End of training

README.md

@@ -1,14 +1,29 @@
 ---
 library_name: transformers
+language:
+- en
 license: apache-2.0
 base_model: bert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- glue
 metrics:
 - accuracy
 model-index:
 - name: bert-base-uncased-finetuned-mnli
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8439788445890968
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-uncased-finetuned-mnli
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the GLUE MNLI dataset.
 It achieves the following results on the evaluation set:
-- Accuracy: 0.8469
-- Loss: 0.5565
+- Loss: 0.5878
+- Accuracy: 0.8440
 
 ## Model description
 

all_results.json

@@ -2,17 +2,17 @@
     "epoch": 3.0,
     "epoch_mm": 3.0,
     "eval_accuracy": 0.8419765664798777,
-    "eval_accuracy_mm": 0.8480471928397071,
+    "eval_accuracy_mm": 0.8439788445890968,
     "eval_loss": 0.5939174294471741,
-    "eval_loss_mm": 0.5605696439743042,
-    "eval_runtime": 398.3434,
-    "eval_runtime_mm": 628.8257,
+    "eval_loss_mm": 0.5877671241760254,
+    "eval_runtime": 387.9521,
+    "eval_runtime_mm": 292.3908,
     "eval_samples": 9815,
     "eval_samples_mm": 9832,
-    "eval_samples_per_second": 24.64,
-    "eval_samples_per_second_mm": 15.635,
-    "eval_steps_per_second": 3.08,
-    "eval_steps_per_second_mm": 1.954,
+    "eval_samples_per_second": 25.3,
+    "eval_samples_per_second_mm": 33.626,
+    "eval_steps_per_second": 3.163,
+    "eval_steps_per_second_mm": 4.203,
     "total_flos": 3.099754961058632e+17,
     "train_loss": 0.0,
     "train_runtime": 0.0013,

config.json

@@ -29,6 +29,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.45.0.dev0",
   "type_vocab_size": 2,

eval_results.json

@@ -1,9 +1,16 @@
 {
     "epoch": 3.0,
+    "epoch_mm": 3.0,
     "eval_accuracy": 0.8419765664798777,
+    "eval_accuracy_mm": 0.8439788445890968,
     "eval_loss": 0.5939174294471741,
-    "eval_runtime": 398.3434,
+    "eval_loss_mm": 0.5877671241760254,
+    "eval_runtime": 387.9521,
+    "eval_runtime_mm": 292.3908,
     "eval_samples": 9815,
-    "eval_samples_per_second": 24.64,
-    "eval_steps_per_second": 3.08
+    "eval_samples_mm": 9832,
+    "eval_samples_per_second": 25.3,
+    "eval_samples_per_second_mm": 33.626,
+    "eval_steps_per_second": 3.163,
+    "eval_steps_per_second_mm": 4.203
 }

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 512
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbff65672b5973c29c8639637809abad6563464c6fd8b0947e61849e00f0771c
+oid sha256:892dd22aecbb6b0682621ff68af839b05a8511e6c60f972bb0a7e3c3f5bc22ca
 size 5240