Training in progress, step 3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilbert/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 sha256:933930f9397aef70a81050ca1692784907982190a93a16f234f257adc5c35d32
+size 328693404

runs/Jul12_08-09-55_ce9466088e9e/events.out.tfevents.1720771797.ce9466088e9e.4519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6e171a27d9ceb29f8c0a202f8f359b1f721acff70d545b7955bc83f69066a4
+size 6019

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78627b4ba186c90faac6d5ddd626c4e3f04b2e44a9da844e44551f6cd273906e
+size 5112