Training in progress, step 6220

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:f3333ee8e53af6b1f85bcd67c929a51ec25d553108f47034bd343e26211f8a32
-size 174303
+oid sha256:927f431de7ce4e1ea9c341f8117ca3748190de20455628b650b57805a47bfbe1
+size 721661957

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f32a40766506810aeb69e5aff37fb21a6951556747267b8b3d151d03dea2616
-size 377644503
+oid sha256:2f3e0c86203048b55a478f0d5d6f563a4886d3d79134deab79ef29ea87f55197
+size 377646433

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370432457d1899c6918618be0ebb3c1ad372c7a0deee55d5ebd556abf838be44
-size 14567
+oid sha256:5ad1f76f42c6b6db74eff6108567b57feed75b7f920793f46fb271d321687bec
+size 14703

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f68c7cae533afea841f7981dbe73911683ef32c6ec89d7710d32dbdc3c08462
-size 559
+oid sha256:cda56571df27698319b374c2d8c5a88b0f34877e85fb00c92caccf17f01645df
+size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cff7900d8bc1e4ddaeb333afa964d4173b26154ba7e42e952ecc04b0838218a
-size 623
+oid sha256:34adf423566f00eb1ba5621161b4351c08313bd50e3c016789c25bb5f425ae85
+size 627

last-checkpoint/trainer_state.json

@@ -1,176 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 250.0,
-  "global_step": 124500,
+  "epoch": 10.0,
+  "global_step": 6220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 25.0,
-      "learning_rate": 9.474360600295921e-05,
-      "loss": 19.6049,
-      "step": 12450
+      "epoch": 10.0,
+      "learning_rate": 9.475038077508885e-05,
+      "loss": 4.7101,
+      "step": 6220
     },
     {
-      "epoch": 25.0,
-      "eval_cer": 0.9922077922077922,
-      "eval_loss": 3.1665115356445312,
-      "eval_runtime": 1.0509,
-      "eval_samples_per_second": 199.825,
-      "eval_steps_per_second": 25.692,
+      "epoch": 10.0,
+      "eval_cer": 0.7567099567099567,
+      "eval_loss": 5.277076244354248,
+      "eval_runtime": 7.9435,
+      "eval_samples_per_second": 26.437,
+      "eval_steps_per_second": 3.399,
       "eval_wer": 1.0,
-      "step": 12450
-    },
-    {
-      "epoch": 50.0,
-      "learning_rate": 8.422067216233354e-05,
-      "loss": 2.746,
-      "step": 24900
-    },
-    {
-      "epoch": 50.0,
-      "eval_cer": 0.9489177489177489,
-      "eval_loss": 3.065709352493286,
-      "eval_runtime": 1.0247,
-      "eval_samples_per_second": 204.941,
-      "eval_steps_per_second": 26.35,
-      "eval_wer": 1.0,
-      "step": 24900
-    },
-    {
-      "epoch": 75.0,
-      "learning_rate": 7.36994292961319e-05,
-      "loss": 2.5773,
-      "step": 37350
-    },
-    {
-      "epoch": 75.0,
-      "eval_cer": 0.929004329004329,
-      "eval_loss": 3.0779831409454346,
-      "eval_runtime": 1.0289,
-      "eval_samples_per_second": 204.093,
-      "eval_steps_per_second": 26.241,
-      "eval_wer": 1.0,
-      "step": 37350
-    },
-    {
-      "epoch": 100.0,
-      "learning_rate": 6.317734094271824e-05,
-      "loss": 2.511,
-      "step": 49800
-    },
-    {
-      "epoch": 100.0,
-      "eval_cer": 0.9333333333333333,
-      "eval_loss": 3.0956246852874756,
-      "eval_runtime": 1.0323,
-      "eval_samples_per_second": 203.432,
-      "eval_steps_per_second": 26.155,
-      "eval_wer": 1.0,
-      "step": 49800
-    },
-    {
-      "epoch": 125.0,
-      "learning_rate": 5.265609807651659e-05,
-      "loss": 2.4727,
-      "step": 62250
-    },
-    {
-      "epoch": 125.0,
-      "eval_cer": 0.9341991341991343,
-      "eval_loss": 3.10306978225708,
-      "eval_runtime": 1.0322,
-      "eval_samples_per_second": 203.454,
-      "eval_steps_per_second": 26.158,
-      "eval_wer": 1.0,
-      "step": 62250
-    },
-    {
-      "epoch": 150.0,
-      "learning_rate": 4.213400972310294e-05,
-      "loss": 2.449,
-      "step": 74700
-    },
-    {
-      "epoch": 150.0,
-      "eval_cer": 0.9316017316017317,
-      "eval_loss": 3.1064517498016357,
-      "eval_runtime": 1.0551,
-      "eval_samples_per_second": 199.032,
-      "eval_steps_per_second": 25.59,
-      "eval_wer": 1.0,
-      "step": 74700
-    },
-    {
-      "epoch": 175.0,
-      "learning_rate": 3.161276685690129e-05,
-      "loss": 2.4326,
-      "step": 87150
-    },
-    {
-      "epoch": 175.0,
-      "eval_cer": 0.9333333333333333,
-      "eval_loss": 3.1083292961120605,
-      "eval_runtime": 1.0455,
-      "eval_samples_per_second": 200.864,
-      "eval_steps_per_second": 25.825,
-      "eval_wer": 1.0,
-      "step": 87150
-    },
-    {
-      "epoch": 200.0,
-      "learning_rate": 2.1090678503487633e-05,
-      "loss": 2.4226,
-      "step": 99600
-    },
-    {
-      "epoch": 200.0,
-      "eval_cer": 0.9341991341991343,
-      "eval_loss": 3.1126484870910645,
-      "eval_runtime": 1.0516,
-      "eval_samples_per_second": 199.703,
-      "eval_steps_per_second": 25.676,
-      "eval_wer": 1.0,
-      "step": 99600
-    },
-    {
-      "epoch": 225.0,
-      "learning_rate": 1.056859015007398e-05,
-      "loss": 2.4151,
-      "step": 112050
-    },
-    {
-      "epoch": 225.0,
-      "eval_cer": 0.9341991341991343,
-      "eval_loss": 3.1124825477600098,
-      "eval_runtime": 1.0358,
-      "eval_samples_per_second": 202.734,
-      "eval_steps_per_second": 26.066,
-      "eval_wer": 1.0,
-      "step": 112050
-    },
-    {
-      "epoch": 250.0,
-      "learning_rate": 4.7347283872331434e-08,
-      "loss": 2.4121,
-      "step": 124500
-    },
-    {
-      "epoch": 250.0,
-      "eval_cer": 0.935064935064935,
-      "eval_loss": 3.11251163482666,
-      "eval_runtime": 0.9891,
-      "eval_samples_per_second": 212.307,
-      "eval_steps_per_second": 27.297,
-      "eval_wer": 1.0,
-      "step": 124500
+      "step": 6220
     }
   ],
-  "max_steps": 124500,
-  "num_train_epochs": 250,
-  "total_flos": 1.1522414746503514e+20,
+  "max_steps": 62200,
+  "num_train_epochs": 100,
+  "total_flos": 4.6105604043819725e+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 sha256:94a3a3e4c9721bb45336b089b084f2a9f706b1e615467edde5761ec2a859776b
-size 3119
+oid sha256:a7620f2dba0add0f24529ee099e5753c390b45d9c00db8a63639e26ef90afc6f
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f32a40766506810aeb69e5aff37fb21a6951556747267b8b3d151d03dea2616
-size 377644503
+oid sha256:2f3e0c86203048b55a478f0d5d6f563a4886d3d79134deab79ef29ea87f55197
+size 377646433

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a3a3e4c9721bb45336b089b084f2a9f706b1e615467edde5761ec2a859776b
-size 3119
+oid sha256:a7620f2dba0add0f24529ee099e5753c390b45d9c00db8a63639e26ef90afc6f
+size 3451