moshew commited on
Commit
497a700
1 Parent(s): 69a7816

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,12 +1,11 @@
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,
@@ -318,16 +317,16 @@
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
  }
 
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
  "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
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:082cdfd5c038698ff3c9f6b6908dbf34674584434c566d4b411a17b08479f591
3
- size 121451181
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efad9f34ceab98f57b30f6c66e6961560765b1520a0574fbfd1f92f92388091
3
+ size 91124013
runs/May10_17-13-30_25056aed8f14/events.out.tfevents.1652202836.25056aed8f14.79.16 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4437ca8a140ce33988f62a1c287ff84ab95b853cd36a95281740dd89fb91f84
3
- size 13738
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6d28792166142f0503520a70d509a061cb47a47fe3e389755bf85fbb7cf4b7
3
+ size 14092
runs/May10_17-20-18_25056aed8f14/1652203236.7023866/events.out.tfevents.1652203236.25056aed8f14.79.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a8fa711438dd17362f55541a6511a67a07a6e9ac60dd64227fa642eb94d409
3
+ size 4892
runs/May10_17-20-18_25056aed8f14/events.out.tfevents.1652203236.25056aed8f14.79.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd79df7eb07a8f50b2099c65cb366590dc13492764bd8d5a0c800937159c848d
3
+ size 12078
special_tokens_map.json CHANGED
@@ -1 +1 @@
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}}
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
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"}
 
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"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f21e0e9e24d64a19aa3801cb64eebc48dd98f8e65adb845edd1fb57ede9f8c0
3
  size 3119
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cc86913d23a7d672e56be8d9caecbd97deb867140d8d99453b71148ddc66ef6
3
  size 3119