Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbad73333d3880772336a625e35504a2ee30e02405a6dc0acdda9e638172d21
+oid sha256:9117ec4f950dea6754224554f5e2c755a6836a7961b4ded5f21c63c21c445fb9
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1405f2590bc8a2add99042e9e49fb8954369bbfb3b18ea111e4bab55d4aef4
+oid sha256:f5cc484e5182c4715a2a6109e3cc2b4d706785d329d27d5874fca6c049423045
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb634ec7f171d96ec4db3077b1dfe85e8869023201bf15be33fad6a0ce2ffda
+oid sha256:77350fb64cb2dda91c46d447fdf9444b805615f96cc40b39ffa14f4a21adc432
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96abe9f8a68e6d0c748eb46e8d20fb4fad6bc47b204e7f7e5c0da3fbe14595be
+oid sha256:f3b82fa79f11f9a89c3adc8c26018f9952557f53a7145deb6860a551470206d5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdd7639db17312a4ecd7d288107da009f92352ae931ff71ff9086e467c2a7e1
+oid sha256:e301c4e597049f65c33ebf04fcf53823c852f1e3ca861cecc7edcee425492837
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 8500,
-  "best_metric": 1.516330361366272,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-8500",
-  "epoch": 4.0075692222067625,
+  "best_global_step": 9500,
+  "best_metric": 1.5118227005004883,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-9500",
+  "epoch": 4.230193404758592,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1412,6 +1412,84 @@
       "eval_samples_per_second": 395.778,
       "eval_steps_per_second": 49.488,
       "step": 9000
+    },
+    {
+      "epoch": 4.029831640461945,
+      "grad_norm": 1.2552838325500488,
+      "learning_rate": 5e-05,
+      "loss": 1.6371,
+      "step": 9050
+    },
+    {
+      "epoch": 4.052094058717128,
+      "grad_norm": 1.3415331840515137,
+      "learning_rate": 5e-05,
+      "loss": 1.6345,
+      "step": 9100
+    },
+    {
+      "epoch": 4.074356476972311,
+      "grad_norm": 1.029757022857666,
+      "learning_rate": 5e-05,
+      "loss": 1.629,
+      "step": 9150
+    },
+    {
+      "epoch": 4.096618895227494,
+      "grad_norm": 1.1435120105743408,
+      "learning_rate": 5e-05,
+      "loss": 1.6287,
+      "step": 9200
+    },
+    {
+      "epoch": 4.118881313482677,
+      "grad_norm": 1.385100245475769,
+      "learning_rate": 5e-05,
+      "loss": 1.6335,
+      "step": 9250
+    },
+    {
+      "epoch": 4.14114373173786,
+      "grad_norm": 1.062818169593811,
+      "learning_rate": 5e-05,
+      "loss": 1.6184,
+      "step": 9300
+    },
+    {
+      "epoch": 4.163406149993043,
+      "grad_norm": 1.3703244924545288,
+      "learning_rate": 5e-05,
+      "loss": 1.631,
+      "step": 9350
+    },
+    {
+      "epoch": 4.185668568248226,
+      "grad_norm": 1.1130529642105103,
+      "learning_rate": 5e-05,
+      "loss": 1.6284,
+      "step": 9400
+    },
+    {
+      "epoch": 4.207930986503409,
+      "grad_norm": 1.189207911491394,
+      "learning_rate": 5e-05,
+      "loss": 1.619,
+      "step": 9450
+    },
+    {
+      "epoch": 4.230193404758592,
+      "grad_norm": 1.0979055166244507,
+      "learning_rate": 5e-05,
+      "loss": 1.6324,
+      "step": 9500
+    },
+    {
+      "epoch": 4.230193404758592,
+      "eval_loss": 1.5118227005004883,
+      "eval_runtime": 40.2303,
+      "eval_samples_per_second": 396.989,
+      "eval_steps_per_second": 49.639,
+      "step": 9500
     }
   ],
   "logging_steps": 50,
@@ -1426,7 +1504,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -1440,7 +1518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.444898329997824e+16,
+  "total_flos": 3.492920965883597e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null