Training in progress, epoch 0

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "/home/aiops/zhuty/lmind_nq_train6000_eval6489_v1_docidx_v3_meta-llama_Llama-2-7b-hf_lora2/checkpoint-683_merged",
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b32475435e81674f74c91b835ce6f1447953a076b3c31a848c0a9269241d213
+size 112130416

added_tokens.json

@@ -1,5 +1,5 @@
 {
-  "</s>": 2,
-  "<s>": 1,
-  "<unk>": 0
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
 }

special_tokens_map.json

@@ -1,11 +1,14 @@
 {
   "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,23 +1,24 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "151645": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,23 +27,17 @@
     }
   },
   "additional_special_tokens": [
-    "<unk>",
-    "<s>",
-    "</s>"
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "bos_token": "<s>",
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "max_length": 1024,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "padding_side": "left",
-  "sp_model_kwargs": {},
-  "stride": 0,
-  "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518a27ee9247e4c9ef1d43beb1c77640874c6c64ce8eda1fd302542d069288b4
-size 4728
+oid sha256:9a48e2910c0614efc83f1cdab0e18284ec3fdf02b7a0946bdd13c56e7e15f701
+size 5304