Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9117ec4f950dea6754224554f5e2c755a6836a7961b4ded5f21c63c21c445fb9
+oid sha256:234a74342f029ed78afc7504951e30209937ebfc40da414b5c0ddba808050cde
 size 30214176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cc484e5182c4715a2a6109e3cc2b4d706785d329d27d5874fca6c049423045
+oid sha256:edf3bd7c510bb22c9bef6a5be4eb2c5e53373f8b91d20a894a89d9aca7dcee5f
 size 291962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77350fb64cb2dda91c46d447fdf9444b805615f96cc40b39ffa14f4a21adc432
+oid sha256:12bdf3459ffab5d32ec375231a2eebdf56e9dbd56f588155f39eb4841c87ad7b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b82fa79f11f9a89c3adc8c26018f9952557f53a7145deb6860a551470206d5
+oid sha256:536bf64114e88301429208f737493c4ae0d118f5c27c3327e4079f245e1d631e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e301c4e597049f65c33ebf04fcf53823c852f1e3ca861cecc7edcee425492837
+oid sha256:c477b290e5f0acc03a821a7eef064a5961781fd60d9d238c571a7e7c070565f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9500,
-  "best_metric": 1.5118227005004883,
-  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-9500",
-  "epoch": 4.230193404758592,
+  "best_global_step": 10000,
+  "best_metric": 1.5091972351074219,
+  "best_model_checkpoint": "./results/hierarchical_music_t5_small_finetune/checkpoint-10000",
+  "epoch": 4.452817587310421,
   "eval_steps": 500,
-  "global_step": 9500,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1490,6 +1490,84 @@
       "eval_samples_per_second": 396.989,
       "eval_steps_per_second": 49.639,
       "step": 9500
+    },
+    {
+      "epoch": 4.252455823013775,
+      "grad_norm": 1.1394270658493042,
+      "learning_rate": 5e-05,
+      "loss": 1.6229,
+      "step": 9550
+    },
+    {
+      "epoch": 4.274718241268958,
+      "grad_norm": 1.0398465394973755,
+      "learning_rate": 5e-05,
+      "loss": 1.625,
+      "step": 9600
+    },
+    {
+      "epoch": 4.296980659524141,
+      "grad_norm": 1.1344504356384277,
+      "learning_rate": 5e-05,
+      "loss": 1.6113,
+      "step": 9650
+    },
+    {
+      "epoch": 4.319243077779324,
+      "grad_norm": 0.9889805316925049,
+      "learning_rate": 5e-05,
+      "loss": 1.6195,
+      "step": 9700
+    },
+    {
+      "epoch": 4.3415054960345065,
+      "grad_norm": 1.2321630716323853,
+      "learning_rate": 5e-05,
+      "loss": 1.6133,
+      "step": 9750
+    },
+    {
+      "epoch": 4.3637679142896895,
+      "grad_norm": 1.0766791105270386,
+      "learning_rate": 5e-05,
+      "loss": 1.587,
+      "step": 9800
+    },
+    {
+      "epoch": 4.386030332544872,
+      "grad_norm": 0.9230866432189941,
+      "learning_rate": 5e-05,
+      "loss": 1.5747,
+      "step": 9850
+    },
+    {
+      "epoch": 4.408292750800055,
+      "grad_norm": 1.036097526550293,
+      "learning_rate": 5e-05,
+      "loss": 1.5673,
+      "step": 9900
+    },
+    {
+      "epoch": 4.430555169055238,
+      "grad_norm": 1.0321383476257324,
+      "learning_rate": 5e-05,
+      "loss": 1.5641,
+      "step": 9950
+    },
+    {
+      "epoch": 4.452817587310421,
+      "grad_norm": 0.9865553379058838,
+      "learning_rate": 5e-05,
+      "loss": 1.5481,
+      "step": 10000
+    },
+    {
+      "epoch": 4.452817587310421,
+      "eval_loss": 1.5091972351074219,
+      "eval_runtime": 40.5505,
+      "eval_samples_per_second": 393.855,
+      "eval_steps_per_second": 49.247,
+      "step": 10000
     }
   ],
   "logging_steps": 50,
@@ -1518,7 +1596,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.492920965883597e+16,
+  "total_flos": 3.945897129811661e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null