Training in progress, epoch 1

config.json

@@ -4,10 +4,10 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": 1,
   "dtype": "float32",
   "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "eos_token_id": 2,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -27,5 +27,5 @@
   "summary_use_proj": true,
   "transformers_version": "4.57.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 8192
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.57.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:956420d3c573d7f77036b8e51f2e2e187332857a8526c01f5337e3daf2923708
-size 65155056
+oid sha256:1d7b3526349a299a4d159e77115825b1662172e60c405de4adb3f6370ab8f652
+size 22080496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a04c860d08c80039ffe0996267290961732a27df61b34bf8940813a5e38cc71
+oid sha256:65acd1d7f2d53e8ff4c06aadbb970382b48ebb477d6374b52df831557a9f9f81
 size 5496