Training in progress epoch 0

.gitignore

@@ -0,0 +1,2 @@
+step_*
+epoch_*

config.json

@@ -5,7 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "eos_token_id": 128001,
   "head_dim": 64,
   "hidden_act": "silu",
@@ -31,6 +31,6 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
   "transformers_version": "5.0.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -2,9 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 128000,
   "do_sample": true,
-  "eos_token_id": [
-    128001
-  ],
+  "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "5.0.0.dev0"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf4179f1b72f9a49b9145090d8bc68c5ce6cfa163bffbcafbb1715b48c4f1eb
-size 2471645608
+oid sha256:0e2dfd43157da5e148021226e1ad08a6bb36d30daf5ead0036633ee78984e8ed
+size 4943274328

special_tokens_map.json

@@ -12,6 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<|end_of_text|>"
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8455cd05329f9cb9895e200605934b714e7fc55873b9969c77d1c3c01ccc60e0
-size 17210188
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -2058,6 +2058,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|end_of_text|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }