Training in progress, epoch 1

config.json

@@ -21,81 +21,39 @@
   "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
-    "0": "AI Applications",
-    "1": "AI Infrastructure",
-    "2": "Agents",
-    "3": "Argilla",
-    "4": "Audio",
-    "5": "Cloud Deployment",
-    "6": "Code",
-    "7": "Computer Vision",
-    "8": "Data Engineering",
-    "9": "Data Science",
-    "10": "Deep Learning",
-    "11": "Embeddings",
-    "12": "Ethics",
-    "13": "Evaluation",
-    "14": "Fine-Tuning",
-    "15": "Gaming",
-    "16": "Generative AI",
-    "17": "Gradio",
-    "18": "Hardware",
-    "19": "Hugging Face",
-    "20": "Image",
-    "21": "LLMs",
-    "22": "ML Theory",
-    "23": "MLOps",
-    "24": "Model Optimization",
-    "25": "Multimodal",
-    "26": "NLP",
-    "27": "Reinforcement Learning",
-    "28": "Research Papers",
-    "29": "Robotics",
-    "30": "Security",
-    "31": "Time Series",
-    "32": "Tutorials",
-    "33": "Video",
-    "34": "XetHub"
+    "0": "embeddings",
+    "1": "ai ethics",
+    "10": "data engineering",
+    "11": "robotics",
+    "12": "speech & audio",
+    "13": "code models",
+    "2": "game development",
+    "3": "llm evaluation",
+    "4": "rlhf",
+    "5": "deployment & infrastructure",
+    "6": "ml fundamentals",
+    "7": "vision & multimodal",
+    "8": "diffusion models",
+    "9": "hub & platform"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
   "intermediate_size": 1152,
   "label2id": {
-    "AI Applications": 0,
-    "AI Infrastructure": 1,
-    "Agents": 2,
-    "Argilla": 3,
-    "Audio": 4,
-    "Cloud Deployment": 5,
-    "Code": 6,
-    "Computer Vision": 7,
-    "Data Engineering": 8,
-    "Data Science": 9,
-    "Deep Learning": 10,
-    "Embeddings": 11,
-    "Ethics": 12,
-    "Evaluation": 13,
-    "Fine-Tuning": 14,
-    "Gaming": 15,
-    "Generative AI": 16,
-    "Gradio": 17,
-    "Hardware": 18,
-    "Hugging Face": 19,
-    "Image": 20,
-    "LLMs": 21,
-    "ML Theory": 22,
-    "MLOps": 23,
-    "Model Optimization": 24,
-    "Multimodal": 25,
-    "NLP": 26,
-    "Reinforcement Learning": 27,
-    "Research Papers": 28,
-    "Robotics": 29,
-    "Security": 30,
-    "Time Series": 31,
-    "Tutorials": 32,
-    "Video": 33,
-    "XetHub": 34
+    "ai ethics": "1",
+    "code models": "13",
+    "data engineering": "10",
+    "deployment & infrastructure": "5",
+    "diffusion models": "8",
+    "embeddings": "0",
+    "game development": "2",
+    "hub & platform": "9",
+    "llm evaluation": "3",
+    "ml fundamentals": "6",
+    "rlhf": "4",
+    "robotics": "11",
+    "speech & audio": "12",
+    "vision & multimodal": "7"
   },
   "layer_norm_eps": 1e-05,
   "local_attention": 128,
@@ -110,12 +68,13 @@
   "num_hidden_layers": 22,
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
-  "problem_type": "multi_label_classification",
+  "problem_type": "single_label_classification",
   "reference_compile": true,
+  "repad_logits_with_grad": false,
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.0.dev0",
+  "transformers_version": "4.48.0",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d194be30d181b8cfb9202739e9f4b26972d406990975b65d04cc0e9f175d81bb
-size 598541300
+oid sha256:8fdd5f191f0e54fd9c60d9f2b38a1aa12a1d66bafca92d538ad9a94b50f06a95
+size 598476704

runs/Jan10_22-03-30_5e4eb05f69bb/events.out.tfevents.1736546616.5e4eb05f69bb.2578.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b524508fd26c66247528b91dd993a3591a54c36cfb9bbe651bb37e5bd3119dee
+size 6862

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25bd22ddc0517daf7682a75eb884fa14c040494f0abb64be5908371babad56b0
+oid sha256:b3c3573a3c15332c8382d24b442b2669b4d887d5b323de39035c48466545d860
 size 5432