Training in progress, step 100

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "_name_or_path": "/mnt/bn/xuruijie-llm/checkpoints/mistral_sft/prefix2/",
   "architectures": [
     "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 8192,
   "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -22,5 +22,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 32002
 }

runs/May08_15-06-38_n136-082-130/events.out.tfevents.1715152077.n136-082-130.3146567.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870e1d3818199c14d7dfb487fc5e8376be5bf7bf44374529702830c45d5acdad
+size 13021

special_tokens_map.json

@@ -1,4 +1,8 @@
 {
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -7,14 +11,14 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|end_of_turn|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
+    "content": "<|end_of_turn|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -29,6 +29,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<|end_of_turn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32001,
+      "content": "<|pad_0|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -25,19 +25,38 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
   "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": "</s>",
+  "eos_token": "<|end_of_turn|>",
   "legacy": true,
   "model_max_length": 2048,
-  "pad_token": "</s>",
+  "pad_token": "<|end_of_turn|>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7efa248a5a8a6ab31bf58f910df4042972933046baa2c6c548fb0adb08293d
-size 6200
+oid sha256:b431708a202df6e8544b327fc3255251598ac56ce5bd6f456dd8f2601745f383
+size 6264