Training in progress, epoch 1

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "SDLMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "skip_mlp": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0e9d1f6512eab9e3eccea0dce7698192b87788cd2227f6132190694c734e14
+size 1207416128

runs/Jul06_22-21-04_morpheus/events.out.tfevents.1720284665.morpheus.5753.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4af3c8a9c2d6302abb81986a8a02aea6d80554e94d2f3b89782c91b958e69891
+size 5604

runs/Jul06_22-53-01_morpheus/events.out.tfevents.1720286582.morpheus.10192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea88eb1dc22cc6781d863bdd8e795ea422c552aef25b7baa0f166da010b24e7
+size 6719

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:346eaae267c7e6e0c6e4ee4fc19e73ec9a67c98f2d32ae163cf048fce0873360
+size 5176