Training in progress, step 49300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e998f8468cc7c346dc4ab88bf0c2ea3d0619ac332532e3a814afb1ae30e5137
+oid sha256:74a357b98e4ee095ed45472c47587cbff53b11bba8ee52364cf747aec2edad57
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f75452f5c6dacef05179ac21358b2dfe0213c1b720af143f8e2325f3b80e9b
+oid sha256:1045be07891224de41ffc49353bbd9c71f37abedb35e78847a85b94a93414d1f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f320ce414b15cc9e8e335856b46b099587922107eefcdd05c2003fd1b73a4a1
+oid sha256:ab63e00126966b51e82c6cfc37d4154dc70a54f57af4954047f6d1bfa10482e3
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf00c1e2916dc93efcaa39d2802c751ace54d5e0176b36b9c71c02426bcbae3
-size 14567
+oid sha256:f3413234ec77271dbb44be6798264935b5bc29bd7a383e5efca859e1b414dc0d
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3526b76b5bb1c00b0ec05511da6eda21f6c0133130e655d44d777a0153ed64a2
+oid sha256:776174e0cdc8de84863dc2bc871e616ade46ecb971d9ed338d192083a8322ec2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.66933277204799,
+  "epoch": 20.75352557356346,
   "eval_steps": 100,
-  "global_step": 49100,
+  "global_step": 49300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7863,6 +7863,38 @@
       "eval_samples_per_second": 24.202,
       "eval_steps_per_second": 3.026,
       "step": 49100
+    },
+    {
+      "epoch": 20.71,
+      "grad_norm": 5.6570048332214355,
+      "learning_rate": 1.5599293286219083e-05,
+      "loss": 0.4067,
+      "step": 49200
+    },
+    {
+      "epoch": 20.71,
+      "eval_cer": 0.3445235814008056,
+      "eval_loss": 3.190380811691284,
+      "eval_runtime": 410.6709,
+      "eval_samples_per_second": 23.079,
+      "eval_steps_per_second": 2.886,
+      "step": 49200
+    },
+    {
+      "epoch": 20.75,
+      "grad_norm": 6.448336124420166,
+      "learning_rate": 1.5528621908127208e-05,
+      "loss": 0.428,
+      "step": 49300
+    },
+    {
+      "epoch": 20.75,
+      "eval_cer": 0.3451126275859372,
+      "eval_loss": 3.366471529006958,
+      "eval_runtime": 393.2567,
+      "eval_samples_per_second": 24.101,
+      "eval_steps_per_second": 3.013,
+      "step": 49300
     }
   ],
   "logging_steps": 100,
@@ -7870,7 +7902,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.379768925487233e+20,
+  "total_flos": 5.4016158411070066e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null