Training in progress, step 10000

config.json

@@ -1,33 +1,30 @@
 {
-  "add_cross_attentions": false,
+  "_name_or_path": "google/electra-small-discriminator",
   "architectures": [
-    "TextMaskedLanguageModelingTransformer"
+    "ElectraForMaskedLM"
   ],
-  "attention_implementation": "sdpa",
-  "attention_probability_dropout_probability": 0.1,
-  "bos_token_id": 0,
+  "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dropout_probability": 0.1,
   "embedding_size": 128,
-  "eos_token_id": 2,
-  "hidden_activation_function": "gelu",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
-  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
   "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
-  "mask_token_id": 4,
   "max_position_embeddings": 512,
+  "model_type": "electra",
   "num_attention_heads": 4,
   "num_hidden_layers": 12,
-  "num_intermediate_layers": 1,
-  "pad_token_id": 1,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3",
   "type_vocab_size": 2,
-  "use_cache": false,
-  "vocab_size": 50265,
-  "wac_distribution_layers": [],
-  "wac_distribution_matrix": "none",
-  "wac_embedding_size": -1
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727ef4f19c38aa770dae1159135f5a459871e94c1bda50aba8fbc4d09823588d
-size 90403716
+oid sha256:9f7a653787a4436ceb60d45b0861c183c29da65cfb6f6d24e03fcf6189c7710d
+size 54210824

runs/Nov20_12-01-23_gpu106/events.out.tfevents.1763665284.gpu106.23816.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0839c3d24ac69b77c3b93abdd561a3095afa092816c5764f5d6fbb52fcc5e21
+size 5219

runs/Nov20_12-02-32_gpu115/events.out.tfevents.1763665353.gpu115.26320.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f16f43cf1e9d2f08c63242841b83f4863e823071c7122f8ee5b732858626c5
+size 7329

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8cb8f26f6721c7ff3bb7b0b8a496921100df85f907c5bcfc12364e71f13273
+oid sha256:e1612a99384da204a1b42dd9729d26b38323bbd563d821e753b751816fea25c2
 size 5368