Training in progress, epoch 13, checkpoint

last-checkpoint/generation_config.json

@@ -65,20 +65,7 @@
     "1": "LABEL_1"
   },
   "init_std": 0.02,
-  "input_ids": [
-    [
-      1,
-      50272
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
-  ],
+  "input_ids": null,
   "is_decoder": false,
   "is_encoder_decoder": true,
   "is_multilingual": true,

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe05555510ebc55c4665edcb6454f5a98c203d73607b74b65485054a8f22985b
+oid sha256:c11e59e81088d0e16b8735b6e597fec79f32d290e36d8def6b66cbbc9e8cd9a1
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7cddb83bff0f688d9d17ae32e3307362f9136346d658e1851dc85b10499958
+oid sha256:104d77fcd199b8f340fb5fd3f8f129fe23300d5bc5c65964c445674c40b1ea3c
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3750103d3d13774fbde9af71a1b620bee7b1f3fd3b4d85d56883589c78d71bd4
+oid sha256:7e08d413e62216cbe63b70a91998470669d513dd371df2cba7b0ead107f19599
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f4c85a973f911d833e8fedb04651de698e4b737fa13407117e3027064f11ba
+oid sha256:7aefee4fd3e11c00d12d383dcb2394d9676c073e8b3c3644d024cad7798c0188
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6c3abe9ceb62539c5bc66c9459beb276c796c31f0262d8a4d34c48cc845a28
+oid sha256:6b9874aa9a588ea803e346f0e1d9fe34891d4c784b3be0ae24270743f1766186
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4680,
   "best_metric": 0.2625994694960212,
   "best_model_checkpoint": "./distil-whisper/checkpoint-4680",
-  "epoch": 14.9536,
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 4680,
+  "global_step": 4875,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -465,12 +465,35 @@
       "eval_steps_per_second": 0.407,
       "eval_wer": 0.2625994694960212,
       "step": 4680
+    },
+    {
+      "epoch": 12.533333333333333,
+      "grad_norm": 114.76351165771484,
+      "learning_rate": 4.021428571428572e-05,
+      "loss": 7.7843,
+      "step": 4700
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 130.2476043701172,
+      "learning_rate": 3.8785714285714285e-05,
+      "loss": 7.0386,
+      "step": 4800
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.12093591690063477,
+      "eval_runtime": 155.7693,
+      "eval_samples_per_second": 3.21,
+      "eval_steps_per_second": 0.404,
+      "eval_wer": 0.27600943118184496,
+      "step": 4875
     }
   ],
   "logging_steps": 100,
-  "max_steps": 4680,
+  "max_steps": 7500,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 20,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -479,12 +502,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.07873860108288e+18,
+  "total_flos": 6.33239878238208e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:800244257547555a23085083233b10cbaa528177ab8061d70f90dafa751bca41
-size 5496
+oid sha256:02bfb31ca1639bb49b771e365c14935b1ca47589e808fb8789c196079d263aa1
+size 5560