Training in progress, epoch 1

config.json

@@ -1,26 +1,25 @@
 {
-  "_name_or_path": "neuralsentry/starencoder-git-commits-mlm",
+  "_name_or_path": "neuralsentry/distilbert-git-commits-mlm",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 1024,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 49152,
-  "position_embedding_type": "absolute",
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.31.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 49156
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13347fb1757974c2b63b8eec09f023b6857850046a5a1cc8fd66f2ea3fc991d2
-size 496820017
+oid sha256:d84f7698ea3ca86001ceec46302020bcb63f2e6b1633b05015baa7969ca41ad2
+size 267855533

special_tokens_map.json

@@ -1,30 +1,7 @@
 {
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<fim_prefix>",
-    "<fim_middle>",
-    "<fim_suffix>",
-    "<fim_pad>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<empty_output>",
-    "<commit_before>",
-    "<commit_msg>",
-    "<commit_after>",
-    "<reponame>"
-  ],
-  "bos_token": "<|endoftext|>",
-  "cls_token": "<cls>",
-  "eos_token": "<|endoftext|>",
-  "mask_token": "<mask>",
-  "pad_token": "<pad>",
-  "sep_token": "<sep>",
-  "unk_token": "<|endoftext|>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,31 +1,13 @@
 {
-  "add_prefix_space": false,
-  "additional_special_tokens": [
-    "<|endoftext|>",
-    "<fim_prefix>",
-    "<fim_middle>",
-    "<fim_suffix>",
-    "<fim_pad>",
-    "<filename>",
-    "<gh_stars>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<empty_output>",
-    "<commit_before>",
-    "<commit_msg>",
-    "<commit_after>",
-    "<reponame>"
-  ],
-  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1000000000000000019884624838656,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>",
-  "vocab_size": 49152
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c814c8e65d6e760ccc1120949b9a7860f564746c3afa5823928121e44702c1
+oid sha256:e7d48099f22a021fa9112ef8d071e40bbc559df9c265e1ba58e2f7ffa66cb031
 size 4091