End of training

README.md

@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1
+- mixed_precision_training: Native AMP
 
 ### Training results
 

config.json

@@ -22,7 +22,7 @@
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.44.0",
   "use_cache": true,
   "use_parallel_residual": true,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a92e4472076cdd574ff3735ffe85ebeb9d760e3416538467e3a5926898a1ed5
-size 4977795456
+oid sha256:387861076b736199475344073a5ffef07f9a25a869bad78eac4cf52635cc0977
+size 4977795320

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4c20f15d0f7cc218667adf9ff7b6ea790f06dd11b5a3744007e3d32f50ef5e
-size 4967384136
+oid sha256:1997687dc7825df18e69c022bee50624f691da64a2791a5fe319cbe0b654f403
+size 4967383992

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e5bc784b59ddb5deecbb96106d3efa0f7857ca54f8a85bd07751c2f70b3828
-size 3769470736
+oid sha256:a51f1957c1f312fae6e2e895675af06a2e71d3bd5dfe0083523adfdc9efcea45
+size 3769470640

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ec4f712dee7b6fb9e2d0a77d7805c1e63871874f13fafcf3daca7bac90a852
-size 6712
+oid sha256:f1022d8ff3b08f249eb0e6299a2f1ea8345e60ca4825bf55e0b6d1bc1f6e0954
+size 6776