Rami commited on
Commit
da7d3c1
1 Parent(s): 05227f9

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,13 +1,14 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "3rd party",
13
  "1": "accelerator: tpu",
@@ -56,6 +57,7 @@
56
  "44": "working as intended"
57
  },
58
  "initializer_range": 0.02,
 
59
  "label2id": {
60
  "3rd party": 0,
61
  "accelerator: tpu": 1,
@@ -103,17 +105,17 @@
103
  "won't fix": 43,
104
  "working as intended": 44
105
  },
 
106
  "max_position_embeddings": 512,
107
- "model_type": "distilbert",
108
- "n_heads": 12,
109
- "n_layers": 6,
110
  "pad_token_id": 0,
 
111
  "problem_type": "multi_label_classification",
112
- "qa_dropout": 0.1,
113
- "seq_classif_dropout": 0.2,
114
- "sinusoidal_pos_embds": false,
115
- "tie_weights_": true,
116
  "torch_dtype": "float32",
117
  "transformers_version": "4.25.1",
 
 
118
  "vocab_size": 30522
119
  }
 
1
  {
2
+ "_name_or_path": "neuralmagic/oBERT-12-upstream-pruned-unstructured-97",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "id2label": {
13
  "0": "3rd party",
14
  "1": "accelerator: tpu",
 
57
  "44": "working as intended"
58
  },
59
  "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
  "label2id": {
62
  "3rd party": 0,
63
  "accelerator: tpu": 1,
 
105
  "won't fix": 43,
106
  "working as intended": 44
107
  },
108
+ "layer_norm_eps": 1e-12,
109
  "max_position_embeddings": 512,
110
+ "model_type": "bert",
111
+ "num_attention_heads": 12,
112
+ "num_hidden_layers": 12,
113
  "pad_token_id": 0,
114
+ "position_embedding_type": "absolute",
115
  "problem_type": "multi_label_classification",
 
 
 
 
116
  "torch_dtype": "float32",
117
  "transformers_version": "4.25.1",
118
+ "type_vocab_size": 2,
119
+ "use_cache": true,
120
  "vocab_size": 30522
121
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7746a749f7ae77160f515d6e5da058fb9e4812fe5f3d027676e1b2f48b1c28e
3
- size 267987757
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc42fd396cf8948dbc33d18c9b7a311a3df761b365a10b1315889578f5b1762
3
+ size 438140149
runs/Jan08_19-21-52_50cc6bd24d93/1673205800.3757684/events.out.tfevents.1673205800.50cc6bd24d93.212.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ead9a71ca4fca0aff56849deb067c9a338c926623c51e5c3f7775eb065286a
3
+ size 5617
runs/Jan08_19-21-52_50cc6bd24d93/events.out.tfevents.1673205800.50cc6bd24d93.212.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d158261513413920a7a31f3464be5f326647f8e8c8f776da89557de2b9098fec
3
+ size 6077
runs/Jan08_19-39-39_50cc6bd24d93/1673206783.0456414/events.out.tfevents.1673206783.50cc6bd24d93.212.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b21df8cfccbcb612d6fc640e6a867119149b83035260114249b8726b63a7bba
3
+ size 5617
runs/Jan08_19-39-39_50cc6bd24d93/events.out.tfevents.1673206783.50cc6bd24d93.212.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb16c9c686978b5d5f5d06100a6788d6529581fb8bfed4b4b8245786cf806c5
3
+ size 4136
runs/Jan08_19-40-38_50cc6bd24d93/1673206842.1135204/events.out.tfevents.1673206842.50cc6bd24d93.212.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7118864f3df6e246cabc194f206f2736760dfa05dd3474861448f1c52c7095a
3
+ size 5617
runs/Jan08_19-40-38_50cc6bd24d93/events.out.tfevents.1673206842.50cc6bd24d93.212.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493dd40f6f11f78414fab96d2c41a6b635c17c471ebb6d8cb7e55f302a01e879
3
+ size 6445
tokenizer_config.json CHANGED
@@ -1,15 +1,16 @@
1
  {
2
  "cls_token": "[CLS]",
 
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
  "model_max_length": 512,
6
- "name_or_path": "distilbert-base-uncased",
 
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
10
  "strip_accents": null,
11
  "tokenize_chinese_chars": true,
12
- "tokenizer_class": "DistilBertTokenizer",
13
- "truncation": true,
14
  "unk_token": "[UNK]"
15
  }
 
1
  {
2
  "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
  "do_lower_case": true,
5
  "mask_token": "[MASK]",
6
  "model_max_length": 512,
7
+ "name_or_path": "neuralmagic/oBERT-12-upstream-pruned-unstructured-97",
8
+ "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
  "special_tokens_map_file": null,
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
 
15
  "unk_token": "[UNK]"
16
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d90f3ec95b666e1fdafb40ac1f8d63074a826e7433c787a55c867fb9f136192
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6ec9c9ca659acf27accff3e3121c52d315c243ee09d612ded942be789eae6f
3
  size 3515