Hugging Face's logo

moshew
/
MiniLM-L6-clinc-distilled

Text Classification
Transformers
PyTorch
TensorBoard
roberta
Inference Endpoints
Model card Files Metrics Community
moshew commited on
Commit
e300358
•
1 Parent(s): db15683

Training in progress, epoch 1

Browse files
Files changed (12) hide show
  1. config.json +10 -9
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. runs/May10_16-56-13_25056aed8f14/events.out.tfevents.1652201836.25056aed8f14.79.10 +2 -2
  5. runs/May10_16-56-13_25056aed8f14/events.out.tfevents.1652202034.25056aed8f14.79.12 +3 -0
  6. runs/May10_17-13-30_25056aed8f14/1652202836.6342902/events.out.tfevents.1652202836.25056aed8f14.79.17 +3 -0
  7. runs/May10_17-13-30_25056aed8f14/events.out.tfevents.1652202836.25056aed8f14.79.16 +3 -0
  8. special_tokens_map.json +1 -1
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +1 -1
  11. training_args.bin +1 -1
  12. vocab.json +0 -0
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
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": 384,
@@ -317,16 +318,16 @@
317
  "who_made_you": "96",
318
  "yes": "107"
319
  },
320
- "layer_norm_eps": 1e-12,
321
- "max_position_embeddings": 512,
322
- "model_type": "bert",
323
  "num_attention_heads": 12,
324
  "num_hidden_layers": 6,
325
- "pad_token_id": 0,
326
  "position_embedding_type": "absolute",
327
  "torch_dtype": "float32",
328
  "transformers_version": "4.18.0",
329
- "type_vocab_size": 2,
330
  "use_cache": true,
331
- "vocab_size": 30522
332
  }
 
1
  {
2
+ "_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
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": 384,
 
318
  "who_made_you": "96",
319
  "yes": "107"
320
  },
321
+ "layer_norm_eps": 1e-05,
322
+ "max_position_embeddings": 514,
323
+ "model_type": "roberta",
324
  "num_attention_heads": 12,
325
  "num_hidden_layers": 6,
326
+ "pad_token_id": 1,
327
  "position_embedding_type": "absolute",
328
  "torch_dtype": "float32",
329
  "transformers_version": "4.18.0",
330
+ "type_vocab_size": 1,
331
  "use_cache": true,
332
+ "vocab_size": 50265
333
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc1ef51d3bfdf7642504d4c051ffa8d159abc39781c48a91349c638f9a4c5fe
3
- size 91124013
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:babcc0e20feaa51fd82ad9211bfd136eb86ad473aa4cbf49f94e3cc013ba9e40
3
+ size 121451181
runs/May10_16-56-13_25056aed8f14/events.out.tfevents.1652201836.25056aed8f14.79.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86f2b6dd0ef3956a927f5163f23550a6522c3ebb131c493aa31725d36057ac6a
3
- size 13050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4474e5313ae62a1e7145701d396c78785b0d8e34dd0c6e757631566bb9b66cf
3
+ size 14050
runs/May10_16-56-13_25056aed8f14/events.out.tfevents.1652202034.25056aed8f14.79.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f0da772cf0e7e29d7a25c7d11f472447c3ef18df8083470a3a9fd729f7c75f
3
+ size 363
runs/May10_17-13-30_25056aed8f14/1652202836.6342902/events.out.tfevents.1652202836.25056aed8f14.79.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515d2e78b1cde0a6982def92f2e6a29141a54a8aadb3229d71705d587adfc891
3
+ size 4892
runs/May10_17-13-30_25056aed8f14/events.out.tfevents.1652202836.25056aed8f14.79.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f48dbd70db264aa4c08dd597ec67b693774dc96f9cd5683cc3f0e3cac07437
3
+ size 11643
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "nreimers/MiniLM-L6-H384-uncased", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/4bab06d0845c01b218fc031866e62ccf55a15d3f649549f76c89e002ba24d5d9.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_class": "BertTokenizer"}
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large", "tokenizer_class": "RobertaTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83648aebd52f4d37ad11f6b43818dfaf2ad6df5f776112a532a8295a83b38e6d
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f21e0e9e24d64a19aa3801cb64eebc48dd98f8e65adb845edd1fb57ede9f8c0
3
  size 3119
vocab.json ADDED
The diff for this file is too large to render. See raw diff