Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mprzibilla/large_base_M14",
+  "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mprzibilla/large_base_M14",
+  "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2e35834074f19bc5222d3c8af123732ecaf310f7c9f23dccd514a0fefc4c57
-size 174443
+oid sha256:213bb0e0a90d5954b503e688cc3c3a9aa15741ebd8a352784b1ba115f324844d
+size 721661957

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdd83bce0be94c1d45bb977937e9084dac2cb76e797eac4044daa3dc8639b22
+oid sha256:8c1450349389d08ad66823b39334b010395a34ccee54ae96db36aa7efca4b3e3
 size 377646433

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d5ccf1b0ffdd4638e6e2647e36a4f32f89f322ea80cdd67e65f7a7c51f6a0c
+oid sha256:58da74621a4bbb5bbbe8b99cb57ffcf083b444d150e3a3a43ef88eb4f947ea0d
 size 14639

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614dcd144644e40eeba8333744c7822a05c774de62a1e066c6cfdf0f6212d9b6
+oid sha256:e3439e56a6be40162c72ef7587f90cdd2fae59b61ca49cc3743f83ca19cfdd8b
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29d56619f19dd624dc3d9ce779248fcca781dca28f83547cd64f3f5a24ff43b
+oid sha256:69329aa5f5ce6722e627e837927ad2e18f7a9b9c2acd8a4165059b6ad1f66c71
 size 627

last-checkpoint/trainer_state.json

@@ -1,271 +1,33 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.0,
-  "global_step": 64050,
+  "epoch": 1.0,
+  "global_step": 4270,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 9.826288456481726e-05,
-      "loss": 37.9017,
+      "learning_rate": 9.825795424664739e-05,
+      "loss": 7.898,
       "step": 4270
     },
     {
       "epoch": 1.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.8080713748931885,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.7466,
-      "eval_samples_per_second": 27.109,
-      "eval_steps_per_second": 3.485,
+      "eval_cer": 0.18354978354978355,
+      "eval_loss": 0.892418622970581,
+      "eval_new_wer": 0.1,
+      "eval_old_wer": 0.4714285714285714,
+      "eval_runtime": 8.5895,
+      "eval_samples_per_second": 24.448,
+      "eval_steps_per_second": 3.143,
       "step": 4270
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 9.124539836970814e-05,
-      "loss": 3.3383,
-      "step": 8540
-    },
-    {
-      "epoch": 2.0,
-      "eval_cer": 1.0,
-      "eval_loss": 3.6899821758270264,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.6904,
-      "eval_samples_per_second": 27.307,
-      "eval_steps_per_second": 3.511,
-      "step": 8540
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 8.4227912174599e-05,
-      "loss": 3.2564,
-      "step": 12810
-    },
-    {
-      "epoch": 3.0,
-      "eval_cer": 0.9982683982683983,
-      "eval_loss": 3.388317823410034,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.7217,
-      "eval_samples_per_second": 27.196,
-      "eval_steps_per_second": 3.497,
-      "step": 12810
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 7.721042597948987e-05,
-      "loss": 3.104,
-      "step": 17080
-    },
-    {
-      "epoch": 4.0,
-      "eval_cer": 0.9939393939393939,
-      "eval_loss": 3.202686071395874,
-      "eval_new_wer": 1.0,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.9831,
-      "eval_samples_per_second": 26.306,
-      "eval_steps_per_second": 3.382,
-      "step": 17080
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 7.019622666316067e-05,
-      "loss": 2.997,
-      "step": 21350
-    },
-    {
-      "epoch": 5.0,
-      "eval_cer": 0.9904761904761905,
-      "eval_loss": 3.177474021911621,
-      "eval_new_wer": 0.9904761904761905,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.7653,
-      "eval_samples_per_second": 27.043,
-      "eval_steps_per_second": 3.477,
-      "step": 21350
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 6.318202734683146e-05,
-      "loss": 2.9391,
-      "step": 25620
-    },
-    {
-      "epoch": 6.0,
-      "eval_cer": 0.9861471861471861,
-      "eval_loss": 3.1568691730499268,
-      "eval_new_wer": 0.9809523809523809,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.7615,
-      "eval_samples_per_second": 27.057,
-      "eval_steps_per_second": 3.479,
-      "step": 25620
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 5.616782803050224e-05,
-      "loss": 2.8989,
-      "step": 29890
-    },
-    {
-      "epoch": 7.0,
-      "eval_cer": 0.9766233766233766,
-      "eval_loss": 3.164285182952881,
-      "eval_new_wer": 0.9714285714285714,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.8832,
-      "eval_samples_per_second": 26.639,
-      "eval_steps_per_second": 3.425,
-      "step": 29890
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 4.9153628714173024e-05,
-      "loss": 2.8731,
-      "step": 34160
-    },
-    {
-      "epoch": 8.0,
-      "eval_cer": 0.9670995670995671,
-      "eval_loss": 3.1436803340911865,
-      "eval_new_wer": 0.9523809523809523,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.7748,
-      "eval_samples_per_second": 27.01,
-      "eval_steps_per_second": 3.473,
-      "step": 34160
-    },
-    {
-      "epoch": 9.0,
-      "learning_rate": 4.213778595845386e-05,
-      "loss": 2.8549,
-      "step": 38430
-    },
-    {
-      "epoch": 9.0,
-      "eval_cer": 0.9645021645021645,
-      "eval_loss": 3.1454625129699707,
-      "eval_new_wer": 0.9428571428571428,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.8309,
-      "eval_samples_per_second": 26.817,
-      "eval_steps_per_second": 3.448,
-      "step": 38430
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 3.512358664212464e-05,
-      "loss": 2.8407,
-      "step": 42700
-    },
-    {
-      "epoch": 10.0,
-      "eval_cer": 0.9627705627705627,
-      "eval_loss": 3.1407470703125,
-      "eval_new_wer": 0.9380952380952381,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.787,
-      "eval_samples_per_second": 26.968,
-      "eval_steps_per_second": 3.467,
-      "step": 42700
-    },
-    {
-      "epoch": 11.0,
-      "learning_rate": 2.8107743886405467e-05,
-      "loss": 2.8301,
-      "step": 46970
-    },
-    {
-      "epoch": 11.0,
-      "eval_cer": 0.9601731601731601,
-      "eval_loss": 3.141080141067505,
-      "eval_new_wer": 0.9333333333333333,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.8547,
-      "eval_samples_per_second": 26.735,
-      "eval_steps_per_second": 3.437,
-      "step": 46970
-    },
-    {
-      "epoch": 12.0,
-      "learning_rate": 2.1093544570076258e-05,
-      "loss": 2.8215,
-      "step": 51240
-    },
-    {
-      "epoch": 12.0,
-      "eval_cer": 0.9601731601731601,
-      "eval_loss": 3.1361286640167236,
-      "eval_new_wer": 0.9380952380952381,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.7971,
-      "eval_samples_per_second": 26.933,
-      "eval_steps_per_second": 3.463,
-      "step": 51240
-    },
-    {
-      "epoch": 13.0,
-      "learning_rate": 1.4079345253747043e-05,
-      "loss": 2.8178,
-      "step": 55510
-    },
-    {
-      "epoch": 13.0,
-      "eval_cer": 0.9567099567099567,
-      "eval_loss": 3.1265242099761963,
-      "eval_new_wer": 0.9285714285714286,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 7.8518,
-      "eval_samples_per_second": 26.746,
-      "eval_steps_per_second": 3.439,
-      "step": 55510
-    },
-    {
-      "epoch": 14.0,
-      "learning_rate": 7.065145937417829e-06,
-      "loss": 2.816,
-      "step": 59780
-    },
-    {
-      "epoch": 14.0,
-      "eval_cer": 0.9575757575757575,
-      "eval_loss": 3.1279547214508057,
-      "eval_new_wer": 0.9238095238095239,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 8.6197,
-      "eval_samples_per_second": 24.363,
-      "eval_steps_per_second": 3.132,
-      "step": 59780
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 4.930318169865895e-08,
-      "loss": 2.8106,
-      "step": 64050
-    },
-    {
-      "epoch": 15.0,
-      "eval_cer": 0.9593073593073593,
-      "eval_loss": 3.131213426589966,
-      "eval_new_wer": 0.9333333333333333,
-      "eval_old_wer": 1.0,
-      "eval_runtime": 8.5832,
-      "eval_samples_per_second": 24.466,
-      "eval_steps_per_second": 3.146,
-      "step": 64050
     }
   ],
   "max_steps": 64050,
   "num_train_epochs": 15,
-  "total_flos": 5.079400634281409e+19,
+  "total_flos": 3.2353018871683277e+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:ad917b31fae4bcf0c67ae1beb47de0804b8ba68209481d92e5d1d35cad1bd196
+oid sha256:3ad40ee222896fd4a776c83ffc757e3dbaa79c87f1bf52a69de9306ee72fdb26
 size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdd83bce0be94c1d45bb977937e9084dac2cb76e797eac4044daa3dc8639b22
+oid sha256:8c1450349389d08ad66823b39334b010395a34ccee54ae96db36aa7efca4b3e3
 size 377646433

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad917b31fae4bcf0c67ae1beb47de0804b8ba68209481d92e5d1d35cad1bd196
+oid sha256:3ad40ee222896fd4a776c83ffc757e3dbaa79c87f1bf52a69de9306ee72fdb26
 size 3451