Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b835329ef4709c0d0c8d1cc92ce20cf0824c93a00beec28c143cb8b65a626849
+oid sha256:0c251d99d91b1688198a576bd284d526bc8c64c668230153c5206921df22e939
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8430cf2cfc85209ec72b14935d060f9be6b5ceeaf9fe7ebb3e07ce441c6e8d05
+oid sha256:b3fccd79082e460b132de5707302dfdc687cf969faa26441cbfc3af3a2f24364
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e6e721ef589f426d117d352e598663f682c797ffd64051fbd7dfcfb7bd6fac
+oid sha256:5c5b9d591372e5065a8120169931ca394511eeff5b6e9d239a15928090e157ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9bed5473f5660663309a68e94acd97d7760b053fdd2cb87c2ed61460498bb6
+oid sha256:45e12526c8172a948234d8cb869935e517c484d36da5eb6ac9a7382e7d268eff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 26.55630683142924,
-  "best_model_checkpoint": "./whisper-small-clean_6-v2/checkpoint-200",
-  "epoch": 0.5,
+  "best_metric": 25.775238983446023,
+  "best_model_checkpoint": "./whisper-small-clean_6-v2/checkpoint-400",
+  "epoch": 1.0,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -72,6 +72,71 @@
       "eval_steps_per_second": 0.072,
       "eval_wer": 26.55630683142924,
       "step": 200
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 3.616425037384033,
+      "learning_rate": 5e-06,
+      "loss": 0.2072,
+      "step": 225
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 3.8101563453674316,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.189,
+      "step": 250
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 3.7268102169036865,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.194,
+      "step": 275
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.762694835662842,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.1853,
+      "step": 300
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 4.289006233215332,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.1988,
+      "step": 325
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 3.323763132095337,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.1948,
+      "step": 350
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 4.1935200691223145,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.2095,
+      "step": 375
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.7287049293518066,
+      "learning_rate": 0.0,
+      "loss": 0.1923,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.29943087697029114,
+      "eval_runtime": 656.7909,
+      "eval_samples_per_second": 2.322,
+      "eval_steps_per_second": 0.073,
+      "eval_wer": 25.775238983446023,
+      "step": 400
     }
   ],
   "logging_steps": 25,
@@ -86,12 +151,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.693893124096e+18,
+  "total_flos": 7.387786248192e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null