Training in progress, epoch 1, checkpoint

checkpoint-56/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ntu-spml/distilhubert",
+  "_name_or_path": "arshsin/distilhubert-finetuned-gtzan",
   "activation_dropout": 0.1,
   "apply_spec_augment": false,
   "architectures": [

checkpoint-56/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79260246d365035f9707e2ebe4f56571ebbf8991f8149a4077a2a601171c30ac
+oid sha256:fd1b842eac14f882f0845e06fa92fabb046e1eeb806e542205a6cc56313e26db
 size 94771728

checkpoint-56/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9082cd06dd579e3271d0105b56f0d8e846c9e545c7a06e61cb41e5a2ccc840c1
+oid sha256:413edb1c807262ce125f49a6659f79a3b35a9f6fb2b4e3819a201d6a68904a98
 size 189575930

checkpoint-56/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d80c482adc0bf69fb6533d98998b0f610c663026a7d2d3e262919fe827b14b0
+oid sha256:2ec53eaa68c4c55193fc6d3f84ff83ddf726625d2b43eae85fb551c775a1de57
 size 14244

checkpoint-56/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a41d9d94f50ff1436cbdabc7e4624705b1da0b0f8d7c8ca0a9d41940a9f16e
+oid sha256:85b8f0c1d2ac8d82fdab4d399b07207b3f536098dd46f5762c5f40d75530538b
 size 1064

checkpoint-56/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.27,
+  "best_metric": 0.83,
   "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-56",
-  "epoch": 0.9911504424778761,
+  "epoch": 1.9823008849557522,
   "eval_steps": 500,
   "global_step": 56,
   "is_hyper_param_search": false,
@@ -9,86 +9,95 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.09,
-      "learning_rate": 4.464285714285714e-05,
-      "loss": 2.2976,
+      "epoch": 0.18,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.0338,
       "step": 5
     },
     {
-      "epoch": 0.18,
-      "learning_rate": 8.928571428571429e-05,
-      "loss": 2.2855,
+      "epoch": 0.35,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0053,
       "step": 10
     },
     {
-      "epoch": 0.27,
-      "learning_rate": 0.00013392857142857144,
-      "loss": 2.2307,
+      "epoch": 0.53,
+      "learning_rate": 9.920634920634922e-06,
+      "loss": 0.0056,
       "step": 15
     },
     {
-      "epoch": 0.35,
-      "learning_rate": 0.00017857142857142857,
-      "loss": 2.1327,
+      "epoch": 0.71,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.0437,
       "step": 20
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.00022321428571428573,
-      "loss": 2.0339,
+      "epoch": 0.88,
+      "learning_rate": 9.126984126984127e-06,
+      "loss": 0.0017,
       "step": 25
     },
     {
-      "epoch": 0.53,
-      "learning_rate": 0.00026785714285714287,
-      "loss": 1.9633,
+      "epoch": 0.99,
+      "eval_accuracy": 0.82,
+      "eval_loss": 1.0909959077835083,
+      "eval_runtime": 72.1207,
+      "eval_samples_per_second": 1.387,
+      "eval_steps_per_second": 0.18,
+      "step": 28
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 8.730158730158731e-06,
+      "loss": 0.0013,
       "step": 30
     },
     {
-      "epoch": 0.62,
-      "learning_rate": 0.0003125,
-      "loss": 1.8021,
+      "epoch": 1.24,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0373,
       "step": 35
     },
     {
-      "epoch": 0.71,
-      "learning_rate": 0.00035714285714285714,
-      "loss": 1.6938,
+      "epoch": 1.42,
+      "learning_rate": 7.936507936507936e-06,
+      "loss": 0.0041,
       "step": 40
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.00040178571428571433,
-      "loss": 1.5271,
+      "epoch": 1.59,
+      "learning_rate": 7.53968253968254e-06,
+      "loss": 0.0012,
       "step": 45
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.00044642857142857147,
-      "loss": 1.4038,
+      "epoch": 1.77,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.0338,
       "step": 50
     },
     {
-      "epoch": 0.97,
-      "learning_rate": 0.0004910714285714286,
-      "loss": 1.496,
+      "epoch": 1.95,
+      "learning_rate": 6.746031746031747e-06,
+      "loss": 0.0143,
       "step": 55
     },
     {
-      "epoch": 0.99,
-      "eval_accuracy": 0.27,
-      "eval_loss": 1.8467493057250977,
-      "eval_runtime": 72.5718,
-      "eval_samples_per_second": 1.378,
-      "eval_steps_per_second": 0.179,
+      "epoch": 1.98,
+      "eval_accuracy": 0.83,
+      "eval_loss": 1.1379410028457642,
+      "eval_runtime": 71.5138,
+      "eval_samples_per_second": 1.398,
+      "eval_steps_per_second": 0.182,
       "step": 56
     }
   ],
   "logging_steps": 5,
-  "max_steps": 560,
-  "num_train_epochs": 10,
+  "max_steps": 140,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 6.133988274624e+16,
+  "total_flos": 1.2267976549248e+17,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-56/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbef9bdfa53985d2dd1361cb595119941d5a4b9581e158c102613a779ed26711
+oid sha256:94c8327b62c2d89df2d87b86e12181649733dbdfae7f66da82435847a359e69a
 size 4600