Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a464be9fec0b1c828e8a3be4ac1fb7168b03c5ed4d2dbaa87a5f47702a4b740
+oid sha256:557a7b887efea43f30540591296b172670f833eb24b7fcde5d38500396cd2120
 size 344814656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0adda3532a4298fb3546704495979338b3071ea44e0487623379f887c7621f51
+oid sha256:2cfe7ba32285d8aca52e368728864045e3b3198f2b05634e71e6db69fa512bc6
 size 689741690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c39630ef971dd09b3fe4dd100706148d6dbc710ecd4f44ada87a34fe07ca75
+oid sha256:c8e927e0c71d62c9d3968420452b731232314f4117cc838742af50f1ba552059
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.89,
   "best_model_checkpoint": "ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan/checkpoint-339",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 339,
+  "global_step": 452,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -436,13 +436,160 @@
       "eval_samples_per_second": 6.583,
       "eval_steps_per_second": 0.856,
       "step": 339
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 3.883972468043265e-05,
+      "loss": 0.2607,
+      "step": 340
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 3.859390363815143e-05,
+      "loss": 0.2316,
+      "step": 345
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 3.834808259587021e-05,
+      "loss": 0.0272,
+      "step": 350
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 3.810226155358899e-05,
+      "loss": 0.1928,
+      "step": 355
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 3.7856440511307774e-05,
+      "loss": 0.0225,
+      "step": 360
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.7610619469026545e-05,
+      "loss": 0.0359,
+      "step": 365
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.736479842674533e-05,
+      "loss": 0.0208,
+      "step": 370
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.711897738446411e-05,
+      "loss": 0.0131,
+      "step": 375
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.687315634218289e-05,
+      "loss": 0.0209,
+      "step": 380
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 3.6627335299901674e-05,
+      "loss": 0.1438,
+      "step": 385
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 3.638151425762045e-05,
+      "loss": 0.4599,
+      "step": 390
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 3.6135693215339236e-05,
+      "loss": 0.0166,
+      "step": 395
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 3.588987217305801e-05,
+      "loss": 0.0156,
+      "step": 400
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 3.56440511307768e-05,
+      "loss": 0.0039,
+      "step": 405
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 3.5398230088495574e-05,
+      "loss": 0.0753,
+      "step": 410
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 3.515240904621436e-05,
+      "loss": 0.0047,
+      "step": 415
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 3.4906588003933136e-05,
+      "loss": 0.1596,
+      "step": 420
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 3.466076696165192e-05,
+      "loss": 0.409,
+      "step": 425
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 3.44149459193707e-05,
+      "loss": 0.0616,
+      "step": 430
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 3.416912487708948e-05,
+      "loss": 0.0113,
+      "step": 435
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 3.3923303834808265e-05,
+      "loss": 0.107,
+      "step": 440
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 3.367748279252704e-05,
+      "loss": 0.0516,
+      "step": 445
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.343166175024583e-05,
+      "loss": 0.0142,
+      "step": 450
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.89,
+      "eval_loss": 0.6147953271865845,
+      "eval_runtime": 15.3899,
+      "eval_samples_per_second": 6.498,
+      "eval_steps_per_second": 0.845,
+      "step": 452
     }
   ],
   "logging_steps": 5,
   "max_steps": 1130,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1.8282336762986496e+17,
+  "total_flos": 2.4376449017315328e+17,
   "trial_name": null,
   "trial_params": null
 }