Training in progress, step 1343

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648bf4d6f8205604f2c379a74384e514d7f2533dd82c411f4ffdee9089dd6805
+oid sha256:58a235f577ae951c5e41a12ab4c71ecf6f8ff9821412f5343182aec8704e4c6f
 size 187673752

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648bf4d6f8205604f2c379a74384e514d7f2533dd82c411f4ffdee9089dd6805
+oid sha256:5a51eecea612921a6892b36f9e2fcc3227e5628e806fc19d387ce2fe411c6e31
 size 187673752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebb85871c6b082b1647229471377e7b5105a2a487b4d45f2d3da63c8cc636ad
+oid sha256:412b801a2500e3aa534b612e94d6dc16d9f6a36cf9ac9739de58b5ec90974d6d
 size 14921099

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89feea09a6f1ed288a67c1a57e2fb79641d0f921fce49294468baca12e30898e
+oid sha256:1e65f55bd28c553c15e73931a90cf38e36a32b6d9c47c087efaedd446d7a2964
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317914e1b0b7e57d42f0fa6759aa19d9a30f1d604cc5192b2404476b6f3f4a62
+oid sha256:849fbe2f82a426b1b4997bc0878657e98737a4dd461d8a5a40a85e49101baa28
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd751fe8073c015fdc1ec3ce0bf61f0e1eacae42b35b7bf9f0f55f3d6c99fcf2
+oid sha256:3bb987046d6617ffac50447cbd191330d5f9f74750af09bfa65367796337436b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.02680565897245,
+  "epoch": 0.03723008190618019,
   "eval_steps": 50,
-  "global_step": 1300,
+  "global_step": 850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -280,150 +280,6 @@
       "eval_steps_per_second": 10.897,
       "eval_wer": 16.452007692755988,
       "step": 850
-    },
-    {
-      "epoch": 1.0029784065524945,
-      "grad_norm": 0.48208168148994446,
-      "learning_rate": 3.3183856502242154e-05,
-      "loss": 1.1043916320800782,
-      "step": 900
-    },
-    {
-      "epoch": 1.0029784065524945,
-      "eval_loss": 0.3950841724872589,
-      "eval_runtime": 156.2906,
-      "eval_samples_per_second": 11.114,
-      "eval_steps_per_second": 11.114,
-      "eval_wer": 16.1081648114692,
-      "step": 900
-    },
-    {
-      "epoch": 2.005956813104989,
-      "grad_norm": 0.4363427460193634,
-      "learning_rate": 2.944693572496263e-05,
-      "loss": 1.002419662475586,
-      "step": 950
-    },
-    {
-      "epoch": 2.005956813104989,
-      "eval_loss": 0.3973139822483063,
-      "eval_runtime": 150.5158,
-      "eval_samples_per_second": 11.54,
-      "eval_steps_per_second": 11.54,
-      "eval_wer": 16.16644326592459,
-      "step": 950
-    },
-    {
-      "epoch": 3.0089352196574835,
-      "grad_norm": 0.4448009133338928,
-      "learning_rate": 2.571001494768311e-05,
-      "loss": 0.9439057159423828,
-      "step": 1000
-    },
-    {
-      "epoch": 3.0089352196574835,
-      "eval_loss": 0.4021342992782593,
-      "eval_runtime": 151.2965,
-      "eval_samples_per_second": 11.481,
-      "eval_steps_per_second": 11.481,
-      "eval_wer": 16.236377411271054,
-      "step": 1000
-    },
-    {
-      "epoch": 4.011913626209978,
-      "grad_norm": 0.32352492213249207,
-      "learning_rate": 2.197309417040359e-05,
-      "loss": 0.9013279724121094,
-      "step": 1050
-    },
-    {
-      "epoch": 4.011913626209978,
-      "eval_loss": 0.4091801941394806,
-      "eval_runtime": 149.3668,
-      "eval_samples_per_second": 11.629,
-      "eval_steps_per_second": 11.629,
-      "eval_wer": 16.20141033859782,
-      "step": 1050
-    },
-    {
-      "epoch": 5.014892032762472,
-      "grad_norm": 0.29706525802612305,
-      "learning_rate": 1.8236173393124067e-05,
-      "loss": 0.8674221801757812,
-      "step": 1100
-    },
-    {
-      "epoch": 5.014892032762472,
-      "eval_loss": 0.40518996119499207,
-      "eval_runtime": 157.4047,
-      "eval_samples_per_second": 11.035,
-      "eval_steps_per_second": 11.035,
-      "eval_wer": 16.271344483944286,
-      "step": 1100
-    },
-    {
-      "epoch": 6.017870439314967,
-      "grad_norm": 0.36136195063591003,
-      "learning_rate": 1.4499252615844544e-05,
-      "loss": 0.842430648803711,
-      "step": 1150
-    },
-    {
-      "epoch": 6.017870439314967,
-      "eval_loss": 0.40126579999923706,
-      "eval_runtime": 154.0519,
-      "eval_samples_per_second": 11.275,
-      "eval_steps_per_second": 11.275,
-      "eval_wer": 16.259688793053208,
-      "step": 1150
-    },
-    {
-      "epoch": 7.0208488458674605,
-      "grad_norm": 0.40088629722595215,
-      "learning_rate": 1.0762331838565023e-05,
-      "loss": 0.8319394683837891,
-      "step": 1200
-    },
-    {
-      "epoch": 7.0208488458674605,
-      "eval_loss": 0.39827466011047363,
-      "eval_runtime": 157.3801,
-      "eval_samples_per_second": 11.037,
-      "eval_steps_per_second": 11.037,
-      "eval_wer": 16.24803310216213,
-      "step": 1200
-    },
-    {
-      "epoch": 8.023827252419956,
-      "grad_norm": 0.3946095108985901,
-      "learning_rate": 7.025411061285502e-06,
-      "loss": 0.834195785522461,
-      "step": 1250
-    },
-    {
-      "epoch": 8.023827252419956,
-      "eval_loss": 0.3936406075954437,
-      "eval_runtime": 154.2809,
-      "eval_samples_per_second": 11.259,
-      "eval_steps_per_second": 11.259,
-      "eval_wer": 16.277172329389824,
-      "step": 1250
-    },
-    {
-      "epoch": 9.02680565897245,
-      "grad_norm": 0.3853761553764343,
-      "learning_rate": 3.2884902840059795e-06,
-      "loss": 0.8308474731445312,
-      "step": 1300
-    },
-    {
-      "epoch": 9.02680565897245,
-      "eval_loss": 0.3941210210323334,
-      "eval_runtime": 154.465,
-      "eval_samples_per_second": 11.245,
-      "eval_steps_per_second": 11.245,
-      "eval_wer": 16.323795092954136,
-      "step": 1300
     }
   ],
   "logging_steps": 50,
@@ -443,7 +299,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.863411472785408e+19,
+  "total_flos": 3.157242221887488e+19,
   "train_batch_size": 64,
   "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:f3ea77af43b1094f8223c24207bfa2d82d65643fa265a38412be3476877d8220
+oid sha256:1c41c98e6d3ee70c478d1ea32d80592130dbc19c7448399d91812e9d8c8424f7
 size 5457

runs/Mar27_10-11-38_63249a1410af/events.out.tfevents.1774606298.63249a1410af.3168.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa7a7483266950bffe4d4d79e6e258a1b5009ddd6d1b78c1a2b3a75a6225e0d
-size 10047
+oid sha256:2fc22c1b8390b3408e68cd57be17aba48b050440f21a496b6450b47a8a72a8de
+size 10401