Training in progress, step 1000

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bert-large-cased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5f80192b6ea82f11a32ce52a1ec98d9f9bf45482b7319245e8550c04311edc
+size 1334488416

runs/Apr21_07-37-36_d035447469da/events.out.tfevents.1713685062.d035447469da.3247.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28851e0a3c8ff197a547a933a162231bbedd8ada835473a40cf7492460683d8
+size 4184

runs/Apr21_07-38-28_d035447469da/events.out.tfevents.1713685109.d035447469da.3899.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5adef9d8aa35f5bfeaae6913deac58b3d973df6d2d0445c0cc2347001ef051b3
+size 4184

runs/Apr21_07-39-38_d035447469da/events.out.tfevents.1713685180.d035447469da.4282.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2990df37a9b8fa726179b5697ff6ec883e701d215b16e6090b895eb0b1f3e4
+size 5242

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cb591c070a13fb8a7abd872289a700f16a2a8aa2c5d3a6cd575d20bcef48b2
+size 4984