Training in progress, step 25100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aa20e2b38250193cad458cf6456b61e6cd6835a46242974faa3ec0299ec5ea4
+oid sha256:a0b2a2c9f8344a3f056b41a055ba9cf877677c2dede06360e05800239312e065
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88b290e93444e04eefb18622c42a9a940aff44ce0eda0c58591c91dc43a6a3dd
+oid sha256:eb9bfb4c0a2b76d8b30938a2caef3eb118732683751a4670b6ab11d3b39c0610
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3373348509d838df2d91838bf6b82e31c363c37e5d53df01088e5c1c66ab9a
+oid sha256:b1acf7311c0f23bc84bddad3deeab6a4cfcfaa3ca76f58cfe0d6a0329df3636c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c776c552df10e3c2a8556af43ed9ebfa465725f7a1da047b3136cac82d2fb08
+oid sha256:113c90aed7dad459e7db4de53a69323c72d9290e82b00754843d802358d49636
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26499c8b545397e8b27fe7e548b6c4eb9be915474b77242dab10c6c05c196cd0
+oid sha256:e4411797b8145dd5445709c94a20af5733ce9c239a915874b89315a2a4a6edd8
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.482003788676067,
+  "epoch": 10.566196590191538,
   "eval_steps": 100,
-  "global_step": 24900,
+  "global_step": 25100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3991,6 +3991,38 @@
       "eval_samples_per_second": 25.513,
       "eval_steps_per_second": 3.19,
       "step": 24900
+    },
+    {
+      "epoch": 10.52,
+      "grad_norm": 3.406538724899292,
+      "learning_rate": 3.269540636042403e-05,
+      "loss": 1.2144,
+      "step": 25000
+    },
+    {
+      "epoch": 10.52,
+      "eval_cer": 0.4353711235383833,
+      "eval_loss": 1.5310605764389038,
+      "eval_runtime": 388.4081,
+      "eval_samples_per_second": 24.402,
+      "eval_steps_per_second": 3.051,
+      "step": 25000
+    },
+    {
+      "epoch": 10.57,
+      "grad_norm": 21.588300704956055,
+      "learning_rate": 3.2624734982332155e-05,
+      "loss": 1.1869,
+      "step": 25100
+    },
+    {
+      "epoch": 10.57,
+      "eval_cer": 0.41679294904383873,
+      "eval_loss": 1.753686785697937,
+      "eval_runtime": 363.8235,
+      "eval_samples_per_second": 26.051,
+      "eval_steps_per_second": 3.257,
+      "step": 25100
     }
   ],
   "logging_steps": 100,
@@ -3998,7 +4030,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.727692663769625e+20,
+  "total_flos": 2.7498708584420557e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null