Training in progress, epoch 0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046e722acda85a70da53cb82ffc7b86a2196d814defe8e0b00672bf4eefa3207
+oid sha256:5ffb41dc343d26e8dc2d4df77f68d991f4fbd7ba68524aa8068e88282284a1ec
 size 18908110

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "MixFormerSequentialForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mixformer-sequential",
+  "n_embd": 2048,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88225f7d0febf682c8d749839bd5791bd044a414b3085f4e68a00b7176d08270
+size 5673158870

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9651ca82d9a018a42539ecb8e4dda620314b543c4fd7e49d52cc3cc0a4ba9079
+oid sha256:c6b086353e59f9ffc00f8ce79de6f8152ccbbde37382150a13049580f749fb5b
 size 4536