Training in progress, step 500

README.md

@@ -1,16 +1,12 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: bert-base-cased
 tags:
 - generated_from_trainer
 model-index:
 - name: DistilBERT-MLM-IMDb
   results: []
-datasets:
-- stanfordnlp/imdb
-metrics:
-- perplexity
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # DistilBERT-MLM-IMDb
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.2924
-- Model Preparation Time: 0.0036
+- Loss: 1.9568
+- Model Preparation Time: 0.0093
 
 ## Model description
 
@@ -53,9 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
 |:-------------:|:-----:|:----:|:---------------:|:----------------------:|
-| 2.5364        | 1.0   | 958  | 2.3577          | 0.0036                 |
-| 2.426         | 2.0   | 1916 | 2.3132          | 0.0036                 |
-| 2.3902        | 3.0   | 2874 | 2.2983          | 0.0036                 |
+| 2.2075        | 1.0   | 985  | 2.0081          | 0.0093                 |
+| 2.0945        | 2.0   | 1970 | 1.9688          | 0.0093                 |
+| 2.0508        | 3.0   | 2955 | 1.9517          | 0.0093                 |
 
 
 ### Framework versions
@@ -63,4 +59,4 @@ The following hyperparameters were used during training:
 - Transformers 4.47.1
 - Pytorch 2.5.1+cu124
 - Datasets 3.2.0
-- Tokenizers 0.21.0
+- Tokenizers 0.21.0

config.json

@@ -1,26 +1,24 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForMaskedLM"
+    "DistilBertForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "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": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30522
 }

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f33d29fab32a3ec886d1eba6e5fd7ea7f7203d57c18d5d132c0eed4e19d95bd
-size 433386912
+oid sha256:f972b5db51161cc0ff1e6f38a8f12d205016bd718ec409c58f84b4e737f770e0
+size 267954768

tokenizer_config.json

@@ -43,7 +43,7 @@
   },
   "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 512,
@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a24bdb319c371d6c480e56b3da29983e1b3e89e5ab79ab91755aac461033ec
+oid sha256:acfd9da59fe8d1cbee15f2daaebe5e95c904aee1651c0187f983b3bf6631e5d5
 size 5304