Training in progress, step 54100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b2dcef9f26179151435e50d8e64e0973728607ca53d2c9bca9890649ccae83
+oid sha256:9725c0510d94ab5e0140ad3201e32ed737274a6d4e461498ae6bdd113ef06849
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:631fa048ad4716521ddf3c742f0d06469909e5075a79096a62d3bf501816a346
+oid sha256:81bf7a92a5a327d64457d7c6387c246d832fe8f59b8de59d5c1025c011c364cb
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e6a675d71cea3e043d398f0c5c226166bd97c3d96321b395a156a2148869be
+oid sha256:3cea699148c2601628a445ae2b32cfee07e117de7d22a2437d44ecaff7272137
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5210adbdeeb201664228e6f6260e1e39bb443611ef0bc349a9a68a41921abb3
+oid sha256:e358efef44d196c67f0e17e744f7c27742f90ad5db5357f0e687c4ef64d94e2c
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f72bd9fcf066733ad01f4170825cb13eef2cf7fb9d9def60eafcaf568f587f6
+oid sha256:c7091ad2e5c28e017a8f83466c3c7d5ebb62f0cc73aff7e61e05a5b21904f0be
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.68996000841928,
+  "epoch": 22.77415280993475,
   "eval_steps": 100,
-  "global_step": 53900,
+  "global_step": 54100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8631,6 +8631,38 @@
       "eval_samples_per_second": 24.333,
       "eval_steps_per_second": 3.042,
       "step": 53900
+    },
+    {
+      "epoch": 22.73,
+      "grad_norm": 1.8495489358901978,
+      "learning_rate": 1.2207773851590106e-05,
+      "loss": 0.2977,
+      "step": 54000
+    },
+    {
+      "epoch": 22.73,
+      "eval_cer": 0.3380245199640217,
+      "eval_loss": 2.4169256687164307,
+      "eval_runtime": 432.3991,
+      "eval_samples_per_second": 21.92,
+      "eval_steps_per_second": 2.741,
+      "step": 54000
+    },
+    {
+      "epoch": 22.77,
+      "grad_norm": 1.7505403757095337,
+      "learning_rate": 1.2137102473498234e-05,
+      "loss": 0.3062,
+      "step": 54100
+    },
+    {
+      "epoch": 22.77,
+      "eval_cer": 0.3384766923467991,
+      "eval_loss": 2.552931070327759,
+      "eval_runtime": 394.4096,
+      "eval_samples_per_second": 24.031,
+      "eval_steps_per_second": 3.004,
+      "step": 54100
     }
   ],
   "logging_steps": 100,
@@ -8638,7 +8670,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.906211157631806e+20,
+  "total_flos": 5.928113111954343e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null