Training in progress, step 56500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1932436298b8fb538e4cf80bed7163defd092b6328eb4bbc212e7fb308846d2
+oid sha256:37b48cfd98f64c5d125f771e54c20395665d1d877037bac06b3572191009699e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9f7d35cf87748eddf9bf58f61c5ba700e389c31489d78a290697c06c313346
+oid sha256:44acee1aeb254e47b183795a7e974bb04e859045fbcb8a60cd68541f1f93e9ee
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec88f79f8a5c3ad18d543cea65ddcfd2fe9aa517c23d778574b571f8236405d
+oid sha256:fe2dee411cbfa983ddb90c55ee2a72b7fe583cabda1a874be6896ce43b84a43d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56a788fea959cad8157c6c6dc5342a179f5cfb4ced637d221d4c0e4c02d4c3c
-size 14567
+oid sha256:0d2921f22486aac351c57cbb7c2191104e5b51ae494fc326c3d7293b77f62dc6
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6a938385f789102516706256ee22f9b98b3e9613d4f67c8346e35dc285e21c
+oid sha256:25166827dfb1f80c901f38f580504a29f3bfd9dd8b2e815ea7c1992907c058ce
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.700273626604925,
+  "epoch": 23.784466428120396,
   "eval_steps": 100,
-  "global_step": 56300,
+  "global_step": 56500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9015,6 +9015,38 @@
       "eval_samples_per_second": 23.556,
       "eval_steps_per_second": 2.945,
       "step": 56300
+    },
+    {
+      "epoch": 23.74,
+      "grad_norm": 2.900815725326538,
+      "learning_rate": 1.051166077738516e-05,
+      "loss": 0.2671,
+      "step": 56400
+    },
+    {
+      "epoch": 23.74,
+      "eval_cer": 0.33364211411364436,
+      "eval_loss": 2.6333584785461426,
+      "eval_runtime": 425.9033,
+      "eval_samples_per_second": 22.254,
+      "eval_steps_per_second": 2.782,
+      "step": 56400
+    },
+    {
+      "epoch": 23.78,
+      "grad_norm": 1.366709589958191,
+      "learning_rate": 1.0440989399293287e-05,
+      "loss": 0.2509,
+      "step": 56500
+    },
+    {
+      "epoch": 23.78,
+      "eval_cer": 0.3335125728364163,
+      "eval_loss": 2.557394504547119,
+      "eval_runtime": 402.0125,
+      "eval_samples_per_second": 23.576,
+      "eval_steps_per_second": 2.948,
+      "step": 56500
     }
   ],
   "logging_steps": 100,
@@ -9022,7 +9054,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.169297958480331e+20,
+  "total_flos": 6.191168025761128e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null