Training in progress, step 27900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a9b68d851de5d3211a5786bc155bb288dd74d58e4dc5493cda8e9bb8f5b66c
+oid sha256:5d49c4af7d6780b5bb59189d0dd1867f0b68d29fb3ba703be67e4405ffdd2f7b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91c760806ff07f3048741537eb7db0ce9a9fc0545b24f11d5446b75977c0636
+oid sha256:b3d226082b9d4eb89eb67558845e0d50815390f41da6ece0ea8d6981473441ce
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006fe2f9891b8bb244bfb635af4ee42dc360b27e8e2fbe6b729ce4508aa080ac
+oid sha256:8cb4a963bc15dc86cedf79321c880d41e114671433f6bd415c17a07b684173dd
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fad5d4b2449cf648eabcb3d279346b6662a87e99fb79ac46b0c8815722381f
-size 14567
+oid sha256:8dd54598a42f926ce0b6c3ce03e26f6e03ec6fcf83016be5d7c0d02f5bedcfc6
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739f0eb8d8ec6d67ffc73cb7a845f894d3c8ae14810b720e71f07a82de397bb6
+oid sha256:b0ced60e8e837d5a867fc1635f2587bd5e4112e1921c82905c17a08e817c88f2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.660703009892654,
+  "epoch": 11.744895811408124,
   "eval_steps": 100,
-  "global_step": 27700,
+  "global_step": 27900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4439,6 +4439,38 @@
       "eval_samples_per_second": 25.78,
       "eval_steps_per_second": 3.223,
       "step": 27700
+    },
+    {
+      "epoch": 11.7,
+      "grad_norm": 6.817134380340576,
+      "learning_rate": 3.071802120141343e-05,
+      "loss": 1.581,
+      "step": 27800
+    },
+    {
+      "epoch": 11.7,
+      "eval_cer": 0.4181641312424231,
+      "eval_loss": 2.996872901916504,
+      "eval_runtime": 382.8066,
+      "eval_samples_per_second": 24.759,
+      "eval_steps_per_second": 3.096,
+      "step": 27800
+    },
+    {
+      "epoch": 11.74,
+      "grad_norm": 4.087586879730225,
+      "learning_rate": 3.0647349823321555e-05,
+      "loss": 1.1385,
+      "step": 27900
+    },
+    {
+      "epoch": 11.74,
+      "eval_cer": 0.42436255914903603,
+      "eval_loss": 2.688666343688965,
+      "eval_runtime": 375.5428,
+      "eval_samples_per_second": 25.238,
+      "eval_steps_per_second": 3.155,
+      "step": 27900
     }
   ],
   "logging_steps": 100,
@@ -4446,7 +4478,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.035915998579374e+20,
+  "total_flos": 3.057677998172635e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null