Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6b21136738d464237c49291ff492715ac0f778d29877772de0b737cf2d2640
+oid sha256:1f97a88fe7f1551daa9480177b00b35e40e856a0d9c9d91d43e2560efb86dee1
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e9083055cf358cde08cffa8e089e39a4e8e3d9798eb13a83732e0956151494
+oid sha256:10b8042297e02ae9d3215844c9e256c5210db3f5a2e0699113654e0cb79f59db
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bf623617defaefad1aba1b3887b66f9a371c45bd4aa888efe87b4d5bd11431
+oid sha256:a2bf650a618e96844362d12ee82d70a5f8affd2f2e50a31dc12be324f0ee9e79
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6789c572dce92a1a63d5943c701f294de1d60d1ba0534cc546d8d898ea5a0067
+oid sha256:9ade71fa77b3bec5df0f87e5afbe1254f30e68aa4fe3c4885f1c8c1ab0dff354
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0b34b2ac94b6ae1b1e612c27fa9cd4fd3034532b792dc74af68839fa9ffe62
+oid sha256:f27936a64077570bbaa5a635febe904df73463b4153ec77db6495bfeb53a907d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2500,
-  "best_metric": 1.6233899593353271,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-2500",
-  "epoch": 1.1130930847363294,
+  "best_global_step": 3000,
+  "best_metric": 1.6028199195861816,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-3000",
+  "epoch": 1.3357172672881592,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -398,6 +398,84 @@
       "eval_samples_per_second": 388.882,
       "eval_steps_per_second": 48.626,
       "step": 2500
+    },
+    {
+      "epoch": 1.1353555029915126,
+      "grad_norm": 1.172264575958252,
+      "learning_rate": 5e-05,
+      "loss": 1.7348,
+      "step": 2550
+    },
+    {
+      "epoch": 1.1576179212466955,
+      "grad_norm": 1.076794981956482,
+      "learning_rate": 5e-05,
+      "loss": 1.7463,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1798803395018784,
+      "grad_norm": 1.0754376649856567,
+      "learning_rate": 5e-05,
+      "loss": 1.7378,
+      "step": 2650
+    },
+    {
+      "epoch": 1.2021427577570614,
+      "grad_norm": 1.3081718683242798,
+      "learning_rate": 5e-05,
+      "loss": 1.7251,
+      "step": 2700
+    },
+    {
+      "epoch": 1.2244051760122443,
+      "grad_norm": 1.0483145713806152,
+      "learning_rate": 5e-05,
+      "loss": 1.7414,
+      "step": 2750
+    },
+    {
+      "epoch": 1.2466675942674272,
+      "grad_norm": 1.2890243530273438,
+      "learning_rate": 5e-05,
+      "loss": 1.7254,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2689300125226102,
+      "grad_norm": 1.0999932289123535,
+      "learning_rate": 5e-05,
+      "loss": 1.7333,
+      "step": 2850
+    },
+    {
+      "epoch": 1.291192430777793,
+      "grad_norm": 1.0996226072311401,
+      "learning_rate": 5e-05,
+      "loss": 1.7151,
+      "step": 2900
+    },
+    {
+      "epoch": 1.3134548490329763,
+      "grad_norm": 1.3446428775787354,
+      "learning_rate": 5e-05,
+      "loss": 1.7088,
+      "step": 2950
+    },
+    {
+      "epoch": 1.3357172672881592,
+      "grad_norm": 0.9657168388366699,
+      "learning_rate": 5e-05,
+      "loss": 1.7171,
+      "step": 3000
+    },
+    {
+      "epoch": 1.3357172672881592,
+      "eval_loss": 1.6028199195861816,
+      "eval_runtime": 41.2736,
+      "eval_samples_per_second": 386.954,
+      "eval_steps_per_second": 48.384,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -426,7 +504,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9917592675207168.0,
+  "total_flos": 1.0474381397673984e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null