Training in progress, step 1044

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "_name_or_path": "yosefw/llama-3.2-amharic-32k-1024-v6",
   "architectures": [
     "LlamaForCausalLM"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad354d160e062b3f651262b35c756510ffbbb746e7ae93d5b84dfbe72301dba
+oid sha256:9555dc146177e449c19714c2f42c8f2c9ee8642591ed6312609e3f1485372550
 size 1650127032

runs/Dec05_15-10-09_0cfc3e3bcad6/events.out.tfevents.1733411437.0cfc3e3bcad6.1494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3096b9441f77c0988dfe8fdd595318c28fda0b8fd4cc8947dee439d10e4a20c8
+size 6535

tokenizer_config.json

@@ -2056,7 +2056,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 1024,
+  "model_max_length": 131072,
   "pad_token": "<|end_of_text|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf72483fe067d31dae65efdeae11c4f789f17b079802bfadc89086c7981f87d
+oid sha256:a4e380fb61b9b499fed024c6130464fec87fc8eaa0b1227f8874ed41d98cac2c
 size 5304