Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b56fbdf7fe55206aba37bd5ae400349b2464f89eeb757ae10fcf1d6efcc7644f
+oid sha256:e0ba7be4e1197b6ebae5a1fb0d6ae29bbafd16d90726437a2da8408d73641f03
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613a8d1a657ba89ada23ab7d7633f3cf31fb4364c0614b7c8174ec86a031e3af
+oid sha256:2bebcf4136f2e6e53dd975d0ec5899e311738161c26efd5f1866b8fbda4dd14d
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78393450795811d9dfafdce73145f39f52c703d761292801d15750c186cc2118
+oid sha256:788c6b064d884311e214b6335a80e7fe5e75085f966367611657f1664cf160c2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27cf200ae168599617b8ef6dbb08dc689bd11010b7655ba355b260440e03cb3c
+oid sha256:09a2836138899bf244344610cf1cfa7f6c9e6417ce66d8196cf2ef6125f38e4e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa325f8460c9be76052157bd9b7d0c22035d7e2dbd36acf508d25edf25974d7b
+oid sha256:e81fbcc85fe8453ce60c9a14a7fd7bb3512bae9747d397407e0552c8567a7c1e
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4500,
   "best_metric": 1.5784235000610352,
   "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-4500",
-  "epoch": 2.4488103520244886,
+  "epoch": 2.6714345345763184,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -866,6 +866,84 @@
       "eval_samples_per_second": 392.036,
       "eval_steps_per_second": 49.02,
       "step": 5500
+    },
+    {
+      "epoch": 2.4710727702796715,
+      "grad_norm": 1.2289257049560547,
+      "learning_rate": 5e-05,
+      "loss": 1.5918,
+      "step": 5550
+    },
+    {
+      "epoch": 2.4933351885348545,
+      "grad_norm": 1.0900951623916626,
+      "learning_rate": 5e-05,
+      "loss": 1.6005,
+      "step": 5600
+    },
+    {
+      "epoch": 2.5155976067900374,
+      "grad_norm": 0.9930930137634277,
+      "learning_rate": 5e-05,
+      "loss": 1.6151,
+      "step": 5650
+    },
+    {
+      "epoch": 2.5378600250452203,
+      "grad_norm": 0.9901494979858398,
+      "learning_rate": 5e-05,
+      "loss": 1.59,
+      "step": 5700
+    },
+    {
+      "epoch": 2.5601224433004033,
+      "grad_norm": 0.9367809891700745,
+      "learning_rate": 5e-05,
+      "loss": 1.5844,
+      "step": 5750
+    },
+    {
+      "epoch": 2.582384861555586,
+      "grad_norm": 1.0291093587875366,
+      "learning_rate": 5e-05,
+      "loss": 1.5841,
+      "step": 5800
+    },
+    {
+      "epoch": 2.6046472798107696,
+      "grad_norm": 0.8904668688774109,
+      "learning_rate": 5e-05,
+      "loss": 1.5883,
+      "step": 5850
+    },
+    {
+      "epoch": 2.6269096980659525,
+      "grad_norm": 0.9640474915504456,
+      "learning_rate": 5e-05,
+      "loss": 1.5855,
+      "step": 5900
+    },
+    {
+      "epoch": 2.6491721163211355,
+      "grad_norm": 0.979326605796814,
+      "learning_rate": 5e-05,
+      "loss": 1.5798,
+      "step": 5950
+    },
+    {
+      "epoch": 2.6714345345763184,
+      "grad_norm": 1.2588844299316406,
+      "learning_rate": 5e-05,
+      "loss": 1.6018,
+      "step": 6000
+    },
+    {
+      "epoch": 2.6714345345763184,
+      "eval_loss": 1.5868676900863647,
+      "eval_runtime": 40.9701,
+      "eval_samples_per_second": 389.821,
+      "eval_steps_per_second": 48.743,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -880,7 +958,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -889,12 +967,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.4081224007407616e+16,
+  "total_flos": 2.7676743726557184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null