Training in progress, step 2400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce5374a700f6cb8856fec0d069890cb1c699a8142cbab7571daa3287a2b3058b
+oid sha256:427ae072cbc49ae148942a74b9f051c838d316269f69b8f3611c391c8a391f3c
 size 966995080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10dcd11e2cb1895f7c3e1c68032ca79221ba9837804ddc4c0ad628db4cb3bbbb
+oid sha256:08fe004ed695904662ce35ea3ec86602835c8a8f59b8179ec9a51565518cb6bf
 size 1925064044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f1fe924fb046e82f32a9e9633992150d028a3f688d46144a5a5c7f5cbc6bad
+oid sha256:ff499e04130faa18bab8a5b949aa9f38474523cf8282520e9cbda71727ce4299
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c2e8507c15e11b5d34f126b0dbb02f39afdf32066bd4c386593945bed215e3
+oid sha256:8b19556c05ce15c76b44c442588d62a6615081b49579cf8217e66cc8d1a38558
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 70.1955074875208,
   "best_model_checkpoint": "./whisper-it/checkpoint-300",
-  "epoch": 4.00763358778626,
+  "epoch": 4.580152671755725,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -700,6 +700,105 @@
       "eval_steps_per_second": 0.111,
       "eval_wer": 134.65058236272878,
       "step": 2100
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 5.374285714285715e-06,
+      "loss": 0.018,
+      "step": 2125
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 5.3028571428571425e-06,
+      "loss": 0.0165,
+      "step": 2150
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 5.2314285714285716e-06,
+      "loss": 0.0157,
+      "step": 2175
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 5.1600000000000006e-06,
+      "loss": 0.0173,
+      "step": 2200
+    },
+    {
+      "epoch": 4.2,
+      "eval_loss": 0.4140649735927582,
+      "eval_runtime": 1834.1524,
+      "eval_samples_per_second": 0.818,
+      "eval_steps_per_second": 0.102,
+      "eval_wer": 189.33721575152524,
+      "step": 2200
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 5.08857142857143e-06,
+      "loss": 0.0157,
+      "step": 2225
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 5.017142857142857e-06,
+      "loss": 0.015,
+      "step": 2250
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 4.945714285714286e-06,
+      "loss": 0.0146,
+      "step": 2275
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 4.874285714285715e-06,
+      "loss": 0.0174,
+      "step": 2300
+    },
+    {
+      "epoch": 4.39,
+      "eval_loss": 0.41064801812171936,
+      "eval_runtime": 1771.4749,
+      "eval_samples_per_second": 0.847,
+      "eval_steps_per_second": 0.106,
+      "eval_wer": 175.0207986688852,
+      "step": 2300
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 4.802857142857143e-06,
+      "loss": 0.0164,
+      "step": 2325
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 4.731428571428572e-06,
+      "loss": 0.0156,
+      "step": 2350
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 4.66e-06,
+      "loss": 0.0145,
+      "step": 2375
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 4.588571428571429e-06,
+      "loss": 0.0165,
+      "step": 2400
+    },
+    {
+      "epoch": 4.58,
+      "eval_loss": 0.4204367697238922,
+      "eval_runtime": 1768.9183,
+      "eval_samples_per_second": 0.848,
+      "eval_steps_per_second": 0.106,
+      "eval_wer": 179.64503605102607,
+      "step": 2400
     }
   ],
   "logging_steps": 25,
@@ -707,7 +806,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 100,
-  "total_flos": 1.938485851029504e+19,
+  "total_flos": 2.215527835336704e+19,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77aa736647908221a6b18a6489ddd200e9a64629e700dfb2729d6eac836a4004
+oid sha256:ec4f3c4eccd10d40b1e2a9f33f5736b02d4539dda80932770d03eaca234d4288
 size 4856