End of training

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 4
+- num_epochs: 3
 
 ### Training results
 

config.json

@@ -12,10 +12,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 128,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 512,
+  "n_head": 8,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 8,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443bdda554eacf7be250a15e586d98314843eb15030b44dab2c070365cceab57
-size 497774208
+oid sha256:0c812841399038a7e3d5f3e6d77ab3df8ec9360a2dd87de2c5a0835d1f465537
+size 205913840

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c0a9c78f4bcafdae8e384456f35821acc7902d3d39b050d3851c8bf618268e
+oid sha256:cd5336d2f3476d71cc91f7392921079f7829d909a461ae5e2aa5ed9273d6f969
 size 4728