Model save

README.md

@@ -1,11 +1,8 @@
 ---
 license: apache-2.0
-base_model: bert-large-uncased
+base_model: albert-base-v2
 tags:
-- question-answering
 - generated_from_trainer
-datasets:
-- squad
 model-index:
 - name: out
   results: []
@@ -16,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out
 
-This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the squad dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
 
 ## Model description
 
@@ -36,12 +33,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
+- train_batch_size: 256
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50.0
+- num_epochs: 3.0
 
 ### Training results
 

added_tokens.json

@@ -1,7 +1,7 @@
 {
-  "[CLS]": 101,
-  "[MASK]": 103,
-  "[PAD]": 0,
-  "[SEP]": 102,
-  "[UNK]": 100
+  "<pad>": 0,
+  "<unk>": 1,
+  "[CLS]": 2,
+  "[MASK]": 4,
+  "[SEP]": 3
 }

config.json

@@ -1,26 +1,33 @@
 {
-  "_name_or_path": "bert-large-uncased",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "BertForQuestionAnswering"
+    "AlbertForQuestionAnswering"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.35.0.dev0",
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30000
 }

pruning_config.json

@@ -18,7 +18,7 @@
   },
   "pruning_fn": "unstructured_magnitude",
   "pruning_fn_default_kwargs": {
-    "target_sparsity": 0.8
+    "target_sparsity": 0.85
   },
   "pruning_frequency": 100,
   "scheduler": "iterative",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc5a0caf6ceb474c643e307c6264652b6507a8366656fa0e96652358bbba29af
-size 1336511590
+oid sha256:59c8b45d58cc16f8be68b58c766c18149b106ba6c63923e4e660069e34e7fff0
+size 44387257

raw_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341f83823378ba97d0a68be556576119c284c52ad83fb52fd464e7e90660adaf
-size 2544552978
+oid sha256:990d6dcf19e7b47d49c419810e1b5a77fcafce7f87a95dd98a00357b924f9eda
+size 73096798

special_tokens_map.json

@@ -1,7 +1,9 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,9 +32,9 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
@@ -42,15 +42,17 @@
     }
   },
   "additional_special_tokens": [],
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64b18483f886adf7517aaaf61c469d7c5d271f322e4108022b29cfc18203061
+oid sha256:9322bc2bcb7a8886f68ebf17e543e082e1598e8a1909dedfcca9c382180b7d8c
 size 4664