Training in progress, step 32700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09eceed9906bfe27bd3680afd50c41121c73b82c7cd5ef345c69fad35c0ab8b8
+oid sha256:cc051f6398a756522cc490f0a8f154f42b3f2b30d98bf7d60f11ac1888cdb3da
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf99370e0c7555ecb290c63576152db41e5b2dbb69d0454ac7e5f89074f7bd4
+oid sha256:02021cbbbec3246b6712aecc4cd14c4d4dfc08e3dbc00c5473d548a791306375
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e617199afd6c3a950fb46336c901b1ff9024ac6556123985ed6b261b689855f
+oid sha256:b1539346c05dd0db53e003a5edfb0638d6fd9baf85cb3d6708792dcf6b2d6967
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd931d9164958a9409e10cbb2086014b2f7f92c6de1fd6882064a496d5c52211
+oid sha256:2c999f4c1d5bb7ee3e6b99ed7a27056b2b32e84ae4ae775052bdec993bdba558
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b9126a6c1c8e3c86ea30228e288a1b5e1ab3597232760fc5ccce02139d2524
+oid sha256:9f278373e69e9ebd2b300373366d8c349b14d9205b631b0731c93a52b7c91f8b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.681330246263945,
+  "epoch": 13.765523047779414,
   "eval_steps": 100,
-  "global_step": 32500,
+  "global_step": 32700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5207,6 +5207,38 @@
       "eval_samples_per_second": 25.515,
       "eval_steps_per_second": 3.19,
       "step": 32500
+    },
+    {
+      "epoch": 13.72,
+      "grad_norm": 2.935277223587036,
+      "learning_rate": 2.7326501766784452e-05,
+      "loss": 1.0508,
+      "step": 32600
+    },
+    {
+      "epoch": 13.72,
+      "eval_cer": 0.40732665910601856,
+      "eval_loss": 2.4883534908294678,
+      "eval_runtime": 395.2638,
+      "eval_samples_per_second": 23.979,
+      "eval_steps_per_second": 2.998,
+      "step": 32600
+    },
+    {
+      "epoch": 13.77,
+      "grad_norm": 2.7527854442596436,
+      "learning_rate": 2.7255830388692584e-05,
+      "loss": 1.0314,
+      "step": 32700
+    },
+    {
+      "epoch": 13.77,
+      "eval_cer": 0.40216944976731456,
+      "eval_loss": 2.4499011039733887,
+      "eval_runtime": 369.8082,
+      "eval_samples_per_second": 25.63,
+      "eval_steps_per_second": 3.204,
+      "step": 32700
     }
   ],
   "logging_steps": 100,
@@ -5214,7 +5246,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.560483539431464e+20,
+  "total_flos": 3.582774517736169e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null