Training in progress, step 31100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48a3ca955f4c3490521ffa16267bda052fbae1914e6e361907a2828816f0c77
+oid sha256:237468a1c8fe2d6d8ef6319e2cc1c429e454b699da043b4f7922bed2a6fc5d74
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982196fc29592e305eafca95afb014310ab8940220bbbb1a5a33250f58ddf315
+oid sha256:44c1b2ca9ce98af1ff8d88d334a04a834fe19c5bc2e097ac0d5ed5d2377807c5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3a59837b584d61da7f6862e8ac72f4bc9bb2b3b48e0a427fa8da7ba5143bf40
+oid sha256:2720894a0c9398314cecc93d46ae5c361788de8d1908781b48e4915d7b52beca
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea975816aac3d40a8b3d99eca8a891c93c967ac80c950988bae3dd44c17f8cc
+oid sha256:547bb396072d7ce130c2b2f0586bfd93bbc9d358ed6e66e47535cd097a9d5243
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35cbb8ba5802e44e1ce90c535d286211f64f07ac10efce360c20ea86aa5c0fe7
+oid sha256:4c79b2a118092e551c5c318e5a915708d0417938e7e99546a1fe499d26306ef7
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.007787834140181,
+  "epoch": 13.091980635655652,
   "eval_steps": 100,
-  "global_step": 30900,
+  "global_step": 31100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4951,6 +4951,38 @@
       "eval_samples_per_second": 25.602,
       "eval_steps_per_second": 3.201,
       "step": 30900
+    },
+    {
+      "epoch": 13.05,
+      "grad_norm": 3.738598585128784,
+      "learning_rate": 2.845724381625442e-05,
+      "loss": 0.9841,
+      "step": 31000
+    },
+    {
+      "epoch": 13.05,
+      "eval_cer": 0.4061705643111337,
+      "eval_loss": 2.7012014389038086,
+      "eval_runtime": 394.4654,
+      "eval_samples_per_second": 24.027,
+      "eval_steps_per_second": 3.004,
+      "step": 31000
+    },
+    {
+      "epoch": 13.09,
+      "grad_norm": 3.3957040309906006,
+      "learning_rate": 2.8386572438162544e-05,
+      "loss": 1.444,
+      "step": 31100
+    },
+    {
+      "epoch": 13.09,
+      "eval_cer": 0.3994588596456924,
+      "eval_loss": 2.732797861099243,
+      "eval_runtime": 371.9235,
+      "eval_samples_per_second": 25.484,
+      "eval_steps_per_second": 3.186,
+      "step": 31100
     }
   ],
   "logging_steps": 100,
@@ -4958,7 +4990,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.386567819260411e+20,
+  "total_flos": 3.408482296230056e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null