Training in progress, step 168

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "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": "bert",
+  "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 sha256:1b0a1036de50323b0e7fc916dc3847f913ee08effec231c1df4a108dd256eb16
+size 328693188

runs/Jul30_07-20-15_1560c60627f9/events.out.tfevents.1722324016.1560c60627f9.147.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd915c15162a00cdbcaddd548a2536ac8c5ad2d47981d0d66ad089a7d6acba69
+size 4823

runs/Jul30_07-21-25_1560c60627f9/events.out.tfevents.1722324085.1560c60627f9.147.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc69f0b6ed4a72a0a07057b865cf4bd83fbe0a9bf4200113d35bafd0d71056ab
+size 4823

runs/Jul30_07-24-43_1560c60627f9/events.out.tfevents.1722324283.1560c60627f9.147.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bf02c2fbe0c71ccc62ccbb2f2848135b2b502ecbe6dd9b3435579319c2a8c4
+size 4823

runs/Jul30_07-25-27_1560c60627f9/events.out.tfevents.1722324328.1560c60627f9.147.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3a6a37f17d180fc7e3c2b3f9870ee72e7ef1326137bf4c93450c83589bb611
+size 5367

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988935cbdfb38d3d6cddb42095adac057f6aefc27936e62bab8f06d0da71f6c3
+size 5112