Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860eca3961053936b241a5a2d4fa22d5d55c591199aaa9b78de4fdc667354710
+oid sha256:fdb6e98797334d8dad686390c3a871babad8123963611e212956f6662bc5a8e1
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0908b4e68e646f4581a0026b2c4fa54184efb4bcbd7553998a1c4a4c12cd731e
+oid sha256:e49f34f35179e3613b976ab84b875c3b7727044e3d2f20224c5caf29eec11c3a
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f81c651a86e496a8a0683bb40cfa7b5abd415344f225e4b6cf5b7f3bf0d148
+oid sha256:f0e87d0594583c91449bed8c9b57cd31ad9ac1a2ab308d4940cbd5e7a3fa296b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d094517def3bab9b1b376a801fd8dd8681180f5ccdb5bd9fd6776c1cd25c2968
+oid sha256:4d966dee3ea83ae9edc170643edbeead55aecfa7f6d46f849824e98b9ee7cee7
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd17e6a2456b591e82434cf85c6c3687643ac9b76a0a0c080b341aa852e38872
+oid sha256:18a6e60ee80e57778e5fd78a1d8c91d6a0cd4ce7b1800f1645350ad02d55ca76
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 10000,
-  "best_metric": 1.5091972351074219,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-10000",
-  "epoch": 4.6754417698622515,
+  "best_global_step": 11000,
+  "best_metric": 1.5041238069534302,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-11000",
+  "epoch": 4.898065952414081,
   "eval_steps": 500,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1646,6 +1646,84 @@
       "eval_samples_per_second": 394.461,
       "eval_steps_per_second": 49.323,
       "step": 10500
+    },
+    {
+      "epoch": 4.697704188117434,
+      "grad_norm": 1.236370325088501,
+      "learning_rate": 5e-05,
+      "loss": 1.5426,
+      "step": 10550
+    },
+    {
+      "epoch": 4.719966606372617,
+      "grad_norm": 1.1259009838104248,
+      "learning_rate": 5e-05,
+      "loss": 1.5701,
+      "step": 10600
+    },
+    {
+      "epoch": 4.7422290246278,
+      "grad_norm": 1.0653769969940186,
+      "learning_rate": 5e-05,
+      "loss": 1.5543,
+      "step": 10650
+    },
+    {
+      "epoch": 4.764491442882983,
+      "grad_norm": 1.1116371154785156,
+      "learning_rate": 5e-05,
+      "loss": 1.557,
+      "step": 10700
+    },
+    {
+      "epoch": 4.786753861138166,
+      "grad_norm": 1.0332480669021606,
+      "learning_rate": 5e-05,
+      "loss": 1.5513,
+      "step": 10750
+    },
+    {
+      "epoch": 4.809016279393349,
+      "grad_norm": 1.1142674684524536,
+      "learning_rate": 5e-05,
+      "loss": 1.5448,
+      "step": 10800
+    },
+    {
+      "epoch": 4.831278697648532,
+      "grad_norm": 1.0316691398620605,
+      "learning_rate": 5e-05,
+      "loss": 1.5456,
+      "step": 10850
+    },
+    {
+      "epoch": 4.853541115903715,
+      "grad_norm": 0.987628161907196,
+      "learning_rate": 5e-05,
+      "loss": 1.5535,
+      "step": 10900
+    },
+    {
+      "epoch": 4.875803534158898,
+      "grad_norm": 1.125772476196289,
+      "learning_rate": 5e-05,
+      "loss": 1.5583,
+      "step": 10950
+    },
+    {
+      "epoch": 4.898065952414081,
+      "grad_norm": 0.9541718363761902,
+      "learning_rate": 5e-05,
+      "loss": 1.5584,
+      "step": 11000
+    },
+    {
+      "epoch": 4.898065952414081,
+      "eval_loss": 1.5041238069534302,
+      "eval_runtime": 40.2547,
+      "eval_samples_per_second": 396.749,
+      "eval_steps_per_second": 49.609,
+      "step": 11000
     }
   ],
   "logging_steps": 50,
@@ -1660,7 +1738,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -1674,7 +1752,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.37287432012032e+16,
+  "total_flos": 4.530938070076723e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null