Training in progress, step 26700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a6f6f50b75e53f88f456a440ba99a4024e31f9424c3be014a002cb574db9080
+oid sha256:eff3cdcb7d4b7ed611afcd9ebd6643d02bc2e1b35c4bb74c08c50cf9a5f561a7
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0d3f50750973222fb25da6c949b2a0a8537e325e53090985a92f861de32eea
+oid sha256:e3b6b9e0933269179cf5434f263f8f9d9d7b6fff1b073c6931905cc4b53994b5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad6c81cb83edbb3cfd00fa6e082ac509892ec328a2c87c50274cee2405cde601
+oid sha256:ad304c52a9c03014020a10f709aaf27545830076ddab93a26c7de57de9dde158
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6696be169116cd06c49001a7406234fedc653144f3b5c806d950a921ea10d5f1
-size 14567
+oid sha256:840a7138cc3ba7fbc10190e1e4c329f4c41a56a5385a8c0310bf23bf7b9dc752
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30c44f6f4c7b9b608f34a4bbe0eeff7385b81ec6e639bfbef514ac626117dc6
+oid sha256:8ac896d0e921c51d399d94984f4a87a03619430db29ebc79fed180feeab8b5af
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.155546200799831,
+  "epoch": 11.239739002315302,
   "eval_steps": 100,
-  "global_step": 26500,
+  "global_step": 26700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4247,6 +4247,38 @@
       "eval_samples_per_second": 25.322,
       "eval_steps_per_second": 3.166,
       "step": 26500
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 2.1193289756774902,
+      "learning_rate": 3.156537102473498e-05,
+      "loss": 1.1587,
+      "step": 26600
+    },
+    {
+      "epoch": 11.2,
+      "eval_cer": 0.4244921004262641,
+      "eval_loss": 2.2303755283355713,
+      "eval_runtime": 390.1983,
+      "eval_samples_per_second": 24.29,
+      "eval_steps_per_second": 3.037,
+      "step": 26600
+    },
+    {
+      "epoch": 11.24,
+      "grad_norm": 13.682442665100098,
+      "learning_rate": 3.149469964664311e-05,
+      "loss": 1.1569,
+      "step": 26700
+    },
+    {
+      "epoch": 11.24,
+      "eval_cer": 0.4308762856360721,
+      "eval_loss": 1.715321660041809,
+      "eval_runtime": 368.2313,
+      "eval_samples_per_second": 25.739,
+      "eval_steps_per_second": 3.218,
+      "step": 26700
     }
   ],
   "logging_steps": 100,
@@ -4254,7 +4286,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.9042272694513363e+20,
+  "total_flos": 2.9261113218403457e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null