Training in progress, step 54700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18b1ffc01be06a7d955de27541e116d684fa2a9a6af297dbb7f02ff2552fcb9
+oid sha256:05998676356b74d7c92b6812b63ed321d5aed0628cebf08c2ee29c8e25ded659
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b88e4c89ab318c14f3a49bcac249af4939619e98fce1829a0711517576dfb87
+oid sha256:4a140009122cc68264684b8e7e44a0f2add6449b362232c82da46bba4bd1f38f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e7d9c1caa0d1b3d5c6725d4b4337ebc28a60d58662fcc30551cee24b6f8682
+oid sha256:61dccc7f9aa66bb3bdbf3827a99b783e8d3ff2a21c448e6b0bf285e4c681e826
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683cc9fc24d2ae77adc186a85857b0c580cacfda070070405742dd40f4a6f6bb
-size 14503
+oid sha256:5d342c123bb7af95f844e094f9c88253628b7bfd6ee7206f7d36e137affa42cb
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6284b9930aef0581c1cf4c3684706693afb2aa3723205627204c06ef0b42946b
+oid sha256:f9b53dd7c1cefcb49136d37605b4f71f449ff39b3e8504f8e2386e6c892f1b73
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.942538412965693,
+  "epoch": 23.026731214481163,
   "eval_steps": 100,
-  "global_step": 54500,
+  "global_step": 54700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8727,6 +8727,38 @@
       "eval_samples_per_second": 23.573,
       "eval_steps_per_second": 2.947,
       "step": 54500
+    },
+    {
+      "epoch": 22.98,
+      "grad_norm": 4.0244011878967285,
+      "learning_rate": 1.178374558303887e-05,
+      "loss": 0.3026,
+      "step": 54600
+    },
+    {
+      "epoch": 22.98,
+      "eval_cer": 0.33435581322592,
+      "eval_loss": 2.545149564743042,
+      "eval_runtime": 441.4018,
+      "eval_samples_per_second": 21.473,
+      "eval_steps_per_second": 2.685,
+      "step": 54600
+    },
+    {
+      "epoch": 23.03,
+      "grad_norm": 2.544414758682251,
+      "learning_rate": 1.1713074204946998e-05,
+      "loss": 0.2848,
+      "step": 54700
+    },
+    {
+      "epoch": 23.03,
+      "eval_cer": 0.33448291032810606,
+      "eval_loss": 2.603243112564087,
+      "eval_runtime": 394.5283,
+      "eval_samples_per_second": 24.024,
+      "eval_steps_per_second": 3.004,
+      "step": 54700
     }
   ],
   "logging_steps": 100,
@@ -8734,7 +8766,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.971614270421255e+20,
+  "total_flos": 5.994471184119739e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null