Training in progress, step 25

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b55555217936b8eb29c285357f3d1d81ed1cad6a27e9cd39b08b525bb898a3
+oid sha256:bfecaae1688ba4f8b369a8c9b7db4a4aa0c0da229a63b42ea9506ddf582da495
 size 328693404

tmp-checkpoint-525/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": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

tmp-checkpoint-525/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002e58551f77c74fd817cc03917e1e8da8a7f324455a21b6b80a244771bcb55d
+size 165806080

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57bb79b6beaf28ef1fb09ae7eff54f3e34da01722a8791752d9109f2995cf38c
+oid sha256:c976dede04bbc17e5799d66d873b61d00c97ecef624c14c91ccc5492fa5a31c0
 size 4920