Training in progress, epoch 5

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "sdadas/mmlw-retrieval-roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "film",
+    "1": "history",
+    "2": "food",
+    "3": "medicine",
+    "4": "motorization",
+    "5": "work",
+    "6": "sport",
+    "7": "technology"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "RobertaTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 128001
+}

logs/events.out.tfevents.1705501812.9ec1b4c1fdd1.19771.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00b92220caa29fd6505b0a2e8ed6c8be8f55d9785d275ca519a27cd8bd2d051
+size 7832

logs/events.out.tfevents.1705502464.9ec1b4c1fdd1.39811.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af63f1cdd6e7f525c730767a6196a3dd8995fb0c455db9e597430c23bdccab7e
+size 104015

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8b930b90a3bcbc3382d9b659904b466637bcf6d299635584fbffdc18894f79
+size 1739926864

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941a3441d057e58a6cedadbd0104ca384c550106a491e670bc6ecdf7220bbb97
+size 4600