Training in progress, step 5500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d626255d3fda2c0de4ca84328c83dbcced0b5ce4b0d0e1c6cf31b50694922b
+oid sha256:b56fbdf7fe55206aba37bd5ae400349b2464f89eeb757ae10fcf1d6efcc7644f
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d6d4bce7a94c7ee7f993f30f3cb3a1b9aebeeef0cdc917b1c334ecd930d145
+oid sha256:613a8d1a657ba89ada23ab7d7633f3cf31fb4364c0614b7c8174ec86a031e3af
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716e3016868ceaf8d4f0dbe38b820cfb087f035aa02a736305ef885eb0b2f9a9
+oid sha256:78393450795811d9dfafdce73145f39f52c703d761292801d15750c186cc2118
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38bb49bc916eec650d156e5efb1f9040e7833436ca5df10a36a3cd87a7164579
+oid sha256:27cf200ae168599617b8ef6dbb08dc689bd11010b7655ba355b260440e03cb3c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c6cad2f916ae1c4597aa277a2ae6583004fe151268a304e96495ea21dc7bbe
+oid sha256:fa325f8460c9be76052157bd9b7d0c22035d7e2dbd36acf508d25edf25974d7b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4500,
   "best_metric": 1.5784235000610352,
   "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-4500",
-  "epoch": 2.226186169472659,
+  "epoch": 2.4488103520244886,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -788,6 +788,84 @@
       "eval_samples_per_second": 390.719,
       "eval_steps_per_second": 48.855,
       "step": 5000
+    },
+    {
+      "epoch": 2.2484485877278417,
+      "grad_norm": 1.1154942512512207,
+      "learning_rate": 5e-05,
+      "loss": 1.6964,
+      "step": 5050
+    },
+    {
+      "epoch": 2.270711005983025,
+      "grad_norm": 1.117543339729309,
+      "learning_rate": 5e-05,
+      "loss": 1.6862,
+      "step": 5100
+    },
+    {
+      "epoch": 2.292973424238208,
+      "grad_norm": 0.9821292161941528,
+      "learning_rate": 5e-05,
+      "loss": 1.6819,
+      "step": 5150
+    },
+    {
+      "epoch": 2.315235842493391,
+      "grad_norm": 1.1892586946487427,
+      "learning_rate": 5e-05,
+      "loss": 1.6964,
+      "step": 5200
+    },
+    {
+      "epoch": 2.337498260748574,
+      "grad_norm": 1.3049404621124268,
+      "learning_rate": 5e-05,
+      "loss": 1.682,
+      "step": 5250
+    },
+    {
+      "epoch": 2.359760679003757,
+      "grad_norm": 1.0873595476150513,
+      "learning_rate": 5e-05,
+      "loss": 1.6399,
+      "step": 5300
+    },
+    {
+      "epoch": 2.38202309725894,
+      "grad_norm": 1.0370205640792847,
+      "learning_rate": 5e-05,
+      "loss": 1.6153,
+      "step": 5350
+    },
+    {
+      "epoch": 2.4042855155141227,
+      "grad_norm": 0.8503725528717041,
+      "learning_rate": 5e-05,
+      "loss": 1.6022,
+      "step": 5400
+    },
+    {
+      "epoch": 2.4265479337693057,
+      "grad_norm": 0.9510111212730408,
+      "learning_rate": 5e-05,
+      "loss": 1.6106,
+      "step": 5450
+    },
+    {
+      "epoch": 2.4488103520244886,
+      "grad_norm": 0.9935341477394104,
+      "learning_rate": 5e-05,
+      "loss": 1.6049,
+      "step": 5500
+    },
+    {
+      "epoch": 2.4488103520244886,
+      "eval_loss": 1.586571455001831,
+      "eval_runtime": 40.7387,
+      "eval_samples_per_second": 392.036,
+      "eval_steps_per_second": 49.02,
+      "step": 5500
     }
   ],
   "logging_steps": 50,
@@ -802,7 +880,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -816,7 +894,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.984755905276928e+16,
+  "total_flos": 2.4081224007407616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null