Training in progress, step 500

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "microsoft/DialoGPT-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "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_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f3668e1a921d68670f825e5d58c50e878f060991f85aa159c31fcae547b463
+size 1419322880

runs/Dec17_18-56-52_1e4849c28ceb/events.out.tfevents.1702839441.1e4849c28ceb.368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63eb24534db63a2e4d2f3e6aadc14586c39ab424eb62bf937c926cf67be7bdf6
+size 4956

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca11b5f01d852596f5dda65721e8706a5d40a79a93efe73b27f4180c3512113a
+size 4728