Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ba7be4e1197b6ebae5a1fb0d6ae29bbafd16d90726437a2da8408d73641f03
+oid sha256:66f0bf969e7c4f10819387c514099288befb4d6a92b18fedb97919efb7838146
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bebcf4136f2e6e53dd975d0ec5899e311738161c26efd5f1866b8fbda4dd14d
+oid sha256:50326021a12350d0fd340fb39b69dcb99c4d9d7625607f1ea78848e8533735ef
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788c6b064d884311e214b6335a80e7fe5e75085f966367611657f1664cf160c2
+oid sha256:2aba6f3b60d25e9d80bfa48704513608d3c51338a99fc68164f2cda5539a2e88
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a2836138899bf244344610cf1cfa7f6c9e6417ce66d8196cf2ef6125f38e4e
+oid sha256:0b18b3eda07668461b2815107443aa6a6c68056a4e1c0be8b74117cc02ff9391
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81fbcc85fe8453ce60c9a14a7fd7bb3512bae9747d397407e0552c8567a7c1e
+oid sha256:2167d86470a0af7e2c7e124cb3b9e089d70c4424875cd5dabb7a3f9dabe21d16
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 4500,
-  "best_metric": 1.5784235000610352,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-4500",
-  "epoch": 2.6714345345763184,
+  "best_global_step": 6500,
+  "best_metric": 1.5628445148468018,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-6500",
+  "epoch": 2.894058717128148,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -944,6 +944,84 @@
       "eval_samples_per_second": 389.821,
       "eval_steps_per_second": 48.743,
       "step": 6000
+    },
+    {
+      "epoch": 2.6936969528315013,
+      "grad_norm": 1.070421814918518,
+      "learning_rate": 5e-05,
+      "loss": 1.6947,
+      "step": 6050
+    },
+    {
+      "epoch": 2.7159593710866843,
+      "grad_norm": 0.9952645301818848,
+      "learning_rate": 5e-05,
+      "loss": 1.6907,
+      "step": 6100
+    },
+    {
+      "epoch": 2.738221789341867,
+      "grad_norm": 1.2595455646514893,
+      "learning_rate": 5e-05,
+      "loss": 1.6954,
+      "step": 6150
+    },
+    {
+      "epoch": 2.76048420759705,
+      "grad_norm": 0.9722006916999817,
+      "learning_rate": 5e-05,
+      "loss": 1.6832,
+      "step": 6200
+    },
+    {
+      "epoch": 2.782746625852233,
+      "grad_norm": 1.2001519203186035,
+      "learning_rate": 5e-05,
+      "loss": 1.6832,
+      "step": 6250
+    },
+    {
+      "epoch": 2.805009044107416,
+      "grad_norm": 1.316867709159851,
+      "learning_rate": 5e-05,
+      "loss": 1.6873,
+      "step": 6300
+    },
+    {
+      "epoch": 2.8272714623625994,
+      "grad_norm": 1.2271651029586792,
+      "learning_rate": 5e-05,
+      "loss": 1.6865,
+      "step": 6350
+    },
+    {
+      "epoch": 2.8495338806177823,
+      "grad_norm": 1.2443265914916992,
+      "learning_rate": 5e-05,
+      "loss": 1.6779,
+      "step": 6400
+    },
+    {
+      "epoch": 2.8717962988729653,
+      "grad_norm": 1.1751494407653809,
+      "learning_rate": 5e-05,
+      "loss": 1.666,
+      "step": 6450
+    },
+    {
+      "epoch": 2.894058717128148,
+      "grad_norm": 0.9704211950302124,
+      "learning_rate": 5e-05,
+      "loss": 1.6628,
+      "step": 6500
+    },
+    {
+      "epoch": 2.894058717128148,
+      "eval_loss": 1.5628445148468018,
+      "eval_runtime": 41.0455,
+      "eval_samples_per_second": 389.105,
+      "eval_steps_per_second": 48.653,
+      "step": 6500
     }
   ],
   "logging_steps": 50,
@@ -958,7 +1036,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -967,12 +1045,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.7676743726557184e+16,
+  "total_flos": 2.8160444868950016e+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 sha256:02aa50af5025c9f0ca029c8bf84c80140d605447e8fbdf2b3d4a1f55708551a3
+oid sha256:98bf107852bd8fb9f94e9f610ccce3445faf6710de67a8a094330338e1efd116
 size 5624