Training in progress, step 42810

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:c6ac29af520d5b2c069e2f7210724ba20e90c5f6f39bc3151aa9d5293bef63a0
-size 168159
+oid sha256:abd1f7f1d403297755f3d5195182f64066b3cbb14ad9df999173a8b2f6e7e8ea
+size 721655813

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2015c73f6c80fbd0a2ba632ff719eda3740f56cbcaf2a3e5487334058ef0a285
-size 377641431
+oid sha256:0181507564a84d0fc009847c4a6d46858cec8fce11b23062e1354e25fc731f5c
+size 377643361

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9cb857b45444ea61e5d59104fd2a2497b5a0c76c5450fc0dec3c98b46cbf46b
-size 14567
+oid sha256:aaff527cca738862a3889886f51982fcadd6245064e289441c0eaa95ec6106e0
+size 14639

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b4faa452efd0a4a469d55ad9c163be9464d5bc46c60bd640b8de4bf05f76ce
-size 559
+oid sha256:97493d56a553721cad772ef2f326ac53e7a9868c5f23452c6a85ca3f0f2d22ee
+size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66dfc18c5043e3149c14c5c2e4388023eb1538d8f034288e82cfe5d1c38745f5
-size 623
+oid sha256:f49cc27f208749ba85176e054a1f70b78d9840311ad2659b2725be6de92e8534
+size 627

last-checkpoint/trainer_state.json

@@ -1,176 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 100.0,
-  "global_step": 342500,
+  "epoch": 10.0,
+  "global_step": 42810,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 10.0,
-      "learning_rate": 9.474237418363428e-05,
-      "loss": 13.0104,
-      "step": 34250
+      "learning_rate": 9.474151391091605e-05,
+      "loss": 2.6003,
+      "step": 42810
     },
     {
       "epoch": 10.0,
-      "eval_cer": 0.9922077922077922,
-      "eval_loss": 3.114701747894287,
-      "eval_runtime": 0.6909,
-      "eval_samples_per_second": 202.628,
-      "eval_steps_per_second": 26.052,
-      "eval_wer": 1.0,
-      "step": 34250
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 8.422005378409528e-05,
-      "loss": 2.7462,
-      "step": 68500
-    },
-    {
-      "epoch": 20.0,
-      "eval_cer": 0.9896103896103896,
-      "eval_loss": 3.1291749477386475,
-      "eval_runtime": 0.6768,
-      "eval_samples_per_second": 206.855,
-      "eval_steps_per_second": 26.596,
-      "eval_wer": 1.0,
-      "step": 68500
-    },
-    {
-      "epoch": 30.0,
-      "learning_rate": 7.369804072224357e-05,
-      "loss": 2.676,
-      "step": 102750
-    },
-    {
-      "epoch": 30.0,
-      "eval_cer": 0.987012987012987,
-      "eval_loss": 3.133396863937378,
-      "eval_runtime": 0.6746,
-      "eval_samples_per_second": 207.544,
-      "eval_steps_per_second": 26.684,
-      "eval_wer": 1.0,
-      "step": 102750
-    },
-    {
-      "epoch": 40.0,
-      "learning_rate": 6.317572032270458e-05,
-      "loss": 2.649,
-      "step": 137000
-    },
-    {
-      "epoch": 40.0,
-      "eval_cer": 0.9831168831168832,
-      "eval_loss": 3.13140869140625,
-      "eval_runtime": 0.6742,
-      "eval_samples_per_second": 207.644,
-      "eval_steps_per_second": 26.697,
-      "eval_wer": 1.0,
-      "step": 137000
-    },
-    {
-      "epoch": 50.0,
-      "learning_rate": 5.2652785247791016e-05,
-      "loss": 2.6338,
-      "step": 171250
-    },
-    {
-      "epoch": 50.0,
-      "eval_cer": 0.9844155844155844,
-      "eval_loss": 3.1373016834259033,
-      "eval_runtime": 0.6758,
-      "eval_samples_per_second": 207.177,
-      "eval_steps_per_second": 26.637,
-      "eval_wer": 1.0,
-      "step": 171250
-    },
-    {
-      "epoch": 60.0,
-      "learning_rate": 4.213107952362659e-05,
-      "loss": 2.6245,
-      "step": 205500
-    },
-    {
-      "epoch": 60.0,
-      "eval_cer": 0.9831168831168832,
-      "eval_loss": 3.1429381370544434,
-      "eval_runtime": 0.6795,
-      "eval_samples_per_second": 206.043,
-      "eval_steps_per_second": 26.491,
-      "eval_wer": 1.0,
-      "step": 205500
-    },
-    {
-      "epoch": 70.0,
-      "learning_rate": 3.160937379946216e-05,
-      "loss": 2.619,
-      "step": 239750
-    },
-    {
-      "epoch": 70.0,
-      "eval_cer": 0.9831168831168832,
-      "eval_loss": 3.1534180641174316,
-      "eval_runtime": 0.6752,
-      "eval_samples_per_second": 207.339,
-      "eval_steps_per_second": 26.658,
-      "eval_wer": 1.0,
-      "step": 239750
-    },
-    {
-      "epoch": 80.0,
-      "learning_rate": 2.108705339992317e-05,
-      "loss": 2.6147,
-      "step": 274000
-    },
-    {
-      "epoch": 80.0,
-      "eval_cer": 0.9844155844155844,
-      "eval_loss": 3.146252155303955,
-      "eval_runtime": 0.6763,
-      "eval_samples_per_second": 207.007,
-      "eval_steps_per_second": 26.615,
-      "eval_wer": 1.0,
-      "step": 274000
-    },
-    {
-      "epoch": 90.0,
-      "learning_rate": 1.056534767575874e-05,
-      "loss": 2.6115,
-      "step": 308250
-    },
-    {
-      "epoch": 90.0,
-      "eval_cer": 0.9831168831168832,
-      "eval_loss": 3.1405744552612305,
-      "eval_runtime": 0.6771,
-      "eval_samples_per_second": 206.768,
-      "eval_steps_per_second": 26.584,
-      "eval_wer": 1.0,
-      "step": 308250
-    },
-    {
-      "epoch": 100.0,
-      "learning_rate": 4.333461390703035e-08,
-      "loss": 2.6102,
-      "step": 342500
-    },
-    {
-      "epoch": 100.0,
-      "eval_cer": 0.9831168831168832,
-      "eval_loss": 3.1426713466644287,
-      "eval_runtime": 0.6615,
-      "eval_samples_per_second": 211.646,
-      "eval_steps_per_second": 27.212,
-      "eval_wer": 1.0,
-      "step": 342500
+      "eval_cer": 0.8103896103896104,
+      "eval_loss": 4.999092102050781,
+      "eval_runtime": 5.1797,
+      "eval_samples_per_second": 27.029,
+      "eval_steps_per_second": 3.475,
+      "eval_wer": 0.9142857142857143,
+      "step": 42810
     }
   ],
-  "max_steps": 342500,
+  "max_steps": 428100,
   "num_train_epochs": 100,
-  "total_flos": 3.2538079241368614e+20,
+  "total_flos": 3.2399059329860952e+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 sha256:4bcd8c032f4a5e4bcadd8bc2ab6e77f3af4dc94f7fcec7d8f1bbc6210bc9d629
-size 3119
+oid sha256:b9145f12772e3151c498dd0872c61d0f5e569349f097fa28226c40c4cf0a531a
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2015c73f6c80fbd0a2ba632ff719eda3740f56cbcaf2a3e5487334058ef0a285
-size 377641431
+oid sha256:0181507564a84d0fc009847c4a6d46858cec8fce11b23062e1354e25fc731f5c
+size 377643361

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bcd8c032f4a5e4bcadd8bc2ab6e77f3af4dc94f7fcec7d8f1bbc6210bc9d629
-size 3119
+oid sha256:b9145f12772e3151c498dd0872c61d0f5e569349f097fa28226c40c4cf0a531a
+size 3451