Training in progress, step 46500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:910ecd859a8d0f32e129cb369bc21dd817ab4778aab303a77df38a75142b51b4
+oid sha256:b27f517045a239ca3d4c09cfcbc5d90d49a9dc5fb03fcb2ed0885dce063b5310
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807d8fc0cd6b048948b226e59c943374d2cd199c6af744483c8f646a6e1f1672
+oid sha256:5a4020fe34ad40d60ab49cb79998fc9757fa6962619664a49f924687783b3f01
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44160a285c7e249f016d0e21e83db493778843b94be95b839943989b935239a
+oid sha256:4b3789d043057ca3bdf90a7ba4cfb8ad1bdc5bbc2f61f9921c6b8d8b227b8605
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3b2642d68c442cbe013ded4c0016af936b97de48da28f05df95d93cbf16db5
+oid sha256:3497a81af3830b12cea55fc1a002714afd90521c8567293cc3b2539688efc021
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8541f60b5d8dccf40450d6d85c1815ea0602e8747955d9567362b4052680b42
+oid sha256:7c96c7193a25b743904e5970326ee4765878ca8dbd521d975c5aaa2469d0561c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.490633550831404,
+  "epoch": 19.574826352346875,
   "eval_steps": 100,
-  "global_step": 46300,
+  "global_step": 46500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7415,6 +7415,38 @@
       "eval_samples_per_second": 25.65,
       "eval_steps_per_second": 3.207,
       "step": 46300
+    },
+    {
+      "epoch": 19.53,
+      "grad_norm": 2.0051708221435547,
+      "learning_rate": 1.75773851590106e-05,
+      "loss": 0.4878,
+      "step": 46400
+    },
+    {
+      "epoch": 19.53,
+      "eval_cer": 0.3492921669078253,
+      "eval_loss": 3.078077793121338,
+      "eval_runtime": 380.6797,
+      "eval_samples_per_second": 24.898,
+      "eval_steps_per_second": 3.113,
+      "step": 46400
+    },
+    {
+      "epoch": 19.57,
+      "grad_norm": 2.106623888015747,
+      "learning_rate": 1.750671378091873e-05,
+      "loss": 0.4886,
+      "step": 46500
+    },
+    {
+      "epoch": 19.57,
+      "eval_cer": 0.34946814751085215,
+      "eval_loss": 3.198930263519287,
+      "eval_runtime": 372.2046,
+      "eval_samples_per_second": 25.464,
+      "eval_steps_per_second": 3.184,
+      "step": 46500
     }
   ],
   "logging_steps": 100,
@@ -7422,7 +7454,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.0742971232760116e+20,
+  "total_flos": 5.096052922697529e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null