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": "4.38.1",
+  "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:de6bc4280292a811a814b93e75ca266731f71449d41c985e8d64c552082a05c3
+size 328693404

runs/Mar13_22-15-00_8e4eda0f5b8f/events.out.tfevents.1710368125.8e4eda0f5b8f.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432c4f7fe499274c09935ef00b0e148a1779d20df2702a693e0440856eb853da
+size 13805

runs/Mar13_22-23-17_8e4eda0f5b8f/events.out.tfevents.1710368600.8e4eda0f5b8f.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5bd8ca5e31367346ec023af2c21d6e2bbdf1a09a81f6f4ce1f521b8c059416
+size 4590

runs/Mar13_22-25-15_8e4eda0f5b8f/events.out.tfevents.1710368716.8e4eda0f5b8f.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de125d6ff61e31c82535ca327b15db73d41a10026e9d191086ee6626c352021
+size 4590

runs/Mar13_22-36-15_8e4eda0f5b8f/events.out.tfevents.1710369376.8e4eda0f5b8f.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0907cff3817d323e0babe453927a1501f2225b9cb22d5002e63cb6c9cdd73f80
+size 4801

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5040d183ad59221d12448f7c1d9e1b8f4749a83614a838d482f4e442d99d3268
+size 4920