Training in progress, step 1000

config.json

@@ -3,18 +3,18 @@
     "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "batch_size": 8,
+  "batch_size": 128,
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 128,
+  "hidden_size": 256,
   "initializer_range": 0.02,
-  "intermediate_size": 512,
+  "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f08c03ccfb48442852e4015a1f5912777e991952dd18cbaaf7074ac2495c93e
-size 27735986
+oid sha256:a43206381eafb73a8ddd82c6f8587510bd137434014e685e0a4d35c49e677c19
+size 64859346

runs/Apr05_05-59-46_bd7031fef7e0/events.out.tfevents.1680674394.bd7031fef7e0.979.75

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32204bd4ab26a97d6fe65a4c4fd3e0208d80a9c1a4f0333dd46ce778fef64547
-size 32922
+oid sha256:b67eed356e0c05427dfea43614af7bcf58d165b88f95912adb7934fc4da34b75
+size 33082

runs/Apr05_08-02-29_bd7031fef7e0/1680681758.072393/events.out.tfevents.1680681758.bd7031fef7e0.979.78

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d97206d1d414b253a46040b26a19e1986c038c581aed19342b7f1214312df4
+size 5806

runs/Apr05_08-02-29_bd7031fef7e0/events.out.tfevents.1680681758.bd7031fef7e0.979.77

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e861ebf816e826e7db1737af8e359b38bab2852001de99facc226120a7d7f882
+size 4272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe8937682d30f77194943518020a732617effb334785bf9992963360cf90b4e
+oid sha256:9afe91046268e3b4d6e4c9e77ec960f55d7fb073249e643d9a761c93e9f5bb5e
 size 3579