Training in progress, step 56700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b48cfd98f64c5d125f771e54c20395665d1d877037bac06b3572191009699e
+oid sha256:bcb0638e9518badfd63abf2ece00d350144f9d41acccefe9bae1bc9a7e5e16b6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44acee1aeb254e47b183795a7e974bb04e859045fbcb8a60cd68541f1f93e9ee
+oid sha256:3fa1f50c2149cedbbcdc0a0b3f97d9da7bdaa07ae30698972e4b2783c4e4cae3
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2dee411cbfa983ddb90c55ee2a72b7fe583cabda1a874be6896ce43b84a43d
+oid sha256:7bae8989ab317e310c96be055cf193f107aac21ae74e30496cb700ed26fcca54
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2921f22486aac351c57cbb7c2191104e5b51ae494fc326c3d7293b77f62dc6
-size 14503
+oid sha256:47efbf05c9bdc39e09c06488a9440a7d4c26b3f59083d9e5abc4e7e8931b8a48
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25166827dfb1f80c901f38f580504a29f3bfd9dd8b2e815ea7c1992907c058ce
+oid sha256:2262615ae76018b8db25bb87fb7e7da2c4f7f0d991b75e87912b6a8c588ade12
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.784466428120396,
+  "epoch": 23.868659229635867,
   "eval_steps": 100,
-  "global_step": 56500,
+  "global_step": 56700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9047,6 +9047,38 @@
       "eval_samples_per_second": 23.576,
       "eval_steps_per_second": 2.948,
       "step": 56500
+    },
+    {
+      "epoch": 23.83,
+      "grad_norm": 3.0282020568847656,
+      "learning_rate": 1.0370318021201413e-05,
+      "loss": 0.2639,
+      "step": 56600
+    },
+    {
+      "epoch": 23.83,
+      "eval_cer": 0.33265222322161825,
+      "eval_loss": 2.564777374267578,
+      "eval_runtime": 430.1757,
+      "eval_samples_per_second": 22.033,
+      "eval_steps_per_second": 2.755,
+      "step": 56600
+    },
+    {
+      "epoch": 23.87,
+      "grad_norm": 1.940981388092041,
+      "learning_rate": 1.0299646643109541e-05,
+      "loss": 0.2606,
+      "step": 56700
+    },
+    {
+      "epoch": 23.87,
+      "eval_cer": 0.33390608501818464,
+      "eval_loss": 2.5213394165039062,
+      "eval_runtime": 397.5174,
+      "eval_samples_per_second": 23.843,
+      "eval_steps_per_second": 2.981,
+      "step": 56700
     }
   ],
   "logging_steps": 100,
@@ -9054,7 +9086,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.191168025761128e+20,
+  "total_flos": 6.212938084955773e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null