Training in progress, step 29900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e68ea1988adeb339de8fec3f9339ae2e610fdc78d37a899de33b92dc31a8778e
+oid sha256:c65a4983271581f7832e9fd374dbc6b246da39cee2dfc60b53fa1d44b5bb1aa8
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104344ee154889869d6dedaa406882521e8ffda57ed470d6f198a5ee48bd5eaf
+oid sha256:9e48477b3833582447d116b3875b936c6fbc79f219715a7548f995e773a3beb9
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc040a80a5272a21db9b6b731bb1e83dc816581c92f952fb1897abe3414cc9a7
+oid sha256:2393a4407e77990cc384c3df22dabed19ea02921b1539d0c2226cdd68e80dbfc
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359f2156e19f2ec5bc6dded0d2150c295c3c63a7ad8ee22ed71b68fed5bc2e23
-size 14567
+oid sha256:3a75caa93515fbe3b2dde54a5881684cb3634e004fc9e181a959f7cb2a3a1cf4
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9221d64181d2487e327013dbd89210af652170a383b61db186b5d6c56be9471
+oid sha256:140f760da868d14f720ef947f1dcef91d11508bf77dfffd336552f0c1d799f8d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.502631025047359,
+  "epoch": 12.58682382656283,
   "eval_steps": 100,
-  "global_step": 29700,
+  "global_step": 29900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4759,6 +4759,38 @@
       "eval_samples_per_second": 25.48,
       "eval_steps_per_second": 3.186,
       "step": 29700
+    },
+    {
+      "epoch": 12.54,
+      "grad_norm": 4.518542766571045,
+      "learning_rate": 2.9304593639575972e-05,
+      "loss": 1.0679,
+      "step": 29800
+    },
+    {
+      "epoch": 12.54,
+      "eval_cer": 0.4047798287122131,
+      "eval_loss": 2.345759868621826,
+      "eval_runtime": 387.3324,
+      "eval_samples_per_second": 24.47,
+      "eval_steps_per_second": 3.059,
+      "step": 29800
+    },
+    {
+      "epoch": 12.59,
+      "grad_norm": 3.159818410873413,
+      "learning_rate": 2.9233922261484097e-05,
+      "loss": 1.0724,
+      "step": 29900
+    },
+    {
+      "epoch": 12.59,
+      "eval_cer": 0.4022965468695006,
+      "eval_loss": 2.1892457008361816,
+      "eval_runtime": 368.124,
+      "eval_samples_per_second": 25.747,
+      "eval_steps_per_second": 3.219,
+      "step": 29900
     }
   ],
   "logging_steps": 100,
@@ -4766,7 +4798,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.254575201001735e+20,
+  "total_flos": 3.276539803799841e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null