Training in progress, step 500

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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef5e21e7eba70b1b31360989eec735a482e0ea72da208331c5e443dbefbe04e
+size 328693404

runs/Mar11_18-33-42_05a93bae51b0/events.out.tfevents.1710182024.05a93bae51b0.81.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f6a4ab776bc167120b80825f6c6e363e6c39eba7d5482454cd6cf41c7c2772
+size 4592

runs/Mar11_18-34-43_05a93bae51b0/events.out.tfevents.1710182083.05a93bae51b0.81.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1947298d97934a82ccbdd0d643cda65199bfe3c3fc978f9a450973a295d204
+size 4184

runs/Mar11_18-35-33_05a93bae51b0/events.out.tfevents.1710182134.05a93bae51b0.81.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02af9fef923742622757f06b91b8de79ddda46e2bdabae4866ec89874e6df4bb
+size 4803

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41370b787ca1f74b9c5559c0f02c07ac45d3c3ad1b87bfebb10f6b5c9e9f9523
+size 4920