Training in progress, step 43800, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b709baef67fd1c70a4136cfde38477fb5a6e9c3240080d0b85506f3def62d8a
+oid sha256:4ee0ab11786b912c2f0f9e3b57f5ffbe9d0694ec931e2307992de1c69fcc6067
 size 4978139416

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ebcabeac1dd27f3a1a58e33c36b54755e9bd9f84e6da954e2b3b4fd9ac082ac
+oid sha256:a2e55e361ac64d7291febab7443b2f6a44b10aa8eab4266d488df2b631e69bb9
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3839fe4830117e92509497bfa377895fc133a13ad1ca94900d3c03f445d3d1
+oid sha256:523b100723d242bcd643f3d25fa3179a70891cdcb5922df989d44d3134b47c80
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5fd9cc74931c14959da906b0f206817b94b75f65dd8dbaa5210a66f6b6816aa
+oid sha256:3bc8b57edba631898d0c329c841283aca0c73672887396826c194a70381d9299
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af49fc0e7d967b4565d316088b696d2da18440fc4e85cafa2dc525a2bc61c22e
+oid sha256:504183be9a2961ad91183bbca527d7ccf44c7b7d7af7b2247d4cb4fe8fc9255e
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.354030730372553,
+  "epoch": 18.438223531888024,
   "eval_steps": 100,
-  "global_step": 43600,
+  "global_step": 43800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6983,6 +6983,38 @@
       "eval_samples_per_second": 24.798,
       "eval_steps_per_second": 3.1,
       "step": 43600
+    },
+    {
+      "epoch": 18.4,
+      "grad_norm": 5.3773956298828125,
+      "learning_rate": 1.9484805653710248e-05,
+      "loss": 0.5594,
+      "step": 43700
+    },
+    {
+      "epoch": 18.4,
+      "eval_cer": 0.3562653983027648,
+      "eval_loss": 2.0783262252807617,
+      "eval_runtime": 404.1105,
+      "eval_samples_per_second": 23.454,
+      "eval_steps_per_second": 2.932,
+      "step": 43700
+    },
+    {
+      "epoch": 18.44,
+      "grad_norm": 1.7726545333862305,
+      "learning_rate": 1.9414134275618376e-05,
+      "loss": 0.5482,
+      "step": 43800
+    },
+    {
+      "epoch": 18.44,
+      "eval_cer": 0.3563827187047828,
+      "eval_loss": 2.1228716373443604,
+      "eval_runtime": 379.1678,
+      "eval_samples_per_second": 24.997,
+      "eval_steps_per_second": 3.125,
+      "step": 43800
     }
   ],
   "logging_steps": 100,
@@ -6990,7 +7022,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.777677491506297e+20,
+  "total_flos": 4.799417110573236e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null