Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f97a88fe7f1551daa9480177b00b35e40e856a0d9c9d91d43e2560efb86dee1
+oid sha256:59598fbdd1c5e2f583902dedafc3608ce33bbba310616bf6dc87ed894499216c
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b8042297e02ae9d3215844c9e256c5210db3f5a2e0699113654e0cb79f59db
+oid sha256:c36ca00300f8149041f48da61b5fca592e064fd49ac67d29a37c6bcaba238d3e
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2bf650a618e96844362d12ee82d70a5f8affd2f2e50a31dc12be324f0ee9e79
+oid sha256:b337ce57e0e628ac23a51821ba9829dc5591967e2ff7b7d7b32c74e1aad03b79
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ade71fa77b3bec5df0f87e5afbe1254f30e68aa4fe3c4885f1c8c1ab0dff354
+oid sha256:018616c73745e54f08c106f2414258a1870a189c7fffafe7f792b5acbfd19fdc
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27936a64077570bbaa5a635febe904df73463b4153ec77db6495bfeb53a907d
+oid sha256:a164f17f191d714fcd6bbbbbba58c57fe70c8ab069a5df01c4e86e5fc119f19d
 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": 1.3357172672881592,
+  "epoch": 1.5583414498399888,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -476,6 +476,84 @@
       "eval_samples_per_second": 386.954,
       "eval_steps_per_second": 48.384,
       "step": 3000
+    },
+    {
+      "epoch": 1.3579796855433421,
+      "grad_norm": 0.904662549495697,
+      "learning_rate": 5e-05,
+      "loss": 1.6656,
+      "step": 3050
+    },
+    {
+      "epoch": 1.380242103798525,
+      "grad_norm": 1.2054646015167236,
+      "learning_rate": 5e-05,
+      "loss": 1.6409,
+      "step": 3100
+    },
+    {
+      "epoch": 1.402504522053708,
+      "grad_norm": 0.8623887300491333,
+      "learning_rate": 5e-05,
+      "loss": 1.6378,
+      "step": 3150
+    },
+    {
+      "epoch": 1.4247669403088912,
+      "grad_norm": 0.931481659412384,
+      "learning_rate": 5e-05,
+      "loss": 1.6395,
+      "step": 3200
+    },
+    {
+      "epoch": 1.447029358564074,
+      "grad_norm": 0.8971887826919556,
+      "learning_rate": 5e-05,
+      "loss": 1.6338,
+      "step": 3250
+    },
+    {
+      "epoch": 1.469291776819257,
+      "grad_norm": 0.9754030704498291,
+      "learning_rate": 5e-05,
+      "loss": 1.6341,
+      "step": 3300
+    },
+    {
+      "epoch": 1.49155419507444,
+      "grad_norm": 0.9373458027839661,
+      "learning_rate": 5e-05,
+      "loss": 1.6214,
+      "step": 3350
+    },
+    {
+      "epoch": 1.513816613329623,
+      "grad_norm": 1.1765072345733643,
+      "learning_rate": 5e-05,
+      "loss": 1.622,
+      "step": 3400
+    },
+    {
+      "epoch": 1.5360790315848059,
+      "grad_norm": 0.9341714382171631,
+      "learning_rate": 5e-05,
+      "loss": 1.6242,
+      "step": 3450
+    },
+    {
+      "epoch": 1.5583414498399888,
+      "grad_norm": 0.8690816164016724,
+      "learning_rate": 5e-05,
+      "loss": 1.6238,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5583414498399888,
+      "eval_loss": 1.6130000352859497,
+      "eval_runtime": 40.5463,
+      "eval_samples_per_second": 393.896,
+      "eval_steps_per_second": 49.252,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -490,7 +568,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -504,7 +582,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0474381397673984e+16,
+  "total_flos": 1.6653272703277056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null