Training in progress, step 1000

config.json

@@ -11,9 +11,9 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 64,
-  "n_embd": 256,
-  "n_head": 4,
+  "n_ctx": 512,
+  "n_embd": 1024,
+  "n_head": 16,
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b313e11e772e9ba2980783a686e0b575f06d3e98a5be3821d0d1bbd6dd215590
-size 69693792
+oid sha256:0b2de214e8f1502e86bc9b61c8992505f98d77a5eedb4cfa1d1be2f33014ea1c
+size 731716424

runs/Apr10_22-26-23_gpu-pod/events.out.tfevents.1712787988.gpu-pod.1209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a947d0eeba31181aa5c45bb90a184efcb5ffdd46eb02b8a1146ce2c4f4eda351
+size 4829

runs/Apr10_22-28-16_gpu-pod/events.out.tfevents.1712788101.gpu-pod.1718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5f7d9cac196fb4d025037ddada8c79424da90c8e0f6fcd7c122cbd38d122eb1
+size 5038

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79ff99c21d55e1c1f39f37b943fa36dd8722ca063673bb56f6a1bd5de558fec
+oid sha256:c0358968f457a6b9893184cffc2a04fbb2483bc3c78b69ffbb670d89f6c31ef8
 size 4475