Training in progress epoch 0

checkpoint-14000/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-14000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87918e43cc92782f8e34eca0123904456cb96c43b39fcae9294c26c4376be074
-size 7438256
+oid sha256:43b07c5eebc7b391a5c440d18cea8a8258e844c7accf893495063b287200518a
+size 5849744

checkpoint-14000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d39356bb001b15143935e532efee721eff9a386c0ba06f5e1c5b3f28bcf8fda0
-size 14910074
+oid sha256:a63312ba1239666a6bf32a2f6127515a87dc65490956838e7f8539209d1b6d54
+size 11717834

checkpoint-14000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02365ccea03970d371bb52cefc42bb586ef957ef2817ffca8c579fd97a941840
+oid sha256:190b176f89c9bf9a40e5c7a146d2857ffe8303aa088c0ca90b542fb6a50cabd9
 size 14604

checkpoint-14000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c0c02be146518b2bcb042ef5f66079e8e31213a12e04ad738690a808095a38
+oid sha256:02a167c11969b318c2214f9299b8cf18cdbbee9735e8380f8565897e6603562d
 size 1064

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b07c5eebc7b391a5c440d18cea8a8258e844c7accf893495063b287200518a
+oid sha256:5c2b7249cd6c186a5cfae63449f492c8906a9657ebb7f08ffbbbf2993bbaf663
 size 5849744