Upload model files

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ed1308b0197b664afafb89a324c964fe1a9b13d8c0f169503cc8a5884da0c2
+oid sha256:cdc5fe22caf3ab0da5d9a8af717c0dca82d1f6ae9e7aa9027c737dde62a71094
 size 966995080

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b934b418ef4ab7a7360fe2ce1e5cd08221e8ad6b463fbc828c3d356e84195b
+oid sha256:bfd13714e336de6cd1e10eeaa48e28e676ba46841563aa44a914e471f1911b0c
 size 1925064044

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3540179bbcfe2a2e55d05fad49c806615d68122d33b057e8a5ff20ca08833829
+oid sha256:8aa131b1b19ffaf82f661066d702d457162e5d38c85d7e947e66a47635d27005
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49054e3b5dea463b82349ae8b05bc44c24728fc8e9d56eee16e9fedd96e927d4
+oid sha256:8e1fede3213fedd1ecd15bbdf7ba8ade02616774e6b63ad166ac555b429a6a8a
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 85.87243015287297,
   "best_model_checkpoint": "./Shukv4/checkpoint-500",
-  "epoch": 2.688172043010753,
+  "epoch": 5.376344086021505,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,155 @@
       "eval_steps_per_second": 0.029,
       "eval_wer": 85.87243015287297,
       "step": 500
+    },
+    {
+      "epoch": 2.8225806451612905,
+      "grad_norm": 115137.6015625,
+      "learning_rate": 6.597222222222223e-06,
+      "loss": 0.0293,
+      "step": 525
+    },
+    {
+      "epoch": 2.956989247311828,
+      "grad_norm": 148418.078125,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0264,
+      "step": 550
+    },
+    {
+      "epoch": 3.0913978494623655,
+      "grad_norm": 44248.91796875,
+      "learning_rate": 5.902777777777778e-06,
+      "loss": 0.0157,
+      "step": 575
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 86631.046875,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.0101,
+      "step": 600
+    },
+    {
+      "epoch": 3.360215053763441,
+      "grad_norm": 69759.2421875,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 0.0175,
+      "step": 625
+    },
+    {
+      "epoch": 3.4946236559139785,
+      "grad_norm": 79651.625,
+      "learning_rate": 4.861111111111111e-06,
+      "loss": 0.0121,
+      "step": 650
+    },
+    {
+      "epoch": 3.629032258064516,
+      "grad_norm": 78669.6171875,
+      "learning_rate": 4.513888888888889e-06,
+      "loss": 0.0137,
+      "step": 675
+    },
+    {
+      "epoch": 3.763440860215054,
+      "grad_norm": 104462.546875,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.0114,
+      "step": 700
+    },
+    {
+      "epoch": 3.8978494623655915,
+      "grad_norm": 79927.2109375,
+      "learning_rate": 3.819444444444445e-06,
+      "loss": 0.0105,
+      "step": 725
+    },
+    {
+      "epoch": 4.032258064516129,
+      "grad_norm": 69011.8984375,
+      "learning_rate": 3.4722222222222224e-06,
+      "loss": 0.0074,
+      "step": 750
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 43131.57421875,
+      "learning_rate": 3.125e-06,
+      "loss": 0.0036,
+      "step": 775
+    },
+    {
+      "epoch": 4.301075268817204,
+      "grad_norm": 15227.64453125,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.0038,
+      "step": 800
+    },
+    {
+      "epoch": 4.435483870967742,
+      "grad_norm": 27650.37890625,
+      "learning_rate": 2.4305555555555557e-06,
+      "loss": 0.0082,
+      "step": 825
+    },
+    {
+      "epoch": 4.56989247311828,
+      "grad_norm": 146017.515625,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.0066,
+      "step": 850
+    },
+    {
+      "epoch": 4.704301075268817,
+      "grad_norm": 41058.7421875,
+      "learning_rate": 1.7361111111111112e-06,
+      "loss": 0.0047,
+      "step": 875
+    },
+    {
+      "epoch": 4.838709677419355,
+      "grad_norm": 6614.59765625,
+      "learning_rate": 1.388888888888889e-06,
+      "loss": 0.0051,
+      "step": 900
+    },
+    {
+      "epoch": 4.973118279569892,
+      "grad_norm": 24049.263671875,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 0.0026,
+      "step": 925
+    },
+    {
+      "epoch": 5.10752688172043,
+      "grad_norm": 42294.18359375,
+      "learning_rate": 6.944444444444445e-07,
+      "loss": 0.0047,
+      "step": 950
+    },
+    {
+      "epoch": 5.241935483870968,
+      "grad_norm": 9962.9453125,
+      "learning_rate": 3.4722222222222224e-07,
+      "loss": 0.0013,
+      "step": 975
+    },
+    {
+      "epoch": 5.376344086021505,
+      "grad_norm": 18759.73828125,
+      "learning_rate": 0.0,
+      "loss": 0.0047,
+      "step": 1000
+    },
+    {
+      "epoch": 5.376344086021505,
+      "eval_loss": 0.0025792771484702826,
+      "eval_runtime": 847.1283,
+      "eval_samples_per_second": 0.242,
+      "eval_steps_per_second": 0.031,
+      "eval_wer": 96.36267791249341,
+      "step": 1000
     }
   ],
   "logging_steps": 25,
@@ -170,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.72804937711616e+18,
+  "total_flos": 3.4543672418304e+18,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null