Training in progress epoch 0

README.md

@@ -3,18 +3,26 @@ license: apache-2.0
 tags:
 - generated_from_keras_callback
 model-index:
-- name: Albert
+- name: Mr-Wick/Albert
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
 probably proofread and complete it, then remove this comment. -->
 
-# Albert
+# Mr-Wick/Albert
 
-This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
+This model is a fine-tuned version of [Mr-Wick/Albert](https://huggingface.co/Mr-Wick/Albert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-
+- Train Loss: 0.6581
+- Train End Logits Accuracy: 0.3488
+- Train Loss Accuracy: 0.0671
+- Train Start Logits Accuracy: 0.3529
+- Validation Loss: 0.9366
+- Validation End Logits Accuracy: 0.4415
+- Validation Loss Accuracy: 0.0657
+- Validation Start Logits Accuracy: 0.4486
+- Epoch: 0
 
 ## Model description
 
@@ -38,6 +46,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Train Loss | Train End Logits Accuracy | Train Loss Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Loss Accuracy | Validation Start Logits Accuracy | Epoch |
+|:----------:|:-------------------------:|:-------------------:|:---------------------------:|:---------------:|:------------------------------:|:------------------------:|:--------------------------------:|:-----:|
+| 0.6581     | 0.3488                    | 0.0671              | 0.3529                      | 0.9366          | 0.4415                         | 0.0657                   | 0.4486                           | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "Mr-Wick/Albert",
   "architectures": [
     "AlbertForQuestionAnswering"
   ],

logs/train/events.out.tfevents.1648182038.83bc270a2613.81.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd6d1c31c169a1dafbd5b21448a8ddec903e1a728358a314da62bcb5483870a
+size 2821681

logs/validation/events.out.tfevents.1648188363.83bc270a2613.81.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15efbf46c19018e8acb7cde14f34bd040885b7a9709f99538792f66281efb906
+size 738

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7350bde11ff12a4aa7ec9b09cd990d804358ff6272070466e7ce061edeb321ac
+oid sha256:934285ce59918e71ce507bc398d91175ec32a336515903bf5a44e93640943b6f
 size 44417752

tokenizer_config.json

@@ -1 +1 @@
-{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Mr-Wick/Albert", "tokenizer_class": "AlbertTokenizer"}