Training in progress, step 6160

config.json

@@ -110,7 +110,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.23.1",
   "use_weighted_layer_sum": false,
   "vocab_size": 27,
   "xvector_output_dim": 512

last-checkpoint/config.json

@@ -110,7 +110,7 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.23.1",
   "use_weighted_layer_sum": false,
   "vocab_size": 27,
   "xvector_output_dim": 512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b496b77db0775d4aafe63ebf99bb48b4cedc2b148375ade0078f50c49fcc12
-size 168159
+oid sha256:cec9875bd026091efa36e8010d350104fd0a4d2a4764c3c36ceadcb6052a0c39
+size 721655813

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac76cdc6a11567deba22d2bf5690104a29bb9409be961b2f7cc85ec601ed2faf
-size 377641431
+oid sha256:a272e9147c0ac341d1a851b4f9beb9ad6e2a45b5ad4099cbb0bfb70cfe100965
+size 377643361

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf5cf665edebc10f59a508b1bdd4459e2986107eff89494df9748ccc5e92d22
-size 14567
+oid sha256:617dd7671016dca2a947f53be356990669bafa6ea2f783a55f6f3a1236b37a0b
+size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87eba8509565f31935d4802d6fd893f9a52221dec1363e87afb68f2247d77ad4
-size 559
+oid sha256:6b613b2755a27abb572474750570fb952279e467c6ae92352953cf4de82eeaee
+size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0bf0b5bd1d17ed1b58127b096eff11d292865966f32e83e2cd2210f9b28d40c
-size 623
+oid sha256:3970e66b4828758eb5d9ec8312235775ae992b288b8e94eeb891496be72cd0a5
+size 627

last-checkpoint/trainer_state.json

@@ -1,176 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 250.0,
-  "global_step": 123250,
+  "epoch": 10.0,
+  "global_step": 6160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 25.0,
-      "learning_rate": 9.474412407761683e-05,
-      "loss": 19.1039,
-      "step": 12325
+      "epoch": 10.0,
+      "learning_rate": 9.475051264524949e-05,
+      "loss": 4.1068,
+      "step": 6160
     },
     {
-      "epoch": 25.0,
-      "eval_cer": 0.9757575757575757,
-      "eval_loss": 3.695141077041626,
-      "eval_runtime": 1.0205,
-      "eval_samples_per_second": 205.79,
-      "eval_steps_per_second": 26.459,
-      "eval_wer": 1.0,
-      "step": 12325
-    },
-    {
-      "epoch": 50.0,
-      "learning_rate": 8.422041541404757e-05,
-      "loss": 2.7071,
-      "step": 24650
-    },
-    {
-      "epoch": 50.0,
-      "eval_cer": 0.9341991341991343,
-      "eval_loss": 3.8789684772491455,
-      "eval_runtime": 1.0032,
-      "eval_samples_per_second": 209.335,
-      "eval_steps_per_second": 26.914,
-      "eval_wer": 1.0,
-      "step": 24650
-    },
-    {
-      "epoch": 75.0,
-      "learning_rate": 7.369841486745012e-05,
-      "loss": 2.5758,
-      "step": 36975
-    },
-    {
-      "epoch": 75.0,
-      "eval_cer": 0.9125541125541126,
-      "eval_loss": 3.856503963470459,
-      "eval_runtime": 0.9967,
-      "eval_samples_per_second": 210.695,
-      "eval_steps_per_second": 27.089,
-      "eval_wer": 1.0,
-      "step": 36975
-    },
-    {
-      "epoch": 100.0,
-      "learning_rate": 6.317726837933862e-05,
-      "loss": 2.5155,
-      "step": 49300
-    },
-    {
-      "epoch": 100.0,
-      "eval_cer": 0.9168831168831169,
-      "eval_loss": 3.8677046298980713,
-      "eval_runtime": 1.0011,
-      "eval_samples_per_second": 209.777,
-      "eval_steps_per_second": 26.971,
-      "eval_wer": 1.0,
-      "step": 49300
-    },
-    {
-      "epoch": 125.0,
-      "learning_rate": 5.2655267832741184e-05,
-      "loss": 2.4801,
-      "step": 61625
-    },
-    {
-      "epoch": 125.0,
-      "eval_cer": 0.9168831168831169,
-      "eval_loss": 3.8714091777801514,
-      "eval_runtime": 1.0139,
-      "eval_samples_per_second": 207.112,
-      "eval_steps_per_second": 26.629,
-      "eval_wer": 1.0,
-      "step": 61625
-    },
-    {
-      "epoch": 150.0,
-      "learning_rate": 4.213241322765783e-05,
-      "loss": 2.4591,
-      "step": 73950
-    },
-    {
-      "epoch": 150.0,
-      "eval_cer": 0.922943722943723,
-      "eval_loss": 3.857038736343384,
-      "eval_runtime": 1.0003,
-      "eval_samples_per_second": 209.939,
-      "eval_steps_per_second": 26.992,
-      "eval_wer": 1.0,
-      "step": 73950
-    },
-    {
-      "epoch": 175.0,
-      "learning_rate": 3.16104126810604e-05,
-      "loss": 2.4435,
-      "step": 86275
-    },
-    {
-      "epoch": 175.0,
-      "eval_cer": 0.9125541125541126,
-      "eval_loss": 3.8484246730804443,
-      "eval_runtime": 0.9998,
-      "eval_samples_per_second": 210.042,
-      "eval_steps_per_second": 27.005,
-      "eval_wer": 1.0,
-      "step": 86275
-    },
-    {
-      "epoch": 200.0,
-      "learning_rate": 2.108841213446297e-05,
-      "loss": 2.4329,
-      "step": 98600
-    },
-    {
-      "epoch": 200.0,
-      "eval_cer": 0.9125541125541126,
-      "eval_loss": 3.83984637260437,
-      "eval_runtime": 1.0007,
-      "eval_samples_per_second": 209.858,
-      "eval_steps_per_second": 26.982,
-      "eval_wer": 1.0,
-      "step": 98600
-    },
-    {
-      "epoch": 225.0,
-      "learning_rate": 1.0565557529379612e-05,
-      "loss": 2.4266,
-      "step": 110925
-    },
-    {
-      "epoch": 225.0,
-      "eval_cer": 0.90995670995671,
-      "eval_loss": 3.8467934131622314,
-      "eval_runtime": 1.0035,
-      "eval_samples_per_second": 209.258,
-      "eval_steps_per_second": 26.905,
-      "eval_wer": 1.0,
-      "step": 110925
-    },
-    {
-      "epoch": 250.0,
-      "learning_rate": 4.355698278218093e-08,
-      "loss": 2.4229,
-      "step": 123250
-    },
-    {
-      "epoch": 250.0,
-      "eval_cer": 0.9116883116883117,
-      "eval_loss": 3.849649667739868,
-      "eval_runtime": 1.0002,
-      "eval_samples_per_second": 209.958,
-      "eval_steps_per_second": 26.995,
-      "eval_wer": 1.0,
-      "step": 123250
+      "epoch": 10.0,
+      "eval_cer": 0.47359307359307357,
+      "eval_loss": 4.263599395751953,
+      "eval_runtime": 7.5888,
+      "eval_samples_per_second": 27.672,
+      "eval_steps_per_second": 3.558,
+      "eval_wer": 0.8904761904761904,
+      "step": 6160
     }
   ],
-  "max_steps": 123250,
-  "num_train_epochs": 250,
-  "total_flos": 1.1400455629774925e+20,
+  "max_steps": 61600,
+  "num_train_epochs": 100,
+  "total_flos": 4.5525339060428145e+18,
   "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:d1284c9db1fbd6ffd1a05741124b3d17a18ce5a697d22cde3b856c57d54e1290
-size 3119
+oid sha256:a93853e8d3350b9736431ab93f767de49f660529f7cab12962ec53dd998b74d7
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac76cdc6a11567deba22d2bf5690104a29bb9409be961b2f7cc85ec601ed2faf
-size 377641431
+oid sha256:a272e9147c0ac341d1a851b4f9beb9ad6e2a45b5ad4099cbb0bfb70cfe100965
+size 377643361

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1284c9db1fbd6ffd1a05741124b3d17a18ce5a697d22cde3b856c57d54e1290
-size 3119
+oid sha256:a93853e8d3350b9736431ab93f767de49f660529f7cab12962ec53dd998b74d7
+size 3451