Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.26.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1f29066f62cc51e933586cb3ab47ab13994ba6d31f589a31f115c740ec556e
+size 328721273

runs/Jan31_21-25-02_7ffccb7b9618/1675200320.2953904/events.out.tfevents.1675200320.7ffccb7b9618.148.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee114639ffb532e6167377566128ccea281d2cb72aea8a4da481ac64aaf39131
+size 5694

runs/Jan31_21-25-02_7ffccb7b9618/events.out.tfevents.1675200320.7ffccb7b9618.148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c815bcfcb0d9f9908511554cdd2bd5c58bddc27d9a3155d830b392ef599032
+size 4276

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7242997b5d711770a2f04fc16840d2fffae9856a76029ad0e98173e7fa68ef9
+size 3515