End of training
Browse files- README.md +68 -0
- config.json +146 -0
- model.safetensors +3 -0
- runs/Mar03_17-10-22_712e06e696e9/events.out.tfevents.1709485824.712e06e696e9.384.0 +3 -0
- runs/Mar03_17-15-44_712e06e696e9/events.out.tfevents.1709486146.712e06e696e9.2791.0 +3 -0
- runs/Mar03_17-15-44_712e06e696e9/events.out.tfevents.1709488263.712e06e696e9.2791.1 +3 -0
- runs/Mar03_18-17-58_712e06e696e9/events.out.tfevents.1709489880.712e06e696e9.18779.0 +3 -0
- runs/Mar03_18-19-52_712e06e696e9/events.out.tfevents.1709489994.712e06e696e9.19532.0 +3 -0
- runs/Mar03_18-19-52_712e06e696e9/events.out.tfevents.1709492090.712e06e696e9.19532.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- precision
|
| 8 |
+
- recall
|
| 9 |
+
- f1
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: distilbert-base-uncased-finetuned-srl
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# distilbert-base-uncased-finetuned-srl
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1249
|
| 24 |
+
- Precision: 0.7177
|
| 25 |
+
- Recall: 0.7372
|
| 26 |
+
- F1: 0.7273
|
| 27 |
+
- Accuracy: 0.9650
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 2e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 16
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 3
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 0.1264 | 1.0 | 2531 | 0.1421 | 0.6992 | 0.6799 | 0.6894 | 0.9606 |
|
| 59 |
+
| 0.097 | 2.0 | 5062 | 0.1266 | 0.7220 | 0.7181 | 0.7200 | 0.9642 |
|
| 60 |
+
| 0.0839 | 3.0 | 7593 | 0.1249 | 0.7177 | 0.7372 | 0.7273 | 0.9650 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.38.1
|
| 66 |
+
- Pytorch 2.1.0+cu121
|
| 67 |
+
- Datasets 2.18.0
|
| 68 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6",
|
| 19 |
+
"7": "LABEL_7",
|
| 20 |
+
"8": "LABEL_8",
|
| 21 |
+
"9": "LABEL_9",
|
| 22 |
+
"10": "LABEL_10",
|
| 23 |
+
"11": "LABEL_11",
|
| 24 |
+
"12": "LABEL_12",
|
| 25 |
+
"13": "LABEL_13",
|
| 26 |
+
"14": "LABEL_14",
|
| 27 |
+
"15": "LABEL_15",
|
| 28 |
+
"16": "LABEL_16",
|
| 29 |
+
"17": "LABEL_17",
|
| 30 |
+
"18": "LABEL_18",
|
| 31 |
+
"19": "LABEL_19",
|
| 32 |
+
"20": "LABEL_20",
|
| 33 |
+
"21": "LABEL_21",
|
| 34 |
+
"22": "LABEL_22",
|
| 35 |
+
"23": "LABEL_23",
|
| 36 |
+
"24": "LABEL_24",
|
| 37 |
+
"25": "LABEL_25",
|
| 38 |
+
"26": "LABEL_26",
|
| 39 |
+
"27": "LABEL_27",
|
| 40 |
+
"28": "LABEL_28",
|
| 41 |
+
"29": "LABEL_29",
|
| 42 |
+
"30": "LABEL_30",
|
| 43 |
+
"31": "LABEL_31",
|
| 44 |
+
"32": "LABEL_32",
|
| 45 |
+
"33": "LABEL_33",
|
| 46 |
+
"34": "LABEL_34",
|
| 47 |
+
"35": "LABEL_35",
|
| 48 |
+
"36": "LABEL_36",
|
| 49 |
+
"37": "LABEL_37",
|
| 50 |
+
"38": "LABEL_38",
|
| 51 |
+
"39": "LABEL_39",
|
| 52 |
+
"40": "LABEL_40",
|
| 53 |
+
"41": "LABEL_41",
|
| 54 |
+
"42": "LABEL_42",
|
| 55 |
+
"43": "LABEL_43",
|
| 56 |
+
"44": "LABEL_44",
|
| 57 |
+
"45": "LABEL_45",
|
| 58 |
+
"46": "LABEL_46",
|
| 59 |
+
"47": "LABEL_47",
|
| 60 |
+
"48": "LABEL_48",
|
| 61 |
+
"49": "LABEL_49",
|
| 62 |
+
"50": "LABEL_50",
|
| 63 |
+
"51": "LABEL_51",
|
| 64 |
+
"52": "LABEL_52",
|
| 65 |
+
"53": "LABEL_53",
|
| 66 |
+
"54": "LABEL_54",
|
| 67 |
+
"55": "LABEL_55",
|
| 68 |
+
"56": "LABEL_56",
|
| 69 |
+
"57": "LABEL_57",
|
| 70 |
+
"58": "LABEL_58"
|
| 71 |
+
},
|
| 72 |
+
"initializer_range": 0.02,
|
| 73 |
+
"label2id": {
|
| 74 |
+
"LABEL_0": 0,
|
| 75 |
+
"LABEL_1": 1,
|
| 76 |
+
"LABEL_10": 10,
|
| 77 |
+
"LABEL_11": 11,
|
| 78 |
+
"LABEL_12": 12,
|
| 79 |
+
"LABEL_13": 13,
|
| 80 |
+
"LABEL_14": 14,
|
| 81 |
+
"LABEL_15": 15,
|
| 82 |
+
"LABEL_16": 16,
|
| 83 |
+
"LABEL_17": 17,
|
| 84 |
+
"LABEL_18": 18,
|
| 85 |
+
"LABEL_19": 19,
|
| 86 |
+
"LABEL_2": 2,
|
| 87 |
+
"LABEL_20": 20,
|
| 88 |
+
"LABEL_21": 21,
|
| 89 |
+
"LABEL_22": 22,
|
| 90 |
+
"LABEL_23": 23,
|
| 91 |
+
"LABEL_24": 24,
|
| 92 |
+
"LABEL_25": 25,
|
| 93 |
+
"LABEL_26": 26,
|
| 94 |
+
"LABEL_27": 27,
|
| 95 |
+
"LABEL_28": 28,
|
| 96 |
+
"LABEL_29": 29,
|
| 97 |
+
"LABEL_3": 3,
|
| 98 |
+
"LABEL_30": 30,
|
| 99 |
+
"LABEL_31": 31,
|
| 100 |
+
"LABEL_32": 32,
|
| 101 |
+
"LABEL_33": 33,
|
| 102 |
+
"LABEL_34": 34,
|
| 103 |
+
"LABEL_35": 35,
|
| 104 |
+
"LABEL_36": 36,
|
| 105 |
+
"LABEL_37": 37,
|
| 106 |
+
"LABEL_38": 38,
|
| 107 |
+
"LABEL_39": 39,
|
| 108 |
+
"LABEL_4": 4,
|
| 109 |
+
"LABEL_40": 40,
|
| 110 |
+
"LABEL_41": 41,
|
| 111 |
+
"LABEL_42": 42,
|
| 112 |
+
"LABEL_43": 43,
|
| 113 |
+
"LABEL_44": 44,
|
| 114 |
+
"LABEL_45": 45,
|
| 115 |
+
"LABEL_46": 46,
|
| 116 |
+
"LABEL_47": 47,
|
| 117 |
+
"LABEL_48": 48,
|
| 118 |
+
"LABEL_49": 49,
|
| 119 |
+
"LABEL_5": 5,
|
| 120 |
+
"LABEL_50": 50,
|
| 121 |
+
"LABEL_51": 51,
|
| 122 |
+
"LABEL_52": 52,
|
| 123 |
+
"LABEL_53": 53,
|
| 124 |
+
"LABEL_54": 54,
|
| 125 |
+
"LABEL_55": 55,
|
| 126 |
+
"LABEL_56": 56,
|
| 127 |
+
"LABEL_57": 57,
|
| 128 |
+
"LABEL_58": 58,
|
| 129 |
+
"LABEL_6": 6,
|
| 130 |
+
"LABEL_7": 7,
|
| 131 |
+
"LABEL_8": 8,
|
| 132 |
+
"LABEL_9": 9
|
| 133 |
+
},
|
| 134 |
+
"max_position_embeddings": 512,
|
| 135 |
+
"model_type": "distilbert",
|
| 136 |
+
"n_heads": 12,
|
| 137 |
+
"n_layers": 6,
|
| 138 |
+
"pad_token_id": 0,
|
| 139 |
+
"qa_dropout": 0.1,
|
| 140 |
+
"seq_classif_dropout": 0.2,
|
| 141 |
+
"sinusoidal_pos_embds": false,
|
| 142 |
+
"tie_weights_": true,
|
| 143 |
+
"torch_dtype": "float32",
|
| 144 |
+
"transformers_version": "4.38.1",
|
| 145 |
+
"vocab_size": 30522
|
| 146 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89f95b635203b16dadd9cdfc34657627a7f48f73cdf098d280ae3a20c69acbee
|
| 3 |
+
size 265645356
|
runs/Mar03_17-10-22_712e06e696e9/events.out.tfevents.1709485824.712e06e696e9.384.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f176c2870c16a81b4f220b49407a5de2be5a55f76e2d57833ce639fa0017ea85
|
| 3 |
+
size 6985
|
runs/Mar03_17-15-44_712e06e696e9/events.out.tfevents.1709486146.712e06e696e9.2791.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ce0c248287408a1c8d00b150baa3f535a417103ae7bd27111c83a1b52a84cbe
|
| 3 |
+
size 11963
|
runs/Mar03_17-15-44_712e06e696e9/events.out.tfevents.1709488263.712e06e696e9.2791.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:876c2c1588def375eb16db83a9b05da1940e284e52115e02e25a47723522b691
|
| 3 |
+
size 560
|
runs/Mar03_18-17-58_712e06e696e9/events.out.tfevents.1709489880.712e06e696e9.18779.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2a857b63e329f1b05e093c66565b895285630d2a0d56de3d3ed99f8dc0a6b8d
|
| 3 |
+
size 4184
|
runs/Mar03_18-19-52_712e06e696e9/events.out.tfevents.1709489994.712e06e696e9.19532.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbca9bfd141984e535b2bcf83ce65cba7afede82902613315e584195ca6f6b2e
|
| 3 |
+
size 11963
|
runs/Mar03_18-19-52_712e06e696e9/events.out.tfevents.1709492090.712e06e696e9.19532.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06fb7eef0b6eb6dfc932ec90850e582ee048f2065cca970b77b958a8495b4629
|
| 3 |
+
size 560
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:439730b15c41bb6ef1209cdcc4086858e8be604679fddd022b0cf0622cbec1fb
|
| 3 |
+
size 4984
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|