Training in progress, step 30

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9e63d65f6d08428c032e25192aa55f11dc5e1b0acd7f8b515f7d0cc7309fa6
+oid sha256:38d6c8935db2a822990e31421ab481a49ce5fb8d70f9cf70b16dd94d5afe4359
 size 139512976

config.json

@@ -1,31 +1,36 @@
 {
   "architectures": [
-    "Qwen3ForCausalLM"
+    "Phi3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "head_dim": 128,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
-  "hidden_size": 1024,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "max_position_embeddings": 40960,
-  "max_window_layers": 28,
-  "model_type": "qwen3",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "pad_token_id": 151643,
-  "rms_norm_eps": 1e-06,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 1000000,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
   "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 32064
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247b5c3b676d0cc8dc1421d1f4ac84430aec15869d43b71850cee1d4e259709c
-size 4696694784
+oid sha256:23ba9690ab9d30d6bee3d05b693f01f93e10345b6300e435949b14cac8641a1f
+size 4961852416

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107cc08a9f2982f3af34a2297184ffa22006a938a420d03a33a44a6ba59d7d28
+oid sha256:185aaed5b2c443acb22ff89d1c8491be5a70912edeef68cf3222edf1609e59dc
 size 2384234968