Training in progress, epoch 1

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large",
+  "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
-  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 384,
@@ -318,16 +317,16 @@
     "who_made_you": "96",
     "yes": "107"
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 6,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.18.0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082cdfd5c038698ff3c9f6b6908dbf34674584434c566d4b411a17b08479f591
-size 121451181
+oid sha256:9efad9f34ceab98f57b30f6c66e6961560765b1520a0574fbfd1f92f92388091
+size 91124013

runs/May10_17-13-30_25056aed8f14/events.out.tfevents.1652202836.25056aed8f14.79.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4437ca8a140ce33988f62a1c287ff84ab95b853cd36a95281740dd89fb91f84
-size 13738
+oid sha256:1a6d28792166142f0503520a70d509a061cb47a47fe3e389755bf85fbb7cf4b7
+size 14092

runs/May10_17-20-18_25056aed8f14/1652203236.7023866/events.out.tfevents.1652203236.25056aed8f14.79.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a8fa711438dd17362f55541a6511a67a07a6e9ac60dd64227fa642eb94d409
+size 4892

runs/May10_17-20-18_25056aed8f14/events.out.tfevents.1652203236.25056aed8f14.79.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd79df7eb07a8f50b2099c65cb366590dc13492764bd8d5a0c800937159c848d
+size 12078

special_tokens_map.json

@@ -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}}
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -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"}
+{"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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f21e0e9e24d64a19aa3801cb64eebc48dd98f8e65adb845edd1fb57ede9f8c0
+oid sha256:1cc86913d23a7d672e56be8d9caecbd97deb867140d8d99453b71148ddc66ef6
 size 3119