Training in progress, step 21350

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": 28,
   "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": 28,
   "xvector_output_dim": 512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc7857919e09b77e372558e040f9eb549afe29dd03060a5523a7eb842f9ddbf
-size 174303
+oid sha256:9c7968b8efd13d5fc708b8d575bdfacce3f6faac04d2a82a6681be7767cb3a47
+size 721661957

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b522e60d0d2a6ee27af3602669b1014da231da2f41574acaad118912eceeb40a
-size 377644503
+oid sha256:23c29e7e62821dd9ebdecb0f80999e35b88a4c33b2f765c44a4a3067dd06ef8a
+size 377646433

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b119c6ba94045170ce909d97437f8a62214d60f57d9820329c8e249ad1d0f477
-size 14503
+oid sha256:a815883a2570166bd8681954c208cd0afd701a2550fb682192af67da1655896c
+size 14639

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5beb41d03d0282f86de0df3b3801db507a048b5eb0500763cfc03e40601417
-size 559
+oid sha256:431969896cbea52c0fd9fb08d326480e121ae77403d61e7102d4920fa4fa6518
+size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27135a9065f7161bbce1a83a7e57aa28ecc4c06a7e536eb74226e435b074bac0
-size 623
+oid sha256:0af760cdb84b96d47402463fdc44064dac492fd9b85975a42428ed9c5f980ff1
+size 627

last-checkpoint/trainer_state.json

@@ -1,176 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 100.0,
-  "global_step": 341600,
+  "epoch": 10.0,
+  "global_step": 21350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 10.0,
-      "learning_rate": 9.474208061136448e-05,
-      "loss": 13.2913,
-      "step": 34160
+      "learning_rate": 9.474226549981512e-05,
+      "loss": 2.5212,
+      "step": 21350
     },
     {
       "epoch": 10.0,
-      "eval_cer": 0.9688311688311688,
-      "eval_loss": 3.2334227561950684,
-      "eval_runtime": 1.6446,
-      "eval_samples_per_second": 127.692,
-      "eval_steps_per_second": 16.418,
-      "eval_wer": 1.0,
-      "step": 34160
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 8.421977073832122e-05,
-      "loss": 2.7732,
-      "step": 68320
-    },
-    {
-      "epoch": 20.0,
-      "eval_cer": 0.9541125541125541,
-      "eval_loss": 3.2456371784210205,
-      "eval_runtime": 1.138,
-      "eval_samples_per_second": 184.54,
-      "eval_steps_per_second": 23.727,
-      "eval_wer": 1.0,
-      "step": 68320
-    },
-    {
-      "epoch": 30.0,
-      "learning_rate": 7.369746086527796e-05,
-      "loss": 2.6976,
-      "step": 102480
-    },
-    {
-      "epoch": 30.0,
-      "eval_cer": 0.9558441558441558,
-      "eval_loss": 3.2558517456054688,
-      "eval_runtime": 1.1494,
-      "eval_samples_per_second": 182.707,
-      "eval_steps_per_second": 23.491,
-      "eval_wer": 1.0,
-      "step": 102480
-    },
-    {
-      "epoch": 40.0,
-      "learning_rate": 6.317545913965241e-05,
-      "loss": 2.6683,
-      "step": 136640
-    },
-    {
-      "epoch": 40.0,
-      "eval_cer": 0.9532467532467532,
-      "eval_loss": 3.264427661895752,
-      "eval_runtime": 1.1405,
-      "eval_samples_per_second": 184.136,
-      "eval_steps_per_second": 23.675,
-      "eval_wer": 1.0,
-      "step": 136640
-    },
-    {
-      "epoch": 50.0,
-      "learning_rate": 5.2653457414026874e-05,
-      "loss": 2.6525,
-      "step": 170800
-    },
-    {
-      "epoch": 50.0,
-      "eval_cer": 0.9549783549783549,
-      "eval_loss": 3.274503469467163,
-      "eval_runtime": 1.1464,
-      "eval_samples_per_second": 183.187,
-      "eval_steps_per_second": 23.553,
-      "eval_wer": 1.0,
-      "step": 170800
-    },
-    {
-      "epoch": 60.0,
-      "learning_rate": 4.213176383581906e-05,
-      "loss": 2.6429,
-      "step": 204960
-    },
-    {
-      "epoch": 60.0,
-      "eval_cer": 0.9532467532467532,
-      "eval_loss": 3.263571262359619,
-      "eval_runtime": 1.1355,
-      "eval_samples_per_second": 184.948,
-      "eval_steps_per_second": 23.779,
-      "eval_wer": 1.0,
-      "step": 204960
-    },
-    {
-      "epoch": 70.0,
-      "learning_rate": 3.160976211019352e-05,
-      "loss": 2.6365,
-      "step": 239120
-    },
-    {
-      "epoch": 70.0,
-      "eval_cer": 0.9532467532467532,
-      "eval_loss": 3.2685256004333496,
-      "eval_runtime": 1.1494,
-      "eval_samples_per_second": 182.699,
-      "eval_steps_per_second": 23.49,
-      "eval_wer": 1.0,
-      "step": 239120
-    },
-    {
-      "epoch": 80.0,
-      "learning_rate": 2.108776038456798e-05,
-      "loss": 2.6334,
-      "step": 273280
-    },
-    {
-      "epoch": 80.0,
-      "eval_cer": 0.9601731601731601,
-      "eval_loss": 3.2787115573883057,
-      "eval_runtime": 1.1465,
-      "eval_samples_per_second": 183.166,
-      "eval_steps_per_second": 23.55,
-      "eval_wer": 1.0,
-      "step": 273280
-    },
-    {
-      "epoch": 90.0,
-      "learning_rate": 1.0565450511524715e-05,
-      "loss": 2.6303,
-      "step": 307440
-    },
-    {
-      "epoch": 90.0,
-      "eval_cer": 0.9601731601731601,
-      "eval_loss": 3.2688238620758057,
-      "eval_runtime": 1.148,
-      "eval_samples_per_second": 182.93,
-      "eval_steps_per_second": 23.52,
-      "eval_wer": 1.0,
-      "step": 307440
-    },
-    {
-      "epoch": 100.0,
-      "learning_rate": 4.3448785899174166e-08,
-      "loss": 2.63,
-      "step": 341600
-    },
-    {
-      "epoch": 100.0,
-      "eval_cer": 0.9619047619047619,
-      "eval_loss": 3.274722099304199,
-      "eval_runtime": 1.1513,
-      "eval_samples_per_second": 182.407,
-      "eval_steps_per_second": 23.452,
-      "eval_wer": 1.0,
-      "step": 341600
+      "eval_cer": 0.587012987012987,
+      "eval_loss": 2.120373010635376,
+      "eval_runtime": 8.074,
+      "eval_samples_per_second": 26.009,
+      "eval_steps_per_second": 3.344,
+      "eval_wer": 0.9952380952380953,
+      "step": 21350
     }
   ],
-  "max_steps": 341600,
+  "max_steps": 213500,
   "num_train_epochs": 100,
-  "total_flos": 3.2456870768043944e+20,
+  "total_flos": 3.2799001703543853e+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 sha256:594585b932be751fb4c7e99db27752222da7b2cc805eb1149ec1dc9adf89f864
-size 3119
+oid sha256:e48be025d9de6e427cd8dae3eec60c35384929891f8fc67a0b488ae5ade59c15
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b522e60d0d2a6ee27af3602669b1014da231da2f41574acaad118912eceeb40a
-size 377644503
+oid sha256:23c29e7e62821dd9ebdecb0f80999e35b88a4c33b2f765c44a4a3067dd06ef8a
+size 377646433

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594585b932be751fb4c7e99db27752222da7b2cc805eb1149ec1dc9adf89f864
-size 3119
+oid sha256:e48be025d9de6e427cd8dae3eec60c35384929891f8fc67a0b488ae5ade59c15
+size 3451