Training in progress, step 32500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ef20f83611dc5ecda3865d609d1c2529353faeb6e69db3373387d266c57e6d
+oid sha256:09eceed9906bfe27bd3680afd50c41121c73b82c7cd5ef345c69fad35c0ab8b8
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea2f0b6eea82ec7b672c6f99ffe205fc0b7e54f20c87785b2f34e524aa97736
+oid sha256:0bf99370e0c7555ecb290c63576152db41e5b2dbb69d0454ac7e5f89074f7bd4
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f8cabf689066796731ca11e18b147c9b88c182baa68362d28e596087a999dd
+oid sha256:9e617199afd6c3a950fb46336c901b1ff9024ac6556123985ed6b261b689855f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2604f2db63f8d40bcc859d3c5d9db567a5197e74b5fcf8b847396dd21324043f
+oid sha256:dd931d9164958a9409e10cbb2086014b2f7f92c6de1fd6882064a496d5c52211
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529f0d80ba72a29cd60cd97ed89d7289715ba99737c418335d0e26f49eb2d4a3
+oid sha256:b2b9126a6c1c8e3c86ea30228e288a1b5e1ab3597232760fc5ccce02139d2524
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.597137444748475,
+  "epoch": 13.681330246263945,
   "eval_steps": 100,
-  "global_step": 32300,
+  "global_step": 32500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5175,6 +5175,38 @@
       "eval_samples_per_second": 25.799,
       "eval_steps_per_second": 3.226,
       "step": 32300
+    },
+    {
+      "epoch": 13.64,
+      "grad_norm": 2.740971565246582,
+      "learning_rate": 2.74678445229682e-05,
+      "loss": 1.0443,
+      "step": 32400
+    },
+    {
+      "epoch": 13.64,
+      "eval_cer": 0.422089476359939,
+      "eval_loss": 2.9092776775360107,
+      "eval_runtime": 389.1697,
+      "eval_samples_per_second": 24.354,
+      "eval_steps_per_second": 3.045,
+      "step": 32400
+    },
+    {
+      "epoch": 13.68,
+      "grad_norm": 7.612214088439941,
+      "learning_rate": 2.7397173144876324e-05,
+      "loss": 1.0561,
+      "step": 32500
+    },
+    {
+      "epoch": 13.68,
+      "eval_cer": 0.4040587970748113,
+      "eval_loss": 1.9982529878616333,
+      "eval_runtime": 371.4689,
+      "eval_samples_per_second": 25.515,
+      "eval_steps_per_second": 3.19,
+      "step": 32500
     }
   ],
   "logging_steps": 100,
@@ -5182,7 +5214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.5387141404690835e+20,
+  "total_flos": 3.560483539431464e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null