Training in progress, step 44400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e41fc808d9972ae9a0dfa1a3483f519eb67e999b70042d921835bc59638489
+oid sha256:3d06ff0f6944c977b24ffca97320d1e1b8f33f7982c7c70a085be08e7a0735b3
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d5afb964bb98cac56c816782061036a702eff99b6e3d495ef2fdcf08b01c92
+oid sha256:550419b8cb66535f835e3a3f14342bc79d424335d3d639b4412a2a1dd5996b7f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dd9d6c48cfa65f5b93370ff7f40f7ce3b03a44f928109b20c95774f503d25ee
+oid sha256:01ce359e18f7a90dc84095a6557aa54494e079fb7b5316a22a25e176669fe27f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b51cbb9afcdf6c15a06208b1901272a0f842bc0bb257500541e033fcecde1b3
+oid sha256:6d93266a87661049b9532cd402055d41d22bd07173c685af733fe4ed43cd48d2
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62651611c38fd3a93cb59175e5b537ae65eaf6fa69019b3e8cf5975bd5eadf40
+oid sha256:c8a643c16cd3c86f0ac540d3ef1ce9abf102e6e8b34c059bbc0149468ac8d90c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.606609134918966,
+  "epoch": 18.690801936434436,
   "eval_steps": 100,
-  "global_step": 44200,
+  "global_step": 44400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7079,6 +7079,38 @@
       "eval_samples_per_second": 24.724,
       "eval_steps_per_second": 3.091,
       "step": 44200
+    },
+    {
+      "epoch": 18.65,
+      "grad_norm": 4.608269691467285,
+      "learning_rate": 1.9060777385159013e-05,
+      "loss": 0.5694,
+      "step": 44300
+    },
+    {
+      "epoch": 18.65,
+      "eval_cer": 0.3574825974737007,
+      "eval_loss": 2.2215840816497803,
+      "eval_runtime": 404.7052,
+      "eval_samples_per_second": 23.42,
+      "eval_steps_per_second": 2.928,
+      "step": 44300
+    },
+    {
+      "epoch": 18.69,
+      "grad_norm": 3.4327402114868164,
+      "learning_rate": 1.8990106007067137e-05,
+      "loss": 0.5747,
+      "step": 44400
+    },
+    {
+      "epoch": 18.69,
+      "eval_cer": 0.3554588205388917,
+      "eval_loss": 2.0720789432525635,
+      "eval_runtime": 385.2409,
+      "eval_samples_per_second": 24.603,
+      "eval_steps_per_second": 3.076,
+      "step": 44400
     }
   ],
   "logging_steps": 100,
@@ -7086,7 +7118,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.843579747142292e+20,
+  "total_flos": 4.86506326346161e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null