Instructions to use pax-k/privacy-filter-mini2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pax-k/privacy-filter-mini2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="pax-k/privacy-filter-mini2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("pax-k/privacy-filter-mini2") model = AutoModelForTokenClassification.from_pretrained("pax-k/privacy-filter-mini2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-1126/config.json +84 -0
- checkpoint-1126/model.safetensors +3 -0
- checkpoint-1126/optimizer.pt +3 -0
- checkpoint-1126/rng_state.pth +3 -0
- checkpoint-1126/scheduler.pt +3 -0
- checkpoint-1126/trainer_state.json +717 -0
- checkpoint-1126/training_args.bin +3 -0
- config.json +84 -0
- model.safetensors +3 -0
- runs/Apr23_01-03-59_r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j/events.out.tfevents.1776906240.r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j.105.0 +2 -2
- runs/Apr23_01-03-59_r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j/events.out.tfevents.1776906612.r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j.105.1 +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-base
|
| 8 |
+
widget:
|
| 9 |
+
- text: "I love AutoTrain"
|
| 10 |
+
datasets:
|
| 11 |
+
- pax-k/privacy-filter-mini-data
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Trained Using AutoTrain
|
| 15 |
+
|
| 16 |
+
- Problem type: Token Classification
|
| 17 |
+
|
| 18 |
+
## Validation Metrics
|
| 19 |
+
loss: 0.2570085823535919
|
| 20 |
+
|
| 21 |
+
precision: 0.758298755186722
|
| 22 |
+
|
| 23 |
+
recall: 0.78419452887538
|
| 24 |
+
|
| 25 |
+
f1: 0.7710292695789751
|
| 26 |
+
|
| 27 |
+
accuracy: 0.9033240375677148
|
checkpoint-1126/config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-base",
|
| 3 |
+
"_num_labels": 16,
|
| 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": 768,
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "O",
|
| 26 |
+
"1": "B-account_number",
|
| 27 |
+
"2": "B-private_address",
|
| 28 |
+
"3": "B-private_date",
|
| 29 |
+
"4": "B-private_email",
|
| 30 |
+
"5": "B-private_person",
|
| 31 |
+
"6": "B-private_phone",
|
| 32 |
+
"7": "B-private_url",
|
| 33 |
+
"8": "B-secret",
|
| 34 |
+
"9": "I-account_number",
|
| 35 |
+
"10": "I-private_address",
|
| 36 |
+
"11": "I-private_date",
|
| 37 |
+
"12": "I-private_email",
|
| 38 |
+
"13": "I-private_person",
|
| 39 |
+
"14": "I-private_phone",
|
| 40 |
+
"15": "I-secret"
|
| 41 |
+
},
|
| 42 |
+
"initializer_cutoff_factor": 2.0,
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 1152,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"B-account_number": 1,
|
| 47 |
+
"B-private_address": 2,
|
| 48 |
+
"B-private_date": 3,
|
| 49 |
+
"B-private_email": 4,
|
| 50 |
+
"B-private_person": 5,
|
| 51 |
+
"B-private_phone": 6,
|
| 52 |
+
"B-private_url": 7,
|
| 53 |
+
"B-secret": 8,
|
| 54 |
+
"I-account_number": 9,
|
| 55 |
+
"I-private_address": 10,
|
| 56 |
+
"I-private_date": 11,
|
| 57 |
+
"I-private_email": 12,
|
| 58 |
+
"I-private_person": 13,
|
| 59 |
+
"I-private_phone": 14,
|
| 60 |
+
"I-secret": 15,
|
| 61 |
+
"O": 0
|
| 62 |
+
},
|
| 63 |
+
"layer_norm_eps": 1e-05,
|
| 64 |
+
"local_attention": 128,
|
| 65 |
+
"local_rope_theta": 10000.0,
|
| 66 |
+
"max_position_embeddings": 8192,
|
| 67 |
+
"mlp_bias": false,
|
| 68 |
+
"mlp_dropout": 0.0,
|
| 69 |
+
"model_type": "modernbert",
|
| 70 |
+
"norm_bias": false,
|
| 71 |
+
"norm_eps": 1e-05,
|
| 72 |
+
"num_attention_heads": 12,
|
| 73 |
+
"num_hidden_layers": 22,
|
| 74 |
+
"pad_token_id": 50283,
|
| 75 |
+
"position_embedding_type": "absolute",
|
| 76 |
+
"reference_compile": true,
|
| 77 |
+
"repad_logits_with_grad": false,
|
| 78 |
+
"sep_token_id": 50282,
|
| 79 |
+
"sparse_pred_ignore_index": -100,
|
| 80 |
+
"sparse_prediction": false,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.48.0",
|
| 83 |
+
"vocab_size": 50368
|
| 84 |
+
}
|
checkpoint-1126/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a428a73b8a6d4d1125cbf6efd7adf36b7445e2f5588435ad4712c9ebec3d85
|
| 3 |
+
size 598482856
|
checkpoint-1126/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ac0ddf01a440cc0599c855a2cb3b3afe46777e56851c9e502f4d80d39ed62fa
|
| 3 |
+
size 1197053562
|
checkpoint-1126/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
|
| 3 |
+
size 14244
|
checkpoint-1126/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:437a5f4f6ac486d5ff0e4a93df46f18638d9247f43ae4a762a622623f40181ba
|
| 3 |
+
size 1064
|
checkpoint-1126/trainer_state.json
ADDED
|
@@ -0,0 +1,717 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2570085823535919,
|
| 3 |
+
"best_model_checkpoint": "privacy-filter-mini2/checkpoint-1126",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1126,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.021314387211367674,
|
| 13 |
+
"grad_norm": 29.965667724609375,
|
| 14 |
+
"learning_rate": 1.7730496453900712e-06,
|
| 15 |
+
"loss": 3.0493,
|
| 16 |
+
"step": 12
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04262877442273535,
|
| 20 |
+
"grad_norm": 18.551843643188477,
|
| 21 |
+
"learning_rate": 3.9007092198581565e-06,
|
| 22 |
+
"loss": 2.4305,
|
| 23 |
+
"step": 24
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06394316163410302,
|
| 27 |
+
"grad_norm": 12.665560722351074,
|
| 28 |
+
"learning_rate": 6.028368794326241e-06,
|
| 29 |
+
"loss": 1.567,
|
| 30 |
+
"step": 36
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0852575488454707,
|
| 34 |
+
"grad_norm": 12.106671333312988,
|
| 35 |
+
"learning_rate": 8.156028368794328e-06,
|
| 36 |
+
"loss": 1.1361,
|
| 37 |
+
"step": 48
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10657193605683836,
|
| 41 |
+
"grad_norm": 4.470224857330322,
|
| 42 |
+
"learning_rate": 1.0283687943262411e-05,
|
| 43 |
+
"loss": 1.0367,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12788632326820604,
|
| 48 |
+
"grad_norm": 10.088990211486816,
|
| 49 |
+
"learning_rate": 1.2411347517730498e-05,
|
| 50 |
+
"loss": 0.8406,
|
| 51 |
+
"step": 72
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1492007104795737,
|
| 55 |
+
"grad_norm": 36.288516998291016,
|
| 56 |
+
"learning_rate": 1.4539007092198581e-05,
|
| 57 |
+
"loss": 0.7338,
|
| 58 |
+
"step": 84
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.1705150976909414,
|
| 62 |
+
"grad_norm": 8.254074096679688,
|
| 63 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 64 |
+
"loss": 0.64,
|
| 65 |
+
"step": 96
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.19182948490230906,
|
| 69 |
+
"grad_norm": 2.6580331325531006,
|
| 70 |
+
"learning_rate": 1.879432624113475e-05,
|
| 71 |
+
"loss": 0.5128,
|
| 72 |
+
"step": 108
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.21314387211367672,
|
| 76 |
+
"grad_norm": 3.75266695022583,
|
| 77 |
+
"learning_rate": 2.0921985815602837e-05,
|
| 78 |
+
"loss": 0.4988,
|
| 79 |
+
"step": 120
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2344582593250444,
|
| 83 |
+
"grad_norm": 3.971578359603882,
|
| 84 |
+
"learning_rate": 2.3049645390070924e-05,
|
| 85 |
+
"loss": 0.4859,
|
| 86 |
+
"step": 132
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2557726465364121,
|
| 90 |
+
"grad_norm": 3.4526731967926025,
|
| 91 |
+
"learning_rate": 2.5177304964539007e-05,
|
| 92 |
+
"loss": 0.4134,
|
| 93 |
+
"step": 144
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.27708703374777977,
|
| 97 |
+
"grad_norm": 4.090625762939453,
|
| 98 |
+
"learning_rate": 2.7304964539007094e-05,
|
| 99 |
+
"loss": 0.4275,
|
| 100 |
+
"step": 156
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2984014209591474,
|
| 104 |
+
"grad_norm": 3.367293357849121,
|
| 105 |
+
"learning_rate": 2.9432624113475177e-05,
|
| 106 |
+
"loss": 0.3641,
|
| 107 |
+
"step": 168
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3197158081705151,
|
| 111 |
+
"grad_norm": 3.8103346824645996,
|
| 112 |
+
"learning_rate": 3.156028368794326e-05,
|
| 113 |
+
"loss": 0.3534,
|
| 114 |
+
"step": 180
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3410301953818828,
|
| 118 |
+
"grad_norm": 4.539180278778076,
|
| 119 |
+
"learning_rate": 3.3687943262411347e-05,
|
| 120 |
+
"loss": 0.3977,
|
| 121 |
+
"step": 192
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3623445825932504,
|
| 125 |
+
"grad_norm": 4.947201251983643,
|
| 126 |
+
"learning_rate": 3.5815602836879437e-05,
|
| 127 |
+
"loss": 0.4375,
|
| 128 |
+
"step": 204
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3836589698046181,
|
| 132 |
+
"grad_norm": 2.3460354804992676,
|
| 133 |
+
"learning_rate": 3.794326241134752e-05,
|
| 134 |
+
"loss": 0.3783,
|
| 135 |
+
"step": 216
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4049733570159858,
|
| 139 |
+
"grad_norm": 4.669414043426514,
|
| 140 |
+
"learning_rate": 4.007092198581561e-05,
|
| 141 |
+
"loss": 0.4031,
|
| 142 |
+
"step": 228
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.42628774422735344,
|
| 146 |
+
"grad_norm": 4.045742034912109,
|
| 147 |
+
"learning_rate": 4.219858156028369e-05,
|
| 148 |
+
"loss": 0.3858,
|
| 149 |
+
"step": 240
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.44760213143872113,
|
| 153 |
+
"grad_norm": 4.866994380950928,
|
| 154 |
+
"learning_rate": 4.432624113475177e-05,
|
| 155 |
+
"loss": 0.3359,
|
| 156 |
+
"step": 252
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4689165186500888,
|
| 160 |
+
"grad_norm": 4.039434432983398,
|
| 161 |
+
"learning_rate": 4.645390070921986e-05,
|
| 162 |
+
"loss": 0.3449,
|
| 163 |
+
"step": 264
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.49023090586145646,
|
| 167 |
+
"grad_norm": 6.006864547729492,
|
| 168 |
+
"learning_rate": 4.858156028368794e-05,
|
| 169 |
+
"loss": 0.4041,
|
| 170 |
+
"step": 276
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5115452930728241,
|
| 174 |
+
"grad_norm": 3.780167579650879,
|
| 175 |
+
"learning_rate": 4.999969234890107e-05,
|
| 176 |
+
"loss": 0.3228,
|
| 177 |
+
"step": 288
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5328596802841918,
|
| 181 |
+
"grad_norm": 2.782979726791382,
|
| 182 |
+
"learning_rate": 4.999507773385434e-05,
|
| 183 |
+
"loss": 0.3395,
|
| 184 |
+
"step": 300
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.5541740674955595,
|
| 188 |
+
"grad_norm": 3.6217241287231445,
|
| 189 |
+
"learning_rate": 4.9984926580197044e-05,
|
| 190 |
+
"loss": 0.3034,
|
| 191 |
+
"step": 312
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5754884547069272,
|
| 195 |
+
"grad_norm": 2.67720890045166,
|
| 196 |
+
"learning_rate": 4.996924113646208e-05,
|
| 197 |
+
"loss": 0.2939,
|
| 198 |
+
"step": 324
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.5968028419182948,
|
| 202 |
+
"grad_norm": 2.2791261672973633,
|
| 203 |
+
"learning_rate": 4.994802487705611e-05,
|
| 204 |
+
"loss": 0.2747,
|
| 205 |
+
"step": 336
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6181172291296625,
|
| 209 |
+
"grad_norm": 4.456598281860352,
|
| 210 |
+
"learning_rate": 4.992128250148999e-05,
|
| 211 |
+
"loss": 0.309,
|
| 212 |
+
"step": 348
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6394316163410302,
|
| 216 |
+
"grad_norm": 2.314068555831909,
|
| 217 |
+
"learning_rate": 4.988901993333783e-05,
|
| 218 |
+
"loss": 0.2831,
|
| 219 |
+
"step": 360
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.6607460035523979,
|
| 223 |
+
"grad_norm": 2.185884714126587,
|
| 224 |
+
"learning_rate": 4.985124431892483e-05,
|
| 225 |
+
"loss": 0.3332,
|
| 226 |
+
"step": 372
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.6820603907637656,
|
| 230 |
+
"grad_norm": 2.1526551246643066,
|
| 231 |
+
"learning_rate": 4.980796402574438e-05,
|
| 232 |
+
"loss": 0.2998,
|
| 233 |
+
"step": 384
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7033747779751333,
|
| 237 |
+
"grad_norm": 2.2564265727996826,
|
| 238 |
+
"learning_rate": 4.975918864060462e-05,
|
| 239 |
+
"loss": 0.3022,
|
| 240 |
+
"step": 396
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7246891651865008,
|
| 244 |
+
"grad_norm": 1.5854663848876953,
|
| 245 |
+
"learning_rate": 4.970492896750486e-05,
|
| 246 |
+
"loss": 0.2546,
|
| 247 |
+
"step": 408
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.7460035523978685,
|
| 251 |
+
"grad_norm": 2.35032057762146,
|
| 252 |
+
"learning_rate": 4.9645197025242506e-05,
|
| 253 |
+
"loss": 0.2988,
|
| 254 |
+
"step": 420
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.7673179396092362,
|
| 258 |
+
"grad_norm": 1.9311034679412842,
|
| 259 |
+
"learning_rate": 4.958000604475079e-05,
|
| 260 |
+
"loss": 0.2809,
|
| 261 |
+
"step": 432
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.7886323268206039,
|
| 265 |
+
"grad_norm": 1.361736536026001,
|
| 266 |
+
"learning_rate": 4.9509370466168054e-05,
|
| 267 |
+
"loss": 0.2804,
|
| 268 |
+
"step": 444
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8099467140319716,
|
| 272 |
+
"grad_norm": 2.174666166305542,
|
| 273 |
+
"learning_rate": 4.943330593563921e-05,
|
| 274 |
+
"loss": 0.3179,
|
| 275 |
+
"step": 456
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.8312611012433393,
|
| 279 |
+
"grad_norm": 1.4910300970077515,
|
| 280 |
+
"learning_rate": 4.935182930185e-05,
|
| 281 |
+
"loss": 0.2642,
|
| 282 |
+
"step": 468
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8525754884547069,
|
| 286 |
+
"grad_norm": 2.326056480407715,
|
| 287 |
+
"learning_rate": 4.926495861229497e-05,
|
| 288 |
+
"loss": 0.2706,
|
| 289 |
+
"step": 480
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8738898756660746,
|
| 293 |
+
"grad_norm": 2.49320912361145,
|
| 294 |
+
"learning_rate": 4.9172713109279834e-05,
|
| 295 |
+
"loss": 0.3165,
|
| 296 |
+
"step": 492
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8952042628774423,
|
| 300 |
+
"grad_norm": 1.5768948793411255,
|
| 301 |
+
"learning_rate": 4.907511322565917e-05,
|
| 302 |
+
"loss": 0.2513,
|
| 303 |
+
"step": 504
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.91651865008881,
|
| 307 |
+
"grad_norm": 1.4487340450286865,
|
| 308 |
+
"learning_rate": 4.897218058031051e-05,
|
| 309 |
+
"loss": 0.3164,
|
| 310 |
+
"step": 516
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.9378330373001776,
|
| 314 |
+
"grad_norm": 1.9721369743347168,
|
| 315 |
+
"learning_rate": 4.8863937973345596e-05,
|
| 316 |
+
"loss": 0.2512,
|
| 317 |
+
"step": 528
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.9591474245115453,
|
| 321 |
+
"grad_norm": 3.3567473888397217,
|
| 322 |
+
"learning_rate": 4.8750409381060036e-05,
|
| 323 |
+
"loss": 0.3204,
|
| 324 |
+
"step": 540
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.9804618117229129,
|
| 328 |
+
"grad_norm": 1.5789375305175781,
|
| 329 |
+
"learning_rate": 4.8631619950622463e-05,
|
| 330 |
+
"loss": 0.2856,
|
| 331 |
+
"step": 552
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.0,
|
| 335 |
+
"eval_accuracy": 0.9010161233451934,
|
| 336 |
+
"eval_f1": 0.7702541361077946,
|
| 337 |
+
"eval_loss": 0.28040045499801636,
|
| 338 |
+
"eval_precision": 0.7363443665416599,
|
| 339 |
+
"eval_recall": 0.8074378687645271,
|
| 340 |
+
"eval_runtime": 10.453,
|
| 341 |
+
"eval_samples_per_second": 95.666,
|
| 342 |
+
"eval_steps_per_second": 3.061,
|
| 343 |
+
"step": 563
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.0017761989342806,
|
| 347 |
+
"grad_norm": 1.2176109552383423,
|
| 348 |
+
"learning_rate": 4.8507595994504286e-05,
|
| 349 |
+
"loss": 0.2444,
|
| 350 |
+
"step": 564
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.0230905861456483,
|
| 354 |
+
"grad_norm": 1.8041757345199585,
|
| 355 |
+
"learning_rate": 4.8378364984651324e-05,
|
| 356 |
+
"loss": 0.2723,
|
| 357 |
+
"step": 576
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.044404973357016,
|
| 361 |
+
"grad_norm": 1.6936861276626587,
|
| 362 |
+
"learning_rate": 4.824395554639869e-05,
|
| 363 |
+
"loss": 0.2035,
|
| 364 |
+
"step": 588
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.0657193605683837,
|
| 368 |
+
"grad_norm": 2.040034294128418,
|
| 369 |
+
"learning_rate": 4.810439745213006e-05,
|
| 370 |
+
"loss": 0.1779,
|
| 371 |
+
"step": 600
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.0870337477797514,
|
| 375 |
+
"grad_norm": 2.7956368923187256,
|
| 376 |
+
"learning_rate": 4.7959721614682965e-05,
|
| 377 |
+
"loss": 0.2487,
|
| 378 |
+
"step": 612
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.108348134991119,
|
| 382 |
+
"grad_norm": 1.4671745300292969,
|
| 383 |
+
"learning_rate": 4.7809960080501464e-05,
|
| 384 |
+
"loss": 0.255,
|
| 385 |
+
"step": 624
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.1296625222024868,
|
| 389 |
+
"grad_norm": 1.8116635084152222,
|
| 390 |
+
"learning_rate": 4.765514602253765e-05,
|
| 391 |
+
"loss": 0.2165,
|
| 392 |
+
"step": 636
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.1509769094138544,
|
| 396 |
+
"grad_norm": 1.317562460899353,
|
| 397 |
+
"learning_rate": 4.7495313732903695e-05,
|
| 398 |
+
"loss": 0.2502,
|
| 399 |
+
"step": 648
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.1722912966252221,
|
| 403 |
+
"grad_norm": 2.6181671619415283,
|
| 404 |
+
"learning_rate": 4.733049861527596e-05,
|
| 405 |
+
"loss": 0.2559,
|
| 406 |
+
"step": 660
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.1936056838365896,
|
| 410 |
+
"grad_norm": 2.785849094390869,
|
| 411 |
+
"learning_rate": 4.7160737177052924e-05,
|
| 412 |
+
"loss": 0.2219,
|
| 413 |
+
"step": 672
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.2149200710479573,
|
| 417 |
+
"grad_norm": 1.9088388681411743,
|
| 418 |
+
"learning_rate": 4.698606702126854e-05,
|
| 419 |
+
"loss": 0.2741,
|
| 420 |
+
"step": 684
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.236234458259325,
|
| 424 |
+
"grad_norm": 1.3168236017227173,
|
| 425 |
+
"learning_rate": 4.6806526838263044e-05,
|
| 426 |
+
"loss": 0.241,
|
| 427 |
+
"step": 696
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 1.2575488454706927,
|
| 431 |
+
"grad_norm": 1.9296077489852905,
|
| 432 |
+
"learning_rate": 4.662215639711281e-05,
|
| 433 |
+
"loss": 0.2317,
|
| 434 |
+
"step": 708
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.2788632326820604,
|
| 438 |
+
"grad_norm": 2.858198404312134,
|
| 439 |
+
"learning_rate": 4.64329965368213e-05,
|
| 440 |
+
"loss": 0.2487,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.300177619893428,
|
| 445 |
+
"grad_norm": 2.6079294681549072,
|
| 446 |
+
"learning_rate": 4.623908915727303e-05,
|
| 447 |
+
"loss": 0.2328,
|
| 448 |
+
"step": 732
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.3214920071047958,
|
| 452 |
+
"grad_norm": 2.5267722606658936,
|
| 453 |
+
"learning_rate": 4.604047720995246e-05,
|
| 454 |
+
"loss": 0.2433,
|
| 455 |
+
"step": 744
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.3428063943161634,
|
| 459 |
+
"grad_norm": 1.4358534812927246,
|
| 460 |
+
"learning_rate": 4.583720468843014e-05,
|
| 461 |
+
"loss": 0.1994,
|
| 462 |
+
"step": 756
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.3641207815275311,
|
| 466 |
+
"grad_norm": 1.9639769792556763,
|
| 467 |
+
"learning_rate": 4.562931661861779e-05,
|
| 468 |
+
"loss": 0.2208,
|
| 469 |
+
"step": 768
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 1.3854351687388988,
|
| 473 |
+
"grad_norm": 1.2723311185836792,
|
| 474 |
+
"learning_rate": 4.541685904879489e-05,
|
| 475 |
+
"loss": 0.2077,
|
| 476 |
+
"step": 780
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.4067495559502663,
|
| 480 |
+
"grad_norm": 2.3694050312042236,
|
| 481 |
+
"learning_rate": 4.519987903940874e-05,
|
| 482 |
+
"loss": 0.2081,
|
| 483 |
+
"step": 792
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.428063943161634,
|
| 487 |
+
"grad_norm": 3.0022051334381104,
|
| 488 |
+
"learning_rate": 4.497842465265033e-05,
|
| 489 |
+
"loss": 0.2494,
|
| 490 |
+
"step": 804
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.4493783303730017,
|
| 494 |
+
"grad_norm": 1.4325857162475586,
|
| 495 |
+
"learning_rate": 4.4752544941808307e-05,
|
| 496 |
+
"loss": 0.2382,
|
| 497 |
+
"step": 816
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.4706927175843694,
|
| 501 |
+
"grad_norm": 2.299450159072876,
|
| 502 |
+
"learning_rate": 4.4522289940403404e-05,
|
| 503 |
+
"loss": 0.2452,
|
| 504 |
+
"step": 828
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.492007104795737,
|
| 508 |
+
"grad_norm": 2.6608004570007324,
|
| 509 |
+
"learning_rate": 4.4287710651105804e-05,
|
| 510 |
+
"loss": 0.248,
|
| 511 |
+
"step": 840
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.5133214920071048,
|
| 515 |
+
"grad_norm": 1.818243384361267,
|
| 516 |
+
"learning_rate": 4.404885903443775e-05,
|
| 517 |
+
"loss": 0.2115,
|
| 518 |
+
"step": 852
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.5346358792184724,
|
| 522 |
+
"grad_norm": 2.386474132537842,
|
| 523 |
+
"learning_rate": 4.3805787997264016e-05,
|
| 524 |
+
"loss": 0.2146,
|
| 525 |
+
"step": 864
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.5559502664298401,
|
| 529 |
+
"grad_norm": 1.1605068445205688,
|
| 530 |
+
"learning_rate": 4.3558551381072784e-05,
|
| 531 |
+
"loss": 0.2179,
|
| 532 |
+
"step": 876
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.5772646536412078,
|
| 536 |
+
"grad_norm": 1.1802736520767212,
|
| 537 |
+
"learning_rate": 4.3307203950049466e-05,
|
| 538 |
+
"loss": 0.2252,
|
| 539 |
+
"step": 888
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.5985790408525755,
|
| 543 |
+
"grad_norm": 2.108492374420166,
|
| 544 |
+
"learning_rate": 4.305180137894617e-05,
|
| 545 |
+
"loss": 0.2041,
|
| 546 |
+
"step": 900
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.6198934280639432,
|
| 550 |
+
"grad_norm": 1.5070841312408447,
|
| 551 |
+
"learning_rate": 4.279240024074943e-05,
|
| 552 |
+
"loss": 0.2082,
|
| 553 |
+
"step": 912
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 1.641207815275311,
|
| 557 |
+
"grad_norm": 1.7669801712036133,
|
| 558 |
+
"learning_rate": 4.252905799414901e-05,
|
| 559 |
+
"loss": 0.2227,
|
| 560 |
+
"step": 924
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.6625222024866786,
|
| 564 |
+
"grad_norm": 1.54999577999115,
|
| 565 |
+
"learning_rate": 4.226183297081052e-05,
|
| 566 |
+
"loss": 0.2264,
|
| 567 |
+
"step": 936
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.6838365896980463,
|
| 571 |
+
"grad_norm": 1.5729572772979736,
|
| 572 |
+
"learning_rate": 4.199078436245463e-05,
|
| 573 |
+
"loss": 0.2262,
|
| 574 |
+
"step": 948
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.705150976909414,
|
| 578 |
+
"grad_norm": 1.1744568347930908,
|
| 579 |
+
"learning_rate": 4.171597220774581e-05,
|
| 580 |
+
"loss": 0.2299,
|
| 581 |
+
"step": 960
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.7264653641207817,
|
| 585 |
+
"grad_norm": 1.6300952434539795,
|
| 586 |
+
"learning_rate": 4.1437457378993454e-05,
|
| 587 |
+
"loss": 0.2247,
|
| 588 |
+
"step": 972
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.7477797513321494,
|
| 592 |
+
"grad_norm": 2.633084774017334,
|
| 593 |
+
"learning_rate": 4.115530156866836e-05,
|
| 594 |
+
"loss": 0.2447,
|
| 595 |
+
"step": 984
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.7690941385435168,
|
| 599 |
+
"grad_norm": 0.7702670097351074,
|
| 600 |
+
"learning_rate": 4.086956727573751e-05,
|
| 601 |
+
"loss": 0.2379,
|
| 602 |
+
"step": 996
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.7904085257548845,
|
| 606 |
+
"grad_norm": 1.9031496047973633,
|
| 607 |
+
"learning_rate": 4.058031779182023e-05,
|
| 608 |
+
"loss": 0.2479,
|
| 609 |
+
"step": 1008
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.8117229129662522,
|
| 613 |
+
"grad_norm": 1.741963267326355,
|
| 614 |
+
"learning_rate": 4.02876171871688e-05,
|
| 615 |
+
"loss": 0.2206,
|
| 616 |
+
"step": 1020
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.83303730017762,
|
| 620 |
+
"grad_norm": 1.876193642616272,
|
| 621 |
+
"learning_rate": 3.999153029647651e-05,
|
| 622 |
+
"loss": 0.2063,
|
| 623 |
+
"step": 1032
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.8543516873889876,
|
| 627 |
+
"grad_norm": 1.2301545143127441,
|
| 628 |
+
"learning_rate": 3.96921227045165e-05,
|
| 629 |
+
"loss": 0.2082,
|
| 630 |
+
"step": 1044
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.8756660746003553,
|
| 634 |
+
"grad_norm": 1.319881558418274,
|
| 635 |
+
"learning_rate": 3.9389460731614324e-05,
|
| 636 |
+
"loss": 0.2225,
|
| 637 |
+
"step": 1056
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.8969804618117228,
|
| 641 |
+
"grad_norm": 1.2278847694396973,
|
| 642 |
+
"learning_rate": 3.908361141895775e-05,
|
| 643 |
+
"loss": 0.2003,
|
| 644 |
+
"step": 1068
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.9182948490230904,
|
| 648 |
+
"grad_norm": 3.362983226776123,
|
| 649 |
+
"learning_rate": 3.8774642513746694e-05,
|
| 650 |
+
"loss": 0.2491,
|
| 651 |
+
"step": 1080
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.9396092362344581,
|
| 655 |
+
"grad_norm": 1.619757056236267,
|
| 656 |
+
"learning_rate": 3.846262245418692e-05,
|
| 657 |
+
"loss": 0.2185,
|
| 658 |
+
"step": 1092
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.9609236234458258,
|
| 662 |
+
"grad_norm": 1.207379937171936,
|
| 663 |
+
"learning_rate": 3.8147620354330635e-05,
|
| 664 |
+
"loss": 0.2091,
|
| 665 |
+
"step": 1104
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 1.9822380106571935,
|
| 669 |
+
"grad_norm": 1.1611021757125854,
|
| 670 |
+
"learning_rate": 3.782970598876732e-05,
|
| 671 |
+
"loss": 0.2015,
|
| 672 |
+
"step": 1116
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.0,
|
| 676 |
+
"eval_accuracy": 0.9033240375677148,
|
| 677 |
+
"eval_f1": 0.7710292695789751,
|
| 678 |
+
"eval_loss": 0.2570085823535919,
|
| 679 |
+
"eval_precision": 0.758298755186722,
|
| 680 |
+
"eval_recall": 0.78419452887538,
|
| 681 |
+
"eval_runtime": 1.4477,
|
| 682 |
+
"eval_samples_per_second": 690.773,
|
| 683 |
+
"eval_steps_per_second": 22.105,
|
| 684 |
+
"step": 1126
|
| 685 |
+
}
|
| 686 |
+
],
|
| 687 |
+
"logging_steps": 12,
|
| 688 |
+
"max_steps": 2815,
|
| 689 |
+
"num_input_tokens_seen": 0,
|
| 690 |
+
"num_train_epochs": 5,
|
| 691 |
+
"save_steps": 500,
|
| 692 |
+
"stateful_callbacks": {
|
| 693 |
+
"EarlyStoppingCallback": {
|
| 694 |
+
"args": {
|
| 695 |
+
"early_stopping_patience": 5,
|
| 696 |
+
"early_stopping_threshold": 0.01
|
| 697 |
+
},
|
| 698 |
+
"attributes": {
|
| 699 |
+
"early_stopping_patience_counter": 0
|
| 700 |
+
}
|
| 701 |
+
},
|
| 702 |
+
"TrainerControl": {
|
| 703 |
+
"args": {
|
| 704 |
+
"should_epoch_stop": false,
|
| 705 |
+
"should_evaluate": false,
|
| 706 |
+
"should_log": false,
|
| 707 |
+
"should_save": true,
|
| 708 |
+
"should_training_stop": false
|
| 709 |
+
},
|
| 710 |
+
"attributes": {}
|
| 711 |
+
}
|
| 712 |
+
},
|
| 713 |
+
"total_flos": 6134236545024000.0,
|
| 714 |
+
"train_batch_size": 16,
|
| 715 |
+
"trial_name": null,
|
| 716 |
+
"trial_params": null
|
| 717 |
+
}
|
checkpoint-1126/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddf870ed58ce81c5c54fb364a5a1f1c1f56749052ffa20c960f53f1c9f16937f
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-base",
|
| 3 |
+
"_num_labels": 16,
|
| 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": 768,
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "O",
|
| 26 |
+
"1": "B-account_number",
|
| 27 |
+
"2": "B-private_address",
|
| 28 |
+
"3": "B-private_date",
|
| 29 |
+
"4": "B-private_email",
|
| 30 |
+
"5": "B-private_person",
|
| 31 |
+
"6": "B-private_phone",
|
| 32 |
+
"7": "B-private_url",
|
| 33 |
+
"8": "B-secret",
|
| 34 |
+
"9": "I-account_number",
|
| 35 |
+
"10": "I-private_address",
|
| 36 |
+
"11": "I-private_date",
|
| 37 |
+
"12": "I-private_email",
|
| 38 |
+
"13": "I-private_person",
|
| 39 |
+
"14": "I-private_phone",
|
| 40 |
+
"15": "I-secret"
|
| 41 |
+
},
|
| 42 |
+
"initializer_cutoff_factor": 2.0,
|
| 43 |
+
"initializer_range": 0.02,
|
| 44 |
+
"intermediate_size": 1152,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"B-account_number": 1,
|
| 47 |
+
"B-private_address": 2,
|
| 48 |
+
"B-private_date": 3,
|
| 49 |
+
"B-private_email": 4,
|
| 50 |
+
"B-private_person": 5,
|
| 51 |
+
"B-private_phone": 6,
|
| 52 |
+
"B-private_url": 7,
|
| 53 |
+
"B-secret": 8,
|
| 54 |
+
"I-account_number": 9,
|
| 55 |
+
"I-private_address": 10,
|
| 56 |
+
"I-private_date": 11,
|
| 57 |
+
"I-private_email": 12,
|
| 58 |
+
"I-private_person": 13,
|
| 59 |
+
"I-private_phone": 14,
|
| 60 |
+
"I-secret": 15,
|
| 61 |
+
"O": 0
|
| 62 |
+
},
|
| 63 |
+
"layer_norm_eps": 1e-05,
|
| 64 |
+
"local_attention": 128,
|
| 65 |
+
"local_rope_theta": 10000.0,
|
| 66 |
+
"max_position_embeddings": 8192,
|
| 67 |
+
"mlp_bias": false,
|
| 68 |
+
"mlp_dropout": 0.0,
|
| 69 |
+
"model_type": "modernbert",
|
| 70 |
+
"norm_bias": false,
|
| 71 |
+
"norm_eps": 1e-05,
|
| 72 |
+
"num_attention_heads": 12,
|
| 73 |
+
"num_hidden_layers": 22,
|
| 74 |
+
"pad_token_id": 50283,
|
| 75 |
+
"position_embedding_type": "absolute",
|
| 76 |
+
"reference_compile": true,
|
| 77 |
+
"repad_logits_with_grad": false,
|
| 78 |
+
"sep_token_id": 50282,
|
| 79 |
+
"sparse_pred_ignore_index": -100,
|
| 80 |
+
"sparse_prediction": false,
|
| 81 |
+
"torch_dtype": "float32",
|
| 82 |
+
"transformers_version": "4.48.0",
|
| 83 |
+
"vocab_size": 50368
|
| 84 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a428a73b8a6d4d1125cbf6efd7adf36b7445e2f5588435ad4712c9ebec3d85
|
| 3 |
+
size 598482856
|
runs/Apr23_01-03-59_r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j/events.out.tfevents.1776906240.r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j.105.0
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 sha256:3cd3bf515df1d28f7482a0a681389a6b11db0da7afdc63c7f7088c8d5f74e314
|
| 3 |
+
size 58689
|
runs/Apr23_01-03-59_r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j/events.out.tfevents.1776906612.r-pax-k-privacy-filter-mini-autotrain-ojwkttje-623d6-kr86j.105.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab791f6ede18caf820a823ed25d940603d64672bf12e54a1e5b9144c8ee48aac
|
| 3 |
+
size 560
|
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:ddf870ed58ce81c5c54fb364a5a1f1c1f56749052ffa20c960f53f1c9f16937f
|
| 3 |
+
size 5368
|
training_params.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "pax-k/privacy-filter-mini-data",
|
| 3 |
+
"model": "answerdotai/ModernBERT-base",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 5,
|
| 6 |
+
"max_seq_length": 512,
|
| 7 |
+
"batch_size": 16,
|
| 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": "privacy-filter-mini2",
|
| 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": "pax-k",
|
| 27 |
+
"log": "tensorboard",
|
| 28 |
+
"early_stopping_patience": 5,
|
| 29 |
+
"early_stopping_threshold": 0.01
|
| 30 |
+
}
|