Training in progress, step 15000

config.json

@@ -7,7 +7,6 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
   "initializer_range": 0.02,
@@ -24,7 +23,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0.dev0",
+  "transformers_version": "4.44.2",
   "use_cache": false,
   "vocab_size": 49152
 }

logs/attn_weight=0.0, per_device_train_batch_size=4, run_name=bs4_NO_liger_baseline, student_model_use_liger=False/events.out.tfevents.1726140851.1c1a426a2fee

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48adebaad129d74115ca5d0e65f5fced9671ac95565cf804049e71d1d6f4c9fc
-size 277022
+oid sha256:b73165cbe5b7634e00295dc85a52f478493e88491c843f032b52b4baa85a2906
+size 412294

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2edac0aa3f004c7d74ace9f4ea65083001bffdb894b7d3ecacb16ad774eca5
+oid sha256:2392770ba433e3966f57d02de2a7f10c7a5737785fb782a4b4d92cbac9887b83
 size 162842416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738e9326fbb30717baf30f64578731beac353bb8abd9108ce8783db4565fa56e
-size 5368
+oid sha256:555ceb45b35190b72c7d1a0f76611e172bacea5f42f7a7ad17b8bf6a95802281
+size 5432