Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21620fd84655c4db896f34197f325633f31514594547ffd7f9568f54bdaa66d4
+oid sha256:78eeada532b08bdf3524032fcb0dd8742b5cbe44f304c2f845a2ec8ac351c803
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3eed10629fabf788491c524b6122d0728f36d0d0d91bd828d85edbb66a60e4
+oid sha256:48ec7b29adac8f13e97e8d0b0016dbfde03e9643c7d13a43fc298e30253e5845
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080ccb46d322e83cec7b5164cc9a9cfad2dd21bf055cdfb1cf5e9ed68adf2f38
+oid sha256:54fde25c1257c410542439f7b30010e731a773e09e44bce8d654fd46bb13b1b3
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b6ff79bc8fa80bd69ca075842b5f5ae497b21ebbcd9737cb146fba40b9d7d8
+oid sha256:68029c1a6b8f58f4897cc068068a39570420fb36c1353d8dd13c010a143f2a88
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21570681f00b76e8eef45e6f4bee892eb4f5cd6f6499a8d0d1225429aab8516
+oid sha256:b5043baea5bed98a56ee64b89f4809a10402dd6a6764f855e2bb19bcd7ba63c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 7500,
-  "best_metric": 1.5381077527999878,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-7500",
-  "epoch": 3.561903436760818,
+  "best_global_step": 8500,
+  "best_metric": 1.516330361366272,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-8500",
+  "epoch": 3.784527619312648,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1256,6 +1256,84 @@
       "eval_samples_per_second": 377.242,
       "eval_steps_per_second": 47.17,
       "step": 8000
+    },
+    {
+      "epoch": 3.584165855016001,
+      "grad_norm": 1.1766951084136963,
+      "learning_rate": 5e-05,
+      "loss": 1.6552,
+      "step": 8050
+    },
+    {
+      "epoch": 3.606428273271184,
+      "grad_norm": 1.0943933725357056,
+      "learning_rate": 5e-05,
+      "loss": 1.6385,
+      "step": 8100
+    },
+    {
+      "epoch": 3.628690691526367,
+      "grad_norm": 1.2377898693084717,
+      "learning_rate": 5e-05,
+      "loss": 1.6288,
+      "step": 8150
+    },
+    {
+      "epoch": 3.65095310978155,
+      "grad_norm": 0.939339280128479,
+      "learning_rate": 5e-05,
+      "loss": 1.6357,
+      "step": 8200
+    },
+    {
+      "epoch": 3.673215528036733,
+      "grad_norm": 1.0802948474884033,
+      "learning_rate": 5e-05,
+      "loss": 1.6367,
+      "step": 8250
+    },
+    {
+      "epoch": 3.695477946291916,
+      "grad_norm": 1.089154601097107,
+      "learning_rate": 5e-05,
+      "loss": 1.6434,
+      "step": 8300
+    },
+    {
+      "epoch": 3.7177403645470988,
+      "grad_norm": 1.095510482788086,
+      "learning_rate": 5e-05,
+      "loss": 1.6445,
+      "step": 8350
+    },
+    {
+      "epoch": 3.740002782802282,
+      "grad_norm": 1.2433582544326782,
+      "learning_rate": 5e-05,
+      "loss": 1.6521,
+      "step": 8400
+    },
+    {
+      "epoch": 3.762265201057465,
+      "grad_norm": 1.3547347784042358,
+      "learning_rate": 5e-05,
+      "loss": 1.6363,
+      "step": 8450
+    },
+    {
+      "epoch": 3.784527619312648,
+      "grad_norm": 1.224070429801941,
+      "learning_rate": 5e-05,
+      "loss": 1.6455,
+      "step": 8500
+    },
+    {
+      "epoch": 3.784527619312648,
+      "eval_loss": 1.516330361366272,
+      "eval_runtime": 40.388,
+      "eval_samples_per_second": 395.439,
+      "eval_steps_per_second": 49.445,
+      "step": 8500
     }
   ],
   "logging_steps": 50,
@@ -1270,7 +1348,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -1284,7 +1362,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.984631313202381e+16,
+  "total_flos": 3.033090820902912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d05e7b884c3329c7231564fbcc24e8e12ef445dff72282ffbf7a4bf4c375f3
+oid sha256:241913eb458c3cd7f38f1105f1ffa37291ed4c7e03a3c94d3d6822f55195b546
 size 5624