Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761ed6751920843cffb7ea195e9fda4cc5b52e9c232bfc7dee3bb45f6619637e
+oid sha256:3d91a252e47567440fa05097e8a1b9f9cfd655ebb6eff2d149a70eed8179f3ab
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1202b871306e5a47b46fb1bcf989facc74951cc8514d655f034a9ea5ed1ee58
+oid sha256:afd6a63953e3ca088918b5a47553148cf1516f98523ee4612b03e5e48b50b798
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288381390ef2c4e9c9473d5ee077feaf5f5cefbdb2b7cf1c96b6907ae793487e
+oid sha256:1bb39ecd9b5069f71ac0c29d2d36a62574cf1415dfe0c4abd4599c7c59329be5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37caeb1bb49fdf577e04e454fc0c1ffb92bd891d0dbc0b5a4547415a9f259799
+oid sha256:f7d5089b28a615f02511d264296c6980fb39c1a64aaf6b3be2813182a38db48d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ac02c40c90996d4ad6bb7daa053a54b85676d36aaa3b4b892740a97de5c357
+oid sha256:9ac573a74d7ecfa65e1fa3220665a94cb8f7df1cc97a38d73ad33d04e26d5f57
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3000,
-  "best_metric": 1.6028199195861816,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-3000",
-  "epoch": 1.7809656323918186,
+  "best_global_step": 4500,
+  "best_metric": 1.5784235000610352,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-4500",
+  "epoch": 2.0035619869208294,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -632,6 +632,84 @@
       "eval_samples_per_second": 387.611,
       "eval_steps_per_second": 48.466,
       "step": 4000
+    },
+    {
+      "epoch": 1.8032280506470015,
+      "grad_norm": 1.137293815612793,
+      "learning_rate": 5e-05,
+      "loss": 1.6288,
+      "step": 4050
+    },
+    {
+      "epoch": 1.8254904689021845,
+      "grad_norm": 1.1091963052749634,
+      "learning_rate": 5e-05,
+      "loss": 1.6421,
+      "step": 4100
+    },
+    {
+      "epoch": 1.8477528871573674,
+      "grad_norm": 1.0500215291976929,
+      "learning_rate": 5e-05,
+      "loss": 1.6594,
+      "step": 4150
+    },
+    {
+      "epoch": 1.8700153054125503,
+      "grad_norm": 1.2211509943008423,
+      "learning_rate": 5e-05,
+      "loss": 1.658,
+      "step": 4200
+    },
+    {
+      "epoch": 1.8922777236677333,
+      "grad_norm": 1.1174074411392212,
+      "learning_rate": 5e-05,
+      "loss": 1.6815,
+      "step": 4250
+    },
+    {
+      "epoch": 1.9145401419229162,
+      "grad_norm": 1.1086102724075317,
+      "learning_rate": 5e-05,
+      "loss": 1.7094,
+      "step": 4300
+    },
+    {
+      "epoch": 1.9368025601780994,
+      "grad_norm": 1.3630105257034302,
+      "learning_rate": 5e-05,
+      "loss": 1.7099,
+      "step": 4350
+    },
+    {
+      "epoch": 1.9590649784332823,
+      "grad_norm": 1.2096022367477417,
+      "learning_rate": 5e-05,
+      "loss": 1.7082,
+      "step": 4400
+    },
+    {
+      "epoch": 1.9813273966884652,
+      "grad_norm": 1.1671497821807861,
+      "learning_rate": 5e-05,
+      "loss": 1.7031,
+      "step": 4450
+    },
+    {
+      "epoch": 2.0035619869208294,
+      "grad_norm": 1.090248465538025,
+      "learning_rate": 5e-05,
+      "loss": 1.7077,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0035619869208294,
+      "eval_loss": 1.5784235000610352,
+      "eval_runtime": 41.0244,
+      "eval_samples_per_second": 389.305,
+      "eval_steps_per_second": 48.678,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -646,7 +724,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -660,7 +738,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8688429934168064e+16,
+  "total_flos": 1.9362186109077504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null