Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f803a8c889d9d644a5c49e418541de3893b6947bdcbba8780ecdd443706692
+oid sha256:655a446aa8aa48a3dc6498704f3cdcd681097e9c9bf89b04354071e2c2dce412
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa8834fdd2339da3f9fbd2d0ed940c360c86dab9321e480b520c5d8523cf8be
+oid sha256:81e1f3d4f7962996a2775b9e4e3ab1ca76cf8c7a897b95060ae0c426e75c6935
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f96556c91f78b167a3a23f1c3f779be5f90901a0a97f9cd4811d2ba7a3f74c
+oid sha256:4b23f626a7efa36d01f5e36f3f34d543aac465661afc2ed75e47913bc2ba74c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db27db35e7525c2fb66e2b1507a6618f76048533344e6fc752dd124aa1ce1bb5
+oid sha256:b2c05afd915c8e685af8c28a2a540666584811385797d3adefaebd8817e7bbd7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 108.23912626940026,
   "best_model_checkpoint": "./whisper-small-ha-v2/checkpoint-1000",
-  "epoch": 9.554140127388536,
+  "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": 123.87430542249473,
       "eval_wer_ortho": 125.99609375,
       "step": 1500
+    },
+    {
+      "epoch": 9.713375796178344,
+      "grad_norm": 5.37247371673584,
+      "learning_rate": 0.0005,
+      "loss": 1.043,
+      "step": 1525
+    },
+    {
+      "epoch": 9.872611464968152,
+      "grad_norm": 5.714049816131592,
+      "learning_rate": 0.0005,
+      "loss": 1.0139,
+      "step": 1550
+    },
+    {
+      "epoch": 10.031847133757962,
+      "grad_norm": 5.447414398193359,
+      "learning_rate": 0.0005,
+      "loss": 0.9852,
+      "step": 1575
+    },
+    {
+      "epoch": 10.19108280254777,
+      "grad_norm": 4.800140380859375,
+      "learning_rate": 0.0005,
+      "loss": 0.8618,
+      "step": 1600
+    },
+    {
+      "epoch": 10.35031847133758,
+      "grad_norm": 4.940687656402588,
+      "learning_rate": 0.0005,
+      "loss": 0.9099,
+      "step": 1625
+    },
+    {
+      "epoch": 10.509554140127388,
+      "grad_norm": 5.976550579071045,
+      "learning_rate": 0.0005,
+      "loss": 0.9144,
+      "step": 1650
+    },
+    {
+      "epoch": 10.668789808917197,
+      "grad_norm": 5.915425777435303,
+      "learning_rate": 0.0005,
+      "loss": 0.9963,
+      "step": 1675
+    },
+    {
+      "epoch": 10.828025477707007,
+      "grad_norm": 6.186098575592041,
+      "learning_rate": 0.0005,
+      "loss": 0.9809,
+      "step": 1700
+    },
+    {
+      "epoch": 10.987261146496815,
+      "grad_norm": 6.102351665496826,
+      "learning_rate": 0.0005,
+      "loss": 0.9992,
+      "step": 1725
+    },
+    {
+      "epoch": 11.146496815286625,
+      "grad_norm": 5.012561798095703,
+      "learning_rate": 0.0005,
+      "loss": 0.8408,
+      "step": 1750
+    },
+    {
+      "epoch": 11.305732484076433,
+      "grad_norm": 4.676059246063232,
+      "learning_rate": 0.0005,
+      "loss": 0.838,
+      "step": 1775
+    },
+    {
+      "epoch": 11.464968152866241,
+      "grad_norm": 4.5027689933776855,
+      "learning_rate": 0.0005,
+      "loss": 0.8774,
+      "step": 1800
+    },
+    {
+      "epoch": 11.624203821656051,
+      "grad_norm": 5.583326816558838,
+      "learning_rate": 0.0005,
+      "loss": 0.9229,
+      "step": 1825
+    },
+    {
+      "epoch": 11.78343949044586,
+      "grad_norm": 5.260093688964844,
+      "learning_rate": 0.0005,
+      "loss": 0.9436,
+      "step": 1850
+    },
+    {
+      "epoch": 11.94267515923567,
+      "grad_norm": 4.777396202087402,
+      "learning_rate": 0.0005,
+      "loss": 0.949,
+      "step": 1875
+    },
+    {
+      "epoch": 12.101910828025478,
+      "grad_norm": 4.361011028289795,
+      "learning_rate": 0.0005,
+      "loss": 0.8302,
+      "step": 1900
+    },
+    {
+      "epoch": 12.261146496815286,
+      "grad_norm": 4.748295783996582,
+      "learning_rate": 0.0005,
+      "loss": 0.843,
+      "step": 1925
+    },
+    {
+      "epoch": 12.420382165605096,
+      "grad_norm": 5.090404510498047,
+      "learning_rate": 0.0005,
+      "loss": 0.8528,
+      "step": 1950
+    },
+    {
+      "epoch": 12.579617834394904,
+      "grad_norm": 5.081445217132568,
+      "learning_rate": 0.0005,
+      "loss": 0.8623,
+      "step": 1975
+    },
+    {
+      "epoch": 12.738853503184714,
+      "grad_norm": 5.345047950744629,
+      "learning_rate": 0.0005,
+      "loss": 0.892,
+      "step": 2000
+    },
+    {
+      "epoch": 12.738853503184714,
+      "eval_loss": 4.75683069229126,
+      "eval_runtime": 241.3599,
+      "eval_samples_per_second": 2.735,
+      "eval_steps_per_second": 0.174,
+      "eval_wer": 114.79210576738839,
+      "eval_wer_ortho": 118.00781250000001,
+      "step": 2000
     }
   ],
   "logging_steps": 25,
@@ -476,7 +626,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.91566053326848e+18,
+  "total_flos": 9.22088071102464e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null