Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239e6ee34c627288f07da635c7607c26cb1658248cb4216138582c969c562c53
+oid sha256:1faae7c834d1bb6209cce5a3f0eba37603cd97968d5ae1b6bf60ee5532f4c25f
 size 62969640

last-checkpoint/adapter_model/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239e6ee34c627288f07da635c7607c26cb1658248cb4216138582c969c562c53
+oid sha256:1faae7c834d1bb6209cce5a3f0eba37603cd97968d5ae1b6bf60ee5532f4c25f
 size 62969640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57dc2a75271934b9272c6e364dbf8843d89c17ee905195eb7b2c5eaf32f6c3c
+oid sha256:f26b7ff9e117acaaf45b07eccb6cd0baa36728fc0f969371979374cc5be60035
 size 84101370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018d3489ed13a5f5303fe87bc05ee3bd7e42fab42cae25b01d59fef9cd4802ee
+oid sha256:1cdd3cf64f5c3a203d2cecf3121f10fda7f7fc667ea30f96acfb98121b8c3035
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a4b6e0ef05ca249f2d6b7f9f3ad1dff81e55842a962df795bb9740c17c8e92
+oid sha256:3c50a9cebe5d66d453d25b140738bff479749ac03e0a43597d8776bc22f6ed0c
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416c83758baa78b1c3e5334d8425b4107684ccd443376b2af239f14f10f93e92
+oid sha256:382782d862255d071016cff9c6a4b56eed27c6324967e51b062457330841da4d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1500,
-  "best_metric": 0.6280742287635803,
-  "best_model_checkpoint": "./whisper-large-v3-lt1/checkpoint-1500",
-  "epoch": 0.75,
+  "best_global_step": 2000,
+  "best_metric": 0.6051455140113831,
+  "best_model_checkpoint": "./whisper-large-v3-lt1/checkpoint-2000",
+  "epoch": 1.179,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,6 +137,49 @@
       "eval_samples_per_second": 2.509,
       "eval_steps_per_second": 0.314,
       "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.4991073608398438,
+      "learning_rate": 2.110526315789474e-06,
+      "loss": 0.6425,
+      "step": 1600
+    },
+    {
+      "epoch": 1.029,
+      "grad_norm": 1.7371805906295776,
+      "learning_rate": 1.5842105263157894e-06,
+      "loss": 0.6223,
+      "step": 1700
+    },
+    {
+      "epoch": 1.079,
+      "grad_norm": 3.491868495941162,
+      "learning_rate": 1.0578947368421054e-06,
+      "loss": 0.6013,
+      "step": 1800
+    },
+    {
+      "epoch": 1.129,
+      "grad_norm": 2.1243815422058105,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 0.5967,
+      "step": 1900
+    },
+    {
+      "epoch": 1.179,
+      "grad_norm": 2.0289883613586426,
+      "learning_rate": 5.263157894736842e-09,
+      "loss": 0.5986,
+      "step": 2000
+    },
+    {
+      "epoch": 1.179,
+      "eval_loss": 0.6051455140113831,
+      "eval_runtime": 1166.0635,
+      "eval_samples_per_second": 2.504,
+      "eval_steps_per_second": 0.313,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -151,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.240969023488e+19,
+  "total_flos": 1.0985211708309504e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null