Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Davlan/afro-xlmr-large-61L",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca7d343cdda58d80bf9a182ba853c0fcf79e470e9fb6c3ed5d2953e3af7449f
+size 2240710265

runs/Jul18_20-18-37_e97fa4584324/1689711523.3723655/events.out.tfevents.1689711523.e97fa4584324.1135.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99001dfc0002dd432c70e9c8669b157297c5531d5636a4e64e595a97b114efc
+size 5682

runs/Jul18_20-18-37_e97fa4584324/events.out.tfevents.1689711523.e97fa4584324.1135.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0cb10418cfd587aa6ee92b6e02ea0febae4370935f287fa161b41656c820519
+size 4061

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5481aea3fdaf2bb0a18d269f8aa437f84c5d8937d8789ea427b8615eee0f0041
+size 3451