Training in progress epoch 0

checkpoint-2000/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-2000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63f198c7497bd2841852386f58c71aa608c42edaaa03864c1c89f28820d7c84
-size 7438256
+oid sha256:72b8f1431861f4f99c8a6c4334d906aadde093d300f60ce124b1f48411c16dfd
+size 5849744

checkpoint-2000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae28a2f41e9984bc2ecf544ce621bbae18c78d30dfa59ebad78c82c9a3eb2b7
-size 14910074
+oid sha256:4f55ebbba1d58789f4d9f559dcb15ace72f8f2929c49d3dedff87915c53b24c7
+size 11717834

checkpoint-2000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4bfbeca8fff7808687f31f7ea0c493baeef2f350c34e0d2c6843bdfbc49374
+oid sha256:8c20ac4079187b7525e81a42cdb5ad3bdc736c79836d9e044d1a0ba96023ba64
 size 14604

checkpoint-2000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ad8562be07622fc9e024c897347ceead7b11b7c6000cf58d9491ab7f219099
+oid sha256:56cab430bf2883ab08ecdb0930091aaa86b7be034aaf50147f79e0060e5cbc6c
 size 1064

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b8f1431861f4f99c8a6c4334d906aadde093d300f60ce124b1f48411c16dfd
+oid sha256:918b0091f7a32f70809205d697ad6626712f47b3f2764df939a53f0160d03dc7
 size 5849744