Training in progress, step 50300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c467a55474359ea150af7f199402cf84590658e0255a9165922970cef84e170
+oid sha256:720bc977d62e7816011389161c4eeae7e71a5e15fa6414fc84828a3a030a05e6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489d7ba688753abe3e33833a76b4ae882115ed3d90c66c7a1a12d1ffa7f82528
+oid sha256:2f5d803a6ecbd25b4508f6830cb0d354f3164cf36de87bc4c942336f1d723990
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f413dee5c854704d5963137b5956e9d25624be5f512c8185c3af5befb0aca4f7
+oid sha256:941eea433be3c1f9adb0f47751c327703c05efe14921d20365ff7c6534eecd09
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7672fe3061dcd7690545b653f58f4ee116feae4c3b67a28c5239aa57cd8e646c
+oid sha256:8cbe5fab90a476cca692ca727115b096b7062ef579d4f32a4ad2921bb938c28b
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08ae60acffa23a34f3e2f8fcc14339c1e29295c511dc2b5dad5d07178f8a8bf5
+oid sha256:08a28e7b27d1cecd73113f4062cdd78f7500a461c5bdb8769059e4729aaa72d3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.09029677962534,
+  "epoch": 21.17448958114081,
   "eval_steps": 100,
-  "global_step": 50100,
+  "global_step": 50300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8023,6 +8023,38 @@
       "eval_samples_per_second": 24.513,
       "eval_steps_per_second": 3.065,
       "step": 50100
+    },
+    {
+      "epoch": 21.13,
+      "grad_norm": 2.7008559703826904,
+      "learning_rate": 1.4892579505300355e-05,
+      "loss": 0.3479,
+      "step": 50200
+    },
+    {
+      "epoch": 21.13,
+      "eval_cer": 0.34289331664776507,
+      "eval_loss": 2.209360122680664,
+      "eval_runtime": 412.345,
+      "eval_samples_per_second": 22.986,
+      "eval_steps_per_second": 2.874,
+      "step": 50200
+    },
+    {
+      "epoch": 21.17,
+      "grad_norm": 1.4452073574066162,
+      "learning_rate": 1.482190812720848e-05,
+      "loss": 0.3465,
+      "step": 50300
+    },
+    {
+      "epoch": 21.17,
+      "eval_cer": 0.33977454929412226,
+      "eval_loss": 2.268566370010376,
+      "eval_runtime": 390.1756,
+      "eval_samples_per_second": 24.292,
+      "eval_steps_per_second": 3.037,
+      "step": 50300
     }
   ],
   "logging_steps": 100,
@@ -8030,7 +8062,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.490253620598738e+20,
+  "total_flos": 5.5126604494545053e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null