Training in progress, step 10000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c2be3452d8137d689d35c0df6e890c78020bf9843bc1e5ee746f483f22d91d
+oid sha256:91a8bc4af41578250a3b744334e77d523696c897dbeb1f992605c463a67991ec
 size 2524414853

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2f9145d655487602d0119001d797a278a1eb42e4a3b0bd88e042a0adbe3136
+oid sha256:611a34e0242d2ec649f0d1a86165d8423ae4a1d7e81641c0d56c2019e5ef6450
 size 1262229869

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a396db9e5798714b943d735d77ab7ab39ac707fd4daa400a37b45acbc4d16e
-size 14639
+oid sha256:6a300d66a0192b31de2f7c8bff794f15d013787aa64770ba8b66b59e79dd7ee3
+size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b0809e95e7bb66d8269d06cf0ed6189035774c3ca188b731868d7c85cab50
+oid sha256:2a8805627ff330405ad609ba9ab7315667856758f8bf2f6a02771e64b1ec5ccb
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.065048427597752,
-  "best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-9000",
-  "epoch": 79.64601769911505,
-  "global_step": 9000,
+  "best_metric": 0.06361353581250748,
+  "best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-10000",
+  "epoch": 88.49557522123894,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2247,11 +2247,260 @@
       "eval_steps_per_second": 1.201,
       "eval_wer": 0.065048427597752,
       "step": 9000
+    },
+    {
+      "epoch": 79.87,
+      "learning_rate": 3.078947368421052e-05,
+      "loss": 0.0052,
+      "step": 9025
+    },
+    {
+      "epoch": 80.09,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 0.0053,
+      "step": 9050
+    },
+    {
+      "epoch": 80.31,
+      "learning_rate": 2.921052631578947e-05,
+      "loss": 0.0049,
+      "step": 9075
+    },
+    {
+      "epoch": 80.53,
+      "learning_rate": 2.8421052631578946e-05,
+      "loss": 0.0049,
+      "step": 9100
+    },
+    {
+      "epoch": 80.75,
+      "learning_rate": 2.7631578947368416e-05,
+      "loss": 0.0045,
+      "step": 9125
+    },
+    {
+      "epoch": 80.97,
+      "learning_rate": 2.6842105263157892e-05,
+      "loss": 0.0053,
+      "step": 9150
+    },
+    {
+      "epoch": 81.19,
+      "learning_rate": 2.605263157894737e-05,
+      "loss": 0.0051,
+      "step": 9175
+    },
+    {
+      "epoch": 81.42,
+      "learning_rate": 2.5263157894736838e-05,
+      "loss": 0.0056,
+      "step": 9200
+    },
+    {
+      "epoch": 81.64,
+      "learning_rate": 2.4473684210526314e-05,
+      "loss": 0.0056,
+      "step": 9225
+    },
+    {
+      "epoch": 81.86,
+      "learning_rate": 2.3684210526315787e-05,
+      "loss": 0.0047,
+      "step": 9250
+    },
+    {
+      "epoch": 82.08,
+      "learning_rate": 2.289473684210526e-05,
+      "loss": 0.0072,
+      "step": 9275
+    },
+    {
+      "epoch": 82.3,
+      "learning_rate": 2.2105263157894733e-05,
+      "loss": 0.0055,
+      "step": 9300
+    },
+    {
+      "epoch": 82.52,
+      "learning_rate": 2.131578947368421e-05,
+      "loss": 0.005,
+      "step": 9325
+    },
+    {
+      "epoch": 82.74,
+      "learning_rate": 2.0526315789473685e-05,
+      "loss": 0.0035,
+      "step": 9350
+    },
+    {
+      "epoch": 82.96,
+      "learning_rate": 1.9736842105263155e-05,
+      "loss": 0.0052,
+      "step": 9375
+    },
+    {
+      "epoch": 83.19,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 0.0046,
+      "step": 9400
+    },
+    {
+      "epoch": 83.41,
+      "learning_rate": 1.8157894736842104e-05,
+      "loss": 0.0056,
+      "step": 9425
+    },
+    {
+      "epoch": 83.63,
+      "learning_rate": 1.7368421052631577e-05,
+      "loss": 0.005,
+      "step": 9450
+    },
+    {
+      "epoch": 83.85,
+      "learning_rate": 1.657894736842105e-05,
+      "loss": 0.0046,
+      "step": 9475
+    },
+    {
+      "epoch": 84.07,
+      "learning_rate": 1.5789473684210522e-05,
+      "loss": 0.0061,
+      "step": 9500
+    },
+    {
+      "epoch": 84.29,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 0.0051,
+      "step": 9525
+    },
+    {
+      "epoch": 84.51,
+      "learning_rate": 1.4210526315789473e-05,
+      "loss": 0.0033,
+      "step": 9550
+    },
+    {
+      "epoch": 84.73,
+      "learning_rate": 1.3421052631578946e-05,
+      "loss": 0.0035,
+      "step": 9575
+    },
+    {
+      "epoch": 84.96,
+      "learning_rate": 1.2631578947368419e-05,
+      "loss": 0.0054,
+      "step": 9600
+    },
+    {
+      "epoch": 85.18,
+      "learning_rate": 1.1842105263157894e-05,
+      "loss": 0.005,
+      "step": 9625
+    },
+    {
+      "epoch": 85.4,
+      "learning_rate": 1.1052631578947366e-05,
+      "loss": 0.0039,
+      "step": 9650
+    },
+    {
+      "epoch": 85.62,
+      "learning_rate": 1.0263157894736843e-05,
+      "loss": 0.0044,
+      "step": 9675
+    },
+    {
+      "epoch": 85.84,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 0.0049,
+      "step": 9700
+    },
+    {
+      "epoch": 86.06,
+      "learning_rate": 8.684210526315788e-06,
+      "loss": 0.0042,
+      "step": 9725
+    },
+    {
+      "epoch": 86.28,
+      "learning_rate": 7.894736842105261e-06,
+      "loss": 0.0041,
+      "step": 9750
+    },
+    {
+      "epoch": 86.5,
+      "learning_rate": 7.105263157894737e-06,
+      "loss": 0.0036,
+      "step": 9775
+    },
+    {
+      "epoch": 86.73,
+      "learning_rate": 6.3157894736842095e-06,
+      "loss": 0.0037,
+      "step": 9800
+    },
+    {
+      "epoch": 86.95,
+      "learning_rate": 5.526315789473683e-06,
+      "loss": 0.005,
+      "step": 9825
+    },
+    {
+      "epoch": 87.17,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.0047,
+      "step": 9850
+    },
+    {
+      "epoch": 87.39,
+      "learning_rate": 3.947368421052631e-06,
+      "loss": 0.0039,
+      "step": 9875
+    },
+    {
+      "epoch": 87.61,
+      "learning_rate": 3.1578947368421047e-06,
+      "loss": 0.0041,
+      "step": 9900
+    },
+    {
+      "epoch": 87.83,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.0052,
+      "step": 9925
+    },
+    {
+      "epoch": 88.05,
+      "learning_rate": 1.5789473684210524e-06,
+      "loss": 0.0041,
+      "step": 9950
+    },
+    {
+      "epoch": 88.27,
+      "learning_rate": 7.894736842105262e-07,
+      "loss": 0.004,
+      "step": 9975
+    },
+    {
+      "epoch": 88.5,
+      "learning_rate": 0.0,
+      "loss": 0.0033,
+      "step": 10000
+    },
+    {
+      "epoch": 88.5,
+      "eval_loss": 0.32122763991355896,
+      "eval_runtime": 10.9251,
+      "eval_samples_per_second": 9.153,
+      "eval_steps_per_second": 1.19,
+      "eval_wer": 0.06361353581250748,
+      "step": 10000
     }
   ],
   "max_steps": 10000,
   "num_train_epochs": 89,
-  "total_flos": 3.5456385787518284e+19,
+  "total_flos": 3.937659402470073e+19,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2f9145d655487602d0119001d797a278a1eb42e4a3b0bd88e042a0adbe3136
+oid sha256:611a34e0242d2ec649f0d1a86165d8423ae4a1d7e81641c0d56c2019e5ef6450
 size 1262229869

runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5ae4f462216938e728a8fba4681e7f5455b3d2c2795cb02eb92e4c0cd05237
-size 64764
+oid sha256:6406d5a68ae370ad6e03e2fd256a904caa05f4dcec974cccfa689cc8778c1dde
+size 71362