Training in progress, step 50500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bc977d62e7816011389161c4eeae7e71a5e15fa6414fc84828a3a030a05e6
+oid sha256:16c8e88b32eee615dcdd83273bd0c194d60a246661903076fda75220e2d10c57
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5d803a6ecbd25b4508f6830cb0d354f3164cf36de87bc4c942336f1d723990
+oid sha256:edd6f8a0eb8dcf9ba10c41e341f88389e7c3db368a255563153dee54ccc680c3
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941eea433be3c1f9adb0f47751c327703c05efe14921d20365ff7c6534eecd09
+oid sha256:3d8741d79b5be03765e57061f191fb50d4ed43fb5803cf2b764313f8dcdd7e48
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbe5fab90a476cca692ca727115b096b7062ef579d4f32a4ad2921bb938c28b
+oid sha256:382ea96905c8f14235ed215a03e93292273bd28d66f86e796f318632bcd7335e
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a28e7b27d1cecd73113f4062cdd78f7500a461c5bdb8769059e4729aaa72d3
+oid sha256:9f01039206f45f4a9f82763ac9b1c4be8f2cba26114400c57368ed9f798a154b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.17448958114081,
+  "epoch": 21.258682382656282,
   "eval_steps": 100,
-  "global_step": 50300,
+  "global_step": 50500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8055,6 +8055,38 @@
       "eval_samples_per_second": 24.292,
       "eval_steps_per_second": 3.037,
       "step": 50300
+    },
+    {
+      "epoch": 21.22,
+      "grad_norm": 4.574779987335205,
+      "learning_rate": 1.475123674911661e-05,
+      "loss": 0.3408,
+      "step": 50400
+    },
+    {
+      "epoch": 21.22,
+      "eval_cer": 0.34143414414766726,
+      "eval_loss": 2.403733491897583,
+      "eval_runtime": 415.1727,
+      "eval_samples_per_second": 22.829,
+      "eval_steps_per_second": 2.854,
+      "step": 50400
+    },
+    {
+      "epoch": 21.26,
+      "grad_norm": 1.5709911584854126,
+      "learning_rate": 1.4680565371024735e-05,
+      "loss": 0.3363,
+      "step": 50500
+    },
+    {
+      "epoch": 21.26,
+      "eval_cer": 0.3419229791560752,
+      "eval_loss": 2.4089136123657227,
+      "eval_runtime": 388.419,
+      "eval_samples_per_second": 24.401,
+      "eval_steps_per_second": 3.051,
+      "step": 50500
     }
   ],
   "logging_steps": 100,
@@ -8062,7 +8094,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.5126604494545053e+20,
+  "total_flos": 5.5342994893395676e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null