Training in progress, step 49100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4f68444eb86bbfd60685a66d682e2a4bcb950d07e58124c2888ef026741c77
+oid sha256:7e998f8468cc7c346dc4ab88bf0c2ea3d0619ac332532e3a814afb1ae30e5137
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4ed37b5aa7caa4b3db7c781c0c0a436041060f568b10a355bc722544491e3e
+oid sha256:26f75452f5c6dacef05179ac21358b2dfe0213c1b720af143f8e2325f3b80e9b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35803e2074649e47f1ae99ba302701281690a9b94739796e166947b76a2870de
+oid sha256:2f320ce414b15cc9e8e335856b46b099587922107eefcdd05c2003fd1b73a4a1
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a52d490e29ec96c5632acb35c769c2e04ef5ac5a150bd5b4ec42317318d278
-size 14503
+oid sha256:fbf00c1e2916dc93efcaa39d2802c751ace54d5e0176b36b9c71c02426bcbae3
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04deeab2ce545af1dd2aa0d8b2c7079874a851a6d59f58491424b131cccbdc2
+oid sha256:3526b76b5bb1c00b0ec05511da6eda21f6c0133130e655d44d777a0153ed64a2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.58513997053252,
+  "epoch": 20.66933277204799,
   "eval_steps": 100,
-  "global_step": 48900,
+  "global_step": 49100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7831,6 +7831,38 @@
       "eval_samples_per_second": 24.524,
       "eval_steps_per_second": 3.066,
       "step": 48900
+    },
+    {
+      "epoch": 20.63,
+      "grad_norm": 1.9635140895843506,
+      "learning_rate": 1.574063604240283e-05,
+      "loss": 0.4048,
+      "step": 49000
+    },
+    {
+      "epoch": 20.63,
+      "eval_cer": 0.34388076336474915,
+      "eval_loss": 2.86527156829834,
+      "eval_runtime": 408.1952,
+      "eval_samples_per_second": 23.219,
+      "eval_steps_per_second": 2.903,
+      "step": 49000
+    },
+    {
+      "epoch": 20.67,
+      "grad_norm": 2.3898985385894775,
+      "learning_rate": 1.5669964664310955e-05,
+      "loss": 0.4189,
+      "step": 49100
+    },
+    {
+      "epoch": 20.67,
+      "eval_cer": 0.34160034805052597,
+      "eval_loss": 3.328908681869507,
+      "eval_runtime": 391.6176,
+      "eval_samples_per_second": 24.202,
+      "eval_steps_per_second": 3.026,
+      "step": 49100
     }
   ],
   "logging_steps": 100,
@@ -7838,7 +7870,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.357917546821734e+20,
+  "total_flos": 5.379768925487233e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null