Training in progress, step 2800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b114ec9aae5f56c896dc809331fe15ed8ccb9c22a63d8091cf763b49c85e3d
+oid sha256:07cc1e0dffcd80eac14f87d0d9619540d3f5cf1771ecd556cf377b27a876168c
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edcd52e16b677aaaa2c66be498a66202ce1cc335af39cbbad43ce8a2ad734b75
+oid sha256:4654516b018d8c1d8ee7f380300e2cfab5a3d33f9a966babd44885140fecda5d
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f3e0f4d936e870e79e3be44a85542644bf76c70c4bbcaa7cf95399760c586a
+oid sha256:9590931db28029d3072811ed01a2ef3a2eb67fd96a33277147916dc1a126b69f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df198c0270152417dac5be430450a9752660b128bc2ee48e34c53ddc72b40e6e
+oid sha256:2a378d0eab4cd862a8b75ae52dc72877722c788e485acf876520c8995544ef8d
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d75303d12b74496ad035c93f7f537a1c9eccd4f5cc765415d2bf1655e9477134
+oid sha256:d0d22202ff71180e976c20ff3356dc9e86ce8ae5966c95daf7b725e761a03663
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 2400,
   "best_metric": 0.2371058060713233,
   "best_model_checkpoint": "./distil-whisper/checkpoint-2400",
-  "epoch": 1.7097808658471405,
+  "epoch": 1.9948334224122573,
   "eval_steps": 400,
-  "global_step": 2400,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,43 @@
       "eval_steps_per_second": 0.404,
       "eval_wer": 0.2371058060713233,
       "step": 2400
+    },
+    {
+      "epoch": 1.7810440049884197,
+      "grad_norm": 44.21736145019531,
+      "learning_rate": 4.6481531410083585e-05,
+      "loss": 5.6636,
+      "step": 2500
+    },
+    {
+      "epoch": 1.852307144129699,
+      "grad_norm": 47.173553466796875,
+      "learning_rate": 4.3785386896737665e-05,
+      "loss": 5.5392,
+      "step": 2600
+    },
+    {
+      "epoch": 1.923570283270978,
+      "grad_norm": 52.33578872680664,
+      "learning_rate": 4.108924238339175e-05,
+      "loss": 5.6191,
+      "step": 2700
+    },
+    {
+      "epoch": 1.9948334224122573,
+      "grad_norm": 76.79695892333984,
+      "learning_rate": 3.839309787004584e-05,
+      "loss": 5.2035,
+      "step": 2800
+    },
+    {
+      "epoch": 1.9948334224122573,
+      "eval_loss": 0.11128760129213333,
+      "eval_runtime": 157.0495,
+      "eval_samples_per_second": 3.184,
+      "eval_steps_per_second": 0.401,
+      "eval_wer": 0.23946360153256704,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
@@ -249,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.12079259271168e+18,
+  "total_flos": 3.64112116973568e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null