Training in progress, step 135

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "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,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57736da07ef17c2aadcec5e4f63df3de0ee2bd19c5306521915018344fe7d9da
+size 328693404

runs/Jul30_02-57-27_1560c60627f9/events.out.tfevents.1722308249.1560c60627f9.147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f6c7d0481a87afa14f21f360290062d65c633e3c870575b416645ff92679c3
+size 4865

runs/Jul30_03-30-31_1560c60627f9/events.out.tfevents.1722310232.1560c60627f9.147.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed019a41d96f236c34d59944ce1361da880309db3ddad83642612b3ffcceb56
+size 4865

runs/Jul30_03-50-11_1560c60627f9/events.out.tfevents.1722311412.1560c60627f9.147.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f126001ff87a6d93d0d7b1a0d0a39d91840a8f8139878bb0c641dd9d5240c00
+size 4865

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45faa52d174a115d35a34b76590f2036fc19dfd4d8de8590afa880b261baccfa
+size 5112