Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "_name_or_path": "meta-llama/Llama-3.2-3B",
   "architectures": [
     "LlamaForQuestionAnswering"
   ],
@@ -7,16 +7,16 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128001,
-  "head_dim": 64,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 16,
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf2b1fc83d69410c791e6026f17d1391aa398b5920a91e2a62c9ab87714de62
+oid sha256:e9b1ab6a8ec60e4b3ff91817f04136edf81f03ccc7c918fdffa2a227a69a915a
 size 4998780112

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c745eefb3f841fb4d5c056bcdb6702575c535b223988f4a426d04bcb52d66a0
+oid sha256:38d22c86cc2ec74e98d24cbd13ef80b0f4dc0749c95fcec74fa3e54fe7d28052
 size 4932809624

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2f2951ed77b256753def73c04f971c88dbaca7d436c3e34bc550fea4bc113c
+oid sha256:ca392b92678d58e774b194663ec5fde0341cdb98c021d41c4fce71bc9e695ebd
 size 2919477304

runs/Dec23_12-43-00_xgpi7/events.out.tfevents.1734929185.xgpi7.47489.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5585de225f3e16f83f8595bd12d3f080a97e7e47be6f1004af2b357644df04a9
+size 5518

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81e684b1201c0137d1d684fe55a11ea6e635ba8734ab38812bd697d6606bd890
+oid sha256:694c0c778b5a7dcf097fd8714352284b7c53fb854e5b5c1eaede032469382933
 size 5368