Training in progress, step 44600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d06ff0f6944c977b24ffca97320d1e1b8f33f7982c7c70a085be08e7a0735b3
+oid sha256:3ae988bcf1e80d64fc3c50daaef60bc1bad12fb87f548e09dc40aad3485bc941
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550419b8cb66535f835e3a3f14342bc79d424335d3d639b4412a2a1dd5996b7f
+oid sha256:d962bf48fdb22f97a263b871d805534e31f88c562fea1fd3091e25ec9fe6fca5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01ce359e18f7a90dc84095a6557aa54494e079fb7b5316a22a25e176669fe27f
+oid sha256:a4f7df543c28f7b1d4e237537e55af3a1c5c2f2ab50783f01bbf2aff73580c05
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d93266a87661049b9532cd402055d41d22bd07173c685af733fe4ed43cd48d2
-size 14567
+oid sha256:341280b36e33bee4b43d726478793b13fc021522a0fb4ba6c0b4344e30e91f0e
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a643c16cd3c86f0ac540d3ef1ce9abf102e6e8b34c059bbc0149468ac8d90c
+oid sha256:e165bf74ae366b7834cfc96ebc1c64c1b63d8ca28272d2793ae0769f087d7fdf
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.690801936434436,
+  "epoch": 18.774994737949907,
   "eval_steps": 100,
-  "global_step": 44400,
+  "global_step": 44600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7111,6 +7111,38 @@
       "eval_samples_per_second": 24.603,
       "eval_steps_per_second": 3.076,
       "step": 44400
+    },
+    {
+      "epoch": 18.73,
+      "grad_norm": 2.587009906768799,
+      "learning_rate": 1.8919434628975266e-05,
+      "loss": 0.5442,
+      "step": 44500
+    },
+    {
+      "epoch": 18.73,
+      "eval_cer": 0.35546126471393374,
+      "eval_loss": 2.185746192932129,
+      "eval_runtime": 399.8878,
+      "eval_samples_per_second": 23.702,
+      "eval_steps_per_second": 2.963,
+      "step": 44500
+    },
+    {
+      "epoch": 18.77,
+      "grad_norm": 2.142084836959839,
+      "learning_rate": 1.8849469964664314e-05,
+      "loss": 0.9587,
+      "step": 44600
+    },
+    {
+      "epoch": 18.77,
+      "eval_cer": 0.353083082398029,
+      "eval_loss": 2.363218307495117,
+      "eval_runtime": 384.8343,
+      "eval_samples_per_second": 24.629,
+      "eval_steps_per_second": 3.079,
+      "step": 44600
     }
   ],
   "logging_steps": 100,
@@ -7118,7 +7150,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.86506326346161e+20,
+  "total_flos": 4.8869923018175506e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null