Training in progress, step 24100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534d2ec58806cf0406b243b3a40b55aced31f1221f35942206aebf1011f8eb45
+oid sha256:0d1d86a67812950b8066ed1bd4785f9e5f74864e9e185c3c7d65a737e73412eb
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2de9be3becc541ed69b75b47fcb52e55d337b4bb44dd3461d867a50ece8370f
+oid sha256:c9bb1ef4ed06294b4512beffd9b8417f18d9d6c0bf30582a61d1b2418d2d7ea6
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a3ca665b49a6ee94542cba4571576580ed40077cbe8f242c5e2c4a3a9715e9
+oid sha256:2964d4840b876fd5ea402f55cbb3d3ecf1ccd015054120c9986b8308a80fe3b6
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c012312b5f595ff9a144d4688b864116f1aa4fd2b3b74ba5004f78c1e3dd36
-size 14567
+oid sha256:29deb45594f2ffe1b33e01ccb1b744191d09d4b58ab92a56ff666176b2e013c6
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8afa21305abd66240d65fd4f9e149e423e42ae4f4d5f37065fa94d5df4b4f66
+oid sha256:ed638b60d93524052d154552e2b26184c00d0eedea3ca18e5c2db2c0ab950927
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.061039781098716,
+  "epoch": 10.145232582614186,
   "eval_steps": 100,
-  "global_step": 23900,
+  "global_step": 24100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3831,6 +3831,38 @@
       "eval_samples_per_second": 25.853,
       "eval_steps_per_second": 3.232,
       "step": 23900
+    },
+    {
+      "epoch": 10.1,
+      "grad_norm": 2.430925130844116,
+      "learning_rate": 3.340212014134276e-05,
+      "loss": 1.185,
+      "step": 24000
+    },
+    {
+      "epoch": 10.1,
+      "eval_cer": 0.4357133080442689,
+      "eval_loss": 1.5434983968734741,
+      "eval_runtime": 385.0716,
+      "eval_samples_per_second": 24.614,
+      "eval_steps_per_second": 3.077,
+      "step": 24000
+    },
+    {
+      "epoch": 10.15,
+      "grad_norm": 2.367770195007324,
+      "learning_rate": 3.333144876325088e-05,
+      "loss": 1.2225,
+      "step": 24100
+    },
+    {
+      "epoch": 10.15,
+      "eval_cer": 0.4268898361425052,
+      "eval_loss": 1.602295160293579,
+      "eval_runtime": 368.0631,
+      "eval_samples_per_second": 25.751,
+      "eval_steps_per_second": 3.22,
+      "step": 24100
     }
   ],
   "logging_steps": 100,
@@ -3838,7 +3870,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.6188595514552674e+20,
+  "total_flos": 2.6405292408352522e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null