Training in progress, step 3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "gpt2-large",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,13 +12,11 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 36,
   "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013226b1044e4e943b58d3f8411ab92012a2776e8c24ecb426b6dcc5489189f1
-size 1419322880
+oid sha256:9daec3d9afb56155d3065913e51636b232be0e1826a9079623ece03c90eff39f
+size 3096165928

runs/Nov21_13-14-55_76a1de55ef0b/events.out.tfevents.1732194897.76a1de55ef0b.590.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09051e8969e5a4d7da5b01567560df7f9e39b1e6458233164bbe128ae3c4d8d
+size 5601

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643cc8bce87c960d663a0ef78ec7c404e98e8f66d659376e39af7d8fc993a061
+oid sha256:ebdc7aeaaec2ac9c423103b57521145ab0012ac8ca6855b8e48d0a9f94714c23
 size 5240