Training in progress, step 100

README.md

@@ -1,8 +1,8 @@
 ---
 license: mit
+base_model: prajjwal1/bert-small
 tags:
 - generated_from_trainer
-base_model: prajjwal1/bert-small
 model-index:
 - name: art-bert-base-cased
   results: []

config.json

@@ -1,25 +1,26 @@
 {
-  "_name_or_path": "prajjwal1/bert-small",
+  "_name_or_path": "bert-base-cased",
   "architectures": [
     "BertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 4,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 6685
+  "vocab_size": 8554
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e2cfb28f810c0a478e137753d2aa503238bcafa31d68a75236813697e286c3
-size 66275732
+oid sha256:915557df5b8186ab1c6a4bfc5c70d76a17f61edcbfb7767013473a0d56d595e5
+size 370507248

runs/Apr15_04-09-16_939fcec28df8/events.out.tfevents.1713154156.939fcec28df8.3234.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e18224a00dfeab128cf23fa32ecc7c3a80f889d300d857cafd87efc3c1de54
-size 4184
+oid sha256:b57b9eb30618a794fb4caeccf0cd008b6162daeb527798ce730732466cea0e79
+size 4556

runs/Apr15_04-09-33_939fcec28df8/events.out.tfevents.1713154235.939fcec28df8.3234.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8048350c4544d2c484379f74b3c4cbb3afdb80b61a01d72a3701498e4e9ff2b
+size 359

runs/Apr15_04-11-33_939fcec28df8/events.out.tfevents.1713154294.939fcec28df8.3234.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a0d28248bd4a54103ff0df3f9ac081c05b070da46b3eebe48649b85b1ece7f
+size 5030

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0870302987e56e028f5a21aaa3f368a9d3ba8cf3726ab9371352a5f124de2331
+oid sha256:6ba0bec504e8aa15f5222256c4bca11e305c27dc73a7e7c12aabaf2fb103fcbf
 size 4920