Training in progress epoch 0

checkpoint-28000/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-28000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5770f36ff9776b508128b6e2f3c83c7d7652a4d37ac316ac87dfb8f1752ba6
-size 7438256
+oid sha256:6c74d9ac5ff28075359b8112d364c1f39d102b3b9390b0f76e1500391feb0050
+size 5849744

checkpoint-28000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b44638932cc9b8c2c6e57d2210720b06f9357a1840fe577c6b1c3c435c03c1c6
-size 14910074
+oid sha256:8c18ec1477b7d67aad464d2671376be9961f52620e0822d363042044ac0e84cd
+size 11717834

checkpoint-28000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0a435d4a8ec117ff93fa4f338e2dc7b777bf0f41ddc0acb787a798cafe91d2
+oid sha256:36868ac40b542f045e6421cb339983d84212e13f643e35a515ef2e2a14eca099
 size 14604

checkpoint-28000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bda0af9d8c15910d6dbcf229608e2c842290f3a4495e49423eaf1c31348d908
+oid sha256:e3ae2ef37ea201a0cef7fddd85b235c800172d85d7060052931716190d2d0035
 size 1064

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c74d9ac5ff28075359b8112d364c1f39d102b3b9390b0f76e1500391feb0050
+oid sha256:4e11bfbcdc1241f8ac71f7b36d4c5c05eda9a3780c8e9712e25c5483f5c952b5
 size 5849744