Training in progress, epoch 0

config.json

@@ -0,0 +1,26 @@
+{
+  "_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_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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9602902fdbaead5b0e713c4daeb5499ee7340f5d107181c6a6e92c2c5ceb9f9b
+size 5692078714

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3ea7f4224ca0e7575c028f8ca2dec3e0fa850da345e58cef075bd1548c4f49
+oid sha256:b456bf3c2a186970bf1096262f7c5ce5c7d8f761a658eabf1d8bb321d9b296d0
 size 4472