Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-2b-it",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,10 +20,11 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "o_proj",
+    "q_proj",
     "k_proj",
-    "q_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a480e1ab3f1190230012304e680ef32897cf6e0024ca0f48809795d6b009d046
-size 7391688
+oid sha256:bea37fff7ace62575b2989cb54f23092e9d5822e0b098b5f26817e09405ec070
+size 9034304

special_tokens_map.json

@@ -1,23 +1,19 @@
 {
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
   "bos_token": {
-    "content": "<bos>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<eos>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<eos>",
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:861eff971cfc5e6ccabf75148657b0c34fc939c5caf491eb3126ff6b2c5c42c1
-size 17478028
+oid sha256:3cf9f0e73545c00e1f85ad45698f364ca47da10e09cb222de1599ccbf7a45081
+size 1842866

tokenizer_config.json

@@ -3,7 +3,7 @@
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -11,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": "<eos>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -19,31 +19,7 @@
       "special": true
     },
     "2": {
-      "content": "<bos>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "106": {
-      "content": "<start_of_turn>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "107": {
-      "content": "<end_of_turn>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -51,20 +27,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<start_of_turn>",
-    "<end_of_turn>"
-  ],
-  "bos_token": "<bos>",
-  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<eos>",
-  "legacy": null,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<eos>",
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6904e046e9122ea6a909f3932ab9793a8a47340c0da611d09923ba3fdbd3f4f
+oid sha256:78688d623ac4d65cae202be9308ca3e522397a484dca4d792c4930b50729467a
 size 4920