Training in progress, epoch 1

config.json

@@ -1,11 +1,11 @@
 {
   "_name_or_path": "ntu-spml/distilhubert",
-  "activation_dropout": 0.1,
+  "activation_dropout": 0.8,
   "apply_spec_augment": false,
   "architectures": [
     "HubertForSequenceClassification"
   ],
-  "attention_dropout": 0.5,
+  "attention_dropout": 0.25,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "conv_bias": false,
@@ -46,7 +46,7 @@
   "feat_proj_layer_norm": false,
   "final_dropout": 0.0,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.5,
+  "hidden_dropout": 0.25,
   "hidden_size": 768,
   "id2label": {
     "0": "blues",
@@ -90,7 +90,7 @@
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.0.dev0",
+  "transformers_version": "4.38.0.dev0",
   "use_weighted_layer_sum": false,
   "vocab_size": 32
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af78792e38d8163090eb033cbe0486eb6666725f8f2c215d1d730e0abff720c
+oid sha256:b4c211de2a41ed4844a588d87e5e4d89c3237e82cfa48eb0b456aef68c441cb8
 size 94771728

runs/Jan20_01-03-16_0474458f40c0/events.out.tfevents.1705712612.0474458f40c0.12351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3956282e7a053db26c2a14dd8f2918923f3a73d56ca28945708feb05de971c
+size 9284

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bbec6ee556afc9f615a4513b843acfdb71ac164920940e131e733b0dadaf104
+oid sha256:323c05bb97466b5ecfc660c15fd8ab727444a207d23514017e0397a8a6d78b6a
 size 4728