Training in progress, step 5000

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_projector=mlp, per_device_train_batch_size=2, run_name=bs2_liger, student_model_use_liger=True/events.out.tfevents.1726131178.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:640ed650621f26b60037ed72f5c113a7ddf1a9f2065ed699d64d767d20d7acda
+size 44717

logs/attn_weight=0.0, per_device_train_batch_size=4, run_name=logits_only_bs4_liger, student_model_use_liger=True/events.out.tfevents.1726133176.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f8ad5424da9f2234f3fa5c1375fc7e257553e853b87e4e31b9458c3c22a17b
+size 140518

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1ef419f333753f4e4f622274329bc9d47ec44ae3c67e93e974dbc8c2abbc34
+oid sha256:43cc61ad3f95f6e7cef6e4c2caf29d2cf2cb2e2341ba787df664c1ce0946d31d
 size 162842416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738e9326fbb30717baf30f64578731beac353bb8abd9108ce8783db4565fa56e
-size 5368
+oid sha256:bdb30d215278960a24b28efe91c6ca2db7380865e7318789dc26ff26097066c0
+size 5432