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": "mistralai/Mistral-7B-v0.1",
+  "_name_or_path": "imone/Mistral_7B_with_EOT_token",
   "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,
@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": true,
-  "vocab_size": 32000
+  "use_cache": false,
+  "vocab_size": 32002
 }

runs/Apr19_17-47-46_n136-147-090/events.out.tfevents.1713520143.n136-147-090.484016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e1cee2bef8d12f4571730d8738f8dd85accd522f059b52b43782cf8fbbcc96
+size 4975

runs/Apr19_18-10-06_n136-147-090/events.out.tfevents.1713521430.n136-147-090.507324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ce483d6d4a810fbdafc384de19f820f1a4e3436fdbe188296531fe32ab9e05
+size 4768

runs/Apr19_18-22-46_n136-147-090/events.out.tfevents.1713522190.n136-147-090.515476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4edb439c637b7750d9f802801202cb7ccbd932619cb39410eddab32125796c19
+size 6216

runs/Apr19_20-41-32_n136-147-090/events.out.tfevents.1713530517.n136-147-090.541607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f15637a92974fbecff3d655dc7b7049e019b378a74788db927b7036671665c
+size 9114

special_tokens_map.json

@@ -1,4 +1,8 @@
 {
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -7,13 +11,13 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|end_of_turn|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": "<|end_of_turn|>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": 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_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 sha256:9a1a47f129a9c5ef9d01967ad69e7f3da2e377c46b21febbb75510e11224cc4d
-size 6072
+oid sha256:f15c584ca71b3d4cc3c96f7d1a18e25570f54f6d0583f82abc6f124a036ebdc1
+size 6136