Upload 49 files
Browse files- ner_model/config.json +59 -0
- ner_model/model.safetensors +3 -0
- test_ner/checkpoint-1000/config.json +59 -0
- test_ner/checkpoint-1000/merges.txt +0 -0
- test_ner/checkpoint-1000/model.safetensors +3 -0
- test_ner/checkpoint-1000/rng_state.pth +3 -0
- test_ner/checkpoint-1000/scheduler.pt +3 -0
- test_ner/checkpoint-1000/special_tokens_map.json +51 -0
- test_ner/checkpoint-1000/tokenizer_config.json +56 -0
- test_ner/checkpoint-1000/trainer_state.json +116 -0
- test_ner/checkpoint-1000/training_args.bin +3 -0
- test_ner/checkpoint-1000/vocab.json +0 -0
- test_ner/checkpoint-1500/config.json +59 -0
- test_ner/checkpoint-1500/merges.txt +0 -0
- test_ner/checkpoint-1500/model.safetensors +3 -0
- test_ner/checkpoint-1500/optimizer.pt +3 -0
- test_ner/checkpoint-1500/rng_state.pth +3 -0
- test_ner/checkpoint-1500/scheduler.pt +3 -0
- test_ner/checkpoint-1500/special_tokens_map.json +51 -0
- test_ner/checkpoint-1500/tokenizer_config.json +56 -0
- test_ner/checkpoint-1500/trainer_state.json +173 -0
- test_ner/checkpoint-1500/training_args.bin +3 -0
- test_ner/checkpoint-1500/vocab.json +0 -0
- test_ner/checkpoint-2000/config.json +59 -0
- test_ner/checkpoint-2000/merges.txt +0 -0
- test_ner/checkpoint-2000/model.safetensors +3 -0
- test_ner/checkpoint-2000/optimizer.pt +3 -0
- test_ner/checkpoint-2000/rng_state.pth +3 -0
- test_ner/checkpoint-2000/scheduler.pt +3 -0
- test_ner/checkpoint-2000/special_tokens_map.json +51 -0
- test_ner/checkpoint-2000/tokenizer_config.json +56 -0
- test_ner/checkpoint-2000/trainer_state.json +230 -0
- test_ner/checkpoint-2000/training_args.bin +3 -0
- test_ner/checkpoint-2000/vocab.json +0 -0
- test_ner/checkpoint-500/config.json +59 -0
- test_ner/checkpoint-500/merges.txt +0 -0
- test_ner/checkpoint-500/model.safetensors +3 -0
- test_ner/checkpoint-500/optimizer.pt +3 -0
- test_ner/checkpoint-500/rng_state.pth +3 -0
- test_ner/checkpoint-500/scheduler.pt +3 -0
- test_ner/checkpoint-500/special_tokens_map.json +51 -0
- test_ner/checkpoint-500/tokenizer_config.json +56 -0
- test_ner/checkpoint-500/trainer_state.json +59 -0
- test_ner/checkpoint-500/training_args.bin +3 -0
- test_ner/checkpoint-500/vocab.json +0 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +51 -0
- tokenizer/tokenizer_config.json +56 -0
- tokenizer/vocab.json +0 -0
ner_model/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-callsign",
|
| 15 |
+
"1": "B-condition conjunction",
|
| 16 |
+
"10": "I-instruction type",
|
| 17 |
+
"11": "I-instruction unit",
|
| 18 |
+
"12": "I-instruction value",
|
| 19 |
+
"13": "O",
|
| 20 |
+
"2": "B-condition requirement",
|
| 21 |
+
"3": "B-instruction qualifier",
|
| 22 |
+
"4": "B-instruction type",
|
| 23 |
+
"5": "B-instruction unit",
|
| 24 |
+
"6": "B-instruction value",
|
| 25 |
+
"7": "I-callsign",
|
| 26 |
+
"8": "I-condition requirement",
|
| 27 |
+
"9": "I-instruction qualifier"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"B-callsign": "0",
|
| 33 |
+
"B-condition conjunction": "1",
|
| 34 |
+
"B-condition requirement": "2",
|
| 35 |
+
"B-instruction qualifier": "3",
|
| 36 |
+
"B-instruction type": "4",
|
| 37 |
+
"B-instruction unit": "5",
|
| 38 |
+
"B-instruction value": "6",
|
| 39 |
+
"I-callsign": "7",
|
| 40 |
+
"I-condition requirement": "8",
|
| 41 |
+
"I-instruction qualifier": "9",
|
| 42 |
+
"I-instruction type": "10",
|
| 43 |
+
"I-instruction unit": "11",
|
| 44 |
+
"I-instruction value": "12",
|
| 45 |
+
"O": "13"
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"max_position_embeddings": 514,
|
| 49 |
+
"model_type": "roberta",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.39.1",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
ner_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cde5008b0c1e8b590fa4605ca5dcb8807da60b1caba4b76a2cfd40d5e071bf01
|
| 3 |
+
size 496287152
|
test_ner/checkpoint-1000/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-callsign",
|
| 15 |
+
"1": "B-condition conjunction",
|
| 16 |
+
"10": "I-instruction type",
|
| 17 |
+
"11": "I-instruction unit",
|
| 18 |
+
"12": "I-instruction value",
|
| 19 |
+
"13": "O",
|
| 20 |
+
"2": "B-condition requirement",
|
| 21 |
+
"3": "B-instruction qualifier",
|
| 22 |
+
"4": "B-instruction type",
|
| 23 |
+
"5": "B-instruction unit",
|
| 24 |
+
"6": "B-instruction value",
|
| 25 |
+
"7": "I-callsign",
|
| 26 |
+
"8": "I-condition requirement",
|
| 27 |
+
"9": "I-instruction qualifier"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"B-callsign": "0",
|
| 33 |
+
"B-condition conjunction": "1",
|
| 34 |
+
"B-condition requirement": "2",
|
| 35 |
+
"B-instruction qualifier": "3",
|
| 36 |
+
"B-instruction type": "4",
|
| 37 |
+
"B-instruction unit": "5",
|
| 38 |
+
"B-instruction value": "6",
|
| 39 |
+
"I-callsign": "7",
|
| 40 |
+
"I-condition requirement": "8",
|
| 41 |
+
"I-instruction qualifier": "9",
|
| 42 |
+
"I-instruction type": "10",
|
| 43 |
+
"I-instruction unit": "11",
|
| 44 |
+
"I-instruction value": "12",
|
| 45 |
+
"O": "13"
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"max_position_embeddings": 514,
|
| 49 |
+
"model_type": "roberta",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.39.1",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
test_ner/checkpoint-1000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-1000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:520d9115eae82dbb25fb38b68b89a8cedb5e875c03011821dba452e7afc023f3
|
| 3 |
+
size 496287152
|
test_ner/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9176b64b569b8bca907482ec0f4b06a1200d8b006a084cdb6d4bb9b4db34452
|
| 3 |
+
size 14244
|
test_ner/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6b5012776f03aafcd3b72b0e840aa46e74cbd44b047aebdf9e90d9e5353e3ec
|
| 3 |
+
size 1064
|
test_ner/checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
test_ner/checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
test_ner/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.649717514124294,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.5113261938095093,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.1617,
|
| 16 |
+
"step": 177
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9871559395695364,
|
| 21 |
+
"eval_f1": 0.9942739560323971,
|
| 22 |
+
"eval_loss": 0.03775998204946518,
|
| 23 |
+
"eval_precision": 0.9954126025089182,
|
| 24 |
+
"eval_recall": 0.9931379115611415,
|
| 25 |
+
"eval_runtime": 9.8126,
|
| 26 |
+
"eval_samples_per_second": 30.777,
|
| 27 |
+
"eval_steps_per_second": 3.873,
|
| 28 |
+
"step": 177
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.3615623414516449,
|
| 33 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 34 |
+
"loss": 0.0372,
|
| 35 |
+
"step": 354
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9891608029801324,
|
| 40 |
+
"eval_f1": 0.9940221302774663,
|
| 41 |
+
"eval_loss": 0.03091522306203842,
|
| 42 |
+
"eval_precision": 0.9949474681420761,
|
| 43 |
+
"eval_recall": 0.9930985120102964,
|
| 44 |
+
"eval_runtime": 8.9145,
|
| 45 |
+
"eval_samples_per_second": 33.878,
|
| 46 |
+
"eval_steps_per_second": 4.263,
|
| 47 |
+
"step": 354
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 0.9381418824195862,
|
| 52 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 53 |
+
"loss": 0.0295,
|
| 54 |
+
"step": 531
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9920322847682119,
|
| 59 |
+
"eval_f1": 0.9952843510071654,
|
| 60 |
+
"eval_loss": 0.02342694066464901,
|
| 61 |
+
"eval_precision": 0.995460875505807,
|
| 62 |
+
"eval_recall": 0.9951078891033975,
|
| 63 |
+
"eval_runtime": 10.0078,
|
| 64 |
+
"eval_samples_per_second": 30.176,
|
| 65 |
+
"eval_steps_per_second": 3.797,
|
| 66 |
+
"step": 531
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 0.6691648364067078,
|
| 71 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 72 |
+
"loss": 0.0249,
|
| 73 |
+
"step": 708
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9922974441225165,
|
| 78 |
+
"eval_f1": 0.9952737388699671,
|
| 79 |
+
"eval_loss": 0.021945813670754433,
|
| 80 |
+
"eval_precision": 0.9956105478272869,
|
| 81 |
+
"eval_recall": 0.994937157716402,
|
| 82 |
+
"eval_runtime": 8.0868,
|
| 83 |
+
"eval_samples_per_second": 37.345,
|
| 84 |
+
"eval_steps_per_second": 4.699,
|
| 85 |
+
"step": 708
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.32520022988319397,
|
| 90 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 91 |
+
"loss": 0.0216,
|
| 92 |
+
"step": 885
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9924720612582781,
|
| 97 |
+
"eval_f1": 0.9952702525159629,
|
| 98 |
+
"eval_loss": 0.020533699542284012,
|
| 99 |
+
"eval_precision": 0.9956496024183479,
|
| 100 |
+
"eval_recall": 0.9948911915737494,
|
| 101 |
+
"eval_runtime": 8.3353,
|
| 102 |
+
"eval_samples_per_second": 36.231,
|
| 103 |
+
"eval_steps_per_second": 4.559,
|
| 104 |
+
"step": 885
|
| 105 |
+
}
|
| 106 |
+
],
|
| 107 |
+
"logging_steps": 500,
|
| 108 |
+
"max_steps": 2124,
|
| 109 |
+
"num_input_tokens_seen": 0,
|
| 110 |
+
"num_train_epochs": 12,
|
| 111 |
+
"save_steps": 500,
|
| 112 |
+
"total_flos": 2084067713587200.0,
|
| 113 |
+
"train_batch_size": 8,
|
| 114 |
+
"trial_name": null,
|
| 115 |
+
"trial_params": null
|
| 116 |
+
}
|
test_ner/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:589411fcaa1011d1bc4a7f79bb7f19351dcf5e1ecdfe5e386f38e11ad600452f
|
| 3 |
+
size 4920
|
test_ner/checkpoint-1000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-1500/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-callsign",
|
| 15 |
+
"1": "B-condition conjunction",
|
| 16 |
+
"10": "I-instruction type",
|
| 17 |
+
"11": "I-instruction unit",
|
| 18 |
+
"12": "I-instruction value",
|
| 19 |
+
"13": "O",
|
| 20 |
+
"2": "B-condition requirement",
|
| 21 |
+
"3": "B-instruction qualifier",
|
| 22 |
+
"4": "B-instruction type",
|
| 23 |
+
"5": "B-instruction unit",
|
| 24 |
+
"6": "B-instruction value",
|
| 25 |
+
"7": "I-callsign",
|
| 26 |
+
"8": "I-condition requirement",
|
| 27 |
+
"9": "I-instruction qualifier"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"B-callsign": "0",
|
| 33 |
+
"B-condition conjunction": "1",
|
| 34 |
+
"B-condition requirement": "2",
|
| 35 |
+
"B-instruction qualifier": "3",
|
| 36 |
+
"B-instruction type": "4",
|
| 37 |
+
"B-instruction unit": "5",
|
| 38 |
+
"B-instruction value": "6",
|
| 39 |
+
"I-callsign": "7",
|
| 40 |
+
"I-condition requirement": "8",
|
| 41 |
+
"I-instruction qualifier": "9",
|
| 42 |
+
"I-instruction type": "10",
|
| 43 |
+
"I-instruction unit": "11",
|
| 44 |
+
"I-instruction value": "12",
|
| 45 |
+
"O": "13"
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"max_position_embeddings": 514,
|
| 49 |
+
"model_type": "roberta",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.39.1",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
test_ner/checkpoint-1500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-1500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cb114253fe876001a85cb79c7ed3eb75baac508e8cd70e8ca3a119d85e9ba6b
|
| 3 |
+
size 496287152
|
test_ner/checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:759dbec0c5ab3216b786c83ff729abf1e3a21b71e2e0f4e2c575b56ebddefa2a
|
| 3 |
+
size 992692794
|
test_ner/checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3dfb2abfecea1eda6f9930fba39d6248eb797844e9d8b7377defd90d15734fb
|
| 3 |
+
size 14244
|
test_ner/checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc7b369353de906a352aa3b98a50910b2a8af028f3024d216feb0c91f655fee7
|
| 3 |
+
size 1064
|
test_ner/checkpoint-1500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
test_ner/checkpoint-1500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
test_ner/checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.474576271186441,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.5113261938095093,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.1617,
|
| 16 |
+
"step": 177
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9871559395695364,
|
| 21 |
+
"eval_f1": 0.9942739560323971,
|
| 22 |
+
"eval_loss": 0.03775998204946518,
|
| 23 |
+
"eval_precision": 0.9954126025089182,
|
| 24 |
+
"eval_recall": 0.9931379115611415,
|
| 25 |
+
"eval_runtime": 9.8126,
|
| 26 |
+
"eval_samples_per_second": 30.777,
|
| 27 |
+
"eval_steps_per_second": 3.873,
|
| 28 |
+
"step": 177
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.3615623414516449,
|
| 33 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 34 |
+
"loss": 0.0372,
|
| 35 |
+
"step": 354
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9891608029801324,
|
| 40 |
+
"eval_f1": 0.9940221302774663,
|
| 41 |
+
"eval_loss": 0.03091522306203842,
|
| 42 |
+
"eval_precision": 0.9949474681420761,
|
| 43 |
+
"eval_recall": 0.9930985120102964,
|
| 44 |
+
"eval_runtime": 8.9145,
|
| 45 |
+
"eval_samples_per_second": 33.878,
|
| 46 |
+
"eval_steps_per_second": 4.263,
|
| 47 |
+
"step": 354
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 0.9381418824195862,
|
| 52 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 53 |
+
"loss": 0.0295,
|
| 54 |
+
"step": 531
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9920322847682119,
|
| 59 |
+
"eval_f1": 0.9952843510071654,
|
| 60 |
+
"eval_loss": 0.02342694066464901,
|
| 61 |
+
"eval_precision": 0.995460875505807,
|
| 62 |
+
"eval_recall": 0.9951078891033975,
|
| 63 |
+
"eval_runtime": 10.0078,
|
| 64 |
+
"eval_samples_per_second": 30.176,
|
| 65 |
+
"eval_steps_per_second": 3.797,
|
| 66 |
+
"step": 531
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 0.6691648364067078,
|
| 71 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 72 |
+
"loss": 0.0249,
|
| 73 |
+
"step": 708
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9922974441225165,
|
| 78 |
+
"eval_f1": 0.9952737388699671,
|
| 79 |
+
"eval_loss": 0.021945813670754433,
|
| 80 |
+
"eval_precision": 0.9956105478272869,
|
| 81 |
+
"eval_recall": 0.994937157716402,
|
| 82 |
+
"eval_runtime": 8.0868,
|
| 83 |
+
"eval_samples_per_second": 37.345,
|
| 84 |
+
"eval_steps_per_second": 4.699,
|
| 85 |
+
"step": 708
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.32520022988319397,
|
| 90 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 91 |
+
"loss": 0.0216,
|
| 92 |
+
"step": 885
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9924720612582781,
|
| 97 |
+
"eval_f1": 0.9952702525159629,
|
| 98 |
+
"eval_loss": 0.020533699542284012,
|
| 99 |
+
"eval_precision": 0.9956496024183479,
|
| 100 |
+
"eval_recall": 0.9948911915737494,
|
| 101 |
+
"eval_runtime": 8.3353,
|
| 102 |
+
"eval_samples_per_second": 36.231,
|
| 103 |
+
"eval_steps_per_second": 4.559,
|
| 104 |
+
"step": 885
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 0.5477111339569092,
|
| 109 |
+
"learning_rate": 1e-05,
|
| 110 |
+
"loss": 0.0195,
|
| 111 |
+
"step": 1062
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9939078021523179,
|
| 116 |
+
"eval_f1": 0.9962434901391617,
|
| 117 |
+
"eval_loss": 0.017846418544650078,
|
| 118 |
+
"eval_precision": 0.9963547276883062,
|
| 119 |
+
"eval_recall": 0.9961322774253707,
|
| 120 |
+
"eval_runtime": 8.2755,
|
| 121 |
+
"eval_samples_per_second": 36.493,
|
| 122 |
+
"eval_steps_per_second": 4.592,
|
| 123 |
+
"step": 1062
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 0.6245275139808655,
|
| 128 |
+
"learning_rate": 8.333333333333334e-06,
|
| 129 |
+
"loss": 0.0176,
|
| 130 |
+
"step": 1239
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9940048116721855,
|
| 135 |
+
"eval_f1": 0.9963592671260534,
|
| 136 |
+
"eval_loss": 0.018705232068896294,
|
| 137 |
+
"eval_precision": 0.9962382568620628,
|
| 138 |
+
"eval_recall": 0.9964803067911693,
|
| 139 |
+
"eval_runtime": 9.9312,
|
| 140 |
+
"eval_samples_per_second": 30.409,
|
| 141 |
+
"eval_steps_per_second": 3.826,
|
| 142 |
+
"step": 1239
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.6405406594276428,
|
| 147 |
+
"learning_rate": 6.666666666666667e-06,
|
| 148 |
+
"loss": 0.0162,
|
| 149 |
+
"step": 1416
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9943411113410596,
|
| 154 |
+
"eval_f1": 0.9965161599611229,
|
| 155 |
+
"eval_loss": 0.017182840034365654,
|
| 156 |
+
"eval_precision": 0.9965914240491781,
|
| 157 |
+
"eval_recall": 0.9964409072403241,
|
| 158 |
+
"eval_runtime": 8.8446,
|
| 159 |
+
"eval_samples_per_second": 34.145,
|
| 160 |
+
"eval_steps_per_second": 4.296,
|
| 161 |
+
"step": 1416
|
| 162 |
+
}
|
| 163 |
+
],
|
| 164 |
+
"logging_steps": 500,
|
| 165 |
+
"max_steps": 2124,
|
| 166 |
+
"num_input_tokens_seen": 0,
|
| 167 |
+
"num_train_epochs": 12,
|
| 168 |
+
"save_steps": 500,
|
| 169 |
+
"total_flos": 3125448257617920.0,
|
| 170 |
+
"train_batch_size": 8,
|
| 171 |
+
"trial_name": null,
|
| 172 |
+
"trial_params": null
|
| 173 |
+
}
|
test_ner/checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:589411fcaa1011d1bc4a7f79bb7f19351dcf5e1ecdfe5e386f38e11ad600452f
|
| 3 |
+
size 4920
|
test_ner/checkpoint-1500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-callsign",
|
| 15 |
+
"1": "B-condition conjunction",
|
| 16 |
+
"10": "I-instruction type",
|
| 17 |
+
"11": "I-instruction unit",
|
| 18 |
+
"12": "I-instruction value",
|
| 19 |
+
"13": "O",
|
| 20 |
+
"2": "B-condition requirement",
|
| 21 |
+
"3": "B-instruction qualifier",
|
| 22 |
+
"4": "B-instruction type",
|
| 23 |
+
"5": "B-instruction unit",
|
| 24 |
+
"6": "B-instruction value",
|
| 25 |
+
"7": "I-callsign",
|
| 26 |
+
"8": "I-condition requirement",
|
| 27 |
+
"9": "I-instruction qualifier"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"B-callsign": "0",
|
| 33 |
+
"B-condition conjunction": "1",
|
| 34 |
+
"B-condition requirement": "2",
|
| 35 |
+
"B-instruction qualifier": "3",
|
| 36 |
+
"B-instruction type": "4",
|
| 37 |
+
"B-instruction unit": "5",
|
| 38 |
+
"B-instruction value": "6",
|
| 39 |
+
"I-callsign": "7",
|
| 40 |
+
"I-condition requirement": "8",
|
| 41 |
+
"I-instruction qualifier": "9",
|
| 42 |
+
"I-instruction type": "10",
|
| 43 |
+
"I-instruction unit": "11",
|
| 44 |
+
"I-instruction value": "12",
|
| 45 |
+
"O": "13"
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"max_position_embeddings": 514,
|
| 49 |
+
"model_type": "roberta",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.39.1",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
test_ner/checkpoint-2000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63e4476d5dc931bdb8e8c0de135d136ac59f01852feaa5d48aaf0042f486fb05
|
| 3 |
+
size 496287152
|
test_ner/checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e54951f4afd1c950dc282458e6b92468272aeb623d3f3a0859c14bcb52d7206
|
| 3 |
+
size 992692794
|
test_ner/checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:814bf20401ee76a36f4021cc32fbf8663152c79b1d68538e9315ee92678820ce
|
| 3 |
+
size 14244
|
test_ner/checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39b8d1c11e09e5bfc35e2cf80dd825f265a89a10a0203834b563f8b3e8e69668
|
| 3 |
+
size 1064
|
test_ner/checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
test_ner/checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
test_ner/checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,230 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.299435028248588,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.5113261938095093,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.1617,
|
| 16 |
+
"step": 177
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9871559395695364,
|
| 21 |
+
"eval_f1": 0.9942739560323971,
|
| 22 |
+
"eval_loss": 0.03775998204946518,
|
| 23 |
+
"eval_precision": 0.9954126025089182,
|
| 24 |
+
"eval_recall": 0.9931379115611415,
|
| 25 |
+
"eval_runtime": 9.8126,
|
| 26 |
+
"eval_samples_per_second": 30.777,
|
| 27 |
+
"eval_steps_per_second": 3.873,
|
| 28 |
+
"step": 177
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.3615623414516449,
|
| 33 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 34 |
+
"loss": 0.0372,
|
| 35 |
+
"step": 354
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9891608029801324,
|
| 40 |
+
"eval_f1": 0.9940221302774663,
|
| 41 |
+
"eval_loss": 0.03091522306203842,
|
| 42 |
+
"eval_precision": 0.9949474681420761,
|
| 43 |
+
"eval_recall": 0.9930985120102964,
|
| 44 |
+
"eval_runtime": 8.9145,
|
| 45 |
+
"eval_samples_per_second": 33.878,
|
| 46 |
+
"eval_steps_per_second": 4.263,
|
| 47 |
+
"step": 354
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 0.9381418824195862,
|
| 52 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 53 |
+
"loss": 0.0295,
|
| 54 |
+
"step": 531
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.9920322847682119,
|
| 59 |
+
"eval_f1": 0.9952843510071654,
|
| 60 |
+
"eval_loss": 0.02342694066464901,
|
| 61 |
+
"eval_precision": 0.995460875505807,
|
| 62 |
+
"eval_recall": 0.9951078891033975,
|
| 63 |
+
"eval_runtime": 10.0078,
|
| 64 |
+
"eval_samples_per_second": 30.176,
|
| 65 |
+
"eval_steps_per_second": 3.797,
|
| 66 |
+
"step": 531
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 0.6691648364067078,
|
| 71 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 72 |
+
"loss": 0.0249,
|
| 73 |
+
"step": 708
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.9922974441225165,
|
| 78 |
+
"eval_f1": 0.9952737388699671,
|
| 79 |
+
"eval_loss": 0.021945813670754433,
|
| 80 |
+
"eval_precision": 0.9956105478272869,
|
| 81 |
+
"eval_recall": 0.994937157716402,
|
| 82 |
+
"eval_runtime": 8.0868,
|
| 83 |
+
"eval_samples_per_second": 37.345,
|
| 84 |
+
"eval_steps_per_second": 4.699,
|
| 85 |
+
"step": 708
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 0.32520022988319397,
|
| 90 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 91 |
+
"loss": 0.0216,
|
| 92 |
+
"step": 885
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.9924720612582781,
|
| 97 |
+
"eval_f1": 0.9952702525159629,
|
| 98 |
+
"eval_loss": 0.020533699542284012,
|
| 99 |
+
"eval_precision": 0.9956496024183479,
|
| 100 |
+
"eval_recall": 0.9948911915737494,
|
| 101 |
+
"eval_runtime": 8.3353,
|
| 102 |
+
"eval_samples_per_second": 36.231,
|
| 103 |
+
"eval_steps_per_second": 4.559,
|
| 104 |
+
"step": 885
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 0.5477111339569092,
|
| 109 |
+
"learning_rate": 1e-05,
|
| 110 |
+
"loss": 0.0195,
|
| 111 |
+
"step": 1062
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.9939078021523179,
|
| 116 |
+
"eval_f1": 0.9962434901391617,
|
| 117 |
+
"eval_loss": 0.017846418544650078,
|
| 118 |
+
"eval_precision": 0.9963547276883062,
|
| 119 |
+
"eval_recall": 0.9961322774253707,
|
| 120 |
+
"eval_runtime": 8.2755,
|
| 121 |
+
"eval_samples_per_second": 36.493,
|
| 122 |
+
"eval_steps_per_second": 4.592,
|
| 123 |
+
"step": 1062
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 0.6245275139808655,
|
| 128 |
+
"learning_rate": 8.333333333333334e-06,
|
| 129 |
+
"loss": 0.0176,
|
| 130 |
+
"step": 1239
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.9940048116721855,
|
| 135 |
+
"eval_f1": 0.9963592671260534,
|
| 136 |
+
"eval_loss": 0.018705232068896294,
|
| 137 |
+
"eval_precision": 0.9962382568620628,
|
| 138 |
+
"eval_recall": 0.9964803067911693,
|
| 139 |
+
"eval_runtime": 9.9312,
|
| 140 |
+
"eval_samples_per_second": 30.409,
|
| 141 |
+
"eval_steps_per_second": 3.826,
|
| 142 |
+
"step": 1239
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 0.6405406594276428,
|
| 147 |
+
"learning_rate": 6.666666666666667e-06,
|
| 148 |
+
"loss": 0.0162,
|
| 149 |
+
"step": 1416
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.9943411113410596,
|
| 154 |
+
"eval_f1": 0.9965161599611229,
|
| 155 |
+
"eval_loss": 0.017182840034365654,
|
| 156 |
+
"eval_precision": 0.9965914240491781,
|
| 157 |
+
"eval_recall": 0.9964409072403241,
|
| 158 |
+
"eval_runtime": 8.8446,
|
| 159 |
+
"eval_samples_per_second": 34.145,
|
| 160 |
+
"eval_steps_per_second": 4.296,
|
| 161 |
+
"step": 1416
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 0.8095843195915222,
|
| 166 |
+
"learning_rate": 5e-06,
|
| 167 |
+
"loss": 0.015,
|
| 168 |
+
"step": 1593
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.9945998033940397,
|
| 173 |
+
"eval_f1": 0.9968834461401037,
|
| 174 |
+
"eval_loss": 0.016317149624228477,
|
| 175 |
+
"eval_precision": 0.9971093898841785,
|
| 176 |
+
"eval_recall": 0.9966576047699723,
|
| 177 |
+
"eval_runtime": 8.7858,
|
| 178 |
+
"eval_samples_per_second": 34.374,
|
| 179 |
+
"eval_steps_per_second": 4.325,
|
| 180 |
+
"step": 1593
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 0.3927808701992035,
|
| 185 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 186 |
+
"loss": 0.0141,
|
| 187 |
+
"step": 1770
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.9948067570364238,
|
| 192 |
+
"eval_f1": 0.9970283537736623,
|
| 193 |
+
"eval_loss": 0.016839241608977318,
|
| 194 |
+
"eval_precision": 0.9971167550029884,
|
| 195 |
+
"eval_recall": 0.9969399682176957,
|
| 196 |
+
"eval_runtime": 9.7882,
|
| 197 |
+
"eval_samples_per_second": 30.853,
|
| 198 |
+
"eval_steps_per_second": 3.882,
|
| 199 |
+
"step": 1770
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 0.5813747644424438,
|
| 204 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 205 |
+
"loss": 0.0133,
|
| 206 |
+
"step": 1947
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.9949037665562914,
|
| 211 |
+
"eval_f1": 0.9969725029716755,
|
| 212 |
+
"eval_loss": 0.0163129735738039,
|
| 213 |
+
"eval_precision": 0.9970707229928542,
|
| 214 |
+
"eval_recall": 0.9968743022996205,
|
| 215 |
+
"eval_runtime": 8.115,
|
| 216 |
+
"eval_samples_per_second": 37.215,
|
| 217 |
+
"eval_steps_per_second": 4.683,
|
| 218 |
+
"step": 1947
|
| 219 |
+
}
|
| 220 |
+
],
|
| 221 |
+
"logging_steps": 500,
|
| 222 |
+
"max_steps": 2124,
|
| 223 |
+
"num_input_tokens_seen": 0,
|
| 224 |
+
"num_train_epochs": 12,
|
| 225 |
+
"save_steps": 500,
|
| 226 |
+
"total_flos": 4166828801648640.0,
|
| 227 |
+
"train_batch_size": 8,
|
| 228 |
+
"trial_name": null,
|
| 229 |
+
"trial_params": null
|
| 230 |
+
}
|
test_ner/checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:589411fcaa1011d1bc4a7f79bb7f19351dcf5e1ecdfe5e386f38e11ad600452f
|
| 3 |
+
size 4920
|
test_ner/checkpoint-2000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "B-callsign",
|
| 15 |
+
"1": "B-condition conjunction",
|
| 16 |
+
"10": "I-instruction type",
|
| 17 |
+
"11": "I-instruction unit",
|
| 18 |
+
"12": "I-instruction value",
|
| 19 |
+
"13": "O",
|
| 20 |
+
"2": "B-condition requirement",
|
| 21 |
+
"3": "B-instruction qualifier",
|
| 22 |
+
"4": "B-instruction type",
|
| 23 |
+
"5": "B-instruction unit",
|
| 24 |
+
"6": "B-instruction value",
|
| 25 |
+
"7": "I-callsign",
|
| 26 |
+
"8": "I-condition requirement",
|
| 27 |
+
"9": "I-instruction qualifier"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"B-callsign": "0",
|
| 33 |
+
"B-condition conjunction": "1",
|
| 34 |
+
"B-condition requirement": "2",
|
| 35 |
+
"B-instruction qualifier": "3",
|
| 36 |
+
"B-instruction type": "4",
|
| 37 |
+
"B-instruction unit": "5",
|
| 38 |
+
"B-instruction value": "6",
|
| 39 |
+
"I-callsign": "7",
|
| 40 |
+
"I-condition requirement": "8",
|
| 41 |
+
"I-instruction qualifier": "9",
|
| 42 |
+
"I-instruction type": "10",
|
| 43 |
+
"I-instruction unit": "11",
|
| 44 |
+
"I-instruction value": "12",
|
| 45 |
+
"O": "13"
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"max_position_embeddings": 514,
|
| 49 |
+
"model_type": "roberta",
|
| 50 |
+
"num_attention_heads": 12,
|
| 51 |
+
"num_hidden_layers": 12,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"torch_dtype": "float32",
|
| 55 |
+
"transformers_version": "4.39.1",
|
| 56 |
+
"type_vocab_size": 1,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 50265
|
| 59 |
+
}
|
test_ner/checkpoint-500/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
test_ner/checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60c25af67f5a0adae595836902c211e42a4c2002e24a9d44b84068ad16c572a7
|
| 3 |
+
size 496287152
|
test_ner/checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6005a81030b2410fd4894e22c78b4a539f6cc593fcacb69f8037836792b6bc4
|
| 3 |
+
size 992692794
|
test_ner/checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28e4535b8c14579a7d5d4f4aa94c3b782c0fa4069392a0636498e5d337f93ba7
|
| 3 |
+
size 14244
|
test_ner/checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b7091ce6d9cd0c3bec5f24484d6956083f067a883a5198af4777d551490cd99
|
| 3 |
+
size 1064
|
test_ner/checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
test_ner/checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
test_ner/checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.824858757062147,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.5113261938095093,
|
| 14 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 15 |
+
"loss": 0.1617,
|
| 16 |
+
"step": 177
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9871559395695364,
|
| 21 |
+
"eval_f1": 0.9942739560323971,
|
| 22 |
+
"eval_loss": 0.03775998204946518,
|
| 23 |
+
"eval_precision": 0.9954126025089182,
|
| 24 |
+
"eval_recall": 0.9931379115611415,
|
| 25 |
+
"eval_runtime": 9.8126,
|
| 26 |
+
"eval_samples_per_second": 30.777,
|
| 27 |
+
"eval_steps_per_second": 3.873,
|
| 28 |
+
"step": 177
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 0.3615623414516449,
|
| 33 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 34 |
+
"loss": 0.0372,
|
| 35 |
+
"step": 354
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.9891608029801324,
|
| 40 |
+
"eval_f1": 0.9940221302774663,
|
| 41 |
+
"eval_loss": 0.03091522306203842,
|
| 42 |
+
"eval_precision": 0.9949474681420761,
|
| 43 |
+
"eval_recall": 0.9930985120102964,
|
| 44 |
+
"eval_runtime": 8.9145,
|
| 45 |
+
"eval_samples_per_second": 33.878,
|
| 46 |
+
"eval_steps_per_second": 4.263,
|
| 47 |
+
"step": 354
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"logging_steps": 500,
|
| 51 |
+
"max_steps": 2124,
|
| 52 |
+
"num_input_tokens_seen": 0,
|
| 53 |
+
"num_train_epochs": 12,
|
| 54 |
+
"save_steps": 500,
|
| 55 |
+
"total_flos": 1042687169556480.0,
|
| 56 |
+
"train_batch_size": 8,
|
| 57 |
+
"trial_name": null,
|
| 58 |
+
"trial_params": null
|
| 59 |
+
}
|
test_ner/checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:589411fcaa1011d1bc4a7f79bb7f19351dcf5e1ecdfe5e386f38e11ad600452f
|
| 3 |
+
size 4920
|
test_ner/checkpoint-500/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|