Training in progress, step 24900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ced1d4dde33aefe5dc39b13645ee47a4fd8e1770aa5a898de3b845e505ff1c54
+oid sha256:4aa20e2b38250193cad458cf6456b61e6cd6835a46242974faa3ec0299ec5ea4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66f1f55268dc994db0d05cb94152e6bf792c2200b525e6387d02aaf9ae9bccf5
+oid sha256:88b290e93444e04eefb18622c42a9a940aff44ce0eda0c58591c91dc43a6a3dd
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5119a87747b87e471b8a600bd8ac1f15b46eea46cd11df632ac6499078f8b490
+oid sha256:cf3373348509d838df2d91838bf6b82e31c363c37e5d53df01088e5c1c66ab9a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25c2ae242c4ef3e74feef24b9532eb46e95b0eb0e303649bd76f8613a1702b0
-size 14503
+oid sha256:5c776c552df10e3c2a8556af43ed9ebfa465725f7a1da047b3136cac82d2fb08
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e7497143a450b0fe1b393b84fb43e48289b6099fa5e2bc00a016595988f9227
+oid sha256:26499c8b545397e8b27fe7e548b6c4eb9be915474b77242dab10c6c05c196cd0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.397810987160598,
+  "epoch": 10.482003788676067,
   "eval_steps": 100,
-  "global_step": 24700,
+  "global_step": 24900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3959,6 +3959,38 @@
       "eval_samples_per_second": 25.338,
       "eval_steps_per_second": 3.168,
       "step": 24700
+    },
+    {
+      "epoch": 10.44,
+      "grad_norm": 6.735607624053955,
+      "learning_rate": 3.283674911660777e-05,
+      "loss": 1.4708,
+      "step": 24800
+    },
+    {
+      "epoch": 10.44,
+      "eval_cer": 0.4388076336474913,
+      "eval_loss": 1.9250705242156982,
+      "eval_runtime": 386.263,
+      "eval_samples_per_second": 24.538,
+      "eval_steps_per_second": 3.068,
+      "step": 24800
+    },
+    {
+      "epoch": 10.48,
+      "grad_norm": 1.8092114925384521,
+      "learning_rate": 3.2766077738515906e-05,
+      "loss": 1.1854,
+      "step": 24900
+    },
+    {
+      "epoch": 10.48,
+      "eval_cer": 0.4322132493840679,
+      "eval_loss": 1.8587048053741455,
+      "eval_runtime": 371.4948,
+      "eval_samples_per_second": 25.513,
+      "eval_steps_per_second": 3.19,
+      "step": 24900
     }
   ],
   "logging_steps": 100,
@@ -3966,7 +3998,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.7057203744998287e+20,
+  "total_flos": 2.727692663769625e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null