Training in progress, step 500

config.json

@@ -5,10 +5,10 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.0,
-  "bos_token_id": 1,
+  "bos_token_id": 2,
   "dtype": "float32",
   "embd_pdrop": 0.0,
-  "eos_token_id": 2,
+  "eos_token_id": 3,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -18,7 +18,7 @@
   "n_inner": 3072,
   "n_layer": 8,
   "n_positions": 1024,
-  "pad_token_id": 3,
+  "pad_token_id": 0,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": false,
@@ -31,5 +31,5 @@
   "tie_word_embeddings": true,
   "transformers_version": "5.0.0",
   "use_cache": false,
-  "vocab_size": 4
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,12 +1,12 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
+  "bos_token_id": 2,
   "eos_token_id": [
-    2
+    3
   ],
   "output_attentions": false,
   "output_hidden_states": false,
-  "pad_token_id": 3,
+  "pad_token_id": 0,
   "transformers_version": "5.0.0",
   "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7506a1280aec2dd18c1213ed1020dae2e07f4f943a5bd4dd04540876174160
-size 229986128
+oid sha256:87ff9a10f70d200b2c856dee103d85c0b4769807377164ae058876c9b2f8cdf4
+size 328277848

tokenizer_config.json

@@ -1,13 +1,10 @@
 {
-  "add_prefix_space": null,
   "backend": "tokenizers",
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "is_local": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "TokenizersBackend",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2c5bf738d3dfdf4bb29b32f549e85540e511a9724f3a1b5d213bbd748c534c
+oid sha256:fce02471cb82f83442a696c0b3bab66a52bc0f41341df1b015701dd7299e8f59
 size 5201