Training in progress, step 125

config.json

@@ -6,11 +6,12 @@
   "context_len": 1024,
   "eos_token_id": 2,
   "eps": 1e-06,
-  "hidden_size": 20,
+  "hidden_size": 100,
   "model_type": "llama",
   "num_attention_heads": 10,
-  "num_hidden_layers": 5,
+  "num_hidden_layers": 10,
   "pad_token_id": 2,
+  "rope_theta": 10000.0,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "vocab_size": 32000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1490252c5cd5aaef365775417f8b41fb33a738c213e1d250c3ff3fe063289cd0
-size 9626256
+oid sha256:a780efe493861a458a1dfc4710d10fe0a6b996710393fe48f1c0b38eecdc9d37
+size 66017896

runs/Nov11_16-58-41_18ffd9f1a532/events.out.tfevents.1731344326.18ffd9f1a532.7115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1f7b6a580a3ff860d85b7b78b78064bd542e68fd6e17a13375df90fef2cc34
+size 5433

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8ea94dafb3c67b9ad49918f768afa47e3ad2655d90916ffc1d2df233d9358d
+oid sha256:28d10408adfa2f79a0115aa0493cfe092db64050f3c94912bd5c0e236c69b8fc
 size 5240