Training in progress, step 500

config.json

@@ -1,42 +1,33 @@
 {
   "architectures": [
-    "LongformerForQuestionAnswering"
+    "AlbertForQuestionAnswering"
   ],
-  "attention_mode": "longformer",
-  "attention_probs_dropout_prob": 0.1,
-  "attention_window": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "ignore_attention_mask": false,
+  "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": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 4098,
-  "model_type": "longformer",
-  "num_attention_heads": 12,
+  "inner_group_num": 1,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-12,
+  "layers_to_keep": [],
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 64,
+  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "onnx_export": false,
-  "pad_token_id": 1,
-  "sep_token_id": 2,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.53.2",
-  "type_vocab_size": 1,
-  "vocab_size": 50265
+  "type_vocab_size": 2,
+  "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17d7c4cd5ff533f7fd2be7d44cf9a7d6b03a417a515364b1386e8692c2bb748
-size 592315616
+oid sha256:92b84b1d0cd35557764908f4f3a81475fd17e653cc6375e029b16ac6de618f4c
+size 823293160

runs/Jul22_18-36-26_add3dc826a53/events.out.tfevents.1753209389.add3dc826a53.619.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3f0a0c27012c72763f365ca9fb7e6c200b9b78a9c263df5a464ef3e5fe064d
+size 6163

special_tokens_map.json

@@ -1,51 +1,15 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": {
-    "content": "<mask>",
+    "content": "[MASK]",
     "lstrip": true,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
 }

spiece.model

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feabd36fa5798e2d3a8209b3efcb3045a46bfea3e458dc5dc401d6646d01ed5f
-size 3558908
+oid sha256:17976fe5b1fa2cfd2c6def7b353dea6a1768d463b559b69d7cf9657237d67a41
+size 2272611

tokenizer_config.json

@@ -1,40 +1,39 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
+    "4": {
+      "content": "[MASK]",
       "lstrip": true,
       "normalized": false,
       "rstrip": false,
@@ -42,18 +41,18 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "errors": "replace",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
-  "model_max_length": 4096,
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "LongformerTokenizer",
-  "trim_offsets": true,
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c4c6176b663027bb64cbbc04af17548dc9905c5f2c85ec105ee80eded4dfe16
+oid sha256:4ad263a73cde0e6824bed2b1a2929867d999b28ac958340645b1d4293aceec39
 size 5304