Training in progress, step 125

config.json

@@ -12,7 +12,7 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 40,
-  "n_embd": 120,
+  "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.42.3",
   "use_cache": true,
-  "vocab_size": 35000
+  "vocab_size": 20000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c5c655153abf2e15c7e987ec8b9c5696395c4266932ccfd688b591f6a6c9e1
-size 25676152
+oid sha256:a6dc8d9f3b5efc2223385e131694b011b07d423e663ccbe15297aad285604e91
+size 404824704

runs/Jul02_18-33-10_submit00.mit.edu/events.out.tfevents.1719959594.submit00.mit.edu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:037940a2a93c4d26ea5c2062cd9d64b0505c6f42d181d0992325d99eed7f1da0
+size 7368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634b6d8f9fb0bd6d1fa112cf02e48786eb4d84dcdb20fd93dd6456ea4c40b504
+oid sha256:9bdff206dc9817564d796b00b7f9a68626ad227c1f0b9d1b5655e9dd8eb1c4b9
 size 5176