Training in progress, step 100

config.json

@@ -3,6 +3,7 @@
   "architectures": [
     "MistralForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -19,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.36.2",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jan09_01-04-39_ip-26-0-175-170/events.out.tfevents.1704762517.ip-26-0-175-170.1764083.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb11f48d4f6d55d5d67146e62c0ce6fe2be6ef5e0350ca60c3c4c210b7b23bc
+size 12084

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -37,5 +39,5 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0cfeef488c76d81097985b677ed0b0472418232cb8ef928f69733a5bd91920a
-size 5688
+oid sha256:f8223da2f2f0ee9475bd12cdfd5985b88e1af713b8c6fb49804c639b8f261335
+size 5944