Training in progress epoch 0

checkpoint-8000/config.json

@@ -3,18 +3,20 @@
   "architectures": [
     "GPT2LMHeadModel"
   ],
+  "attention_probs_dropout_prob": 0.1,
   "attn_pdrop": 0.1,
   "bos_token_id": 5,
   "embd_pdrop": 0.1,
   "eos_token_id": 4,
+  "hidden_dropout_prob": 0.1,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 128,
   "n_embd": 128,
-  "n_head": 4,
+  "n_head": 32,
   "n_inner": null,
-  "n_layer": 4,
+  "n_layer": 2,
   "n_positions": 128,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

checkpoint-8000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd7ac21adbc12a3fc9a44ab4a5233cb92b35fa329448e1e1245879cd7951d4c
-size 7438256
+oid sha256:1c48263e53fed3b1e70cbebe9dcdbff317fc6e66783421b5a32cb17ce6a92962
+size 5849744

checkpoint-8000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee8f333a9123aa24b6b410d9421e3c8bb3b8d384353d603cd0c75e2f822c4c43
-size 14910074
+oid sha256:ca284f49545b2379cea09ed3a29e442520c8935553d11ca294136690cfabd7a9
+size 11717834

checkpoint-8000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172e86524f4f824821f771cdd9c70256f65e1ed5b2c5dad17aa3e81d1af5cc45
+oid sha256:cb104259376d1f35a078f32d4ece191bef1affc1b596736b25a5aee650653e25
 size 14604

checkpoint-8000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6022e5659beab2c786acf068ad22292448b4d6489172182cbec85dee2ea7e2cb
+oid sha256:52e9e4c3722f3b3b683728e0ace28f9ef80a907bd0a41976153b1f3d2cfa9da1
 size 1064

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c48263e53fed3b1e70cbebe9dcdbff317fc6e66783421b5a32cb17ce6a92962
+oid sha256:2c2fa97994b0ded351666dedacf1aedcf550c4e793872ce6aedfc2bbde2291c7
 size 5849744