Training in progress, epoch 1

adapter_config.json

@@ -19,11 +19,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "dense",
     "k_proj",
-    "fc2"
+    "dense",
+    "fc2",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e78b168a34794a2c18600d522f5525983daa16e80e41760e5fe25e1edaf00e
+oid sha256:46a03d0cfcd8a23b46fee1350c4a20d02ef6bd8625a0098dc10b17325581ea92
 size 40926200

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.36.2"
+}

runs/Jan14_10-59-25_ac990a94000f/events.out.tfevents.1705229997.ac990a94000f.718.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87672128f2af73a247de9a1a1ee430a03344783600d821c41c3f9c50012e0b7
-size 4184
+oid sha256:6ff2ed0e2bbfc23635920664f09200e31f490b78f5f4b898ffce45f070e4e03e
+size 5484

runs/Jan14_11-08-53_ac990a94000f/events.out.tfevents.1705230536.ac990a94000f.2177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849042697c70c39eeeff6df17ede9e1f552e4c4dc173e6577670f35beb267d43
+size 4184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50bf58d5ddc44c71bfd1e4e8effde8ccfd8617ab9bdc5103e983b36c7399f7a
+oid sha256:230d9c796fa3e005f86ed4202cd04a36f825612a8c1f4b03f5d59b01eb3f17c1
 size 4728