Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528acce4eeefb061c097acfb9ca7e6fc5ab314a8429ca3948ff09d6a90997bd6
+oid sha256:d9823ac5309a0121bbf68af5c301f793de92bd5383b19486c5693e3292544ae2
 size 290403936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbbefa2ef22e00c34054734db2a07c9770f916d6c82bc64d90ed181ce942145
+oid sha256:c79e864eb767de59929633bcbe6ca5222d062c56994cdbfb20401cd8c361bea7
 size 574811514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e98fd272d33e7550f8dfe572825884fc7fe39dcfc4b6f6c9c5093c97453356c
+oid sha256:9dbbba60e72aa1d9209f2713e04111ddbf0bbbba59dd22bae5b72fb8174ffea8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9abfb3126a3b44bc9deb9899980d0ae442551061749da8089fea81fef25d9c
+oid sha256:efe70d33f3fbb9c10a2f188c0a23f007fecdb7a03f5a154054e5c79c6735f222
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 112.41617168039855,
-  "best_model_checkpoint": "./whisper-base-ha/checkpoint-1500",
-  "epoch": 9.554140127388536,
+  "best_metric": 104.92431500287411,
+  "best_model_checkpoint": "./whisper-base-ha/checkpoint-2000",
+  "epoch": 12.738853503184714,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,6 +457,156 @@
       "eval_wer": 112.41617168039855,
       "eval_wer_ortho": 113.9453125,
       "step": 1500
+    },
+    {
+      "epoch": 9.713375796178344,
+      "grad_norm": 4.020846366882324,
+      "learning_rate": 1e-05,
+      "loss": 0.0466,
+      "step": 1525
+    },
+    {
+      "epoch": 9.872611464968152,
+      "grad_norm": 5.376700401306152,
+      "learning_rate": 1e-05,
+      "loss": 0.0441,
+      "step": 1550
+    },
+    {
+      "epoch": 10.031847133757962,
+      "grad_norm": 1.6738530397415161,
+      "learning_rate": 1e-05,
+      "loss": 0.0453,
+      "step": 1575
+    },
+    {
+      "epoch": 10.19108280254777,
+      "grad_norm": 1.8049341440200806,
+      "learning_rate": 1e-05,
+      "loss": 0.0276,
+      "step": 1600
+    },
+    {
+      "epoch": 10.35031847133758,
+      "grad_norm": 2.4481654167175293,
+      "learning_rate": 1e-05,
+      "loss": 0.0272,
+      "step": 1625
+    },
+    {
+      "epoch": 10.509554140127388,
+      "grad_norm": 1.8371031284332275,
+      "learning_rate": 1e-05,
+      "loss": 0.0231,
+      "step": 1650
+    },
+    {
+      "epoch": 10.668789808917197,
+      "grad_norm": 4.078380107879639,
+      "learning_rate": 1e-05,
+      "loss": 0.025,
+      "step": 1675
+    },
+    {
+      "epoch": 10.828025477707007,
+      "grad_norm": 3.8198206424713135,
+      "learning_rate": 1e-05,
+      "loss": 0.0324,
+      "step": 1700
+    },
+    {
+      "epoch": 10.987261146496815,
+      "grad_norm": 1.7313209772109985,
+      "learning_rate": 1e-05,
+      "loss": 0.0276,
+      "step": 1725
+    },
+    {
+      "epoch": 11.146496815286625,
+      "grad_norm": 4.576403617858887,
+      "learning_rate": 1e-05,
+      "loss": 0.0187,
+      "step": 1750
+    },
+    {
+      "epoch": 11.305732484076433,
+      "grad_norm": 1.7391539812088013,
+      "learning_rate": 1e-05,
+      "loss": 0.0163,
+      "step": 1775
+    },
+    {
+      "epoch": 11.464968152866241,
+      "grad_norm": 1.6256043910980225,
+      "learning_rate": 1e-05,
+      "loss": 0.0181,
+      "step": 1800
+    },
+    {
+      "epoch": 11.624203821656051,
+      "grad_norm": 1.2041560411453247,
+      "learning_rate": 1e-05,
+      "loss": 0.0177,
+      "step": 1825
+    },
+    {
+      "epoch": 11.78343949044586,
+      "grad_norm": 1.2015411853790283,
+      "learning_rate": 1e-05,
+      "loss": 0.0185,
+      "step": 1850
+    },
+    {
+      "epoch": 11.94267515923567,
+      "grad_norm": 1.7597877979278564,
+      "learning_rate": 1e-05,
+      "loss": 0.0185,
+      "step": 1875
+    },
+    {
+      "epoch": 12.101910828025478,
+      "grad_norm": 1.2829164266586304,
+      "learning_rate": 1e-05,
+      "loss": 0.014,
+      "step": 1900
+    },
+    {
+      "epoch": 12.261146496815286,
+      "grad_norm": 1.5107444524765015,
+      "learning_rate": 1e-05,
+      "loss": 0.0115,
+      "step": 1925
+    },
+    {
+      "epoch": 12.420382165605096,
+      "grad_norm": 1.1438385248184204,
+      "learning_rate": 1e-05,
+      "loss": 0.0118,
+      "step": 1950
+    },
+    {
+      "epoch": 12.579617834394904,
+      "grad_norm": 2.5098214149475098,
+      "learning_rate": 1e-05,
+      "loss": 0.0113,
+      "step": 1975
+    },
+    {
+      "epoch": 12.738853503184714,
+      "grad_norm": 0.9226982593536377,
+      "learning_rate": 1e-05,
+      "loss": 0.0134,
+      "step": 2000
+    },
+    {
+      "epoch": 12.738853503184714,
+      "eval_loss": 2.5008862018585205,
+      "eval_runtime": 168.7552,
+      "eval_samples_per_second": 3.911,
+      "eval_steps_per_second": 0.249,
+      "eval_wer": 104.92431500287411,
+      "eval_wer_ortho": 106.28906250000001,
+      "step": 2000
     }
   ],
   "logging_steps": 25,
@@ -476,7 +626,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.55430494797824e+18,
+  "total_flos": 2.07240659730432e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null