"grad_norm": 2.796954870223999,
|
| 49 |
+
"learning_rate": 4.157239819004525e-06,
|
| 50 |
+
"loss": 0.5213,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04950495049504951,
|
| 55 |
+
"grad_norm": 2.0742604732513428,
|
| 56 |
+
"learning_rate": 4.864253393665159e-06,
|
| 57 |
+
"loss": 0.4437,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.056577086280056574,
|
| 62 |
+
"grad_norm": 1.6229099035263062,
|
| 63 |
+
"learning_rate": 5.5712669683257925e-06,
|
| 64 |
+
"loss": 0.3827,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.06364922206506365,
|
| 69 |
+
"grad_norm": 2.0883893966674805,
|
| 70 |
+
"learning_rate": 6.278280542986425e-06,
|
| 71 |
+
"loss": 0.3385,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07072135785007072,
|
| 76 |
+
"grad_norm": 2.5166773796081543,
|
| 77 |
+
"learning_rate": 6.985294117647059e-06,
|
| 78 |
+
"loss": 0.2949,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07779349363507779,
|
| 83 |
+
"grad_norm": 2.4907472133636475,
|
| 84 |
+
"learning_rate": 7.692307692307694e-06,
|
| 85 |
+
"loss": 0.2776,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08486562942008487,
|
| 90 |
+
"grad_norm": 2.4089417457580566,
|
| 91 |
+
"learning_rate": 8.399321266968327e-06,
|
| 92 |
+
"loss": 0.2867,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09193776520509193,
|
| 97 |
+
"grad_norm": 1.0878061056137085,
|
| 98 |
+
"learning_rate": 9.10633484162896e-06,
|
| 99 |
+
"loss": 0.2567,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09900990099009901,
|
| 104 |
+
"grad_norm": 1.353794813156128,
|
| 105 |
+
"learning_rate": 9.813348416289593e-06,
|
| 106 |
+
"loss": 0.2377,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10608203677510608,
|
| 111 |
+
"grad_norm": 1.3143301010131836,
|
| 112 |
+
"learning_rate": 1.0520361990950227e-05,
|
| 113 |
+
"loss": 0.2446,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.11315417256011315,
|
| 118 |
+
"grad_norm": 1.1061075925827026,
|
| 119 |
+
"learning_rate": 1.122737556561086e-05,
|
| 120 |
+
"loss": 0.2136,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.12022630834512023,
|
| 125 |
+
"grad_norm": 4.132507801055908,
|
| 126 |
+
"learning_rate": 1.1934389140271494e-05,
|
| 127 |
+
"loss": 0.2089,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1272984441301273,
|
| 132 |
+
"grad_norm": 2.015286922454834,
|
| 133 |
+
"learning_rate": 1.2641402714932126e-05,
|
| 134 |
+
"loss": 0.206,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.13437057991513437,
|
| 139 |
+
"grad_norm": 1.3202295303344727,
|
| 140 |
+
"learning_rate": 1.3348416289592761e-05,
|
| 141 |
+
"loss": 0.2135,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.14144271570014144,
|
| 146 |
+
"grad_norm": 1.005441665649414,
|
| 147 |
+
"learning_rate": 1.4055429864253395e-05,
|
| 148 |
+
"loss": 0.198,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1485148514851485,
|
| 153 |
+
"grad_norm": 1.0634604692459106,
|
| 154 |
+
"learning_rate": 1.4762443438914029e-05,
|
| 155 |
+
"loss": 0.1869,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.15558698727015557,
|
| 160 |
+
"grad_norm": 1.5153967142105103,
|
| 161 |
+
"learning_rate": 1.5469457013574662e-05,
|
| 162 |
+
"loss": 0.1938,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.16265912305516267,
|
| 167 |
+
"grad_norm": 1.5015569925308228,
|
| 168 |
+
"learning_rate": 1.6176470588235296e-05,
|
| 169 |
+
"loss": 0.1916,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16973125884016974,
|
| 174 |
+
"grad_norm": 1.3801521062850952,
|
| 175 |
+
"learning_rate": 1.688348416289593e-05,
|
| 176 |
+
"loss": 0.1859,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1768033946251768,
|
| 181 |
+
"grad_norm": 1.4514083862304688,
|
| 182 |
+
"learning_rate": 1.7590497737556563e-05,
|
| 183 |
+
"loss": 0.1794,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.18387553041018387,
|
| 188 |
+
"grad_norm": 1.1229180097579956,
|
| 189 |
+
"learning_rate": 1.8297511312217194e-05,
|
| 190 |
+
"loss": 0.181,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.19094766619519093,
|
| 195 |
+
"grad_norm": 0.9584263563156128,
|
| 196 |
+
"learning_rate": 1.9004524886877827e-05,
|
| 197 |
+
"loss": 0.1702,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.19801980198019803,
|
| 202 |
+
"grad_norm": 1.5446968078613281,
|
| 203 |
+
"learning_rate": 1.971153846153846e-05,
|
| 204 |
+
"loss": 0.1655,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2050919377652051,
|
| 209 |
+
"grad_norm": 1.180188775062561,
|
| 210 |
+
"learning_rate": 2.0418552036199095e-05,
|
| 211 |
+
"loss": 0.1783,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.21216407355021216,
|
| 216 |
+
"grad_norm": 1.4047558307647705,
|
| 217 |
+
"learning_rate": 2.112556561085973e-05,
|
| 218 |
+
"loss": 0.1654,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.21923620933521923,
|
| 223 |
+
"grad_norm": 1.6405079364776611,
|
| 224 |
+
"learning_rate": 2.1832579185520362e-05,
|
| 225 |
+
"loss": 0.1676,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2263083451202263,
|
| 230 |
+
"grad_norm": 0.799575924873352,
|
| 231 |
+
"learning_rate": 2.2539592760180996e-05,
|
| 232 |
+
"loss": 0.1529,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2333804809052334,
|
| 237 |
+
"grad_norm": 1.0612698793411255,
|
| 238 |
+
"learning_rate": 2.324660633484163e-05,
|
| 239 |
+
"loss": 0.158,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.24045261669024046,
|
| 244 |
+
"grad_norm": 0.8970231413841248,
|
| 245 |
+
"learning_rate": 2.3953619909502263e-05,
|
| 246 |
+
"loss": 0.1556,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.24752475247524752,
|
| 251 |
+
"grad_norm": 1.1954729557037354,
|
| 252 |
+
"learning_rate": 2.4660633484162897e-05,
|
| 253 |
+
"loss": 0.1512,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.2545968882602546,
|
| 258 |
+
"grad_norm": 2.2156217098236084,
|
| 259 |
+
"learning_rate": 2.536764705882353e-05,
|
| 260 |
+
"loss": 0.1528,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.26166902404526166,
|
| 265 |
+
"grad_norm": 1.4057120084762573,
|
| 266 |
+
"learning_rate": 2.6074660633484164e-05,
|
| 267 |
+
"loss": 0.1562,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.26874115983026875,
|
| 272 |
+
"grad_norm": 1.9392261505126953,
|
| 273 |
+
"learning_rate": 2.6781674208144798e-05,
|
| 274 |
+
"loss": 0.1601,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.2758132956152758,
|
| 279 |
+
"grad_norm": 1.114762306213379,
|
| 280 |
+
"learning_rate": 2.7488687782805435e-05,
|
| 281 |
+
"loss": 0.1616,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.2828854314002829,
|
| 286 |
+
"grad_norm": 0.6488351225852966,
|
| 287 |
+
"learning_rate": 2.8195701357466065e-05,
|
| 288 |
+
"loss": 0.1564,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.28995756718529,
|
| 293 |
+
"grad_norm": 0.7562068700790405,
|
| 294 |
+
"learning_rate": 2.8902714932126696e-05,
|
| 295 |
+
"loss": 0.1447,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.297029702970297,
|
| 300 |
+
"grad_norm": 1.5005004405975342,
|
| 301 |
+
"learning_rate": 2.9609728506787333e-05,
|
| 302 |
+
"loss": 0.1411,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.3041018387553041,
|
| 307 |
+
"grad_norm": 0.9700536131858826,
|
| 308 |
+
"learning_rate": 3.0316742081447963e-05,
|
| 309 |
+
"loss": 0.1628,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.31117397454031115,
|
| 314 |
+
"grad_norm": 0.9135770797729492,
|
| 315 |
+
"learning_rate": 3.10237556561086e-05,
|
| 316 |
+
"loss": 0.1429,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.31824611032531824,
|
| 321 |
+
"grad_norm": 0.5135190486907959,
|
| 322 |
+
"learning_rate": 3.1730769230769234e-05,
|
| 323 |
+
"loss": 0.1349,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.32531824611032534,
|
| 328 |
+
"grad_norm": 0.7440194487571716,
|
| 329 |
+
"learning_rate": 3.243778280542987e-05,
|
| 330 |
+
"loss": 0.1511,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3323903818953324,
|
| 335 |
+
"grad_norm": 0.774247407913208,
|
| 336 |
+
"learning_rate": 3.31447963800905e-05,
|
| 337 |
+
"loss": 0.1433,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.33946251768033947,
|
| 342 |
+
"grad_norm": 0.9245631098747253,
|
| 343 |
+
"learning_rate": 3.3851809954751135e-05,
|
| 344 |
+
"loss": 0.136,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3465346534653465,
|
| 349 |
+
"grad_norm": 0.5323517918586731,
|
| 350 |
+
"learning_rate": 3.455882352941177e-05,
|
| 351 |
+
"loss": 0.1402,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.3536067892503536,
|
| 356 |
+
"grad_norm": 0.5974646210670471,
|
| 357 |
+
"learning_rate": 3.52658371040724e-05,
|
| 358 |
+
"loss": 0.139,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3606789250353607,
|
| 363 |
+
"grad_norm": 0.7609033584594727,
|
| 364 |
+
"learning_rate": 3.5972850678733036e-05,
|
| 365 |
+
"loss": 0.1414,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.36775106082036774,
|
| 370 |
+
"grad_norm": 0.6598523259162903,
|
| 371 |
+
"learning_rate": 3.667986425339366e-05,
|
| 372 |
+
"loss": 0.1279,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.37482319660537483,
|
| 377 |
+
"grad_norm": 0.646514892578125,
|
| 378 |
+
"learning_rate": 3.73868778280543e-05,
|
| 379 |
+
"loss": 0.1318,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.38189533239038187,
|
| 384 |
+
"grad_norm": 0.6801839470863342,
|
| 385 |
+
"learning_rate": 3.809389140271493e-05,
|
| 386 |
+
"loss": 0.135,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.38896746817538896,
|
| 391 |
+
"grad_norm": 0.43455860018730164,
|
| 392 |
+
"learning_rate": 3.880090497737557e-05,
|
| 393 |
+
"loss": 0.1229,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.39603960396039606,
|
| 398 |
+
"grad_norm": 0.7492242455482483,
|
| 399 |
+
"learning_rate": 3.95079185520362e-05,
|
| 400 |
+
"loss": 0.1336,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.4031117397454031,
|
| 405 |
+
"grad_norm": 0.7798008918762207,
|
| 406 |
+
"learning_rate": 4.021493212669684e-05,
|
| 407 |
+
"loss": 0.1278,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.4101838755304102,
|
| 412 |
+
"grad_norm": 0.5796477794647217,
|
| 413 |
+
"learning_rate": 4.0921945701357465e-05,
|
| 414 |
+
"loss": 0.1231,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.41725601131541723,
|
| 419 |
+
"grad_norm": 0.8398697376251221,
|
| 420 |
+
"learning_rate": 4.1628959276018105e-05,
|
| 421 |
+
"loss": 0.1305,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.4243281471004243,
|
| 426 |
+
"grad_norm": 1.1518373489379883,
|
| 427 |
+
"learning_rate": 4.233597285067873e-05,
|
| 428 |
+
"loss": 0.1345,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.4314002828854314,
|
| 433 |
+
"grad_norm": 0.6339196562767029,
|
| 434 |
+
"learning_rate": 4.304298642533937e-05,
|
| 435 |
+
"loss": 0.1388,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.43847241867043846,
|
| 440 |
+
"grad_norm": 0.6023873090744019,
|
| 441 |
+
"learning_rate": 4.375e-05,
|
| 442 |
+
"loss": 0.1343,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.44554455445544555,
|
| 447 |
+
"grad_norm": 0.6470553874969482,
|
| 448 |
+
"learning_rate": 4.445701357466063e-05,
|
| 449 |
+
"loss": 0.1353,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.4526166902404526,
|
| 454 |
+
"grad_norm": 0.6824638843536377,
|
| 455 |
+
"learning_rate": 4.516402714932127e-05,
|
| 456 |
+
"loss": 0.1233,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.4596888260254597,
|
| 461 |
+
"grad_norm": 0.7944373488426208,
|
| 462 |
+
"learning_rate": 4.58710407239819e-05,
|
| 463 |
+
"loss": 0.1235,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4667609618104668,
|
| 468 |
+
"grad_norm": 0.576715350151062,
|
| 469 |
+
"learning_rate": 4.6578054298642534e-05,
|
| 470 |
+
"loss": 0.1225,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4738330975954738,
|
| 475 |
+
"grad_norm": 0.5373973846435547,
|
| 476 |
+
"learning_rate": 4.728506787330317e-05,
|
| 477 |
+
"loss": 0.1379,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.4809052333804809,
|
| 482 |
+
"grad_norm": 0.6271287798881531,
|
| 483 |
+
"learning_rate": 4.79920814479638e-05,
|
| 484 |
+
"loss": 0.1295,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.48797736916548795,
|
| 489 |
+
"grad_norm": 0.776996374130249,
|
| 490 |
+
"learning_rate": 4.8699095022624435e-05,
|
| 491 |
+
"loss": 0.1284,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.49504950495049505,
|
| 496 |
+
"grad_norm": 0.7526723742485046,
|
| 497 |
+
"learning_rate": 4.940610859728507e-05,
|
| 498 |
+
"loss": 0.1215,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.5021216407355021,
|
| 503 |
+
"grad_norm": 0.5230354070663452,
|
| 504 |
+
"learning_rate": 4.99999921989483e-05,
|
| 505 |
+
"loss": 0.1198,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.5091937765205092,
|
| 510 |
+
"grad_norm": 0.9118756651878357,
|
| 511 |
+
"learning_rate": 4.999958995831941e-05,
|
| 512 |
+
"loss": 0.134,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.5162659123055162,
|
| 517 |
+
"grad_norm": 0.7880003452301025,
|
| 518 |
+
"learning_rate": 4.9998578271728684e-05,
|
| 519 |
+
"loss": 0.1271,
|
| 520 |
+
"step": 1825
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.5233380480905233,
|
| 524 |
+
"grad_norm": 0.47186046838760376,
|
| 525 |
+
"learning_rate": 4.999695716383928e-05,
|
| 526 |
+
"loss": 0.1188,
|
| 527 |
+
"step": 1850
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.5304101838755304,
|
| 531 |
+
"grad_norm": 0.5088236331939697,
|
| 532 |
+
"learning_rate": 4.9994726674170947e-05,
|
| 533 |
+
"loss": 0.1179,
|
| 534 |
+
"step": 1875
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.5374823196605375,
|
| 538 |
+
"grad_norm": 0.6230493187904358,
|
| 539 |
+
"learning_rate": 4.999188685709908e-05,
|
| 540 |
+
"loss": 0.1262,
|
| 541 |
+
"step": 1900
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.5445544554455446,
|
| 545 |
+
"grad_norm": 0.9874520301818848,
|
| 546 |
+
"learning_rate": 4.998843778185343e-05,
|
| 547 |
+
"loss": 0.1244,
|
| 548 |
+
"step": 1925
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.5516265912305516,
|
| 552 |
+
"grad_norm": 0.5979165434837341,
|
| 553 |
+
"learning_rate": 4.998437953251637e-05,
|
| 554 |
+
"loss": 0.1291,
|
| 555 |
+
"step": 1950
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.5586987270155587,
|
| 559 |
+
"grad_norm": 0.8219141364097595,
|
| 560 |
+
"learning_rate": 4.997971220802088e-05,
|
| 561 |
+
"loss": 0.1155,
|
| 562 |
+
"step": 1975
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.5657708628005658,
|
| 566 |
+
"grad_norm": 0.41394418478012085,
|
| 567 |
+
"learning_rate": 4.997443592214809e-05,
|
| 568 |
+
"loss": 0.1198,
|
| 569 |
+
"step": 2000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5728429985855729,
|
| 573 |
+
"grad_norm": 1.253273844718933,
|
| 574 |
+
"learning_rate": 4.996855080352457e-05,
|
| 575 |
+
"loss": 0.1191,
|
| 576 |
+
"step": 2025
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.57991513437058,
|
| 580 |
+
"grad_norm": 0.9971447587013245,
|
| 581 |
+
"learning_rate": 4.9962056995619135e-05,
|
| 582 |
+
"loss": 0.1328,
|
| 583 |
+
"step": 2050
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5869872701555869,
|
| 587 |
+
"grad_norm": 0.49998825788497925,
|
| 588 |
+
"learning_rate": 4.995495465673939e-05,
|
| 589 |
+
"loss": 0.115,
|
| 590 |
+
"step": 2075
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.594059405940594,
|
| 594 |
+
"grad_norm": 0.9231402277946472,
|
| 595 |
+
"learning_rate": 4.994724396002783e-05,
|
| 596 |
+
"loss": 0.1131,
|
| 597 |
+
"step": 2100
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.6011315417256011,
|
| 601 |
+
"grad_norm": 0.5812481641769409,
|
| 602 |
+
"learning_rate": 4.9938925093457684e-05,
|
| 603 |
+
"loss": 0.103,
|
| 604 |
+
"step": 2125
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.6082036775106082,
|
| 608 |
+
"grad_norm": 0.602626383304596,
|
| 609 |
+
"learning_rate": 4.992999825982824e-05,
|
| 610 |
+
"loss": 0.1097,
|
| 611 |
+
"step": 2150
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.6152758132956153,
|
| 615 |
+
"grad_norm": 0.4413115084171295,
|
| 616 |
+
"learning_rate": 4.9920463676759975e-05,
|
| 617 |
+
"loss": 0.1081,
|
| 618 |
+
"step": 2175
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6223479490806223,
|
| 622 |
+
"grad_norm": 0.796340823173523,
|
| 623 |
+
"learning_rate": 4.991032157668924e-05,
|
| 624 |
+
"loss": 0.1134,
|
| 625 |
+
"step": 2200
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.6294200848656294,
|
| 629 |
+
"grad_norm": 0.8647779822349548,
|
| 630 |
+
"learning_rate": 4.989957220686257e-05,
|
| 631 |
+
"loss": 0.1169,
|
| 632 |
+
"step": 2225
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.6364922206506365,
|
| 636 |
+
"grad_norm": 0.5049439072608948,
|
| 637 |
+
"learning_rate": 4.988821582933065e-05,
|
| 638 |
+
"loss": 0.1155,
|
| 639 |
+
"step": 2250
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.6435643564356436,
|
| 643 |
+
"grad_norm": 0.5249194502830505,
|
| 644 |
+
"learning_rate": 4.9876252720941974e-05,
|
| 645 |
+
"loss": 0.1076,
|
| 646 |
+
"step": 2275
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.6506364922206507,
|
| 650 |
+
"grad_norm": 0.9044466018676758,
|
| 651 |
+
"learning_rate": 4.986368317333603e-05,
|
| 652 |
+
"loss": 0.1171,
|
| 653 |
+
"step": 2300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.6577086280056577,
|
| 657 |
+
"grad_norm": 0.6795557141304016,
|
| 658 |
+
"learning_rate": 4.985050749293626e-05,
|
| 659 |
+
"loss": 0.1099,
|
| 660 |
+
"step": 2325
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6647807637906648,
|
| 664 |
+
"grad_norm": 0.5548400282859802,
|
| 665 |
+
"learning_rate": 4.983672600094253e-05,
|
| 666 |
+
"loss": 0.1145,
|
| 667 |
+
"step": 2350
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.6718528995756718,
|
| 671 |
+
"grad_norm": 0.8753097057342529,
|
| 672 |
+
"learning_rate": 4.982233903332335e-05,
|
| 673 |
+
"loss": 0.1086,
|
| 674 |
+
"step": 2375
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6789250353606789,
|
| 678 |
+
"grad_norm": 0.7015976309776306,
|
| 679 |
+
"learning_rate": 4.980734694080763e-05,
|
| 680 |
+
"loss": 0.1134,
|
| 681 |
+
"step": 2400
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.685997171145686,
|
| 685 |
+
"grad_norm": 0.3631691336631775,
|
| 686 |
+
"learning_rate": 4.979175008887619e-05,
|
| 687 |
+
"loss": 0.1102,
|
| 688 |
+
"step": 2425
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.693069306930693,
|
| 692 |
+
"grad_norm": 0.512153685092926,
|
| 693 |
+
"learning_rate": 4.977554885775278e-05,
|
| 694 |
+
"loss": 0.1135,
|
| 695 |
+
"step": 2450
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.7001414427157001,
|
| 699 |
+
"grad_norm": 0.62693190574646,
|
| 700 |
+
"learning_rate": 4.975874364239491e-05,
|
| 701 |
+
"loss": 0.1104,
|
| 702 |
+
"step": 2475
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.7072135785007072,
|
| 706 |
+
"grad_norm": 0.8053261637687683,
|
| 707 |
+
"learning_rate": 4.974133485248409e-05,
|
| 708 |
+
"loss": 0.1092,
|
| 709 |
+
"step": 2500
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.7142857142857143,
|
| 713 |
+
"grad_norm": 0.8354981541633606,
|
| 714 |
+
"learning_rate": 4.972332291241597e-05,
|
| 715 |
+
"loss": 0.1155,
|
| 716 |
+
"step": 2525
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.7213578500707214,
|
| 720 |
+
"grad_norm": 1.4328135251998901,
|
| 721 |
+
"learning_rate": 4.97047082612899e-05,
|
| 722 |
+
"loss": 0.1071,
|
| 723 |
+
"step": 2550
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.7284299858557284,
|
| 727 |
+
"grad_norm": 0.5748372077941895,
|
| 728 |
+
"learning_rate": 4.96854913528983e-05,
|
| 729 |
+
"loss": 0.105,
|
| 730 |
+
"step": 2575
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.7355021216407355,
|
| 734 |
+
"grad_norm": 0.5140411257743835,
|
| 735 |
+
"learning_rate": 4.966567265571553e-05,
|
| 736 |
+
"loss": 0.1076,
|
| 737 |
+
"step": 2600
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.7425742574257426,
|
| 741 |
+
"grad_norm": 0.42150813341140747,
|
| 742 |
+
"learning_rate": 4.9645252652886524e-05,
|
| 743 |
+
"loss": 0.1076,
|
| 744 |
+
"step": 2625
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.7496463932107497,
|
| 748 |
+
"grad_norm": 0.7284517288208008,
|
| 749 |
+
"learning_rate": 4.9624231842214966e-05,
|
| 750 |
+
"loss": 0.1147,
|
| 751 |
+
"step": 2650
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.7567185289957568,
|
| 755 |
+
"grad_norm": 0.3435399830341339,
|
| 756 |
+
"learning_rate": 4.960261073615119e-05,
|
| 757 |
+
"loss": 0.117,
|
| 758 |
+
"step": 2675
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.7637906647807637,
|
| 762 |
+
"grad_norm": 0.5726285576820374,
|
| 763 |
+
"learning_rate": 4.9580389861779676e-05,
|
| 764 |
+
"loss": 0.1028,
|
| 765 |
+
"step": 2700
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.7708628005657708,
|
| 769 |
+
"grad_norm": 0.6155900955200195,
|
| 770 |
+
"learning_rate": 4.955756976080619e-05,
|
| 771 |
+
"loss": 0.1059,
|
| 772 |
+
"step": 2725
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.7779349363507779,
|
| 776 |
+
"grad_norm": 0.5489698052406311,
|
| 777 |
+
"learning_rate": 4.95341509895446e-05,
|
| 778 |
+
"loss": 0.1085,
|
| 779 |
+
"step": 2750
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.785007072135785,
|
| 783 |
+
"grad_norm": 0.4485224783420563,
|
| 784 |
+
"learning_rate": 4.951013411890329e-05,
|
| 785 |
+
"loss": 0.1046,
|
| 786 |
+
"step": 2775
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7920792079207921,
|
| 790 |
+
"grad_norm": 1.4330599308013916,
|
| 791 |
+
"learning_rate": 4.9485519734371254e-05,
|
| 792 |
+
"loss": 0.1066,
|
| 793 |
+
"step": 2800
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.7991513437057991,
|
| 797 |
+
"grad_norm": 0.5611838102340698,
|
| 798 |
+
"learning_rate": 4.946030843600382e-05,
|
| 799 |
+
"loss": 0.108,
|
| 800 |
+
"step": 2825
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.8062234794908062,
|
| 804 |
+
"grad_norm": 0.44172587990760803,
|
| 805 |
+
"learning_rate": 4.943450083840804e-05,
|
| 806 |
+
"loss": 0.1115,
|
| 807 |
+
"step": 2850
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.8132956152758133,
|
| 811 |
+
"grad_norm": 0.5805100798606873,
|
| 812 |
+
"learning_rate": 4.940809757072767e-05,
|
| 813 |
+
"loss": 0.1017,
|
| 814 |
+
"step": 2875
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.8203677510608204,
|
| 818 |
+
"grad_norm": 0.42033523321151733,
|
| 819 |
+
"learning_rate": 4.938109927662786e-05,
|
| 820 |
+
"loss": 0.0987,
|
| 821 |
+
"step": 2900
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.8274398868458275,
|
| 825 |
+
"grad_norm": 0.519852876663208,
|
| 826 |
+
"learning_rate": 4.9353506614279465e-05,
|
| 827 |
+
"loss": 0.1085,
|
| 828 |
+
"step": 2925
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.8345120226308345,
|
| 832 |
+
"grad_norm": 0.41062799096107483,
|
| 833 |
+
"learning_rate": 4.932532025634298e-05,
|
| 834 |
+
"loss": 0.1122,
|
| 835 |
+
"step": 2950
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.8415841584158416,
|
| 839 |
+
"grad_norm": 0.4441488981246948,
|
| 840 |
+
"learning_rate": 4.929654088995216e-05,
|
| 841 |
+
"loss": 0.1075,
|
| 842 |
+
"step": 2975
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.8486562942008486,
|
| 846 |
+
"grad_norm": 0.5983813405036926,
|
| 847 |
+
"learning_rate": 4.926716921669724e-05,
|
| 848 |
+
"loss": 0.105,
|
| 849 |
+
"step": 3000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.8557284299858557,
|
| 853 |
+
"grad_norm": 0.4088096022605896,
|
| 854 |
+
"learning_rate": 4.92372059526079e-05,
|
| 855 |
+
"loss": 0.1055,
|
| 856 |
+
"step": 3025
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.8628005657708628,
|
| 860 |
+
"grad_norm": 0.3722389042377472,
|
| 861 |
+
"learning_rate": 4.92066518281357e-05,
|
| 862 |
+
"loss": 0.1016,
|
| 863 |
+
"step": 3050
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.8698727015558698,
|
| 867 |
+
"grad_norm": 0.3515225946903229,
|
| 868 |
+
"learning_rate": 4.9175507588136395e-05,
|
| 869 |
+
"loss": 0.1061,
|
| 870 |
+
"step": 3075
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.8769448373408769,
|
| 874 |
+
"grad_norm": 0.6641696691513062,
|
| 875 |
+
"learning_rate": 4.914377399185167e-05,
|
| 876 |
+
"loss": 0.0976,
|
| 877 |
+
"step": 3100
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.884016973125884,
|
| 881 |
+
"grad_norm": 1.0824599266052246,
|
| 882 |
+
"learning_rate": 4.911145181289072e-05,
|
| 883 |
+
"loss": 0.0993,
|
| 884 |
+
"step": 3125
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.8910891089108911,
|
| 888 |
+
"grad_norm": 0.9281112551689148,
|
| 889 |
+
"learning_rate": 4.90785418392113e-05,
|
| 890 |
+
"loss": 0.1049,
|
| 891 |
+
"step": 3150
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.8981612446958982,
|
| 895 |
+
"grad_norm": 0.6602789163589478,
|
| 896 |
+
"learning_rate": 4.904504487310061e-05,
|
| 897 |
+
"loss": 0.1105,
|
| 898 |
+
"step": 3175
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.9052333804809052,
|
| 902 |
+
"grad_norm": 0.522657036781311,
|
| 903 |
+
"learning_rate": 4.901096173115567e-05,
|
| 904 |
+
"loss": 0.098,
|
| 905 |
+
"step": 3200
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.9123055162659123,
|
| 909 |
+
"grad_norm": 0.38893359899520874,
|
| 910 |
+
"learning_rate": 4.897629324426343e-05,
|
| 911 |
+
"loss": 0.0992,
|
| 912 |
+
"step": 3225
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.9193776520509194,
|
| 916 |
+
"grad_norm": 0.9329886436462402,
|
| 917 |
+
"learning_rate": 4.894104025758054e-05,
|
| 918 |
+
"loss": 0.1048,
|
| 919 |
+
"step": 3250
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.9264497878359265,
|
| 923 |
+
"grad_norm": 0.4844260811805725,
|
| 924 |
+
"learning_rate": 4.890520363051269e-05,
|
| 925 |
+
"loss": 0.1019,
|
| 926 |
+
"step": 3275
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.9335219236209336,
|
| 930 |
+
"grad_norm": 0.39830756187438965,
|
| 931 |
+
"learning_rate": 4.886878423669373e-05,
|
| 932 |
+
"loss": 0.0996,
|
| 933 |
+
"step": 3300
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.9405940594059405,
|
| 937 |
+
"grad_norm": 0.3621814548969269,
|
| 938 |
+
"learning_rate": 4.8831782963964314e-05,
|
| 939 |
+
"loss": 0.0959,
|
| 940 |
+
"step": 3325
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.9476661951909476,
|
| 944 |
+
"grad_norm": 0.43947598338127136,
|
| 945 |
+
"learning_rate": 4.87942007143503e-05,
|
| 946 |
+
"loss": 0.1028,
|
| 947 |
+
"step": 3350
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.9547383309759547,
|
| 951 |
+
"grad_norm": 0.4322707951068878,
|
| 952 |
+
"learning_rate": 4.87560384040407e-05,
|
| 953 |
+
"loss": 0.0957,
|
| 954 |
+
"step": 3375
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.9618104667609618,
|
| 958 |
+
"grad_norm": 0.7152990102767944,
|
| 959 |
+
"learning_rate": 4.8717296963365446e-05,
|
| 960 |
+
"loss": 0.0983,
|
| 961 |
+
"step": 3400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.9688826025459689,
|
| 965 |
+
"grad_norm": 0.36375129222869873,
|
| 966 |
+
"learning_rate": 4.8677977336772576e-05,
|
| 967 |
+
"loss": 0.0986,
|
| 968 |
+
"step": 3425
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.9759547383309759,
|
| 972 |
+
"grad_norm": 0.3541475534439087,
|
| 973 |
+
"learning_rate": 4.8638080482805334e-05,
|
| 974 |
+
"loss": 0.1039,
|
| 975 |
+
"step": 3450
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.983026874115983,
|
| 979 |
+
"grad_norm": 0.5277055501937866,
|
| 980 |
+
"learning_rate": 4.8597607374078734e-05,
|
| 981 |
+
"loss": 0.1009,
|
| 982 |
+
"step": 3475
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.9900990099009901,
|
| 986 |
+
"grad_norm": 0.32760316133499146,
|
| 987 |
+
"learning_rate": 4.855655899725587e-05,
|
| 988 |
+
"loss": 0.0967,
|
| 989 |
+
"step": 3500
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.9971711456859972,
|
| 993 |
+
"grad_norm": 0.4430937170982361,
|
| 994 |
+
"learning_rate": 4.851493635302384e-05,
|
| 995 |
+
"loss": 0.0959,
|
| 996 |
+
"step": 3525
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.0,
|
| 1000 |
+
"eval_accuracy": 0.9641816937160642,
|
| 1001 |
+
"eval_f1": 0.855812468110255,
|
| 1002 |
+
"eval_loss": 0.10302519798278809,
|
| 1003 |
+
"eval_precision": 0.8459347469557771,
|
| 1004 |
+
"eval_recall": 0.8659235929015533,
|
| 1005 |
+
"eval_runtime": 65.6322,
|
| 1006 |
+
"eval_samples_per_second": 765.966,
|
| 1007 |
+
"eval_steps_per_second": 3.002,
|
| 1008 |
+
"step": 3535
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.0042432814710043,
|
| 1012 |
+
"grad_norm": 0.5774176120758057,
|
| 1013 |
+
"learning_rate": 4.8472740456069404e-05,
|
| 1014 |
+
"loss": 0.0883,
|
| 1015 |
+
"step": 3550
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.0113154172560113,
|
| 1019 |
+
"grad_norm": 0.6957634687423706,
|
| 1020 |
+
"learning_rate": 4.842997233505418e-05,
|
| 1021 |
+
"loss": 0.0774,
|
| 1022 |
+
"step": 3575
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.0183875530410185,
|
| 1026 |
+
"grad_norm": 0.3464818000793457,
|
| 1027 |
+
"learning_rate": 4.838663303258961e-05,
|
| 1028 |
+
"loss": 0.0823,
|
| 1029 |
+
"step": 3600
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 1.0254596888260255,
|
| 1033 |
+
"grad_norm": 0.6941576600074768,
|
| 1034 |
+
"learning_rate": 4.8342723605211556e-05,
|
| 1035 |
+
"loss": 0.0826,
|
| 1036 |
+
"step": 3625
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.0325318246110324,
|
| 1040 |
+
"grad_norm": 0.44520071148872375,
|
| 1041 |
+
"learning_rate": 4.829824512335449e-05,
|
| 1042 |
+
"loss": 0.0867,
|
| 1043 |
+
"step": 3650
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.0396039603960396,
|
| 1047 |
+
"grad_norm": 0.3814884126186371,
|
| 1048 |
+
"learning_rate": 4.825319867132545e-05,
|
| 1049 |
+
"loss": 0.0869,
|
| 1050 |
+
"step": 3675
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.0466760961810466,
|
| 1054 |
+
"grad_norm": 0.44684168696403503,
|
| 1055 |
+
"learning_rate": 4.8207585347277574e-05,
|
| 1056 |
+
"loss": 0.0842,
|
| 1057 |
+
"step": 3700
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 1.0537482319660538,
|
| 1061 |
+
"grad_norm": 0.7008658051490784,
|
| 1062 |
+
"learning_rate": 4.816140626318334e-05,
|
| 1063 |
+
"loss": 0.0864,
|
| 1064 |
+
"step": 3725
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.0608203677510608,
|
| 1068 |
+
"grad_norm": 0.45034533739089966,
|
| 1069 |
+
"learning_rate": 4.8114662544807476e-05,
|
| 1070 |
+
"loss": 0.0801,
|
| 1071 |
+
"step": 3750
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.0678925035360678,
|
| 1075 |
+
"grad_norm": 0.6562340259552002,
|
| 1076 |
+
"learning_rate": 4.8067355331679485e-05,
|
| 1077 |
+
"loss": 0.0814,
|
| 1078 |
+
"step": 3775
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.074964639321075,
|
| 1082 |
+
"grad_norm": 0.7696852684020996,
|
| 1083 |
+
"learning_rate": 4.801948577706588e-05,
|
| 1084 |
+
"loss": 0.0837,
|
| 1085 |
+
"step": 3800
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.082036775106082,
|
| 1089 |
+
"grad_norm": 0.38005831837654114,
|
| 1090 |
+
"learning_rate": 4.7971055047942074e-05,
|
| 1091 |
+
"loss": 0.0836,
|
| 1092 |
+
"step": 3825
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.0891089108910892,
|
| 1096 |
+
"grad_norm": 0.5856048464775085,
|
| 1097 |
+
"learning_rate": 4.792206432496392e-05,
|
| 1098 |
+
"loss": 0.0776,
|
| 1099 |
+
"step": 3850
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 1.0961810466760962,
|
| 1103 |
+
"grad_norm": 0.3622016906738281,
|
| 1104 |
+
"learning_rate": 4.787251480243895e-05,
|
| 1105 |
+
"loss": 0.084,
|
| 1106 |
+
"step": 3875
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.1032531824611032,
|
| 1110 |
+
"grad_norm": 0.3826795816421509,
|
| 1111 |
+
"learning_rate": 4.782240768829722e-05,
|
| 1112 |
+
"loss": 0.0822,
|
| 1113 |
+
"step": 3900
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 1.1103253182461104,
|
| 1117 |
+
"grad_norm": 0.4321337938308716,
|
| 1118 |
+
"learning_rate": 4.77717442040619e-05,
|
| 1119 |
+
"loss": 0.0797,
|
| 1120 |
+
"step": 3925
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.1173974540311173,
|
| 1124 |
+
"grad_norm": 0.3895370364189148,
|
| 1125 |
+
"learning_rate": 4.772052558481949e-05,
|
| 1126 |
+
"loss": 0.0808,
|
| 1127 |
+
"step": 3950
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.1244695898161245,
|
| 1131 |
+
"grad_norm": 0.3963691294193268,
|
| 1132 |
+
"learning_rate": 4.766875307918969e-05,
|
| 1133 |
+
"loss": 0.0829,
|
| 1134 |
+
"step": 3975
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.1315417256011315,
|
| 1138 |
+
"grad_norm": 1.1154179573059082,
|
| 1139 |
+
"learning_rate": 4.7616427949294985e-05,
|
| 1140 |
+
"loss": 0.0864,
|
| 1141 |
+
"step": 4000
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 1.1386138613861387,
|
| 1145 |
+
"grad_norm": 0.6903427839279175,
|
| 1146 |
+
"learning_rate": 4.756355147072986e-05,
|
| 1147 |
+
"loss": 0.0816,
|
| 1148 |
+
"step": 4025
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.1456859971711457,
|
| 1152 |
+
"grad_norm": 0.3236379325389862,
|
| 1153 |
+
"learning_rate": 4.751012493252971e-05,
|
| 1154 |
+
"loss": 0.085,
|
| 1155 |
+
"step": 4050
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 1.1527581329561527,
|
| 1159 |
+
"grad_norm": 0.31708064675331116,
|
| 1160 |
+
"learning_rate": 4.745614963713941e-05,
|
| 1161 |
+
"loss": 0.0824,
|
| 1162 |
+
"step": 4075
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.15983026874116,
|
| 1166 |
+
"grad_norm": 0.47363677620887756,
|
| 1167 |
+
"learning_rate": 4.740162690038159e-05,
|
| 1168 |
+
"loss": 0.08,
|
| 1169 |
+
"step": 4100
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 1.166902404526167,
|
| 1173 |
+
"grad_norm": 0.5583330988883972,
|
| 1174 |
+
"learning_rate": 4.7346558051424505e-05,
|
| 1175 |
+
"loss": 0.0864,
|
| 1176 |
+
"step": 4125
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.1739745403111739,
|
| 1180 |
+
"grad_norm": 0.4270670413970947,
|
| 1181 |
+
"learning_rate": 4.729094443274969e-05,
|
| 1182 |
+
"loss": 0.0774,
|
| 1183 |
+
"step": 4150
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 1.181046676096181,
|
| 1187 |
+
"grad_norm": 0.4069669544696808,
|
| 1188 |
+
"learning_rate": 4.7234787400119176e-05,
|
| 1189 |
+
"loss": 0.0856,
|
| 1190 |
+
"step": 4175
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.188118811881188,
|
| 1194 |
+
"grad_norm": 0.3747076988220215,
|
| 1195 |
+
"learning_rate": 4.717808832254251e-05,
|
| 1196 |
+
"loss": 0.09,
|
| 1197 |
+
"step": 4200
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.1951909476661953,
|
| 1201 |
+
"grad_norm": 0.45713725686073303,
|
| 1202 |
+
"learning_rate": 4.71208485822433e-05,
|
| 1203 |
+
"loss": 0.0758,
|
| 1204 |
+
"step": 4225
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.2022630834512023,
|
| 1208 |
+
"grad_norm": 0.41270920634269714,
|
| 1209 |
+
"learning_rate": 4.7063069574625595e-05,
|
| 1210 |
+
"loss": 0.0849,
|
| 1211 |
+
"step": 4250
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 1.2093352192362095,
|
| 1215 |
+
"grad_norm": 0.7367244362831116,
|
| 1216 |
+
"learning_rate": 4.70047527082398e-05,
|
| 1217 |
+
"loss": 0.0938,
|
| 1218 |
+
"step": 4275
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.2164073550212164,
|
| 1222 |
+
"grad_norm": 0.8561830520629883,
|
| 1223 |
+
"learning_rate": 4.6945899404748376e-05,
|
| 1224 |
+
"loss": 0.0822,
|
| 1225 |
+
"step": 4300
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.2234794908062234,
|
| 1229 |
+
"grad_norm": 0.8913972973823547,
|
| 1230 |
+
"learning_rate": 4.6886511098891194e-05,
|
| 1231 |
+
"loss": 0.0898,
|
| 1232 |
+
"step": 4325
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.2305516265912306,
|
| 1236 |
+
"grad_norm": 2.0065510272979736,
|
| 1237 |
+
"learning_rate": 4.682658923845052e-05,
|
| 1238 |
+
"loss": 0.0784,
|
| 1239 |
+
"step": 4350
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.2376237623762376,
|
| 1243 |
+
"grad_norm": 0.36617517471313477,
|
| 1244 |
+
"learning_rate": 4.676613528421575e-05,
|
| 1245 |
+
"loss": 0.0775,
|
| 1246 |
+
"step": 4375
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.2446958981612446,
|
| 1250 |
+
"grad_norm": 0.3758735954761505,
|
| 1251 |
+
"learning_rate": 4.67051507099478e-05,
|
| 1252 |
+
"loss": 0.081,
|
| 1253 |
+
"step": 4400
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.2517680339462518,
|
| 1257 |
+
"grad_norm": 0.4398355782032013,
|
| 1258 |
+
"learning_rate": 4.664363700234312e-05,
|
| 1259 |
+
"loss": 0.0847,
|
| 1260 |
+
"step": 4425
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 1.2588401697312588,
|
| 1264 |
+
"grad_norm": 0.4554755687713623,
|
| 1265 |
+
"learning_rate": 4.658159566099757e-05,
|
| 1266 |
+
"loss": 0.0828,
|
| 1267 |
+
"step": 4450
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 1.265912305516266,
|
| 1271 |
+
"grad_norm": 0.3456956446170807,
|
| 1272 |
+
"learning_rate": 4.651902819836974e-05,
|
| 1273 |
+
"loss": 0.0825,
|
| 1274 |
+
"step": 4475
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.272984441301273,
|
| 1278 |
+
"grad_norm": 0.38322913646698,
|
| 1279 |
+
"learning_rate": 4.645593613974415e-05,
|
| 1280 |
+
"loss": 0.0812,
|
| 1281 |
+
"step": 4500
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.2800565770862802,
|
| 1285 |
+
"grad_norm": 0.5935035943984985,
|
| 1286 |
+
"learning_rate": 4.639232102319403e-05,
|
| 1287 |
+
"loss": 0.0813,
|
| 1288 |
+
"step": 4525
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.2871287128712872,
|
| 1292 |
+
"grad_norm": 0.39350178837776184,
|
| 1293 |
+
"learning_rate": 4.632818439954386e-05,
|
| 1294 |
+
"loss": 0.0828,
|
| 1295 |
+
"step": 4550
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.2942008486562941,
|
| 1299 |
+
"grad_norm": 0.36052772402763367,
|
| 1300 |
+
"learning_rate": 4.626352783233154e-05,
|
| 1301 |
+
"loss": 0.0826,
|
| 1302 |
+
"step": 4575
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 1.3012729844413014,
|
| 1306 |
+
"grad_norm": 0.3978725075721741,
|
| 1307 |
+
"learning_rate": 4.619835289777027e-05,
|
| 1308 |
+
"loss": 0.0831,
|
| 1309 |
+
"step": 4600
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 1.3083451202263083,
|
| 1313 |
+
"grad_norm": 0.4236008822917938,
|
| 1314 |
+
"learning_rate": 4.6132661184710137e-05,
|
| 1315 |
+
"loss": 0.0895,
|
| 1316 |
+
"step": 4625
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 1.3154172560113153,
|
| 1320 |
+
"grad_norm": 0.4994755983352661,
|
| 1321 |
+
"learning_rate": 4.606645429459937e-05,
|
| 1322 |
+
"loss": 0.0882,
|
| 1323 |
+
"step": 4650
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 1.3224893917963225,
|
| 1327 |
+
"grad_norm": 1.0472633838653564,
|
| 1328 |
+
"learning_rate": 4.5999733841445325e-05,
|
| 1329 |
+
"loss": 0.0751,
|
| 1330 |
+
"step": 4675
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.3295615275813295,
|
| 1334 |
+
"grad_norm": 0.29904720187187195,
|
| 1335 |
+
"learning_rate": 4.593250145177511e-05,
|
| 1336 |
+
"loss": 0.0859,
|
| 1337 |
+
"step": 4700
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.3366336633663367,
|
| 1341 |
+
"grad_norm": 0.3832816779613495,
|
| 1342 |
+
"learning_rate": 4.5864758764595927e-05,
|
| 1343 |
+
"loss": 0.0785,
|
| 1344 |
+
"step": 4725
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.3437057991513437,
|
| 1348 |
+
"grad_norm": 0.49846336245536804,
|
| 1349 |
+
"learning_rate": 4.5796507431355174e-05,
|
| 1350 |
+
"loss": 0.075,
|
| 1351 |
+
"step": 4750
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 1.350777934936351,
|
| 1355 |
+
"grad_norm": 0.379282146692276,
|
| 1356 |
+
"learning_rate": 4.5727749115900094e-05,
|
| 1357 |
+
"loss": 0.0858,
|
| 1358 |
+
"step": 4775
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.3578500707213579,
|
| 1362 |
+
"grad_norm": 0.5583311915397644,
|
| 1363 |
+
"learning_rate": 4.56584854944373e-05,
|
| 1364 |
+
"loss": 0.0951,
|
| 1365 |
+
"step": 4800
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 1.3649222065063649,
|
| 1369 |
+
"grad_norm": 0.48655304312705994,
|
| 1370 |
+
"learning_rate": 4.5588718255491865e-05,
|
| 1371 |
+
"loss": 0.0884,
|
| 1372 |
+
"step": 4825
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 1.371994342291372,
|
| 1376 |
+
"grad_norm": 0.6549155116081238,
|
| 1377 |
+
"learning_rate": 4.5518449099866155e-05,
|
| 1378 |
+
"loss": 0.0858,
|
| 1379 |
+
"step": 4850
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.379066478076379,
|
| 1383 |
+
"grad_norm": 0.3174663186073303,
|
| 1384 |
+
"learning_rate": 4.5447679740598403e-05,
|
| 1385 |
+
"loss": 0.0837,
|
| 1386 |
+
"step": 4875
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.386138613861386,
|
| 1390 |
+
"grad_norm": 0.36421680450439453,
|
| 1391 |
+
"learning_rate": 4.537641190292091e-05,
|
| 1392 |
+
"loss": 0.0841,
|
| 1393 |
+
"step": 4900
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.3932107496463932,
|
| 1397 |
+
"grad_norm": 0.3484024107456207,
|
| 1398 |
+
"learning_rate": 4.530464732421801e-05,
|
| 1399 |
+
"loss": 0.0886,
|
| 1400 |
+
"step": 4925
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.4002828854314002,
|
| 1404 |
+
"grad_norm": 0.7408681511878967,
|
| 1405 |
+
"learning_rate": 4.523238775398371e-05,
|
| 1406 |
+
"loss": 0.0813,
|
| 1407 |
+
"step": 4950
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 1.4073550212164074,
|
| 1411 |
+
"grad_norm": 0.35419762134552,
|
| 1412 |
+
"learning_rate": 4.515963495377902e-05,
|
| 1413 |
+
"loss": 0.0768,
|
| 1414 |
+
"step": 4975
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 1.4144271570014144,
|
| 1418 |
+
"grad_norm": 0.3253655731678009,
|
| 1419 |
+
"learning_rate": 4.508639069718904e-05,
|
| 1420 |
+
"loss": 0.0776,
|
| 1421 |
+
"step": 5000
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 1.4214992927864216,
|
| 1425 |
+
"grad_norm": 0.3978010416030884,
|
| 1426 |
+
"learning_rate": 4.501265676977974e-05,
|
| 1427 |
+
"loss": 0.077,
|
| 1428 |
+
"step": 5025
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.4285714285714286,
|
| 1432 |
+
"grad_norm": 0.2976684868335724,
|
| 1433 |
+
"learning_rate": 4.493843496905434e-05,
|
| 1434 |
+
"loss": 0.0727,
|
| 1435 |
+
"step": 5050
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.4356435643564356,
|
| 1439 |
+
"grad_norm": 0.3433378040790558,
|
| 1440 |
+
"learning_rate": 4.486372710440961e-05,
|
| 1441 |
+
"loss": 0.0804,
|
| 1442 |
+
"step": 5075
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.4427157001414428,
|
| 1446 |
+
"grad_norm": 0.5507691502571106,
|
| 1447 |
+
"learning_rate": 4.478853499709167e-05,
|
| 1448 |
+
"loss": 0.0852,
|
| 1449 |
+
"step": 5100
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.4497878359264498,
|
| 1453 |
+
"grad_norm": 0.36808139085769653,
|
| 1454 |
+
"learning_rate": 4.471286048015163e-05,
|
| 1455 |
+
"loss": 0.0832,
|
| 1456 |
+
"step": 5125
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.4568599717114568,
|
| 1460 |
+
"grad_norm": 0.3539692163467407,
|
| 1461 |
+
"learning_rate": 4.46367053984009e-05,
|
| 1462 |
+
"loss": 0.0817,
|
| 1463 |
+
"step": 5150
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.463932107496464,
|
| 1467 |
+
"grad_norm": 0.8253048658370972,
|
| 1468 |
+
"learning_rate": 4.4560071608366216e-05,
|
| 1469 |
+
"loss": 0.0826,
|
| 1470 |
+
"step": 5175
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.471004243281471,
|
| 1474 |
+
"grad_norm": 0.4476601779460907,
|
| 1475 |
+
"learning_rate": 4.448296097824437e-05,
|
| 1476 |
+
"loss": 0.088,
|
| 1477 |
+
"step": 5200
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.4780763790664782,
|
| 1481 |
+
"grad_norm": 1.5917980670928955,
|
| 1482 |
+
"learning_rate": 4.440537538785668e-05,
|
| 1483 |
+
"loss": 0.0828,
|
| 1484 |
+
"step": 5225
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.4851485148514851,
|
| 1488 |
+
"grad_norm": 0.6799459457397461,
|
| 1489 |
+
"learning_rate": 4.432731672860316e-05,
|
| 1490 |
+
"loss": 0.0786,
|
| 1491 |
+
"step": 5250
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.4922206506364923,
|
| 1495 |
+
"grad_norm": 0.34660467505455017,
|
| 1496 |
+
"learning_rate": 4.424878690341642e-05,
|
| 1497 |
+
"loss": 0.0749,
|
| 1498 |
+
"step": 5275
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.4992927864214993,
|
| 1502 |
+
"grad_norm": 0.45074212551116943,
|
| 1503 |
+
"learning_rate": 4.4169787826715225e-05,
|
| 1504 |
+
"loss": 0.0904,
|
| 1505 |
+
"step": 5300
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.5063649222065063,
|
| 1509 |
+
"grad_norm": 0.41240620613098145,
|
| 1510 |
+
"learning_rate": 4.4090321424357914e-05,
|
| 1511 |
+
"loss": 0.078,
|
| 1512 |
+
"step": 5325
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.5134370579915135,
|
| 1516 |
+
"grad_norm": 0.3282380998134613,
|
| 1517 |
+
"learning_rate": 4.401038963359538e-05,
|
| 1518 |
+
"loss": 0.0835,
|
| 1519 |
+
"step": 5350
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.5205091937765205,
|
| 1523 |
+
"grad_norm": 0.3657848536968231,
|
| 1524 |
+
"learning_rate": 4.3929994403023865e-05,
|
| 1525 |
+
"loss": 0.0801,
|
| 1526 |
+
"step": 5375
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.5275813295615275,
|
| 1530 |
+
"grad_norm": 0.3543812930583954,
|
| 1531 |
+
"learning_rate": 4.384913769253746e-05,
|
| 1532 |
+
"loss": 0.081,
|
| 1533 |
+
"step": 5400
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.5346534653465347,
|
| 1537 |
+
"grad_norm": 0.8204165697097778,
|
| 1538 |
+
"learning_rate": 4.376782147328031e-05,
|
| 1539 |
+
"loss": 0.0757,
|
| 1540 |
+
"step": 5425
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 1.541725601131542,
|
| 1544 |
+
"grad_norm": 0.4716034233570099,
|
| 1545 |
+
"learning_rate": 4.368604772759861e-05,
|
| 1546 |
+
"loss": 0.0818,
|
| 1547 |
+
"step": 5450
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 1.5487977369165487,
|
| 1551 |
+
"grad_norm": 0.3865686357021332,
|
| 1552 |
+
"learning_rate": 4.360381844899221e-05,
|
| 1553 |
+
"loss": 0.076,
|
| 1554 |
+
"step": 5475
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.5558698727015559,
|
| 1558 |
+
"grad_norm": 0.5982063412666321,
|
| 1559 |
+
"learning_rate": 4.352113564206606e-05,
|
| 1560 |
+
"loss": 0.0861,
|
| 1561 |
+
"step": 5500
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.562942008486563,
|
| 1565 |
+
"grad_norm": 0.4285977780818939,
|
| 1566 |
+
"learning_rate": 4.343800132248132e-05,
|
| 1567 |
+
"loss": 0.0767,
|
| 1568 |
+
"step": 5525
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.57001414427157,
|
| 1572 |
+
"grad_norm": 0.542254626750946,
|
| 1573 |
+
"learning_rate": 4.3354417516906274e-05,
|
| 1574 |
+
"loss": 0.0814,
|
| 1575 |
+
"step": 5550
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 1.577086280056577,
|
| 1579 |
+
"grad_norm": 0.273899644613266,
|
| 1580 |
+
"learning_rate": 4.327038626296682e-05,
|
| 1581 |
+
"loss": 0.0759,
|
| 1582 |
+
"step": 5575
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 1.5841584158415842,
|
| 1586 |
+
"grad_norm": 0.3528795540332794,
|
| 1587 |
+
"learning_rate": 4.318590960919692e-05,
|
| 1588 |
+
"loss": 0.0785,
|
| 1589 |
+
"step": 5600
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 1.5912305516265912,
|
| 1593 |
+
"grad_norm": 0.4583662748336792,
|
| 1594 |
+
"learning_rate": 4.3100989614988566e-05,
|
| 1595 |
+
"loss": 0.0831,
|
| 1596 |
+
"step": 5625
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 1.5983026874115982,
|
| 1600 |
+
"grad_norm": 0.4005572497844696,
|
| 1601 |
+
"learning_rate": 4.3015628350541595e-05,
|
| 1602 |
+
"loss": 0.0781,
|
| 1603 |
+
"step": 5650
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 1.6053748231966054,
|
| 1607 |
+
"grad_norm": 0.3729841411113739,
|
| 1608 |
+
"learning_rate": 4.2929827896813274e-05,
|
| 1609 |
+
"loss": 0.0849,
|
| 1610 |
+
"step": 5675
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.6124469589816126,
|
| 1614 |
+
"grad_norm": 0.37740039825439453,
|
| 1615 |
+
"learning_rate": 4.284359034546751e-05,
|
| 1616 |
+
"loss": 0.0819,
|
| 1617 |
+
"step": 5700
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.6195190947666194,
|
| 1621 |
+
"grad_norm": 0.45638662576675415,
|
| 1622 |
+
"learning_rate": 4.2756917798823874e-05,
|
| 1623 |
+
"loss": 0.0749,
|
| 1624 |
+
"step": 5725
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 1.6265912305516266,
|
| 1628 |
+
"grad_norm": 0.3588665723800659,
|
| 1629 |
+
"learning_rate": 4.2669812369806374e-05,
|
| 1630 |
+
"loss": 0.0715,
|
| 1631 |
+
"step": 5750
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 1.6336633663366338,
|
| 1635 |
+
"grad_norm": 0.3274244964122772,
|
| 1636 |
+
"learning_rate": 4.258227618189191e-05,
|
| 1637 |
+
"loss": 0.0707,
|
| 1638 |
+
"step": 5775
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 1.6407355021216408,
|
| 1642 |
+
"grad_norm": 0.36558204889297485,
|
| 1643 |
+
"learning_rate": 4.249431136905853e-05,
|
| 1644 |
+
"loss": 0.0732,
|
| 1645 |
+
"step": 5800
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 1.6478076379066477,
|
| 1649 |
+
"grad_norm": 0.32020628452301025,
|
| 1650 |
+
"learning_rate": 4.240592007573341e-05,
|
| 1651 |
+
"loss": 0.0787,
|
| 1652 |
+
"step": 5825
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 1.654879773691655,
|
| 1656 |
+
"grad_norm": 0.4697955846786499,
|
| 1657 |
+
"learning_rate": 4.231710445674056e-05,
|
| 1658 |
+
"loss": 0.0707,
|
| 1659 |
+
"step": 5850
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.661951909476662,
|
| 1663 |
+
"grad_norm": 0.3986113965511322,
|
| 1664 |
+
"learning_rate": 4.222786667724832e-05,
|
| 1665 |
+
"loss": 0.0746,
|
| 1666 |
+
"step": 5875
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.669024045261669,
|
| 1670 |
+
"grad_norm": 0.35733580589294434,
|
| 1671 |
+
"learning_rate": 4.213820891271652e-05,
|
| 1672 |
+
"loss": 0.0787,
|
| 1673 |
+
"step": 5900
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.6760961810466761,
|
| 1677 |
+
"grad_norm": 0.6812814474105835,
|
| 1678 |
+
"learning_rate": 4.204813334884353e-05,
|
| 1679 |
+
"loss": 0.0921,
|
| 1680 |
+
"step": 5925
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.6831683168316833,
|
| 1684 |
+
"grad_norm": 0.3964853584766388,
|
| 1685 |
+
"learning_rate": 4.19576421815129e-05,
|
| 1686 |
+
"loss": 0.0786,
|
| 1687 |
+
"step": 5950
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 1.69024045261669,
|
| 1691 |
+
"grad_norm": 0.4422667324542999,
|
| 1692 |
+
"learning_rate": 4.186673761673989e-05,
|
| 1693 |
+
"loss": 0.0752,
|
| 1694 |
+
"step": 5975
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 1.6973125884016973,
|
| 1698 |
+
"grad_norm": 0.5387901663780212,
|
| 1699 |
+
"learning_rate": 4.177542187061763e-05,
|
| 1700 |
+
"loss": 0.0829,
|
| 1701 |
+
"step": 6000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.7043847241867045,
|
| 1705 |
+
"grad_norm": 0.30730950832366943,
|
| 1706 |
+
"learning_rate": 4.168369716926315e-05,
|
| 1707 |
+
"loss": 0.0782,
|
| 1708 |
+
"step": 6025
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.7114568599717115,
|
| 1712 |
+
"grad_norm": 0.3543797731399536,
|
| 1713 |
+
"learning_rate": 4.159156574876306e-05,
|
| 1714 |
+
"loss": 0.0842,
|
| 1715 |
+
"step": 6050
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.7185289957567185,
|
| 1719 |
+
"grad_norm": 0.44837215542793274,
|
| 1720 |
+
"learning_rate": 4.1499029855119106e-05,
|
| 1721 |
+
"loss": 0.0754,
|
| 1722 |
+
"step": 6075
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.7256011315417257,
|
| 1726 |
+
"grad_norm": 0.4181993007659912,
|
| 1727 |
+
"learning_rate": 4.1406091744193354e-05,
|
| 1728 |
+
"loss": 0.0833,
|
| 1729 |
+
"step": 6100
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.7326732673267327,
|
| 1733 |
+
"grad_norm": 0.47836604714393616,
|
| 1734 |
+
"learning_rate": 4.1312753681653213e-05,
|
| 1735 |
+
"loss": 0.0819,
|
| 1736 |
+
"step": 6125
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.7397454031117396,
|
| 1740 |
+
"grad_norm": 0.42279157042503357,
|
| 1741 |
+
"learning_rate": 4.121901794291622e-05,
|
| 1742 |
+
"loss": 0.0748,
|
| 1743 |
+
"step": 6150
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.7468175388967468,
|
| 1747 |
+
"grad_norm": 0.40630263090133667,
|
| 1748 |
+
"learning_rate": 4.112488681309455e-05,
|
| 1749 |
+
"loss": 0.0812,
|
| 1750 |
+
"step": 6175
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.753889674681754,
|
| 1754 |
+
"grad_norm": 0.414064884185791,
|
| 1755 |
+
"learning_rate": 4.103036258693932e-05,
|
| 1756 |
+
"loss": 0.0815,
|
| 1757 |
+
"step": 6200
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.7609618104667608,
|
| 1761 |
+
"grad_norm": 0.3953958749771118,
|
| 1762 |
+
"learning_rate": 4.0935447568784646e-05,
|
| 1763 |
+
"loss": 0.0839,
|
| 1764 |
+
"step": 6225
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.768033946251768,
|
| 1768 |
+
"grad_norm": 0.4421181082725525,
|
| 1769 |
+
"learning_rate": 4.084014407249145e-05,
|
| 1770 |
+
"loss": 0.0784,
|
| 1771 |
+
"step": 6250
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.7751060820367752,
|
| 1775 |
+
"grad_norm": 0.6101165413856506,
|
| 1776 |
+
"learning_rate": 4.0744454421391095e-05,
|
| 1777 |
+
"loss": 0.084,
|
| 1778 |
+
"step": 6275
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.7821782178217822,
|
| 1782 |
+
"grad_norm": 0.8179222941398621,
|
| 1783 |
+
"learning_rate": 4.064838094822868e-05,
|
| 1784 |
+
"loss": 0.0792,
|
| 1785 |
+
"step": 6300
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 1.7892503536067892,
|
| 1789 |
+
"grad_norm": 0.40432754158973694,
|
| 1790 |
+
"learning_rate": 4.055192599510624e-05,
|
| 1791 |
+
"loss": 0.0769,
|
| 1792 |
+
"step": 6325
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 1.7963224893917964,
|
| 1796 |
+
"grad_norm": 0.36589494347572327,
|
| 1797 |
+
"learning_rate": 4.0455091913425606e-05,
|
| 1798 |
+
"loss": 0.0783,
|
| 1799 |
+
"step": 6350
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 1.8033946251768034,
|
| 1803 |
+
"grad_norm": 0.3545513451099396,
|
| 1804 |
+
"learning_rate": 4.0357881063831105e-05,
|
| 1805 |
+
"loss": 0.0723,
|
| 1806 |
+
"step": 6375
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 1.8104667609618104,
|
| 1810 |
+
"grad_norm": 0.5380228161811829,
|
| 1811 |
+
"learning_rate": 4.026029581615198e-05,
|
| 1812 |
+
"loss": 0.0771,
|
| 1813 |
+
"step": 6400
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 1.8175388967468176,
|
| 1817 |
+
"grad_norm": 0.6094365119934082,
|
| 1818 |
+
"learning_rate": 4.016233854934468e-05,
|
| 1819 |
+
"loss": 0.084,
|
| 1820 |
+
"step": 6425
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 1.8246110325318248,
|
| 1824 |
+
"grad_norm": 0.6324317455291748,
|
| 1825 |
+
"learning_rate": 4.0064011651434776e-05,
|
| 1826 |
+
"loss": 0.0794,
|
| 1827 |
+
"step": 6450
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.8316831683168315,
|
| 1831 |
+
"grad_norm": 0.2819110155105591,
|
| 1832 |
+
"learning_rate": 3.996531751945883e-05,
|
| 1833 |
+
"loss": 0.0853,
|
| 1834 |
+
"step": 6475
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.8387553041018387,
|
| 1838 |
+
"grad_norm": 0.3535131514072418,
|
| 1839 |
+
"learning_rate": 3.986625855940591e-05,
|
| 1840 |
+
"loss": 0.0712,
|
| 1841 |
+
"step": 6500
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 1.845827439886846,
|
| 1845 |
+
"grad_norm": 0.32027262449264526,
|
| 1846 |
+
"learning_rate": 3.9766837186158944e-05,
|
| 1847 |
+
"loss": 0.0751,
|
| 1848 |
+
"step": 6525
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 1.852899575671853,
|
| 1852 |
+
"grad_norm": 0.4550008475780487,
|
| 1853 |
+
"learning_rate": 3.9667055823435885e-05,
|
| 1854 |
+
"loss": 0.0744,
|
| 1855 |
+
"step": 6550
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 1.85997171145686,
|
| 1859 |
+
"grad_norm": 0.30715903639793396,
|
| 1860 |
+
"learning_rate": 3.956691690373055e-05,
|
| 1861 |
+
"loss": 0.0745,
|
| 1862 |
+
"step": 6575
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 1.8670438472418671,
|
| 1866 |
+
"grad_norm": 0.5177515745162964,
|
| 1867 |
+
"learning_rate": 3.946642286825339e-05,
|
| 1868 |
+
"loss": 0.0715,
|
| 1869 |
+
"step": 6600
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.874115983026874,
|
| 1873 |
+
"grad_norm": 0.5210005640983582,
|
| 1874 |
+
"learning_rate": 3.9365576166871964e-05,
|
| 1875 |
+
"loss": 0.0696,
|
| 1876 |
+
"step": 6625
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 1.881188118811881,
|
| 1880 |
+
"grad_norm": 0.28931137919425964,
|
| 1881 |
+
"learning_rate": 3.926437925805118e-05,
|
| 1882 |
+
"loss": 0.0749,
|
| 1883 |
+
"step": 6650
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 1.8882602545968883,
|
| 1887 |
+
"grad_norm": 0.5680564641952515,
|
| 1888 |
+
"learning_rate": 3.916283460879341e-05,
|
| 1889 |
+
"loss": 0.074,
|
| 1890 |
+
"step": 6675
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.8953323903818955,
|
| 1894 |
+
"grad_norm": 0.44310295581817627,
|
| 1895 |
+
"learning_rate": 3.90609446945783e-05,
|
| 1896 |
+
"loss": 0.0805,
|
| 1897 |
+
"step": 6700
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 1.9024045261669023,
|
| 1901 |
+
"grad_norm": 0.6425299644470215,
|
| 1902 |
+
"learning_rate": 3.8958711999302475e-05,
|
| 1903 |
+
"loss": 0.0842,
|
| 1904 |
+
"step": 6725
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 1.9094766619519095,
|
| 1908 |
+
"grad_norm": 0.300752729177475,
|
| 1909 |
+
"learning_rate": 3.885613901521893e-05,
|
| 1910 |
+
"loss": 0.0698,
|
| 1911 |
+
"step": 6750
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 1.9165487977369167,
|
| 1915 |
+
"grad_norm": 0.43727684020996094,
|
| 1916 |
+
"learning_rate": 3.875322824287633e-05,
|
| 1917 |
+
"loss": 0.0767,
|
| 1918 |
+
"step": 6775
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 1.9236209335219236,
|
| 1922 |
+
"grad_norm": 0.41746985912323,
|
| 1923 |
+
"learning_rate": 3.8649982191058e-05,
|
| 1924 |
+
"loss": 0.0795,
|
| 1925 |
+
"step": 6800
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 1.9306930693069306,
|
| 1929 |
+
"grad_norm": 0.35224172472953796,
|
| 1930 |
+
"learning_rate": 3.8546403376720786e-05,
|
| 1931 |
+
"loss": 0.0765,
|
| 1932 |
+
"step": 6825
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 1.9377652050919378,
|
| 1936 |
+
"grad_norm": 0.295906662940979,
|
| 1937 |
+
"learning_rate": 3.8442494324933724e-05,
|
| 1938 |
+
"loss": 0.076,
|
| 1939 |
+
"step": 6850
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.9448373408769448,
|
| 1943 |
+
"grad_norm": 0.2558325529098511,
|
| 1944 |
+
"learning_rate": 3.833825756881645e-05,
|
| 1945 |
+
"loss": 0.0807,
|
| 1946 |
+
"step": 6875
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.9519094766619518,
|
| 1950 |
+
"grad_norm": 0.3434934616088867,
|
| 1951 |
+
"learning_rate": 3.8233695649477426e-05,
|
| 1952 |
+
"loss": 0.0686,
|
| 1953 |
+
"step": 6900
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.958981612446959,
|
| 1957 |
+
"grad_norm": 0.23843282461166382,
|
| 1958 |
+
"learning_rate": 3.8128811115952044e-05,
|
| 1959 |
+
"loss": 0.0795,
|
| 1960 |
+
"step": 6925
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.9660537482319662,
|
| 1964 |
+
"grad_norm": 0.7551613450050354,
|
| 1965 |
+
"learning_rate": 3.802360652514047e-05,
|
| 1966 |
+
"loss": 0.0681,
|
| 1967 |
+
"step": 6950
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.973125884016973,
|
| 1971 |
+
"grad_norm": 0.4647892713546753,
|
| 1972 |
+
"learning_rate": 3.7918084441745275e-05,
|
| 1973 |
+
"loss": 0.0798,
|
| 1974 |
+
"step": 6975
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.9801980198019802,
|
| 1978 |
+
"grad_norm": 0.3910640478134155,
|
| 1979 |
+
"learning_rate": 3.781224743820897e-05,
|
| 1980 |
+
"loss": 0.077,
|
| 1981 |
+
"step": 7000
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.9872701555869874,
|
| 1985 |
+
"grad_norm": 0.3788031339645386,
|
| 1986 |
+
"learning_rate": 3.770609809465124e-05,
|
| 1987 |
+
"loss": 0.0805,
|
| 1988 |
+
"step": 7025
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.9943422913719944,
|
| 1992 |
+
"grad_norm": 0.6797524690628052,
|
| 1993 |
+
"learning_rate": 3.759963899880609e-05,
|
| 1994 |
+
"loss": 0.0726,
|
| 1995 |
+
"step": 7050
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 2.0,
|
| 1999 |
+
"eval_accuracy": 0.9707863671603164,
|
| 2000 |
+
"eval_f1": 0.8914057811793163,
|
| 2001 |
+
"eval_loss": 0.08405517786741257,
|
| 2002 |
+
"eval_precision": 0.8863308401537767,
|
| 2003 |
+
"eval_recall": 0.8965391729373575,
|
| 2004 |
+
"eval_runtime": 54.724,
|
| 2005 |
+
"eval_samples_per_second": 918.646,
|
| 2006 |
+
"eval_steps_per_second": 3.6,
|
| 2007 |
+
"step": 7070
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 2.0014144271570014,
|
| 2011 |
+
"grad_norm": 0.22099077701568604,
|
| 2012 |
+
"learning_rate": 3.749287274595872e-05,
|
| 2013 |
+
"loss": 0.0755,
|
| 2014 |
+
"step": 7075
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 2.0084865629420086,
|
| 2018 |
+
"grad_norm": 0.4921034872531891,
|
| 2019 |
+
"learning_rate": 3.738580193888228e-05,
|
| 2020 |
+
"loss": 0.0501,
|
| 2021 |
+
"step": 7100
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 2.0155586987270158,
|
| 2025 |
+
"grad_norm": 0.23433761298656464,
|
| 2026 |
+
"learning_rate": 3.7278429187774436e-05,
|
| 2027 |
+
"loss": 0.0501,
|
| 2028 |
+
"step": 7125
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 2.0226308345120225,
|
| 2032 |
+
"grad_norm": 0.4263274371623993,
|
| 2033 |
+
"learning_rate": 3.7170757110193697e-05,
|
| 2034 |
+
"loss": 0.0513,
|
| 2035 |
+
"step": 7150
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 2.0297029702970297,
|
| 2039 |
+
"grad_norm": 0.2480274736881256,
|
| 2040 |
+
"learning_rate": 3.7062788330995635e-05,
|
| 2041 |
+
"loss": 0.0509,
|
| 2042 |
+
"step": 7175
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 2.036775106082037,
|
| 2046 |
+
"grad_norm": 0.5820468664169312,
|
| 2047 |
+
"learning_rate": 3.695452548226887e-05,
|
| 2048 |
+
"loss": 0.0573,
|
| 2049 |
+
"step": 7200
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 2.0438472418670437,
|
| 2053 |
+
"grad_norm": 0.42300423979759216,
|
| 2054 |
+
"learning_rate": 3.684597120327094e-05,
|
| 2055 |
+
"loss": 0.0558,
|
| 2056 |
+
"step": 7225
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 2.050919377652051,
|
| 2060 |
+
"grad_norm": 0.41470280289649963,
|
| 2061 |
+
"learning_rate": 3.673712814036392e-05,
|
| 2062 |
+
"loss": 0.0519,
|
| 2063 |
+
"step": 7250
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 2.057991513437058,
|
| 2067 |
+
"grad_norm": 0.2917075753211975,
|
| 2068 |
+
"learning_rate": 3.662799894694995e-05,
|
| 2069 |
+
"loss": 0.0518,
|
| 2070 |
+
"step": 7275
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 2.065063649222065,
|
| 2074 |
+
"grad_norm": 0.41207775473594666,
|
| 2075 |
+
"learning_rate": 3.651858628340649e-05,
|
| 2076 |
+
"loss": 0.0474,
|
| 2077 |
+
"step": 7300
|
| 2078 |
+
},
|
| 2079 |
+
{
|
| 2080 |
+
"epoch": 2.072135785007072,
|
| 2081 |
+
"grad_norm": 0.31983888149261475,
|
| 2082 |
+
"learning_rate": 3.640889281702155e-05,
|
| 2083 |
+
"loss": 0.0583,
|
| 2084 |
+
"step": 7325
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 2.0792079207920793,
|
| 2088 |
+
"grad_norm": 0.65561842918396,
|
| 2089 |
+
"learning_rate": 3.629892122192859e-05,
|
| 2090 |
+
"loss": 0.057,
|
| 2091 |
+
"step": 7350
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 2.0862800565770865,
|
| 2095 |
+
"grad_norm": 1.253188133239746,
|
| 2096 |
+
"learning_rate": 3.6188674179041356e-05,
|
| 2097 |
+
"loss": 0.0524,
|
| 2098 |
+
"step": 7375
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 2.0933521923620932,
|
| 2102 |
+
"grad_norm": 0.34525951743125916,
|
| 2103 |
+
"learning_rate": 3.607815437598853e-05,
|
| 2104 |
+
"loss": 0.0577,
|
| 2105 |
+
"step": 7400
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 2.1004243281471005,
|
| 2109 |
+
"grad_norm": 0.5648230910301208,
|
| 2110 |
+
"learning_rate": 3.5967364507048226e-05,
|
| 2111 |
+
"loss": 0.0564,
|
| 2112 |
+
"step": 7425
|
| 2113 |
+
},
|
| 2114 |
+
{
|
| 2115 |
+
"epoch": 2.1074964639321077,
|
| 2116 |
+
"grad_norm": 0.2504655420780182,
|
| 2117 |
+
"learning_rate": 3.585630727308227e-05,
|
| 2118 |
+
"loss": 0.0476,
|
| 2119 |
+
"step": 7450
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 2.1145685997171144,
|
| 2123 |
+
"grad_norm": 0.3219181299209595,
|
| 2124 |
+
"learning_rate": 3.574498538147035e-05,
|
| 2125 |
+
"loss": 0.0538,
|
| 2126 |
+
"step": 7475
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 2.1216407355021216,
|
| 2130 |
+
"grad_norm": 0.36033445596694946,
|
| 2131 |
+
"learning_rate": 3.563340154604411e-05,
|
| 2132 |
+
"loss": 0.0576,
|
| 2133 |
+
"step": 7500
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 2.128712871287129,
|
| 2137 |
+
"grad_norm": 0.3835320472717285,
|
| 2138 |
+
"learning_rate": 3.552155848702086e-05,
|
| 2139 |
+
"loss": 0.0529,
|
| 2140 |
+
"step": 7525
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 2.1357850070721356,
|
| 2144 |
+
"grad_norm": 0.40226078033447266,
|
| 2145 |
+
"learning_rate": 3.5409458930937346e-05,
|
| 2146 |
+
"loss": 0.0507,
|
| 2147 |
+
"step": 7550
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 2.142857142857143,
|
| 2151 |
+
"grad_norm": 0.34018775820732117,
|
| 2152 |
+
"learning_rate": 3.5297105610583265e-05,
|
| 2153 |
+
"loss": 0.0514,
|
| 2154 |
+
"step": 7575
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 2.14992927864215,
|
| 2158 |
+
"grad_norm": 0.7404220700263977,
|
| 2159 |
+
"learning_rate": 3.518450126493464e-05,
|
| 2160 |
+
"loss": 0.0511,
|
| 2161 |
+
"step": 7600
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 2.157001414427157,
|
| 2165 |
+
"grad_norm": 0.2098894715309143,
|
| 2166 |
+
"learning_rate": 3.507164863908704e-05,
|
| 2167 |
+
"loss": 0.0543,
|
| 2168 |
+
"step": 7625
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 2.164073550212164,
|
| 2172 |
+
"grad_norm": 0.43998876214027405,
|
| 2173 |
+
"learning_rate": 3.4958550484188675e-05,
|
| 2174 |
+
"loss": 0.0547,
|
| 2175 |
+
"step": 7650
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 2.171145685997171,
|
| 2179 |
+
"grad_norm": 0.32174915075302124,
|
| 2180 |
+
"learning_rate": 3.4845209557373315e-05,
|
| 2181 |
+
"loss": 0.0528,
|
| 2182 |
+
"step": 7675
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 2.1782178217821784,
|
| 2186 |
+
"grad_norm": 0.8568967580795288,
|
| 2187 |
+
"learning_rate": 3.4731628621693094e-05,
|
| 2188 |
+
"loss": 0.0511,
|
| 2189 |
+
"step": 7700
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 2.185289957567185,
|
| 2193 |
+
"grad_norm": 0.39218711853027344,
|
| 2194 |
+
"learning_rate": 3.461781044605112e-05,
|
| 2195 |
+
"loss": 0.0556,
|
| 2196 |
+
"step": 7725
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 2.1923620933521923,
|
| 2200 |
+
"grad_norm": 0.2832966446876526,
|
| 2201 |
+
"learning_rate": 3.4503757805134004e-05,
|
| 2202 |
+
"loss": 0.0553,
|
| 2203 |
+
"step": 7750
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 2.1994342291371995,
|
| 2207 |
+
"grad_norm": 0.3094783425331116,
|
| 2208 |
+
"learning_rate": 3.438947347934421e-05,
|
| 2209 |
+
"loss": 0.0482,
|
| 2210 |
+
"step": 7775
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 2.2065063649222063,
|
| 2214 |
+
"grad_norm": 0.40016797184944153,
|
| 2215 |
+
"learning_rate": 3.427496025473227e-05,
|
| 2216 |
+
"loss": 0.0508,
|
| 2217 |
+
"step": 7800
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 2.2135785007072135,
|
| 2221 |
+
"grad_norm": 0.3726707398891449,
|
| 2222 |
+
"learning_rate": 3.416022092292887e-05,
|
| 2223 |
+
"loss": 0.0507,
|
| 2224 |
+
"step": 7825
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 2.2206506364922207,
|
| 2228 |
+
"grad_norm": 0.4792294502258301,
|
| 2229 |
+
"learning_rate": 3.4045258281076766e-05,
|
| 2230 |
+
"loss": 0.0549,
|
| 2231 |
+
"step": 7850
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 2.227722772277228,
|
| 2235 |
+
"grad_norm": 1.009504795074463,
|
| 2236 |
+
"learning_rate": 3.393007513176265e-05,
|
| 2237 |
+
"loss": 0.0558,
|
| 2238 |
+
"step": 7875
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 2.2347949080622347,
|
| 2242 |
+
"grad_norm": 0.40913182497024536,
|
| 2243 |
+
"learning_rate": 3.38146742829488e-05,
|
| 2244 |
+
"loss": 0.058,
|
| 2245 |
+
"step": 7900
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 2.241867043847242,
|
| 2249 |
+
"grad_norm": 0.436496376991272,
|
| 2250 |
+
"learning_rate": 3.369905854790458e-05,
|
| 2251 |
+
"loss": 0.0546,
|
| 2252 |
+
"step": 7925
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 2.248939179632249,
|
| 2256 |
+
"grad_norm": 0.2754940986633301,
|
| 2257 |
+
"learning_rate": 3.358323074513795e-05,
|
| 2258 |
+
"loss": 0.0498,
|
| 2259 |
+
"step": 7950
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 2.256011315417256,
|
| 2263 |
+
"grad_norm": 0.7202574610710144,
|
| 2264 |
+
"learning_rate": 3.3467193698326696e-05,
|
| 2265 |
+
"loss": 0.0542,
|
| 2266 |
+
"step": 7975
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 2.263083451202263,
|
| 2270 |
+
"grad_norm": 0.3375069200992584,
|
| 2271 |
+
"learning_rate": 3.335095023624958e-05,
|
| 2272 |
+
"loss": 0.0501,
|
| 2273 |
+
"step": 8000
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 2.2701555869872703,
|
| 2277 |
+
"grad_norm": 0.34498855471611023,
|
| 2278 |
+
"learning_rate": 3.323450319271744e-05,
|
| 2279 |
+
"loss": 0.0551,
|
| 2280 |
+
"step": 8025
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 2.2772277227722775,
|
| 2284 |
+
"grad_norm": 0.427866131067276,
|
| 2285 |
+
"learning_rate": 3.311785540650405e-05,
|
| 2286 |
+
"loss": 0.0517,
|
| 2287 |
+
"step": 8050
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 2.2842998585572842,
|
| 2291 |
+
"grad_norm": 0.2636614739894867,
|
| 2292 |
+
"learning_rate": 3.300100972127694e-05,
|
| 2293 |
+
"loss": 0.0503,
|
| 2294 |
+
"step": 8075
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 2.2913719943422914,
|
| 2298 |
+
"grad_norm": 0.34367385506629944,
|
| 2299 |
+
"learning_rate": 3.288396898552807e-05,
|
| 2300 |
+
"loss": 0.0512,
|
| 2301 |
+
"step": 8100
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 2.298444130127298,
|
| 2305 |
+
"grad_norm": 0.27327075600624084,
|
| 2306 |
+
"learning_rate": 3.2766736052504385e-05,
|
| 2307 |
+
"loss": 0.0539,
|
| 2308 |
+
"step": 8125
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 2.3055162659123054,
|
| 2312 |
+
"grad_norm": 0.3980356454849243,
|
| 2313 |
+
"learning_rate": 3.264931378013827e-05,
|
| 2314 |
+
"loss": 0.0583,
|
| 2315 |
+
"step": 8150
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 2.3125884016973126,
|
| 2319 |
+
"grad_norm": 0.24006566405296326,
|
| 2320 |
+
"learning_rate": 3.2531705030977864e-05,
|
| 2321 |
+
"loss": 0.0511,
|
| 2322 |
+
"step": 8175
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 2.31966053748232,
|
| 2326 |
+
"grad_norm": 0.5592175722122192,
|
| 2327 |
+
"learning_rate": 3.241391267211729e-05,
|
| 2328 |
+
"loss": 0.0502,
|
| 2329 |
+
"step": 8200
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 2.3267326732673266,
|
| 2333 |
+
"grad_norm": 1.0215811729431152,
|
| 2334 |
+
"learning_rate": 3.229593957512672e-05,
|
| 2335 |
+
"loss": 0.0554,
|
| 2336 |
+
"step": 8225
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 2.333804809052334,
|
| 2340 |
+
"grad_norm": 0.27189400792121887,
|
| 2341 |
+
"learning_rate": 3.2177788615982454e-05,
|
| 2342 |
+
"loss": 0.0501,
|
| 2343 |
+
"step": 8250
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 2.340876944837341,
|
| 2347 |
+
"grad_norm": 0.3555835485458374,
|
| 2348 |
+
"learning_rate": 3.205946267499672e-05,
|
| 2349 |
+
"loss": 0.0563,
|
| 2350 |
+
"step": 8275
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 2.3479490806223478,
|
| 2354 |
+
"grad_norm": 0.36138617992401123,
|
| 2355 |
+
"learning_rate": 3.19409646367475e-05,
|
| 2356 |
+
"loss": 0.0567,
|
| 2357 |
+
"step": 8300
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 2.355021216407355,
|
| 2361 |
+
"grad_norm": 0.8795189261436462,
|
| 2362 |
+
"learning_rate": 3.182229739000822e-05,
|
| 2363 |
+
"loss": 0.0599,
|
| 2364 |
+
"step": 8325
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 2.362093352192362,
|
| 2368 |
+
"grad_norm": 0.26847535371780396,
|
| 2369 |
+
"learning_rate": 3.170346382767731e-05,
|
| 2370 |
+
"loss": 0.0496,
|
| 2371 |
+
"step": 8350
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 2.3691654879773694,
|
| 2375 |
+
"grad_norm": 0.29600900411605835,
|
| 2376 |
+
"learning_rate": 3.158446684670765e-05,
|
| 2377 |
+
"loss": 0.0485,
|
| 2378 |
+
"step": 8375
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 2.376237623762376,
|
| 2382 |
+
"grad_norm": 0.2916370630264282,
|
| 2383 |
+
"learning_rate": 3.1465309348036016e-05,
|
| 2384 |
+
"loss": 0.0499,
|
| 2385 |
+
"step": 8400
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 2.3833097595473833,
|
| 2389 |
+
"grad_norm": 0.5006932616233826,
|
| 2390 |
+
"learning_rate": 3.1345994236512305e-05,
|
| 2391 |
+
"loss": 0.0485,
|
| 2392 |
+
"step": 8425
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 2.3903818953323905,
|
| 2396 |
+
"grad_norm": 0.3413617014884949,
|
| 2397 |
+
"learning_rate": 3.122652442082874e-05,
|
| 2398 |
+
"loss": 0.0506,
|
| 2399 |
+
"step": 8450
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 2.3974540311173973,
|
| 2403 |
+
"grad_norm": 0.3974776268005371,
|
| 2404 |
+
"learning_rate": 3.1106902813448956e-05,
|
| 2405 |
+
"loss": 0.05,
|
| 2406 |
+
"step": 8475
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 2.4045261669024045,
|
| 2410 |
+
"grad_norm": 0.3416425883769989,
|
| 2411 |
+
"learning_rate": 3.098713233053702e-05,
|
| 2412 |
+
"loss": 0.0532,
|
| 2413 |
+
"step": 8500
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 2.4115983026874117,
|
| 2417 |
+
"grad_norm": 0.5350253582000732,
|
| 2418 |
+
"learning_rate": 3.086721589188628e-05,
|
| 2419 |
+
"loss": 0.0505,
|
| 2420 |
+
"step": 8525
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 2.418670438472419,
|
| 2424 |
+
"grad_norm": 0.6094595789909363,
|
| 2425 |
+
"learning_rate": 3.0747156420848275e-05,
|
| 2426 |
+
"loss": 0.0488,
|
| 2427 |
+
"step": 8550
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 2.4257425742574257,
|
| 2431 |
+
"grad_norm": 0.2579383850097656,
|
| 2432 |
+
"learning_rate": 3.0626956844261404e-05,
|
| 2433 |
+
"loss": 0.0531,
|
| 2434 |
+
"step": 8575
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 2.432814710042433,
|
| 2438 |
+
"grad_norm": 0.3322567939758301,
|
| 2439 |
+
"learning_rate": 3.050662009237959e-05,
|
| 2440 |
+
"loss": 0.0521,
|
| 2441 |
+
"step": 8600
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 2.4398868458274396,
|
| 2445 |
+
"grad_norm": 0.2817617654800415,
|
| 2446 |
+
"learning_rate": 3.038614909880084e-05,
|
| 2447 |
+
"loss": 0.0583,
|
| 2448 |
+
"step": 8625
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 2.446958981612447,
|
| 2452 |
+
"grad_norm": 0.36568090319633484,
|
| 2453 |
+
"learning_rate": 3.026554680039575e-05,
|
| 2454 |
+
"loss": 0.0505,
|
| 2455 |
+
"step": 8650
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 2.454031117397454,
|
| 2459 |
+
"grad_norm": 0.32663673162460327,
|
| 2460 |
+
"learning_rate": 3.0144816137235892e-05,
|
| 2461 |
+
"loss": 0.0521,
|
| 2462 |
+
"step": 8675
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 2.4611032531824613,
|
| 2466 |
+
"grad_norm": 0.4173208475112915,
|
| 2467 |
+
"learning_rate": 3.0023960052522148e-05,
|
| 2468 |
+
"loss": 0.0586,
|
| 2469 |
+
"step": 8700
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 2.468175388967468,
|
| 2473 |
+
"grad_norm": 0.2725406289100647,
|
| 2474 |
+
"learning_rate": 2.9902981492512945e-05,
|
| 2475 |
+
"loss": 0.0484,
|
| 2476 |
+
"step": 8725
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 2.4752475247524752,
|
| 2480 |
+
"grad_norm": 0.4088152348995209,
|
| 2481 |
+
"learning_rate": 2.9781883406452453e-05,
|
| 2482 |
+
"loss": 0.0477,
|
| 2483 |
+
"step": 8750
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 2.4823196605374824,
|
| 2487 |
+
"grad_norm": 0.35629716515541077,
|
| 2488 |
+
"learning_rate": 2.966066874649869e-05,
|
| 2489 |
+
"loss": 0.0484,
|
| 2490 |
+
"step": 8775
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 2.489391796322489,
|
| 2494 |
+
"grad_norm": 0.4508310854434967,
|
| 2495 |
+
"learning_rate": 2.9539340467651494e-05,
|
| 2496 |
+
"loss": 0.0525,
|
| 2497 |
+
"step": 8800
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 2.4964639321074964,
|
| 2501 |
+
"grad_norm": 0.49331003427505493,
|
| 2502 |
+
"learning_rate": 2.9417901527680582e-05,
|
| 2503 |
+
"loss": 0.049,
|
| 2504 |
+
"step": 8825
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 2.5035360678925036,
|
| 2508 |
+
"grad_norm": 0.3239150941371918,
|
| 2509 |
+
"learning_rate": 2.9296354887053367e-05,
|
| 2510 |
+
"loss": 0.0522,
|
| 2511 |
+
"step": 8850
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 2.510608203677511,
|
| 2515 |
+
"grad_norm": 0.2788864076137543,
|
| 2516 |
+
"learning_rate": 2.9174703508862828e-05,
|
| 2517 |
+
"loss": 0.0549,
|
| 2518 |
+
"step": 8875
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 2.5176803394625176,
|
| 2522 |
+
"grad_norm": 0.3619994819164276,
|
| 2523 |
+
"learning_rate": 2.9057822401556116e-05,
|
| 2524 |
+
"loss": 0.0525,
|
| 2525 |
+
"step": 8900
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 2.5247524752475248,
|
| 2529 |
+
"grad_norm": 0.25908371806144714,
|
| 2530 |
+
"learning_rate": 2.89359743427919e-05,
|
| 2531 |
+
"loss": 0.057,
|
| 2532 |
+
"step": 8925
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 2.531824611032532,
|
| 2536 |
+
"grad_norm": 0.3243955373764038,
|
| 2537 |
+
"learning_rate": 2.8814030331907134e-05,
|
| 2538 |
+
"loss": 0.052,
|
| 2539 |
+
"step": 8950
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 2.5388967468175387,
|
| 2543 |
+
"grad_norm": 0.3788680136203766,
|
| 2544 |
+
"learning_rate": 2.8691993341681998e-05,
|
| 2545 |
+
"loss": 0.0526,
|
| 2546 |
+
"step": 8975
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 2.545968882602546,
|
| 2550 |
+
"grad_norm": 0.27258631587028503,
|
| 2551 |
+
"learning_rate": 2.856986634716332e-05,
|
| 2552 |
+
"loss": 0.0555,
|
| 2553 |
+
"step": 9000
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 2.553041018387553,
|
| 2557 |
+
"grad_norm": 1.2522977590560913,
|
| 2558 |
+
"learning_rate": 2.8447652325592066e-05,
|
| 2559 |
+
"loss": 0.0574,
|
| 2560 |
+
"step": 9025
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 2.5601131541725604,
|
| 2564 |
+
"grad_norm": 0.23333418369293213,
|
| 2565 |
+
"learning_rate": 2.8325354256330787e-05,
|
| 2566 |
+
"loss": 0.0531,
|
| 2567 |
+
"step": 9050
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 2.567185289957567,
|
| 2571 |
+
"grad_norm": 0.32750052213668823,
|
| 2572 |
+
"learning_rate": 2.8202975120790963e-05,
|
| 2573 |
+
"loss": 0.0505,
|
| 2574 |
+
"step": 9075
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 2.5742574257425743,
|
| 2578 |
+
"grad_norm": 0.3817848861217499,
|
| 2579 |
+
"learning_rate": 2.8080517902360316e-05,
|
| 2580 |
+
"loss": 0.0533,
|
| 2581 |
+
"step": 9100
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 2.581329561527581,
|
| 2585 |
+
"grad_norm": 1.9594416618347168,
|
| 2586 |
+
"learning_rate": 2.7957985586330106e-05,
|
| 2587 |
+
"loss": 0.0499,
|
| 2588 |
+
"step": 9125
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 2.5884016973125883,
|
| 2592 |
+
"grad_norm": 0.3222751021385193,
|
| 2593 |
+
"learning_rate": 2.7835381159822336e-05,
|
| 2594 |
+
"loss": 0.0553,
|
| 2595 |
+
"step": 9150
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 2.5954738330975955,
|
| 2599 |
+
"grad_norm": 0.3441489040851593,
|
| 2600 |
+
"learning_rate": 2.7712707611716938e-05,
|
| 2601 |
+
"loss": 0.0533,
|
| 2602 |
+
"step": 9175
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 2.6025459688826027,
|
| 2606 |
+
"grad_norm": 0.39582306146621704,
|
| 2607 |
+
"learning_rate": 2.75899679325789e-05,
|
| 2608 |
+
"loss": 0.0516,
|
| 2609 |
+
"step": 9200
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 2.6096181046676095,
|
| 2613 |
+
"grad_norm": 0.32057181000709534,
|
| 2614 |
+
"learning_rate": 2.7467165114585358e-05,
|
| 2615 |
+
"loss": 0.0573,
|
| 2616 |
+
"step": 9225
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 2.6166902404526167,
|
| 2620 |
+
"grad_norm": 0.49784281849861145,
|
| 2621 |
+
"learning_rate": 2.734430215145269e-05,
|
| 2622 |
+
"loss": 0.0508,
|
| 2623 |
+
"step": 9250
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 2.623762376237624,
|
| 2627 |
+
"grad_norm": 0.3396826386451721,
|
| 2628 |
+
"learning_rate": 2.7221382038363492e-05,
|
| 2629 |
+
"loss": 0.053,
|
| 2630 |
+
"step": 9275
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 2.6308345120226306,
|
| 2634 |
+
"grad_norm": 0.30675604939460754,
|
| 2635 |
+
"learning_rate": 2.7098407771893563e-05,
|
| 2636 |
+
"loss": 0.0527,
|
| 2637 |
+
"step": 9300
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 2.637906647807638,
|
| 2641 |
+
"grad_norm": 0.7486620545387268,
|
| 2642 |
+
"learning_rate": 2.6975382349938892e-05,
|
| 2643 |
+
"loss": 0.0466,
|
| 2644 |
+
"step": 9325
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 2.644978783592645,
|
| 2648 |
+
"grad_norm": 0.2760941684246063,
|
| 2649 |
+
"learning_rate": 2.685230877164253e-05,
|
| 2650 |
+
"loss": 0.0544,
|
| 2651 |
+
"step": 9350
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 2.6520509193776522,
|
| 2655 |
+
"grad_norm": 0.4320007264614105,
|
| 2656 |
+
"learning_rate": 2.672919003732149e-05,
|
| 2657 |
+
"loss": 0.0516,
|
| 2658 |
+
"step": 9375
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 2.659123055162659,
|
| 2662 |
+
"grad_norm": 0.390225350856781,
|
| 2663 |
+
"learning_rate": 2.6606029148393625e-05,
|
| 2664 |
+
"loss": 0.0491,
|
| 2665 |
+
"step": 9400
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 2.666195190947666,
|
| 2669 |
+
"grad_norm": 0.3701136112213135,
|
| 2670 |
+
"learning_rate": 2.648282910730444e-05,
|
| 2671 |
+
"loss": 0.0531,
|
| 2672 |
+
"step": 9425
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 2.6732673267326734,
|
| 2676 |
+
"grad_norm": 0.554530918598175,
|
| 2677 |
+
"learning_rate": 2.6359592917453897e-05,
|
| 2678 |
+
"loss": 0.0514,
|
| 2679 |
+
"step": 9450
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 2.68033946251768,
|
| 2683 |
+
"grad_norm": 0.7218428254127502,
|
| 2684 |
+
"learning_rate": 2.623632358312319e-05,
|
| 2685 |
+
"loss": 0.0531,
|
| 2686 |
+
"step": 9475
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 2.6874115983026874,
|
| 2690 |
+
"grad_norm": 0.4088691174983978,
|
| 2691 |
+
"learning_rate": 2.6113024109401547e-05,
|
| 2692 |
+
"loss": 0.0517,
|
| 2693 |
+
"step": 9500
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 2.6944837340876946,
|
| 2697 |
+
"grad_norm": 0.2585553228855133,
|
| 2698 |
+
"learning_rate": 2.5989697502112903e-05,
|
| 2699 |
+
"loss": 0.0495,
|
| 2700 |
+
"step": 9525
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 2.701555869872702,
|
| 2704 |
+
"grad_norm": 0.3183114528656006,
|
| 2705 |
+
"learning_rate": 2.58663467677427e-05,
|
| 2706 |
+
"loss": 0.0488,
|
| 2707 |
+
"step": 9550
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 2.7086280056577086,
|
| 2711 |
+
"grad_norm": 0.35523074865341187,
|
| 2712 |
+
"learning_rate": 2.574297491336452e-05,
|
| 2713 |
+
"loss": 0.0507,
|
| 2714 |
+
"step": 9575
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 2.7157001414427158,
|
| 2718 |
+
"grad_norm": 0.3662826120853424,
|
| 2719 |
+
"learning_rate": 2.5619584946566844e-05,
|
| 2720 |
+
"loss": 0.0492,
|
| 2721 |
+
"step": 9600
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 2.7227722772277225,
|
| 2725 |
+
"grad_norm": 0.5980022549629211,
|
| 2726 |
+
"learning_rate": 2.549617987537968e-05,
|
| 2727 |
+
"loss": 0.056,
|
| 2728 |
+
"step": 9625
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 2.7298444130127297,
|
| 2732 |
+
"grad_norm": 0.3375484347343445,
|
| 2733 |
+
"learning_rate": 2.537276270820127e-05,
|
| 2734 |
+
"loss": 0.0545,
|
| 2735 |
+
"step": 9650
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 2.736916548797737,
|
| 2739 |
+
"grad_norm": 0.2702608108520508,
|
| 2740 |
+
"learning_rate": 2.524933645372472e-05,
|
| 2741 |
+
"loss": 0.0483,
|
| 2742 |
+
"step": 9675
|
| 2743 |
+
},
|
| 2744 |
+
{
|
| 2745 |
+
"epoch": 2.743988684582744,
|
| 2746 |
+
"grad_norm": 0.20587654411792755,
|
| 2747 |
+
"learning_rate": 2.512590412086468e-05,
|
| 2748 |
+
"loss": 0.048,
|
| 2749 |
+
"step": 9700
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 2.751060820367751,
|
| 2753 |
+
"grad_norm": 0.40114825963974,
|
| 2754 |
+
"learning_rate": 2.5002468718683985e-05,
|
| 2755 |
+
"loss": 0.0478,
|
| 2756 |
+
"step": 9725
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 2.758132956152758,
|
| 2760 |
+
"grad_norm": 0.25009649991989136,
|
| 2761 |
+
"learning_rate": 2.4879033256320268e-05,
|
| 2762 |
+
"loss": 0.0528,
|
| 2763 |
+
"step": 9750
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 2.7652050919377653,
|
| 2767 |
+
"grad_norm": 0.4038143455982208,
|
| 2768 |
+
"learning_rate": 2.475560074291266e-05,
|
| 2769 |
+
"loss": 0.0536,
|
| 2770 |
+
"step": 9775
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 2.772277227722772,
|
| 2774 |
+
"grad_norm": 0.3600768744945526,
|
| 2775 |
+
"learning_rate": 2.463217418752838e-05,
|
| 2776 |
+
"loss": 0.0513,
|
| 2777 |
+
"step": 9800
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 2.7793493635077793,
|
| 2781 |
+
"grad_norm": 0.2662784457206726,
|
| 2782 |
+
"learning_rate": 2.4508756599089423e-05,
|
| 2783 |
+
"loss": 0.0528,
|
| 2784 |
+
"step": 9825
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 2.7864214992927865,
|
| 2788 |
+
"grad_norm": 0.4926321506500244,
|
| 2789 |
+
"learning_rate": 2.4385350986299162e-05,
|
| 2790 |
+
"loss": 0.0502,
|
| 2791 |
+
"step": 9850
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 2.7934936350777937,
|
| 2795 |
+
"grad_norm": 0.3003157675266266,
|
| 2796 |
+
"learning_rate": 2.4261960357569036e-05,
|
| 2797 |
+
"loss": 0.0491,
|
| 2798 |
+
"step": 9875
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 2.8005657708628005,
|
| 2802 |
+
"grad_norm": 0.3073439598083496,
|
| 2803 |
+
"learning_rate": 2.413858772094521e-05,
|
| 2804 |
+
"loss": 0.051,
|
| 2805 |
+
"step": 9900
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 2.8076379066478077,
|
| 2809 |
+
"grad_norm": 0.4092470109462738,
|
| 2810 |
+
"learning_rate": 2.4015236084035204e-05,
|
| 2811 |
+
"loss": 0.0474,
|
| 2812 |
+
"step": 9925
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 2.814710042432815,
|
| 2816 |
+
"grad_norm": 0.5402696132659912,
|
| 2817 |
+
"learning_rate": 2.389190845393463e-05,
|
| 2818 |
+
"loss": 0.0492,
|
| 2819 |
+
"step": 9950
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 2.8217821782178216,
|
| 2823 |
+
"grad_norm": 0.3162129521369934,
|
| 2824 |
+
"learning_rate": 2.376860783715384e-05,
|
| 2825 |
+
"loss": 0.0509,
|
| 2826 |
+
"step": 9975
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 2.828854314002829,
|
| 2830 |
+
"grad_norm": 0.3184404671192169,
|
| 2831 |
+
"learning_rate": 2.3645337239544658e-05,
|
| 2832 |
+
"loss": 0.0493,
|
| 2833 |
+
"step": 10000
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 2.835926449787836,
|
| 2837 |
+
"grad_norm": 0.33763962984085083,
|
| 2838 |
+
"learning_rate": 2.3522099666227087e-05,
|
| 2839 |
+
"loss": 0.0489,
|
| 2840 |
+
"step": 10025
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 2.8429985855728432,
|
| 2844 |
+
"grad_norm": 0.4636186361312866,
|
| 2845 |
+
"learning_rate": 2.339889812151606e-05,
|
| 2846 |
+
"loss": 0.0545,
|
| 2847 |
+
"step": 10050
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 2.85007072135785,
|
| 2851 |
+
"grad_norm": 0.3926536738872528,
|
| 2852 |
+
"learning_rate": 2.3275735608848208e-05,
|
| 2853 |
+
"loss": 0.0501,
|
| 2854 |
+
"step": 10075
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 2.857142857142857,
|
| 2858 |
+
"grad_norm": 0.4206957519054413,
|
| 2859 |
+
"learning_rate": 2.3152615130708592e-05,
|
| 2860 |
+
"loss": 0.0502,
|
| 2861 |
+
"step": 10100
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 2.864214992927864,
|
| 2865 |
+
"grad_norm": 0.729640781879425,
|
| 2866 |
+
"learning_rate": 2.302953968855759e-05,
|
| 2867 |
+
"loss": 0.0469,
|
| 2868 |
+
"step": 10125
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 2.871287128712871,
|
| 2872 |
+
"grad_norm": 0.37660130858421326,
|
| 2873 |
+
"learning_rate": 2.2906512282757644e-05,
|
| 2874 |
+
"loss": 0.0524,
|
| 2875 |
+
"step": 10150
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 2.8783592644978784,
|
| 2879 |
+
"grad_norm": 0.5026111602783203,
|
| 2880 |
+
"learning_rate": 2.2783535912500187e-05,
|
| 2881 |
+
"loss": 0.0587,
|
| 2882 |
+
"step": 10175
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 2.8854314002828856,
|
| 2886 |
+
"grad_norm": 0.3521290123462677,
|
| 2887 |
+
"learning_rate": 2.266061357573248e-05,
|
| 2888 |
+
"loss": 0.0507,
|
| 2889 |
+
"step": 10200
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 2.8925035360678923,
|
| 2893 |
+
"grad_norm": 0.32747042179107666,
|
| 2894 |
+
"learning_rate": 2.253774826908453e-05,
|
| 2895 |
+
"loss": 0.0531,
|
| 2896 |
+
"step": 10225
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 2.8995756718528995,
|
| 2900 |
+
"grad_norm": 0.3167445659637451,
|
| 2901 |
+
"learning_rate": 2.2414942987796084e-05,
|
| 2902 |
+
"loss": 0.0468,
|
| 2903 |
+
"step": 10250
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 2.9066478076379068,
|
| 2907 |
+
"grad_norm": 0.30890071392059326,
|
| 2908 |
+
"learning_rate": 2.2292200725643534e-05,
|
| 2909 |
+
"loss": 0.0535,
|
| 2910 |
+
"step": 10275
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 2.9137199434229135,
|
| 2914 |
+
"grad_norm": 0.4126497209072113,
|
| 2915 |
+
"learning_rate": 2.216952447486701e-05,
|
| 2916 |
+
"loss": 0.0491,
|
| 2917 |
+
"step": 10300
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 2.9207920792079207,
|
| 2921 |
+
"grad_norm": 1.0146815776824951,
|
| 2922 |
+
"learning_rate": 2.2046917226097387e-05,
|
| 2923 |
+
"loss": 0.0507,
|
| 2924 |
+
"step": 10325
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 2.927864214992928,
|
| 2928 |
+
"grad_norm": 0.3795275390148163,
|
| 2929 |
+
"learning_rate": 2.1924381968283394e-05,
|
| 2930 |
+
"loss": 0.0501,
|
| 2931 |
+
"step": 10350
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 2.934936350777935,
|
| 2935 |
+
"grad_norm": 0.3325127065181732,
|
| 2936 |
+
"learning_rate": 2.1801921688618758e-05,
|
| 2937 |
+
"loss": 0.0438,
|
| 2938 |
+
"step": 10375
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 2.942008486562942,
|
| 2942 |
+
"grad_norm": 0.358235239982605,
|
| 2943 |
+
"learning_rate": 2.167953937246934e-05,
|
| 2944 |
+
"loss": 0.0519,
|
| 2945 |
+
"step": 10400
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 2.949080622347949,
|
| 2949 |
+
"grad_norm": 0.37195077538490295,
|
| 2950 |
+
"learning_rate": 2.1557238003300438e-05,
|
| 2951 |
+
"loss": 0.0472,
|
| 2952 |
+
"step": 10425
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 2.9561527581329563,
|
| 2956 |
+
"grad_norm": 0.3947463929653168,
|
| 2957 |
+
"learning_rate": 2.1435020562603944e-05,
|
| 2958 |
+
"loss": 0.0469,
|
| 2959 |
+
"step": 10450
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 2.963224893917963,
|
| 2963 |
+
"grad_norm": 0.3517344892024994,
|
| 2964 |
+
"learning_rate": 2.1312890029825765e-05,
|
| 2965 |
+
"loss": 0.0451,
|
| 2966 |
+
"step": 10475
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 2.9702970297029703,
|
| 2970 |
+
"grad_norm": 0.4573589861392975,
|
| 2971 |
+
"learning_rate": 2.1190849382293153e-05,
|
| 2972 |
+
"loss": 0.0478,
|
| 2973 |
+
"step": 10500
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 2.9773691654879775,
|
| 2977 |
+
"grad_norm": 0.4348020553588867,
|
| 2978 |
+
"learning_rate": 2.1068901595142076e-05,
|
| 2979 |
+
"loss": 0.0471,
|
| 2980 |
+
"step": 10525
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 2.9844413012729847,
|
| 2984 |
+
"grad_norm": 0.27447789907455444,
|
| 2985 |
+
"learning_rate": 2.0947049641244763e-05,
|
| 2986 |
+
"loss": 0.0525,
|
| 2987 |
+
"step": 10550
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 2.9915134370579914,
|
| 2991 |
+
"grad_norm": 0.5210450291633606,
|
| 2992 |
+
"learning_rate": 2.0825296491137178e-05,
|
| 2993 |
+
"loss": 0.049,
|
| 2994 |
+
"step": 10575
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 2.9985855728429986,
|
| 2998 |
+
"grad_norm": 0.4803789556026459,
|
| 2999 |
+
"learning_rate": 2.0703645112946632e-05,
|
| 3000 |
+
"loss": 0.048,
|
| 3001 |
+
"step": 10600
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 3.0,
|
| 3005 |
+
"eval_accuracy": 0.9731636716504077,
|
| 3006 |
+
"eval_f1": 0.9040792973909716,
|
| 3007 |
+
"eval_loss": 0.080692358314991,
|
| 3008 |
+
"eval_precision": 0.8956920811279763,
|
| 3009 |
+
"eval_recall": 0.9126250733540829,
|
| 3010 |
+
"eval_runtime": 54.8402,
|
| 3011 |
+
"eval_samples_per_second": 916.701,
|
| 3012 |
+
"eval_steps_per_second": 3.592,
|
| 3013 |
+
"step": 10605
|
| 3014 |
+
}
|
| 3015 |
+
],
|
| 3016 |
+
"logging_steps": 25,
|
| 3017 |
+
"max_steps": 17675,
|
| 3018 |
+
"num_input_tokens_seen": 0,
|
| 3019 |
+
"num_train_epochs": 5,
|
| 3020 |
+
"save_steps": 500,
|
| 3021 |
+
"stateful_callbacks": {
|
| 3022 |
+
"EarlyStoppingCallback": {
|
| 3023 |
+
"args": {
|
| 3024 |
+
"early_stopping_patience": 5,
|
| 3025 |
+
"early_stopping_threshold": 0.01
|
| 3026 |
+
},
|
| 3027 |
+
"attributes": {
|
| 3028 |
+
"early_stopping_patience_counter": 1
|
| 3029 |
+
}
|
| 3030 |
+
},
|
| 3031 |
+
"TrainerControl": {
|
| 3032 |
+
"args": {
|
| 3033 |
+
"should_epoch_stop": false,
|
| 3034 |
+
"should_evaluate": false,
|
| 3035 |
+
"should_log": false,
|
| 3036 |
+
"should_save": true,
|
| 3037 |
+
"should_training_stop": false
|
| 3038 |
+
},
|
| 3039 |
+
"attributes": {}
|
| 3040 |
+
}
|
| 3041 |
+
},
|
| 3042 |
+
"total_flos": 3.589143261681162e+17,
|
| 3043 |
+
"train_batch_size": 128,
|
| 3044 |
+
"trial_name": null,
|
| 3045 |
+
"trial_params": null
|
| 3046 |
+
}
|
checkpoint-10605/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc7181b00303f72cd9e8d7e9489278da1dba68ace8042efb585819e98f131563
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-large",
|
| 3 |
+
"_num_labels": 42,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ModernBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_bias": false,
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 50281,
|
| 10 |
+
"classifier_activation": "gelu",
|
| 11 |
+
"classifier_bias": false,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"classifier_pooling": "mean",
|
| 14 |
+
"cls_token_id": 50281,
|
| 15 |
+
"decoder_bias": true,
|
| 16 |
+
"deterministic_flash_attn": false,
|
| 17 |
+
"embedding_dropout": 0.0,
|
| 18 |
+
"eos_token_id": 50282,
|
| 19 |
+
"global_attn_every_n_layers": 3,
|
| 20 |
+
"global_rope_theta": 160000.0,
|
| 21 |
+
"gradient_checkpointing": false,
|
| 22 |
+
"hidden_activation": "gelu",
|
| 23 |
+
"hidden_size": 1024,
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "B-URL",
|
| 26 |
+
"1": "I-URL",
|
| 27 |
+
"2": "O",
|
| 28 |
+
"3": "B-ORG",
|
| 29 |
+
"4": "B-SERVICE",
|
| 30 |
+
"5": "I-ORG",
|
| 31 |
+
"6": "B-SECTOR",
|
| 32 |
+
"7": "I-SECTOR",
|
| 33 |
+
"8": "B-FILEPATH",
|
| 34 |
+
"9": "I-FILEPATH",
|
| 35 |
+
"10": "I-DOMAIN",
|
| 36 |
+
"11": "B-PLATFORM",
|
| 37 |
+
"12": "I-SERVICE",
|
| 38 |
+
"13": "I-PLATFORM",
|
| 39 |
+
"14": "B-THREAT-ACTOR",
|
| 40 |
+
"15": "I-THREAT-ACTOR",
|
| 41 |
+
"16": "B-PRODUCT",
|
| 42 |
+
"17": "B-MALWARE",
|
| 43 |
+
"18": "I-MALWARE",
|
| 44 |
+
"19": "B-LOC",
|
| 45 |
+
"20": "B-CVE",
|
| 46 |
+
"21": "I-CVE",
|
| 47 |
+
"22": "B-TOOL",
|
| 48 |
+
"23": "I-PRODUCT",
|
| 49 |
+
"24": "B-IPV4",
|
| 50 |
+
"25": "I-IPV4",
|
| 51 |
+
"26": "B-MITRE-TACTIC",
|
| 52 |
+
"27": "I-MITRE-TACTIC",
|
| 53 |
+
"28": "B-DOMAIN",
|
| 54 |
+
"29": "I-TOOL",
|
| 55 |
+
"30": "B-MD5",
|
| 56 |
+
"31": "I-LOC",
|
| 57 |
+
"32": "B-CAMPAIGN",
|
| 58 |
+
"33": "I-CAMPAIGN",
|
| 59 |
+
"34": "B-SHA1",
|
| 60 |
+
"35": "B-SHA256",
|
| 61 |
+
"36": "B-EMAIL",
|
| 62 |
+
"37": "I-EMAIL",
|
| 63 |
+
"38": "B-IPV6",
|
| 64 |
+
"39": "I-IPV6",
|
| 65 |
+
"40": "B-REGISTRY-KEYS",
|
| 66 |
+
"41": "I-REGISTRY-KEYS"
|
| 67 |
+
},
|
| 68 |
+
"initializer_cutoff_factor": 2.0,
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 2624,
|
| 71 |
+
"label2id": {
|
| 72 |
+
"B-CAMPAIGN": 32,
|
| 73 |
+
"B-CVE": 20,
|
| 74 |
+
"B-DOMAIN": 28,
|
| 75 |
+
"B-EMAIL": 36,
|
| 76 |
+
"B-FILEPATH": 8,
|
| 77 |
+
"B-IPV4": 24,
|
| 78 |
+
"B-IPV6": 38,
|
| 79 |
+
"B-LOC": 19,
|
| 80 |
+
"B-MALWARE": 17,
|
| 81 |
+
"B-MD5": 30,
|
| 82 |
+
"B-MITRE-TACTIC": 26,
|
| 83 |
+
"B-ORG": 3,
|
| 84 |
+
"B-PLATFORM": 11,
|
| 85 |
+
"B-PRODUCT": 16,
|
| 86 |
+
"B-REGISTRY-KEYS": 40,
|
| 87 |
+
"B-SECTOR": 6,
|
| 88 |
+
"B-SERVICE": 4,
|
| 89 |
+
"B-SHA1": 34,
|
| 90 |
+
"B-SHA256": 35,
|
| 91 |
+
"B-THREAT-ACTOR": 14,
|
| 92 |
+
"B-TOOL": 22,
|
| 93 |
+
"B-URL": 0,
|
| 94 |
+
"I-CAMPAIGN": 33,
|
| 95 |
+
"I-CVE": 21,
|
| 96 |
+
"I-DOMAIN": 10,
|
| 97 |
+
"I-EMAIL": 37,
|
| 98 |
+
"I-FILEPATH": 9,
|
| 99 |
+
"I-IPV4": 25,
|
| 100 |
+
"I-IPV6": 39,
|
| 101 |
+
"I-LOC": 31,
|
| 102 |
+
"I-MALWARE": 18,
|
| 103 |
+
"I-MITRE-TACTIC": 27,
|
| 104 |
+
"I-ORG": 5,
|
| 105 |
+
"I-PLATFORM": 13,
|
| 106 |
+
"I-PRODUCT": 23,
|
| 107 |
+
"I-REGISTRY-KEYS": 41,
|
| 108 |
+
"I-SECTOR": 7,
|
| 109 |
+
"I-SERVICE": 12,
|
| 110 |
+
"I-THREAT-ACTOR": 15,
|
| 111 |
+
"I-TOOL": 29,
|
| 112 |
+
"I-URL": 1,
|
| 113 |
+
"O": 2
|
| 114 |
+
},
|
| 115 |
+
"layer_norm_eps": 1e-05,
|
| 116 |
+
"local_attention": 128,
|
| 117 |
+
"local_rope_theta": 10000.0,
|
| 118 |
+
"max_position_embeddings": 8192,
|
| 119 |
+
"mlp_bias": false,
|
| 120 |
+
"mlp_dropout": 0.0,
|
| 121 |
+
"model_type": "modernbert",
|
| 122 |
+
"norm_bias": false,
|
| 123 |
+
"norm_eps": 1e-05,
|
| 124 |
+
"num_attention_heads": 16,
|
| 125 |
+
"num_hidden_layers": 28,
|
| 126 |
+
"pad_token_id": 50283,
|
| 127 |
+
"position_embedding_type": "absolute",
|
| 128 |
+
"reference_compile": true,
|
| 129 |
+
"repad_logits_with_grad": false,
|
| 130 |
+
"sep_token_id": 50282,
|
| 131 |
+
"sparse_pred_ignore_index": -100,
|
| 132 |
+
"sparse_prediction": false,
|
| 133 |
+
"torch_dtype": "float32",
|
| 134 |
+
"transformers_version": "4.48.0",
|
| 135 |
+
"vocab_size": 50368
|
| 136 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52fe43effd7557bea8056246926a2cc952953b1facb01c2c020f0b8fa5e7927f
|
| 3 |
+
size 1583515640
|
runs/Oct24_07-27-25_r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq/events.out.tfevents.1761290846.r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq.90.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f72922b2d4f23b24b599d2a862a5c2a3785f4349f987a90dc5fd62813d9f869
|
| 3 |
+
size 159645
|
runs/Oct24_07-27-25_r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq/events.out.tfevents.1761295429.r-juanmcristobal-securemodernbert-50nhce16-13175-rr7xq.90.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02d38fb6db1fe852ab57f12fb7b89cf22ca835971860b913acffa0a36f515c69
|
| 3 |
+
size 569
|
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": true,
|
| 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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc7181b00303f72cd9e8d7e9489278da1dba68ace8042efb585819e98f131563
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "juanmcristobal/ner-ioc-dataset3",
|
| 3 |
+
"model": "answerdotai/ModernBERT-large",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 5,
|
| 6 |
+
"max_seq_length": 128,
|
| 7 |
+
"batch_size": 128,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "cosine",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"tokens_column": "tokens",
|
| 18 |
+
"tags_column": "tags",
|
| 19 |
+
"logging_steps": -1,
|
| 20 |
+
"project_name": "autotrain-sec4",
|
| 21 |
+
"auto_find_batch_size": false,
|
| 22 |
+
"mixed_precision": "fp16",
|
| 23 |
+
"save_total_limit": 1,
|
| 24 |
+
"push_to_hub": true,
|
| 25 |
+
"eval_strategy": "epoch",
|
| 26 |
+
"username": "juanmcristobal",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|