Training in progress, step 1200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914ed3e475fbbe59f26091e71a51974474199116498023062b709a224c66d95d
+oid sha256:7d436a2faf2808b5ca3ca4f28513c6308d2f1a669a1126e427e0cafeab0f2c28
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b03d8c06bcb740830b3f010086842870615d8a3a8a6f7c2a4611b228627f3b2
+oid sha256:6158aa31bac85837af2e2a3b6dd823093907acd64000f5d832aef5a3c02e1b27
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c7ed61bfff96080c05a3a3fa9a5f0e691e7c200c850183d459767e5c56eaaa
+oid sha256:ba5c1c59a616aa7b0f9e4dba43c7f771e98199d6e889d414c4046cb6db67e0db
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ec0b15a5fc66e27eb0f4b06b38ed940e856fb7a7b953bddd02a85a47e1b2a62
+oid sha256:5cfa6a40d74b0a4f6ca147fe45b859220132f65b1f4967c356e1f5127a7ae1f1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0a41f1e93dcdfed915b8931ec361cc19c3cfce2fef0013efccb31577ea0b5ee
+oid sha256:ff4f207fb87ffe1badbf72415757a46ce85d22e55b3649589a00635535f33997
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 800,
-  "best_metric": 0.35529030356616564,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-800",
-  "epoch": 0.5701051131302334,
+  "best_global_step": 1200,
+  "best_metric": 0.3020925434718538,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-1200",
+  "epoch": 0.8551576696953501,
   "eval_steps": 400,
-  "global_step": 800,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,43 @@
       "eval_steps_per_second": 0.396,
       "eval_wer": 0.35529030356616564,
       "step": 800
+    },
+    {
+      "epoch": 0.6413682522715125,
+      "grad_norm": 101.50548553466797,
+      "learning_rate": 8.961984362361823e-05,
+      "loss": 14.2258,
+      "step": 900
+    },
+    {
+      "epoch": 0.7126313914127917,
+      "grad_norm": 159.8544158935547,
+      "learning_rate": 8.692369911027231e-05,
+      "loss": 12.9126,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7838945305540709,
+      "grad_norm": 109.82164764404297,
+      "learning_rate": 8.42275545969264e-05,
+      "loss": 11.7962,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8551576696953501,
+      "grad_norm": 108.62500762939453,
+      "learning_rate": 8.153141008358049e-05,
+      "loss": 11.9313,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8551576696953501,
+      "eval_loss": 0.12360513210296631,
+      "eval_runtime": 158.6716,
+      "eval_samples_per_second": 3.151,
+      "eval_steps_per_second": 0.397,
+      "eval_wer": 0.3020925434718538,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -101,7 +138,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.040657154048e+18,
+  "total_flos": 1.560985731072e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null