Training in progress, step 57300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e346f6031cce705b7a51a894f6f6378890db177912b7be7998e56d05733b2858
+oid sha256:02b70489ef8d247cef87879363895d4f10172c2f01a2dce1018521c3e1196062
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1028245122ba4f0c3074dff84fb7696439ffd310961493c9af148d1751f0d0
+oid sha256:0f074e5548cab7f7d8619266bf2b437b7ac6af4dd2c84d102157ca2b21d476a6
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1480bf7de8a85342639e631f5104ad44bcd60ccdd626b0e1def4e6b1302d49f4
+oid sha256:7c9164876ea35a671565a42caafd2e90750339ac21a3f33050ee6f24b574012d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2354b0cf33dcdb8cc3fac9417682e1384f8242d5c4698533d6cd32a821a72d6
+oid sha256:3072c8a89084a4b231262fb6e7855152c0d0f0e572ea1bc0f437092386b0b94a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c15ce344ebb0358d0e2efa0d9ff824c7520b3efdb90c37d82fe6283bcb7100
+oid sha256:26d96a9177e995c4a7993aea1285f8bcbf19f7b0074431df56e02f6ba6af8002
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 24.03704483266681,
+  "epoch": 24.12123763418228,
   "eval_steps": 100,
-  "global_step": 57100,
+  "global_step": 57300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9143,6 +9143,38 @@
       "eval_samples_per_second": 23.982,
       "eval_steps_per_second": 2.998,
       "step": 57100
+    },
+    {
+      "epoch": 24.08,
+      "grad_norm": 5.454607009887695,
+      "learning_rate": 9.946289752650177e-06,
+      "loss": 0.2339,
+      "step": 57200
+    },
+    {
+      "epoch": 24.08,
+      "eval_cer": 0.3325251261194322,
+      "eval_loss": 2.6627321243286133,
+      "eval_runtime": 422.5781,
+      "eval_samples_per_second": 22.429,
+      "eval_steps_per_second": 2.804,
+      "step": 57200
+    },
+    {
+      "epoch": 24.12,
+      "grad_norm": 4.305576801300049,
+      "learning_rate": 9.875618374558305e-06,
+      "loss": 0.2229,
+      "step": 57300
+    },
+    {
+      "epoch": 24.12,
+      "eval_cer": 0.33326815533221227,
+      "eval_loss": 2.737283945083618,
+      "eval_runtime": 400.1034,
+      "eval_samples_per_second": 23.689,
+      "eval_steps_per_second": 2.962,
+      "step": 57300
     }
   ],
   "logging_steps": 100,
@@ -9150,7 +9182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.257522860637754e+20,
+  "total_flos": 6.279302169302917e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null