Training in progress, step 54900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05998676356b74d7c92b6812b63ed321d5aed0628cebf08c2ee29c8e25ded659
+oid sha256:b4b42d92e7c51f1a2870be09d4104f085519061349b0e05bf31d84ecb29c91a0
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a140009122cc68264684b8e7e44a0f2add6449b362232c82da46bba4bd1f38f
+oid sha256:2060a25884097cc91d28479f3135ddc68617e2ec3619ef4b9a089dcbc3bc7227
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61dccc7f9aa66bb3bdbf3827a99b783e8d3ff2a21c448e6b0bf285e4c681e826
+oid sha256:8800fcea3d51fb165ceaefcf56d57ec181e51cad449c080d3d9f463d1c8fc031
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d342c123bb7af95f844e094f9c88253628b7bfd6ee7206f7d36e137affa42cb
+oid sha256:129253610a862a0de2bc5a45173af6ab111f2fcf06d9605e1bf74b6ddc0b72a4
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b53dd7c1cefcb49136d37605b4f71f449ff39b3e8504f8e2386e6c892f1b73
+oid sha256:fe11f129e8f022248014946b3a4b6751b41bfbc796ab56504330e3f243c7496d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.026731214481163,
+  "epoch": 23.110924015996634,
   "eval_steps": 100,
-  "global_step": 54700,
+  "global_step": 54900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8759,6 +8759,38 @@
       "eval_samples_per_second": 24.024,
       "eval_steps_per_second": 3.004,
       "step": 54700
+    },
+    {
+      "epoch": 23.07,
+      "grad_norm": 1.4476730823516846,
+      "learning_rate": 1.1642402826855124e-05,
+      "loss": 0.2693,
+      "step": 54800
+    },
+    {
+      "epoch": 23.07,
+      "eval_cer": 0.3340185170701185,
+      "eval_loss": 2.598785638809204,
+      "eval_runtime": 422.01,
+      "eval_samples_per_second": 22.459,
+      "eval_steps_per_second": 2.808,
+      "step": 54800
+    },
+    {
+      "epoch": 23.11,
+      "grad_norm": 2.027191400527954,
+      "learning_rate": 1.157173144876325e-05,
+      "loss": 0.2632,
+      "step": 54900
+    },
+    {
+      "epoch": 23.11,
+      "eval_cer": 0.33527237886668493,
+      "eval_loss": 2.615438461303711,
+      "eval_runtime": 400.4466,
+      "eval_samples_per_second": 23.669,
+      "eval_steps_per_second": 2.959,
+      "step": 54900
     }
   ],
   "logging_steps": 100,
@@ -8766,7 +8798,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.994471184119739e+20,
+  "total_flos": 6.016263856010292e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null