Training in progress, step 31300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237468a1c8fe2d6d8ef6319e2cc1c429e454b699da043b4f7922bed2a6fc5d74
+oid sha256:fa29abb338d6a75326dee14bb54514669fc07ef4a2e72335a64d77cd7fcc1121
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c1b2ca9ce98af1ff8d88d334a04a834fe19c5bc2e097ac0d5ed5d2377807c5
+oid sha256:62f9343eb22a71e6253dc9bcb034a72c9918b589417ed5e9335db5a3449968e5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2720894a0c9398314cecc93d46ae5c361788de8d1908781b48e4915d7b52beca
+oid sha256:879eb26e4e5fd8690f6fbf910ab02b106f7b314b246a5c7b303584fa63dd27dd
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547bb396072d7ce130c2b2f0586bfd93bbc9d358ed6e66e47535cd097a9d5243
+oid sha256:a1a3a5c20e3acdfe9a70170fd3bf7a512077a46b682d60e3d629c7e39207f8e7
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c79b2a118092e551c5c318e5a915708d0417938e7e99546a1fe499d26306ef7
+oid sha256:ae84d961144f6ebc2aba63ab7cdc9976ca9682b9ff8c142bb73b3633ded53ef3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.091980635655652,
+  "epoch": 13.176173437171123,
   "eval_steps": 100,
-  "global_step": 31100,
+  "global_step": 31300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4983,6 +4983,38 @@
       "eval_samples_per_second": 25.484,
       "eval_steps_per_second": 3.186,
       "step": 31100
+    },
+    {
+      "epoch": 13.13,
+      "grad_norm": 2.130281448364258,
+      "learning_rate": 2.8315901060070672e-05,
+      "loss": 0.9865,
+      "step": 31200
+    },
+    {
+      "epoch": 13.13,
+      "eval_cer": 0.4065005279418091,
+      "eval_loss": 2.812870502471924,
+      "eval_runtime": 395.591,
+      "eval_samples_per_second": 23.959,
+      "eval_steps_per_second": 2.996,
+      "step": 31200
+    },
+    {
+      "epoch": 13.18,
+      "grad_norm": 3.105449676513672,
+      "learning_rate": 2.82452296819788e-05,
+      "loss": 0.9784,
+      "step": 31300
+    },
+    {
+      "epoch": 13.18,
+      "eval_cer": 0.3964916311446561,
+      "eval_loss": 2.1949923038482666,
+      "eval_runtime": 377.7569,
+      "eval_samples_per_second": 25.09,
+      "eval_steps_per_second": 3.137,
+      "step": 31300
     }
   ],
   "logging_steps": 100,
@@ -4990,7 +5022,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.408482296230056e+20,
+  "total_flos": 3.4301640387356184e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null