Training in progress, step 25500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92d0f54d94bb40c36aff6996d6fa628c3ad8f35db1778fc27c392e8f1f297c37
+oid sha256:0ab007dd960c183c2e30e85616514e3da6c3660d56809b3a634e02652595cf69
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11244be255828a4851b0092fd87821c5c801f9a5160bbcbb2f0bc57051dd6c0
+oid sha256:6778800cc796c45ea30ad3a22874ae830638e117c355360ea6c92a3dfd474eab
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67169462303e6fe8077b6f06672390845332995ce37eb008c9c0bf1f85691316
+oid sha256:e13a3e04c3bc95af16ed8a2dd0f5ca31f7946fe6e95a84fd44ba865570960002
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95db0728543ded7d217ea539348d5e5e4f1dbdf964d9771ae6b95d5606964667
+oid sha256:846f249b88befad596e3b348fc9d3af50438f51fe4f7aa809cab2c988dc38c0e
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917056f6954f4dd224b2ffcefa138533388ad3cff19d51f30a910abd911033b3
+oid sha256:3e006367d18ff2557748c2cef8502481c62684745dc5fb7eb9b01c6baf1a2184
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.650389391707009,
+  "epoch": 10.73458219322248,
   "eval_steps": 100,
-  "global_step": 25300,
+  "global_step": 25500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4055,6 +4055,38 @@
       "eval_samples_per_second": 25.82,
       "eval_steps_per_second": 3.228,
       "step": 25300
+    },
+    {
+      "epoch": 10.69,
+      "grad_norm": 2.1997592449188232,
+      "learning_rate": 3.241272084805654e-05,
+      "loss": 1.1923,
+      "step": 25400
+    },
+    {
+      "epoch": 10.69,
+      "eval_cer": 0.42187438895623947,
+      "eval_loss": 2.4305357933044434,
+      "eval_runtime": 385.3951,
+      "eval_samples_per_second": 24.593,
+      "eval_steps_per_second": 3.075,
+      "step": 25400
+    },
+    {
+      "epoch": 10.73,
+      "grad_norm": 1.7977826595306396,
+      "learning_rate": 3.234204946996466e-05,
+      "loss": 1.7363,
+      "step": 25500
+    },
+    {
+      "epoch": 10.73,
+      "eval_cer": 0.4337506354855109,
+      "eval_loss": 2.236682176589966,
+      "eval_runtime": 370.2296,
+      "eval_samples_per_second": 25.6,
+      "eval_steps_per_second": 3.201,
+      "step": 25500
     }
   ],
   "logging_steps": 100,
@@ -4062,7 +4094,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.772097477056956e+20,
+  "total_flos": 2.7941943750609027e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null