Training in progress, step 2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|BOS|>": 50258,
+  "<|PAD|>": 50257
+}

config.json

@@ -1,11 +1,10 @@
 {
   "activation_function": "gelu_new",
-  "add_cross_attention": false,
   "architectures": [
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": 50258,
   "dtype": "float32",
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
@@ -18,7 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 50256,
+  "pad_token_id": 50257,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -34,8 +33,7 @@
       "max_length": 50
     }
   },
-  "tie_word_embeddings": true,
-  "transformers_version": "5.2.0",
-  "use_cache": false,
-  "vocab_size": 50257
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 50259
 }

generation_config.json

@@ -1,9 +1,9 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
+  "bos_token_id": 50258,
   "eos_token_id": [
     50256
   ],
-  "pad_token_id": 50256,
-  "transformers_version": "5.2.0"
+  "pad_token_id": 50257,
+  "transformers_version": "4.57.6"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fed988c4363302414a116b0cf8fc366a9784b4f328219ac8111e0588057ade
-size 497774208
+oid sha256:70cd678e3236aa1b6abdb04c0acd63c81614e93d01c7773284e20ee4622444a7
+size 497780352

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": {
+    "content": "<|BOS|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|PAD|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|BOS|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|BOS|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|PAD|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f488d7fbb3c9aef4120df0fc5fa4e2a37f0e4ab4e032ce073f3250db3e60c90
+size 5432