Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc088dc7806d076db4af87fcb16f32f2f4264c49cbcac76f4cd8fba66849b21
+oid sha256:21620fd84655c4db896f34197f325633f31514594547ffd7f9568f54bdaa66d4
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003ec6e37af7d32937d3f1e82568738b7f475a4953701c29695e87d37bc4fb0a
+oid sha256:6f3eed10629fabf788491c524b6122d0728f36d0d0d91bd828d85edbb66a60e4
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457f1b145880ffefa4ea85b3e7a404600f4cba68a993abb9fd8332c3b47d64e5
+oid sha256:080ccb46d322e83cec7b5164cc9a9cfad2dd21bf055cdfb1cf5e9ed68adf2f38
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae69b2b9c59be93f7a4a7ddc203457ae939a2e00629604613f9975492d82daa9
+oid sha256:49b6ff79bc8fa80bd69ca075842b5f5ae497b21ebbcd9737cb146fba40b9d7d8
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ac391f4dafa2480a707714482d63d0a94b4181ff6c8b0c91815f49c7797b53
+oid sha256:b21570681f00b76e8eef45e6f4bee892eb4f5cd6f6499a8d0d1225429aab8516
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 7500,
   "best_metric": 1.5381077527999878,
   "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-7500",
-  "epoch": 3.339724502574092,
+  "epoch": 3.561903436760818,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1178,6 +1178,84 @@
       "eval_samples_per_second": 363.652,
       "eval_steps_per_second": 45.471,
       "step": 7500
+    },
+    {
+      "epoch": 3.3615416724641713,
+      "grad_norm": 1.4630149602890015,
+      "learning_rate": 5e-05,
+      "loss": 1.6543,
+      "step": 7550
+    },
+    {
+      "epoch": 3.3838040907193543,
+      "grad_norm": 0.9978652596473694,
+      "learning_rate": 5e-05,
+      "loss": 1.6469,
+      "step": 7600
+    },
+    {
+      "epoch": 3.406066508974537,
+      "grad_norm": 0.9942854046821594,
+      "learning_rate": 5e-05,
+      "loss": 1.6524,
+      "step": 7650
+    },
+    {
+      "epoch": 3.42832892722972,
+      "grad_norm": 1.6113872528076172,
+      "learning_rate": 5e-05,
+      "loss": 1.6392,
+      "step": 7700
+    },
+    {
+      "epoch": 3.450591345484903,
+      "grad_norm": 1.2430763244628906,
+      "learning_rate": 5e-05,
+      "loss": 1.6524,
+      "step": 7750
+    },
+    {
+      "epoch": 3.472853763740086,
+      "grad_norm": 0.9973090887069702,
+      "learning_rate": 5e-05,
+      "loss": 1.6396,
+      "step": 7800
+    },
+    {
+      "epoch": 3.4951161819952694,
+      "grad_norm": 1.3717776536941528,
+      "learning_rate": 5e-05,
+      "loss": 1.6463,
+      "step": 7850
+    },
+    {
+      "epoch": 3.5173786002504523,
+      "grad_norm": 1.3711599111557007,
+      "learning_rate": 5e-05,
+      "loss": 1.644,
+      "step": 7900
+    },
+    {
+      "epoch": 3.5396410185056353,
+      "grad_norm": 1.0126900672912598,
+      "learning_rate": 5e-05,
+      "loss": 1.6311,
+      "step": 7950
+    },
+    {
+      "epoch": 3.561903436760818,
+      "grad_norm": 1.0467159748077393,
+      "learning_rate": 5e-05,
+      "loss": 1.64,
+      "step": 8000
+    },
+    {
+      "epoch": 3.561903436760818,
+      "eval_loss": 1.539516806602478,
+      "eval_runtime": 42.3362,
+      "eval_samples_per_second": 377.242,
+      "eval_steps_per_second": 47.17,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1192,7 +1270,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1206,7 +1284,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.936391820718899e+16,
+  "total_flos": 2.984631313202381e+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 sha256:98bf107852bd8fb9f94e9f610ccce3445faf6710de67a8a094330338e1efd116
+oid sha256:53d05e7b884c3329c7231564fbcc24e8e12ef445dff72282ffbf7a4bf4c375f3
 size 5624