Training in progress, step 8700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b51ed093e6c15bc18f94991971206e757e14980a9c5a628c37f62695938205d
+oid sha256:4bc6ee20e92be470779004e487dfec7d1c7ec07a2307cf5787abeeb10837bfba
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d240111503baf208b3258d8cba674443ef0ea2639039331de2ec6efe7692b794
+oid sha256:e3073616d523d72de602ba9879e633da89b6ad0e5050b67500ae028d8db836c3
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b55bdbc49a9bb2c273056a2b2153ade12b910b7c8f359f9751f5d74fa18c9c
+oid sha256:30f6c92c06d152dcf5d8bd4289cc9ae76a99dba6607556e40d75736ff19eb390
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19c12ed0af5993f0a876a6b88522655ebb04b9cbe7b4cb312f3eaf595675e1bf
+oid sha256:b52bc615e0fc35d8314852721291c3faa4ffac229e09429b2519ba20b083ffa6
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b67e153873510a6ad6dd38628964444102a91c7ee710a17268ca1406a3ff007
+oid sha256:a3d5eed609678a53ce1b4b4f600df93cccb5300509c18134b26b05aaf3106e36
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5781940644074934,
+  "epoch": 3.6623868659229637,
   "eval_steps": 100,
-  "global_step": 8500,
+  "global_step": 8700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1367,6 +1367,38 @@
       "eval_samples_per_second": 26.505,
       "eval_steps_per_second": 3.314,
       "step": 8500
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 2.3522162437438965,
+      "learning_rate": 4.428197879858658e-05,
+      "loss": 1.9984,
+      "step": 8600
+    },
+    {
+      "epoch": 3.62,
+      "eval_cer": 0.5185977278948809,
+      "eval_loss": 2.115999221801758,
+      "eval_runtime": 377.0919,
+      "eval_samples_per_second": 25.134,
+      "eval_steps_per_second": 3.142,
+      "step": 8600
+    },
+    {
+      "epoch": 3.66,
+      "grad_norm": 5.214267730712891,
+      "learning_rate": 4.42113074204947e-05,
+      "loss": 1.5957,
+      "step": 8700
+    },
+    {
+      "epoch": 3.66,
+      "eval_cer": 0.5082393140667162,
+      "eval_loss": 1.6540412902832031,
+      "eval_runtime": 357.3421,
+      "eval_samples_per_second": 26.524,
+      "eval_steps_per_second": 3.316,
+      "step": 8700
     }
   ],
   "logging_steps": 100,
@@ -1374,7 +1406,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 9.318809128668452e+19,
+  "total_flos": 9.533433836349682e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null