Training in progress, step 25300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b2a2c9f8344a3f056b41a055ba9cf877677c2dede06360e05800239312e065
+oid sha256:92d0f54d94bb40c36aff6996d6fa628c3ad8f35db1778fc27c392e8f1f297c37
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9bfb4c0a2b76d8b30938a2caef3eb118732683751a4670b6ab11d3b39c0610
+oid sha256:e11244be255828a4851b0092fd87821c5c801f9a5160bbcbb2f0bc57051dd6c0
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1acf7311c0f23bc84bddad3deeab6a4cfcfaa3ca76f58cfe0d6a0329df3636c
+oid sha256:67169462303e6fe8077b6f06672390845332995ce37eb008c9c0bf1f85691316
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113c90aed7dad459e7db4de53a69323c72d9290e82b00754843d802358d49636
+oid sha256:95db0728543ded7d217ea539348d5e5e4f1dbdf964d9771ae6b95d5606964667
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4411797b8145dd5445709c94a20af5733ce9c239a915874b89315a2a4a6edd8
+oid sha256:917056f6954f4dd224b2ffcefa138533388ad3cff19d51f30a910abd911033b3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.566196590191538,
+  "epoch": 10.650389391707009,
   "eval_steps": 100,
-  "global_step": 25100,
+  "global_step": 25300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4023,6 +4023,38 @@
       "eval_samples_per_second": 26.051,
       "eval_steps_per_second": 3.257,
       "step": 25100
+    },
+    {
+      "epoch": 10.61,
+      "grad_norm": 2.433943033218384,
+      "learning_rate": 3.255406360424029e-05,
+      "loss": 1.186,
+      "step": 25200
+    },
+    {
+      "epoch": 10.61,
+      "eval_cer": 0.4293755621602597,
+      "eval_loss": 2.9843032360076904,
+      "eval_runtime": 383.8866,
+      "eval_samples_per_second": 24.69,
+      "eval_steps_per_second": 3.087,
+      "step": 25200
+    },
+    {
+      "epoch": 10.65,
+      "grad_norm": 2.10840106010437,
+      "learning_rate": 3.248339222614841e-05,
+      "loss": 1.2008,
+      "step": 25300
+    },
+    {
+      "epoch": 10.65,
+      "eval_cer": 0.42626657150678504,
+      "eval_loss": 2.721179485321045,
+      "eval_runtime": 367.0761,
+      "eval_samples_per_second": 25.82,
+      "eval_steps_per_second": 3.228,
+      "step": 25300
     }
   ],
   "logging_steps": 100,
@@ -4030,7 +4062,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.7498708584420557e+20,
+  "total_flos": 2.772097477056956e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null