Training in progress, step 500

config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 256,
+  "n_head": 4,
+  "n_inner": 1024,
+  "n_layer": 4,
+  "n_positions": 256,
+  "pad_token_id": 0,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 47
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.12.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e7ae653908ec1097f2131d006e20e1231f2157e53bfd38a7e180a9f47bd980
+size 12953576

tokenizer.json

@@ -0,0 +1,141 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "[\\s\\S]"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "Fuse"
+  },
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<pad>": 0,
+      "<bos>": 1,
+      "<eos>": 2,
+      "<unk>": 3,
+      "\n": 4,
+      "+": 5,
+      "0": 6,
+      "1": 7,
+      "2": 8,
+      "3": 9,
+      "4": 10,
+      "5": 11,
+      "6": 12,
+      "7": 13,
+      "8": 14,
+      "9": 15,
+      "=": 16,
+      "٠": 17,
+      "١": 18,
+      "٢": 19,
+      "٣": 20,
+      "٤": 21,
+      "٥": 22,
+      "٦": 23,
+      "٧": 24,
+      "٨": 25,
+      "٩": 26,
+      "०": 27,
+      "१": 28,
+      "२": 29,
+      "३": 30,
+      "४": 31,
+      "५": 32,
+      "६": 33,
+      "७": 34,
+      "८": 35,
+      "९": 36,
+      "一": 37,
+      "七": 38,
+      "三": 39,
+      "九": 40,
+      "二": 41,
+      "五": 42,
+      "八": 43,
+      "六": 44,
+      "四": 45,
+      "零": 46
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98df703cae131f341c3e77ea1501564987302367867b74ee44f234b92e5305e9
+size 5265