Training in progress, step 30000

config.json

@@ -40,7 +40,7 @@
     }
   },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.44.1",
   "use_cache": true,
   "vocab_size": 50257
 }

logs/attn_norm=layernorm_teacher_only_affine, attn_projector=mlp_256_l2, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=16, warmup_ratio=0/events.out.tfevents.1725468061.e3f806ea38c9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0daa80bb7960e48f8edb2dfa0ffd196c6057fd1488c94ae0974d8f8a2a6b02c4
-size 629668
+oid sha256:2a92d9d85b2afc8e69655ff6cc4f40e17b586e71aaf1d9648f19b22fbf123f14
+size 946271

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eae2fbac34eea82ae71dd738509d8ebb7217072a9cb6e1fdbbfb88043506e87
+oid sha256:6117cb21ba689d240b7281a26ae8cffcda5e8b1494a6692f473e01c98e9dbb45
 size 163832792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea8421bc97af1a9921190732fec21855d6dc9e1a2a5d7598cba2d4e0f1ae8a0e
+oid sha256:e94eaa60413c4cf51d9a6a08dd8682d66f9ca672b582d54a821d965d88721e41
 size 5560