Training in progress, step 5

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./results/checkpoint-35",
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 138626
 }

model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c639cca74f3e21d0d21638ee1f69eedbe280e46c8f61380e17d96f8a7b54808
+oid sha256:12ebfae5b8af8f447067dbedf26bc342f37b5c13f8b716236fc5a44ff83e5ba7
 size 4989259264

model-00007-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:704de3a6018eb9c6f697e4c7127e3abefa57f368847fcd4bfdda2e02a00bbec0
+oid sha256:80d89a79f5f4cdf17c2f149173b6ae2588b1ed0d2987bb36aeb5c3d9afedb81e
 size 2741060264

tokenizer_config.json

@@ -2053,18 +2053,11 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "extra_special_tokens": {},
-  "max_length": 512,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_to_multiple_of": null,
   "pad_token": "<|end_of_text|>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389a43ba2a03dd5d713a6c9be5f780cf98e0d7ffc7ede138d278b385d874f6f9
-size 5368
+oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95
+size 5304