Training in progress, step 500

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Grogros/dmWM-meta-llama-Llama-3.2-1B-Instruct-ft-HarmData-AlpacaGPT4-OpenWebText-RefusalData-d4-a0.25",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c030315683a323ceca5e5012742bc2f5c9e67042b7e0c3925d8894ad6085b15
+size 4943274328

runs/Jan30_17-17-46_209-20-158-245/events.out.tfevents.1738258032.209-20-158-245.3234169.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e014037a2440a315f73851bc85f266aec02a935b1f9d02f39eb3b8f0b9fc7599
+size 6663

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143b5f6c6fe08f3f5ae3c56265d9e4157a9e86249acdc63737a238135515a88f
+size 5432