Training in progress, step 500

config.json

@@ -1,27 +1,33 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "RobertaForMaskedLM"
+    "AlbertForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "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,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
+  "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": "4.46.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "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:a67875057ba38898a624e557896b53527deaca395d47bcd2ceac383928675b8f
-size 328693404
+oid sha256:cb70d8608ad14727eba034c59713ef556a196eed00dbc61b7c033be907d8c612
+size 44890256

runs/Dec03_05-10-54_4997dbea2fe4/events.out.tfevents.1733202704.4997dbea2fe4.1557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ee5253e4daaeea1969c2e5c852cddc1a11c20f90bc237d017716a8e3e46939
+size 5518

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0918a6e539f300046c1115d05fe74940742d7aa41cd4c1c8ce9ced11e99a0d89
+oid sha256:6dbc15c896979e43a8b5bf2ebe3b3c39b13abc10eb8ac53516d24ebeaa15553d
 size 5368