Training in progress, step 19800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00654abbd49ab7c1b06ad13bd92392598e97365698af5ae035f055dddc563eb6
+oid sha256:13d9360e86d6728b712f59c7c4708bbf9b1a6e025cbe69d32a8c222aedcfc489
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3534c0d0d6c087dbb36cf99338a3d176fcf9d951caf7ff8a6cd9a35560fb3bb
+oid sha256:72d17c27964e0a9bb4db1d4e8f9a66d19db2579e7d1a4682579269e4387b23ca
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7c5fb04aed7fd947c3154b620a13560df67c92576c5a2785bb106f21c7b1026
+oid sha256:eb443bec736266f1308adc945a429fcbd90b82f2937dc6e73185a9dc0e104218
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9be4631163448c85f4cf45e9e6c457c57ffe835d72fe349f9f924bacc75fc4
-size 14631
+oid sha256:fad3bce82b1ec9d0e105b84287a1d9a5af1cdbaae50b9ee14dce6c13e9ad62a7
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df926b58d6c14520abeb8fe058a9df1dd12fab7b21c8130e728596730b0a1e5
+oid sha256:8004b4b6a8c520e4ed293ea3a4cb135c114f118b79d1b79d758805030484f7fb
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.250894548516102,
+  "epoch": 8.335087350031571,
   "eval_steps": 100,
-  "global_step": 19600,
+  "global_step": 19800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3143,6 +3143,38 @@
       "eval_samples_per_second": 25.835,
       "eval_steps_per_second": 3.23,
       "step": 19600
+    },
+    {
+      "epoch": 8.29,
+      "grad_norm": 2.2112064361572266,
+      "learning_rate": 3.6440282685512365e-05,
+      "loss": 1.4271,
+      "step": 19700
+    },
+    {
+      "epoch": 8.29,
+      "eval_cer": 0.4538075358804896,
+      "eval_loss": 2.505011796951294,
+      "eval_runtime": 384.1903,
+      "eval_samples_per_second": 24.67,
+      "eval_steps_per_second": 3.084,
+      "step": 19700
+    },
+    {
+      "epoch": 8.34,
+      "grad_norm": 3.7650928497314453,
+      "learning_rate": 3.63696113074205e-05,
+      "loss": 1.665,
+      "step": 19800
+    },
+    {
+      "epoch": 8.34,
+      "eval_cer": 0.4431655977474483,
+      "eval_loss": 2.0151588916778564,
+      "eval_runtime": 364.0023,
+      "eval_samples_per_second": 26.038,
+      "eval_steps_per_second": 3.255,
+      "step": 19800
     }
   ],
   "logging_steps": 100,
@@ -3150,7 +3182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.1473444214428877e+20,
+  "total_flos": 2.169673140779638e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null