Training in progress, step 13500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64bc0a1397bc980ff597684a085c93f8dd2fe2b7b54d58711479664a09d54c3
+oid sha256:31b62a1eed64814fb09932d72e4b158e825506d75ad15f298d9e787f0552502f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1ceb3845f2cb7eceaae674378edb7dd24738c83638a474995504a3ff2267a2
+oid sha256:a47b4b5e03532ead7e8fc7c3e923c4911144dbd2504a20958ebe8635de704ed1
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a32194dd689a72f849b21ab9782143a146208cc1d25018113d6d979749680f1
+oid sha256:78a5cb22af6a2e357b345873f02b48b612899f785e45880c5d3859603cec97ca
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9853e2c9f15d5d445435ee3d094c763606e84907256808b6d8c015e81b32d039
-size 14567
+oid sha256:9e72175515cc54637e49cc1705761942275c0209bb6b05ae32b0a8db952e415f
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1558a03e21b124dc4cf9c782c9fd3ddda4c5e0f9d6236b7ad5d4b4ead1dac474
+oid sha256:8a4b19e6e6a244eb7dd17c9a36301bdbe54a114d743b96df3cd2e7dd5ae72aa2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.598821300778783,
+  "epoch": 5.683014102294254,
   "eval_steps": 100,
-  "global_step": 13300,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2135,6 +2135,38 @@
       "eval_samples_per_second": 24.57,
       "eval_steps_per_second": 3.072,
       "step": 13300
+    },
+    {
+      "epoch": 5.64,
+      "grad_norm": 2.6984710693359375,
+      "learning_rate": 4.08904593639576e-05,
+      "loss": 1.4041,
+      "step": 13400
+    },
+    {
+      "epoch": 5.64,
+      "eval_cer": 0.46995620038324665,
+      "eval_loss": 2.8926751613616943,
+      "eval_runtime": 379.5665,
+      "eval_samples_per_second": 24.971,
+      "eval_steps_per_second": 3.122,
+      "step": 13400
+    },
+    {
+      "epoch": 5.68,
+      "grad_norm": 28.124893188476562,
+      "learning_rate": 4.081978798586573e-05,
+      "loss": 1.3813,
+      "step": 13500
+    },
+    {
+      "epoch": 5.68,
+      "eval_cer": 0.453462907199562,
+      "eval_loss": 3.064070701599121,
+      "eval_runtime": 364.1898,
+      "eval_samples_per_second": 26.025,
+      "eval_steps_per_second": 3.254,
+      "step": 13500
     }
   ],
   "logging_steps": 100,
@@ -2142,7 +2174,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.4577321342657543e+20,
+  "total_flos": 1.4794168929030072e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null