Update training progress and artifacts

README.md

@@ -4,12 +4,12 @@ license: apache-2.0
 library_name: transformers
 ---
 ## Model Trained Sequentially on Hugging Face Datasets
-**Base Model:** arnir0/Tiny-LLM
+**Base Model:** roneneldan/TinyStories-Instuct-1Layer-21M
 This model is being fine-tuned sequentially using LoRA on various datasets
 available on the Hugging Face Hub. The resulting model (base + adapter merged) is saved
 at the root of this repository as `model.safetensors`.
 ### Training Progress
-- **Datasets Processed:** 3
-- **Text Examples Processed:** 12
-- **Tokens Processed:** 6144
-- **Last Update:** 2025-05-07 03:43:35 UTC
+- **Datasets Processed:** 1
+- **Text Examples Processed:** 885
+- **Tokens Processed:** 453120
+- **Last Update:** 2025-05-07 04:17:54 UTC

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fae99d4c1b50b045030868ca143c4020126ace76f1fd0e3ad115467f06edb1d
+oid sha256:545027dc82283ea96876d6df1ad82e9154b646ca5725b72cdc0f48ca654512e6
 size 51957256

special_tokens_map.json

@@ -1,21 +1,21 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "<unk>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -1,26 +1,9 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -28,16 +11,13 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "legacy": true,
   "model_max_length": 2048,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }