Training in progress, step 500

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForCausalLM"
+  ],
+  "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": "4.35.2",
+  "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 sha256:4b7a6ab146c93998563750c7a91a766301d0fe1fa89aa648f69c7a2e948b078e
+size 328693404

runs/Feb13_14-56-38_b1f94d3ccfb2/events.out.tfevents.1707836200.b1f94d3ccfb2.1865.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e793a5f86e59b402b5bb07ff69f9018e3d4314072e26d4a0c4ef33b386e963f4
+size 4708

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ac1a9e3c8dba1da02f8d72fcc3cd65e702b69363b003457fe48350958f4dc9
+size 4600