Training in progress, step 56900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb0638e9518badfd63abf2ece00d350144f9d41acccefe9bae1bc9a7e5e16b6
+oid sha256:eb2c1b8e9be3ed4e5e58861e55bb2300fe594045ed5ac8701cb863f8c64b3b59
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa1f50c2149cedbbcdc0a0b3f97d9da7bdaa07ae30698972e4b2783c4e4cae3
+oid sha256:a227592c640ebf19876714d2dee94144050fa04295abb4b60c4591e30937ca39
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bae8989ab317e310c96be055cf193f107aac21ae74e30496cb700ed26fcca54
+oid sha256:497ed74a4b175aaa80b7d9a67f8e0c9244db6631882ee06a6b637d0107236884
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47efbf05c9bdc39e09c06488a9440a7d4c26b3f59083d9e5abc4e7e8931b8a48
+oid sha256:be286c7fb1c7bc11fa342e9bfd940e27a4b41b2d41eb275264375a0cad4252cb
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2262615ae76018b8db25bb87fb7e7da2c4f7f0d991b75e87912b6a8c588ade12
+oid sha256:ff5227b1a7ff1352d31f4f09975564547391e6e8a0c885a0c20e698eab002a80
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.868659229635867,
+  "epoch": 23.952852031151338,
   "eval_steps": 100,
-  "global_step": 56700,
+  "global_step": 56900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9079,6 +9079,38 @@
       "eval_samples_per_second": 23.843,
       "eval_steps_per_second": 2.981,
       "step": 56700
+    },
+    {
+      "epoch": 23.91,
+      "grad_norm": 1.5934607982635498,
+      "learning_rate": 1.0228975265017668e-05,
+      "loss": 0.256,
+      "step": 56800
+    },
+    {
+      "epoch": 23.91,
+      "eval_cer": 0.33383764811700756,
+      "eval_loss": 2.509065866470337,
+      "eval_runtime": 427.9199,
+      "eval_samples_per_second": 22.149,
+      "eval_steps_per_second": 2.769,
+      "step": 56800
+    },
+    {
+      "epoch": 23.95,
+      "grad_norm": 6.75713586807251,
+      "learning_rate": 1.0158303886925796e-05,
+      "loss": 0.262,
+      "step": 56900
+    },
+    {
+      "epoch": 23.95,
+      "eval_cer": 0.33297974267725156,
+      "eval_loss": 2.544567108154297,
+      "eval_runtime": 400.6912,
+      "eval_samples_per_second": 23.654,
+      "eval_steps_per_second": 2.957,
+      "step": 56900
     }
   ],
   "logging_steps": 100,
@@ -9086,7 +9118,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.212938084955773e+20,
+  "total_flos": 6.23499754043143e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null