Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59598fbdd1c5e2f583902dedafc3608ce33bbba310616bf6dc87ed894499216c
+oid sha256:761ed6751920843cffb7ea195e9fda4cc5b52e9c232bfc7dee3bb45f6619637e
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36ca00300f8149041f48da61b5fca592e064fd49ac67d29a37c6bcaba238d3e
+oid sha256:f1202b871306e5a47b46fb1bcf989facc74951cc8514d655f034a9ea5ed1ee58
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b337ce57e0e628ac23a51821ba9829dc5591967e2ff7b7d7b32c74e1aad03b79
+oid sha256:288381390ef2c4e9c9473d5ee077feaf5f5cefbdb2b7cf1c96b6907ae793487e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018616c73745e54f08c106f2414258a1870a189c7fffafe7f792b5acbfd19fdc
+oid sha256:37caeb1bb49fdf577e04e454fc0c1ffb92bd891d0dbc0b5a4547415a9f259799
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a164f17f191d714fcd6bbbbbba58c57fe70c8ab069a5df01c4e86e5fc119f19d
+oid sha256:50ac02c40c90996d4ad6bb7daa053a54b85676d36aaa3b4b892740a97de5c357
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 3000,
   "best_metric": 1.6028199195861816,
   "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-3000",
-  "epoch": 1.5583414498399888,
+  "epoch": 1.7809656323918186,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -554,6 +554,84 @@
       "eval_samples_per_second": 393.896,
       "eval_steps_per_second": 49.252,
       "step": 3500
+    },
+    {
+      "epoch": 1.5806038680951717,
+      "grad_norm": 1.0579187870025635,
+      "learning_rate": 5e-05,
+      "loss": 1.611,
+      "step": 3550
+    },
+    {
+      "epoch": 1.6028662863503547,
+      "grad_norm": 0.8839408159255981,
+      "learning_rate": 5e-05,
+      "loss": 1.6106,
+      "step": 3600
+    },
+    {
+      "epoch": 1.6251287046055378,
+      "grad_norm": 1.048997402191162,
+      "learning_rate": 5e-05,
+      "loss": 1.6075,
+      "step": 3650
+    },
+    {
+      "epoch": 1.6473911228607208,
+      "grad_norm": 1.201557993888855,
+      "learning_rate": 5e-05,
+      "loss": 1.621,
+      "step": 3700
+    },
+    {
+      "epoch": 1.6696535411159037,
+      "grad_norm": 0.9804443717002869,
+      "learning_rate": 5e-05,
+      "loss": 1.6079,
+      "step": 3750
+    },
+    {
+      "epoch": 1.6919159593710866,
+      "grad_norm": 0.9969685077667236,
+      "learning_rate": 5e-05,
+      "loss": 1.6281,
+      "step": 3800
+    },
+    {
+      "epoch": 1.7141783776262698,
+      "grad_norm": 1.0730953216552734,
+      "learning_rate": 5e-05,
+      "loss": 1.6235,
+      "step": 3850
+    },
+    {
+      "epoch": 1.7364407958814527,
+      "grad_norm": 1.1014162302017212,
+      "learning_rate": 5e-05,
+      "loss": 1.6349,
+      "step": 3900
+    },
+    {
+      "epoch": 1.7587032141366357,
+      "grad_norm": 0.9518324732780457,
+      "learning_rate": 5e-05,
+      "loss": 1.6271,
+      "step": 3950
+    },
+    {
+      "epoch": 1.7809656323918186,
+      "grad_norm": 1.0745582580566406,
+      "learning_rate": 5e-05,
+      "loss": 1.6217,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7809656323918186,
+      "eval_loss": 1.6218018531799316,
+      "eval_runtime": 41.2037,
+      "eval_samples_per_second": 387.611,
+      "eval_steps_per_second": 48.466,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -568,7 +646,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -582,7 +660,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6653272703277056e+16,
+  "total_flos": 1.8688429934168064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null