Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e556d83dfd61e1850cd8370840a614f9a490be52541514308993a0e7c59ea9af
+oid sha256:9bb6260318dbfc41931fe985e1c9f2434352358059c2e869811eeeaf5dd1c2d6
 size 94771728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef9c3d4d9e9fcc0a77cb55f604a658d21809f70dbb85125b8ede9d53faded4b
+oid sha256:04ba8d418f96f3ecca17303f9c5c939af3a5ac131c9431a85d3cc7fee022dd44
 size 189575930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c674e81544453eae2acbcbb62d94276243e1b3569f69a22a43d6f37cedc1ca82
+oid sha256:7a07457e0dbcc2de694df7e069de9849061cb176e4d9666314196b024639d926
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2815ea4361d250d0ba953799d9dfc6e2ece6fe17738b98d3d9abb70f9e9183c9
+oid sha256:345cb19fe1c02f5d7c293deaf1c353b754e6fa6fed4899ede008684cc6cf5dea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.73,
   "best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-25",
-  "epoch": 4.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,13 +163,142 @@
       "eval_samples_per_second": 1.364,
       "eval_steps_per_second": 0.171,
       "step": 100
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.0007,
+      "loss": 0.6077,
+      "step": 105
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0007333333333333333,
+      "loss": 0.2685,
+      "step": 110
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0007666666666666667,
+      "loss": 1.048,
+      "step": 115
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0008,
+      "loss": 1.1636,
+      "step": 120
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0008333333333333334,
+      "loss": 1.0052,
+      "step": 125
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0008666666666666667,
+      "loss": 2.0122,
+      "step": 130
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 1.6791,
+      "step": 135
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0009333333333333333,
+      "loss": 1.3824,
+      "step": 140
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0009666666666666667,
+      "loss": 1.0703,
+      "step": 145
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.001,
+      "loss": 1.4339,
+      "step": 150
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0009962962962962963,
+      "loss": 1.5909,
+      "step": 155
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0009925925925925927,
+      "loss": 2.139,
+      "step": 160
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.000988888888888889,
+      "loss": 1.8476,
+      "step": 165
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.000985185185185185,
+      "loss": 2.1354,
+      "step": 170
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0009814814814814816,
+      "loss": 2.0248,
+      "step": 175
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0009777777777777777,
+      "loss": 2.1732,
+      "step": 180
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0009740740740740741,
+      "loss": 1.9887,
+      "step": 185
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0009703703703703704,
+      "loss": 2.0138,
+      "step": 190
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0009666666666666667,
+      "loss": 1.9447,
+      "step": 195
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0009629629629629629,
+      "loss": 1.9785,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.33,
+      "eval_loss": 2.211935520172119,
+      "eval_runtime": 145.0026,
+      "eval_samples_per_second": 1.379,
+      "eval_steps_per_second": 0.172,
+      "step": 200
     }
   ],
   "logging_steps": 5,
-  "max_steps": 250,
-  "num_train_epochs": 10,
+  "max_steps": 1500,
+  "num_train_epochs": 15,
   "save_steps": 500,
-  "total_flos": 2.1806703588096e+17,
+  "total_flos": 2.725837948512e+17,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7059aed49f7f3c702864807bd132052921d120cd16c44ab7882c5c6d6a30a3f
+oid sha256:76b9f3c262a292cdb0a53531fab23493df1fa0920f505da84357b1aecf0d0281
 size 4600