Training in progress, step 25800

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:ac937a33dea6ea7a219a5d92302391d3b62c72a19f9ff5c54c2bed1c61cdffac
-size 168159
+oid sha256:83701acb6b969bf186789b560373efc2306622973b3c28a8ae14621fa8ea2af9
+size 168299

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970781c36183b1552822b1fd90733e765d39fc56d7e083aa21858cc68f2befee
-size 377641431
+oid sha256:7e53a60ab51721dbacf39cfe0fd8f5d7e000d712c291b9c6468f589550314653
+size 377643361

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bc4c868be43b8aee478444845fee509627b8673243a867ffa21afdae158b023
-size 14567
+oid sha256:6bedc183fe4b3bee6a401ca9cd239cd2f5a261e21b1e0d0d190c9670c2192b2c
+size 14639

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7828115df4dda4d48eed4e47399971a9187269fd1c501ef2b68aaf29a23048
-size 559
+oid sha256:fca9a24db2a129accee9ab827e1ed658add9ad4e2fd21ae130da0a36eb96656d
+size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3fd97d7f7086d7e8d98ca6ed02a950b267fc075dbd24b6b2d7d971d9f49782e
-size 623
+oid sha256:384a9da4de591fb6eb7e3456e25f511cec76615b35d913dc0427c74b105c1704
+size 627

last-checkpoint/trainer_state.json

@@ -1,176 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1000.0,
-  "global_step": 258000,
+  "epoch": 100.0,
+  "global_step": 25800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 100.0,
-      "learning_rate": 9.47421460628315e-05,
-      "loss": 13.3002,
+      "learning_rate": 0.0004737107303141575,
+      "loss": 7.8597,
       "step": 25800
     },
     {
       "epoch": 100.0,
-      "eval_cer": 0.9238095238095239,
-      "eval_loss": 2.9116570949554443,
-      "eval_runtime": 1.0237,
-      "eval_samples_per_second": 205.13,
-      "eval_steps_per_second": 26.374,
+      "eval_cer": 0.8900432900432901,
+      "eval_loss": 2.9528822898864746,
+      "eval_runtime": 7.7723,
+      "eval_samples_per_second": 27.019,
+      "eval_steps_per_second": 3.474,
       "eval_wer": 1.0,
       "step": 25800
-    },
-    {
-      "epoch": 200.0,
-      "learning_rate": 8.422072623419012e-05,
-      "loss": 2.265,
-      "step": 51600
-    },
-    {
-      "epoch": 200.0,
-      "eval_cer": 0.8943722943722944,
-      "eval_loss": 2.9009172916412354,
-      "eval_runtime": 1.0094,
-      "eval_samples_per_second": 208.04,
-      "eval_steps_per_second": 26.748,
-      "eval_wer": 1.0,
-      "step": 51600
-    },
-    {
-      "epoch": 300.0,
-      "learning_rate": 7.369889840881273e-05,
-      "loss": 2.1533,
-      "step": 77400
-    },
-    {
-      "epoch": 300.0,
-      "eval_cer": 0.8943722943722944,
-      "eval_loss": 2.9222800731658936,
-      "eval_runtime": 1.046,
-      "eval_samples_per_second": 200.77,
-      "eval_steps_per_second": 25.813,
-      "eval_wer": 1.0,
-      "step": 77400
-    },
-    {
-      "epoch": 400.0,
-      "learning_rate": 6.317747858017135e-05,
-      "loss": 2.0998,
-      "step": 103200
-    },
-    {
-      "epoch": 400.0,
-      "eval_cer": 0.8891774891774892,
-      "eval_loss": 2.927011489868164,
-      "eval_runtime": 1.0056,
-      "eval_samples_per_second": 208.822,
-      "eval_steps_per_second": 26.849,
-      "eval_wer": 1.0,
-      "step": 103200
-    },
-    {
-      "epoch": 500.0,
-      "learning_rate": 5.265565075479396e-05,
-      "loss": 2.0687,
-      "step": 129000
-    },
-    {
-      "epoch": 500.0,
-      "eval_cer": 0.8891774891774892,
-      "eval_loss": 2.9528825283050537,
-      "eval_runtime": 1.0218,
-      "eval_samples_per_second": 205.522,
-      "eval_steps_per_second": 26.424,
-      "eval_wer": 1.0,
-      "step": 129000
-    },
-    {
-      "epoch": 600.0,
-      "learning_rate": 4.2133822929416564e-05,
-      "loss": 2.0491,
-      "step": 154800
-    },
-    {
-      "epoch": 600.0,
-      "eval_cer": 0.8883116883116883,
-      "eval_loss": 2.966721296310425,
-      "eval_runtime": 1.0092,
-      "eval_samples_per_second": 208.075,
-      "eval_steps_per_second": 26.753,
-      "eval_wer": 1.0,
-      "step": 154800
-    },
-    {
-      "epoch": 700.0,
-      "learning_rate": 3.1611995104039174e-05,
-      "loss": 2.0368,
-      "step": 180600
-    },
-    {
-      "epoch": 700.0,
-      "eval_cer": 0.8874458874458875,
-      "eval_loss": 2.9711692333221436,
-      "eval_runtime": 1.0054,
-      "eval_samples_per_second": 208.874,
-      "eval_steps_per_second": 26.855,
-      "eval_wer": 1.0,
-      "step": 180600
-    },
-    {
-      "epoch": 800.0,
-      "learning_rate": 2.1089759281925745e-05,
-      "loss": 2.0271,
-      "step": 206400
-    },
-    {
-      "epoch": 800.0,
-      "eval_cer": 0.8874458874458875,
-      "eval_loss": 2.976341724395752,
-      "eval_runtime": 1.0209,
-      "eval_samples_per_second": 205.708,
-      "eval_steps_per_second": 26.448,
-      "eval_wer": 1.0,
-      "step": 206400
-    },
-    {
-      "epoch": 900.0,
-      "learning_rate": 1.0567523459812321e-05,
-      "loss": 2.0223,
-      "step": 232200
-    },
-    {
-      "epoch": 900.0,
-      "eval_cer": 0.8883116883116883,
-      "eval_loss": 2.9786393642425537,
-      "eval_runtime": 1.0096,
-      "eval_samples_per_second": 207.998,
-      "eval_steps_per_second": 26.743,
-      "eval_wer": 1.0,
-      "step": 232200
-    },
-    {
-      "epoch": 1000.0,
-      "learning_rate": 4.569563443492452e-08,
-      "loss": 2.0195,
-      "step": 258000
-    },
-    {
-      "epoch": 1000.0,
-      "eval_cer": 0.8883116883116883,
-      "eval_loss": 2.979724645614624,
-      "eval_runtime": 0.9979,
-      "eval_samples_per_second": 210.433,
-      "eval_steps_per_second": 27.056,
-      "eval_wer": 1.0,
-      "step": 258000
     }
   ],
   "max_steps": 258000,
   "num_train_epochs": 1000,
-  "total_flos": 2.393792072555994e+20,
+  "total_flos": 2.393393666838634e+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 sha256:04ede9c1209942d838657385fae4d8de498ffc12e29e19e23dbbe5f1462ebc93
-size 3119
+oid sha256:cceccd22d2aabb29bc215bed86135bf7eb5b60193a7883cd6d1ae8c8d22b66a1
+size 3387

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970781c36183b1552822b1fd90733e765d39fc56d7e083aa21858cc68f2befee
-size 377641431
+oid sha256:7e53a60ab51721dbacf39cfe0fd8f5d7e000d712c291b9c6468f589550314653
+size 377643361

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ede9c1209942d838657385fae4d8de498ffc12e29e19e23dbbe5f1462ebc93
-size 3119
+oid sha256:cceccd22d2aabb29bc215bed86135bf7eb5b60193a7883cd6d1ae8c8d22b66a1
+size 3387