Training in progress, step 500

config.json

@@ -1,26 +1,28 @@
 {
-  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
   "architectures": [
-    "MistralForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.3",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 102400
 }

runs/Jun20_15-28-21_n136-129-074/events.out.tfevents.1718869497.n136-129-074.3627432.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70878c29e1d06504b3433b6495e0221e9ca08f4aa04124743fff6d4d4b3a6d8b
+size 26025

special_tokens_map.json

@@ -1,23 +1,22 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<｜begin▁of▁sentence｜>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
-  "unk_token": {
-    "content": "<unk>",
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -2,42 +2,136 @@
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "100002": {
+      "content": "ø",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '\n\n\nHuman: ' + message['content'] + '<|end_of_turn|>' }}{% elif message['role'] == 'assistant' %}{{ '\n\n\nAssistant: '  + message['content'] + '<|end_of_turn|>' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '\n\n\nAssistant: ' }}{% endif %}{% endfor %}",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ 'User: '+ message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ 'Assistant: '  + message['content'] +  eos_token }}{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ 'Assistant: ' }}{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
+  "eos_token": "<｜end▁of▁sentence｜>",
   "legacy": true,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
+  "unk_token": null,
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3773c98a42ff7371c8283dc6703542d77c04c5f1f0234b4257866273fde024e
+oid sha256:99c954413038ae54893068f1be5a172e843dda5a64dbec190fdf1dfe888eb5bd
 size 6136