Training in progress, step 500

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "id2label": {
+    "0": "Male",
+    "1": "Female",
+    "2": "Non-binary"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "label2id": {
+    "Female": 1,
+    "Male": 0,
+    "Non-binary": 2
+  },
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 4,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 8192
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07c5d2bbf5744b192b22e0c75fc9091c1859241e91645e10c84f70c343d66b3
+size 226691632

runs/Nov12_15-11-03_4c459814b4fa/events.out.tfevents.1762960264.4c459814b4fa.548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ae1378a6dacc19cdb398b058545fa5765f7be038ceb59577210a620a41d4a0
+size 5231

runs/Nov12_15-13-17_4c459814b4fa/events.out.tfevents.1762960398.4c459814b4fa.548.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac4c0d7554358ab4ef3b45f0e68de2cb56c268248966fa98da602af066d1fd8
+size 5762

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee72c87ca87c083d58e2b7c659396a7fe88a6024e2c9cfc3a1d0bacae08a6b9
+size 5841