Training in progress epoch 0

checkpoint-40000/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-40000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:231821029f132392c4aab58f32a525ebd34704e7357a11ba188d411ca7eac4b2
-size 7438256
+oid sha256:ff2795c088f6496c3ffd627f2d027fa612ff0c147b1b44858f507438b40663cf
+size 5849744

checkpoint-40000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddefd7b601e3c40b1720618efd4dd7dae691d736d2a62c1288eb1f8a98ed0c6
-size 14910074
+oid sha256:61c9322e87ef65575652f79499186d25a891c593f55a61e6e04b1472485c21f5
+size 11717834

checkpoint-40000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f90b38d6f3b23a68f7dd6194ffd9b7c55a0e410b02c63dac47704072816427
+oid sha256:33e358e493500367e092a886fdf1e87d5c958ef28e9da461d63fada7c17b4bc2
 size 14604

checkpoint-40000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d58522a4a625b659506c4f966d1386ef9a09434189217ea3f249c952ed164e12
+oid sha256:7ef07393dcea512f4246badc1604dc99700f514c513013c0b66c85725f129edd
 size 1064

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2795c088f6496c3ffd627f2d027fa612ff0c147b1b44858f507438b40663cf
+oid sha256:d5eebfeb1554710d75e6614570ab06e34f00ab05740878d63629adb1ade5a0f6
 size 5849744