Training in progress, step 4400, 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 sha256:69413f73615f83d9af3e012f915779e8feb55af85c0f9865e5b11ad6de4098a7
+oid sha256:f40200e4b2d1a3f9598026f1d0cccc4f5b3103c0aadb8052e27f341f9a27838d
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26ab3bab0f78e1de1ae83243b84b339f9a73fdc9f36898bacd02627010b7e2f
+oid sha256:90ed54e5fca7d5b720f092da54461547fac2b58c7298cca5427eb03096d37f9c
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffa34d617d37d160278a96263e54262610f7be0f6f6036d5ce9daab9c3384b4
+oid sha256:13153c51d9decd414ca15fdaaabc194d8395e3d59a60c4f1e9bfa5a3a8e7aa77
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:700c62e2c409fb74a77e8989f1568b7a1be716546579ac14b2d28333ee737550
+oid sha256:527ed30c0082066de2b11ba3e383f402988390e42a94d94accb5601dac35d4d6
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b18e7fa03b9a1836a4a0d45bc80a9a0024a1c8c3ed77ce70ed3080f8004f4c9
+oid sha256:5c3512f84cd4c65eb0fe727a1e41ca960ab5dd56daf3156a40e9a12ed28a34d9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4000,
   "best_metric": 0.22192749778956675,
   "best_model_checkpoint": "./distil-whisper/checkpoint-4000",
-  "epoch": 2.998396579369321,
+  "epoch": 3.136112595759843,
   "eval_steps": 400,
-  "global_step": 4209,
+  "global_step": 4400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -392,12 +392,35 @@
       "learning_rate": 6.470746832030197e-07,
       "loss": 4.095,
       "step": 4200
+    },
+    {
+      "epoch": 3.064849456618564,
+      "grad_norm": 75.29638671875,
+      "learning_rate": 7.202512934220252e-05,
+      "loss": 3.8662,
+      "step": 4300
+    },
+    {
+      "epoch": 3.136112595759843,
+      "grad_norm": 60.58271789550781,
+      "learning_rate": 7.12860310421286e-05,
+      "loss": 4.2814,
+      "step": 4400
+    },
+    {
+      "epoch": 3.136112595759843,
+      "eval_loss": 0.1134875938296318,
+      "eval_runtime": 150.6507,
+      "eval_samples_per_second": 3.319,
+      "eval_steps_per_second": 0.418,
+      "eval_wer": 0.23017978190391983,
+      "step": 4400
     }
   ],
   "logging_steps": 100,
-  "max_steps": 4209,
+  "max_steps": 14030,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 10,
   "save_steps": 400,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -406,12 +429,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.4727997128704e+18,
+  "total_flos": 5.72125660839936e+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 sha256:571d625a4025cbdd828f3e43d1e551c2865cdc3710a18660b39ca61e19f78063
-size 5496
+oid sha256:2625b2ae202938153fb64f2a01d19411a432d88aa0bb47eeca4b758e05077415
+size 5560