Training in progress, step 100

config.json

@@ -1,28 +1,26 @@
 {
-  "_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "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": 11008,
-  "max_position_embeddings": 4096,
-  "model_type": "llama",
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 32,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
-  "vocab_size": 102400
+  "vocab_size": 32000
 }

runs/Jul23_20-15-45_n122-143-008/events.out.tfevents.1721739057.n122-143-008.113937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1a6081e3e97687cc19e5c2ea5dd2db7a80eacc31ba8171c81851ed474bafbe
+size 9337

runs/Jul23_20-26-09_n122-143-008/events.out.tfevents.1721739061.n122-143-008.121887.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf8cf0909a263042d7750890780b58761c8cef388562d6227887d48efb4044e7
+size 5197

special_tokens_map.json

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

tokenizer_config.json

@@ -2,136 +2,42 @@
   "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
-    "100000": {
-      "content": "<｜begin▁of▁sentence｜>",
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100001": {
-      "content": "<｜end▁of▁sentence｜>",
+    "1": {
+      "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100002": {
-      "content": "ø",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "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
+      "special": true
     }
   },
-  "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 %}",
+  "additional_special_tokens": [],
+  "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": "<｜end▁of▁sentence｜>",
-  "legacy": true,
-  "model_max_length": 4096,
-  "pad_token": "<｜end▁of▁sentence｜>",
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": null,
+  "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c954413038ae54893068f1be5a172e843dda5a64dbec190fdf1dfe888eb5bd
-size 6136
+oid sha256:117c17ecc903a5fe08313ba6810d9ffa8610fac909b5f8a789676510ed27aacf
+size 6392