Training in progress, step 48900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:919479edc9c44b709a6fbc48787e8e31ae9b413ae5d1bf037e00f15a35aa7618
+oid sha256:fd4f68444eb86bbfd60685a66d682e2a4bcb950d07e58124c2888ef026741c77
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10995179ef6d151496a819060d002d0d14d0ae4946c8f3186f134f7b134c7b4c
+oid sha256:9e4ed37b5aa7caa4b3db7c781c0c0a436041060f568b10a355bc722544491e3e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b0edab5285069b45c657b2c1e8a54173d39533689345a0336372816e6ee99f
+oid sha256:35803e2074649e47f1ae99ba302701281690a9b94739796e166947b76a2870de
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8905c27bc949ca26e4d080125b36f4b021cbb40b50e21f90195179c8522e0ada
+oid sha256:a3a52d490e29ec96c5632acb35c769c2e04ef5ac5a150bd5b4ec42317318d278
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5c0c262f0099d55672ec4b48865245d6b1a61a5275913739ab46d7d5cc0df15
+oid sha256:c04deeab2ce545af1dd2aa0d8b2c7079874a851a6d59f58491424b131cccbdc2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.50094716901705,
+  "epoch": 20.58513997053252,
   "eval_steps": 100,
-  "global_step": 48700,
+  "global_step": 48900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7799,6 +7799,38 @@
       "eval_samples_per_second": 24.386,
       "eval_steps_per_second": 3.049,
       "step": 48700
+    },
+    {
+      "epoch": 20.54,
+      "grad_norm": 5.763105392456055,
+      "learning_rate": 1.588197879858657e-05,
+      "loss": 0.4039,
+      "step": 48800
+    },
+    {
+      "epoch": 20.54,
+      "eval_cer": 0.34577988737241405,
+      "eval_loss": 2.2274067401885986,
+      "eval_runtime": 406.2895,
+      "eval_samples_per_second": 23.328,
+      "eval_steps_per_second": 2.917,
+      "step": 48800
+    },
+    {
+      "epoch": 20.59,
+      "grad_norm": 4.299105167388916,
+      "learning_rate": 1.5811307420494702e-05,
+      "loss": 0.4253,
+      "step": 48900
+    },
+    {
+      "epoch": 20.59,
+      "eval_cer": 0.3451859528371984,
+      "eval_loss": 3.0053601264953613,
+      "eval_runtime": 386.4818,
+      "eval_samples_per_second": 24.524,
+      "eval_steps_per_second": 3.066,
+      "step": 48900
     }
   ],
   "logging_steps": 100,
@@ -7806,7 +7838,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.336332584830473e+20,
+  "total_flos": 5.357917546821734e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null