Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vision-classifier
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0002
 

model/config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "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,
   "id2label": {
     "0": "Any vision loss",
     "1": "Monocular vision loss",
@@ -17,7 +16,6 @@
     "4": "Visual impairment"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "Any vision loss": 0,
     "Monocular vision loss": 1,
@@ -25,16 +23,16 @@
     "US-defined blindness": 3,
     "Visual impairment": 4
   },
-  "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": "4.46.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450ee8ec26c86d0ba4ab757938730d173967a3befce85037f78aa802118ea286
-size 437967876
+oid sha256:88bd72e8882b5bab53103ad835125cc3b37386893bb96c5f5e9f54df5f404b74
+size 267841796

model/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af39e02b5feca4c78673cc366314c54e0f3be0fdbb0fbbed1dd5239746c35cd
+oid sha256:5f872015f113c4921fddb78b1df4cb016b2ed40b6711a9efdb5e7e71079e80f7
 size 5304

runs/Nov15_05-27-59_TIM/events.out.tfevents.1731648480.TIM.194564.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d744122b9071b421167708c2acbb77dfe411f2323f3832f11a5f1ce9b921c6
-size 6838
+oid sha256:5a646c9180d0aa256a1dd726df7a8a17382473ee88ce2b6f8fd6e9a4d6c6ee2b
+size 7945