Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3edcd0c450189261c882afd547ab8aa2ed8d8d69f6514bdd036f696631191522
+oid sha256:239e6ee34c627288f07da635c7607c26cb1658248cb4216138582c969c562c53
 size 62969640

last-checkpoint/adapter_model/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3edcd0c450189261c882afd547ab8aa2ed8d8d69f6514bdd036f696631191522
+oid sha256:239e6ee34c627288f07da635c7607c26cb1658248cb4216138582c969c562c53
 size 62969640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5dcfe80745e49d3dda94c607cdd0c6937698a1eee8f03ccc8d98c943d8860e
+oid sha256:b57dc2a75271934b9272c6e364dbf8843d89c17ee905195eb7b2c5eaf32f6c3c
 size 84101370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:658a00b68b67cee9ed9e480f0e8e586986ce85df79a4a11fa9577da999c85123
+oid sha256:018d3489ed13a5f5303fe87bc05ee3bd7e42fab42cae25b01d59fef9cd4802ee
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
+oid sha256:c2a4b6e0ef05ca249f2d6b7f9f3ad1dff81e55842a962df795bb9740c17c8e92
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a379574c9663f8f6b1e4e8f5372c7153e8ea3e03443c673cf8a63a64a20ef3
+oid sha256:416c83758baa78b1c3e5334d8425b4107684ccd443376b2af239f14f10f93e92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 0.6822749972343445,
-  "best_model_checkpoint": "./whisper-large-v3-lt1/checkpoint-1000",
-  "epoch": 0.5,
+  "best_global_step": 1500,
+  "best_metric": 0.6280742287635803,
+  "best_model_checkpoint": "./whisper-large-v3-lt1/checkpoint-1500",
+  "epoch": 0.75,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,49 @@
       "eval_samples_per_second": 2.504,
       "eval_steps_per_second": 0.313,
       "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.2514197826385498,
+      "learning_rate": 4.7421052631578954e-06,
+      "loss": 0.6689,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.271310806274414,
+      "learning_rate": 4.215789473684211e-06,
+      "loss": 0.6526,
+      "step": 1200
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 2.1460328102111816,
+      "learning_rate": 3.6894736842105265e-06,
+      "loss": 0.6299,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.67410945892334,
+      "learning_rate": 3.1631578947368424e-06,
+      "loss": 0.6143,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.5648741722106934,
+      "learning_rate": 2.6368421052631584e-06,
+      "loss": 0.6632,
+      "step": 1500
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.6280742287635803,
+      "eval_runtime": 1163.7066,
+      "eval_samples_per_second": 2.509,
+      "eval_steps_per_second": 0.314,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -113,7 +156,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.493979348992e+19,
+  "total_flos": 8.240969023488e+19,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null