Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3800b0c5082a2a85ba63553ccb85e586a8780fc9caa5196195bfc274e629f12
+oid sha256:6cb4d61bd0a44d470e978c93d28879727cf615ffc64832c149ad24c3cbaea38f
 size 62969640

last-checkpoint/adapter_model/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3800b0c5082a2a85ba63553ccb85e586a8780fc9caa5196195bfc274e629f12
+oid sha256:6cb4d61bd0a44d470e978c93d28879727cf615ffc64832c149ad24c3cbaea38f
 size 62969640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58bce4fb12e9358f8580fd8fee8149bec0d234df41d0f3da1a1dafb4c7be126f
+oid sha256:900d513643e3d002b42ebb4329778e2f53dd10431cd241681dbd3d73f278f24a
 size 84101370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:826fb0f5cab6ac986229f1a67fff03f7200f414af782afb66f437b3beaa7941c
+oid sha256:bb3593b18ee7bc24651b21523951beff2d7d4251bd7a51b740184fc5919e960d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45004596170d4aa0e7d597e7e8646c384a7d41cb44c069f7e129c158ae176d48
+oid sha256:e24cf62bbe9d37fb0fa1bd7605633c18b8267073d955dffec23a49be9f54b879
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37afc474a8896b47757a80cf53f9a5c049fe18cf9e4a0f6d01fd6319603543d
+oid sha256:f9f304e584cfe8d229125612de97e3f29f8ba76a3b8ee16eb4fb26bddfc0a2a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1500,
-  "best_metric": 0.7649029493331909,
-  "best_model_checkpoint": "./whisper-large/checkpoint-1500",
-  "epoch": 0.75,
+  "best_global_step": 2000,
+  "best_metric": 0.745384931564331,
+  "best_model_checkpoint": "./whisper-large/checkpoint-2000",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -452,6 +452,154 @@
       "eval_samples_per_second": 2.413,
       "eval_steps_per_second": 0.302,
       "step": 1500
+    },
+    {
+      "epoch": 0.7625,
+      "grad_norm": 2.7206623554229736,
+      "learning_rate": 2.4461538461538466e-06,
+      "loss": 0.7492,
+      "step": 1525
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 3.6394665241241455,
+      "learning_rate": 2.3179487179487183e-06,
+      "loss": 0.7626,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7875,
+      "grad_norm": 3.5084238052368164,
+      "learning_rate": 2.18974358974359e-06,
+      "loss": 0.7355,
+      "step": 1575
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.666715383529663,
+      "learning_rate": 2.061538461538462e-06,
+      "loss": 0.7641,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 2.775841236114502,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 0.7556,
+      "step": 1625
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 2.926852226257324,
+      "learning_rate": 1.8051282051282054e-06,
+      "loss": 0.7314,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8375,
+      "grad_norm": 3.186278820037842,
+      "learning_rate": 1.676923076923077e-06,
+      "loss": 0.7383,
+      "step": 1675
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.2699010372161865,
+      "learning_rate": 1.5487179487179487e-06,
+      "loss": 0.7442,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8625,
+      "grad_norm": 3.576728105545044,
+      "learning_rate": 1.4205128205128208e-06,
+      "loss": 0.7313,
+      "step": 1725
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 3.307767391204834,
+      "learning_rate": 1.2923076923076924e-06,
+      "loss": 0.73,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8875,
+      "grad_norm": 3.2202937602996826,
+      "learning_rate": 1.1641025641025642e-06,
+      "loss": 0.7331,
+      "step": 1775
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 2.9179611206054688,
+      "learning_rate": 1.0358974358974359e-06,
+      "loss": 0.7187,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9125,
+      "grad_norm": 2.9629781246185303,
+      "learning_rate": 9.076923076923077e-07,
+      "loss": 0.7379,
+      "step": 1825
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 3.4861905574798584,
+      "learning_rate": 7.794871794871796e-07,
+      "loss": 0.7558,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 2.8324718475341797,
+      "learning_rate": 6.512820512820513e-07,
+      "loss": 0.7355,
+      "step": 1875
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.391080856323242,
+      "learning_rate": 5.230769230769231e-07,
+      "loss": 0.7442,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9625,
+      "grad_norm": 3.1133198738098145,
+      "learning_rate": 3.9487179487179493e-07,
+      "loss": 0.7223,
+      "step": 1925
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 2.8490092754364014,
+      "learning_rate": 2.666666666666667e-07,
+      "loss": 0.7157,
+      "step": 1950
+    },
+    {
+      "epoch": 0.9875,
+      "grad_norm": 3.7724802494049072,
+      "learning_rate": 1.384615384615385e-07,
+      "loss": 0.7222,
+      "step": 1975
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.605504274368286,
+      "learning_rate": 1.0256410256410258e-08,
+      "loss": 0.7256,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.745384931564331,
+      "eval_runtime": 1208.2983,
+      "eval_samples_per_second": 2.417,
+      "eval_steps_per_second": 0.302,
+      "step": 2000
     }
   ],
   "logging_steps": 25,
@@ -466,12 +614,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.28749215744e+19,
+  "total_flos": 1.71665620992e+19,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null