Training in progress, step 3000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9462752283f48808e567cfa9b61a780fca95285fcf13c52272085cb1fce9a0b8
+oid sha256:944c1d6b08a21304a7ef94644fa7d9a1b0339ac8db2840865316da5264c3850b
 size 3025686376

runs/Mar27_19-04-06_hf-dgx-01/events.out.tfevents.1711562657.hf-dgx-01.1893386.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a09f8a71f8134c693f79ce3983c1f5e7aeb209e0c4d1d3e01b33d4f51e8fd2
-size 14123
+oid sha256:84eb09edac34b6f730fc5972ebb7401f0b96a5e0db9c5c5ebbeb3ccdd9d2612a
+size 31639

wandb/run-20240327_190418-lwtbcr8s/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.125, "train/grad_norm": 1.3431593179702759, "train/learning_rate": 8.900000000000001e-05, "train/epoch": 4.5, "train/global_step": 1000, "_timestamp": 1711569456.2541177, "_runtime": 6797.689527750015, "_step": 40, "eval/loss": 0.4658036530017853, "eval/wer": 0.43003940353859227, "eval/runtime": 1133.3821, "eval/samples_per_second": 2.755, "eval/steps_per_second": 0.086}
+{"train/loss": 0.0063, "train/grad_norm": 0.51263427734375, "train/learning_rate": 4.4000000000000006e-05, "train/epoch": 13.63, "train/global_step": 3025, "_timestamp": 1711581296.0875716, "_runtime": 18637.522981643677, "_step": 123, "eval/loss": 0.5476499795913696, "eval/wer": 0.35351155064513634, "eval/runtime": 560.2614, "eval/samples_per_second": 5.574, "eval/steps_per_second": 0.175}

wandb/run-20240327_190418-lwtbcr8s/run-lwtbcr8s.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ba05f1e017ca342d3b2973674cb98788723f936678e1306d0f19a09b282999
-size 1430398
+oid sha256:d3ca7bfb8672fa56c8c9fef11a8b0a2abb579ac6859d19baf45b9a34bae8c78e
+size 4084243