Training in progress, step 45100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e422627c4b9c768f46280d63fdbcfda35620e774f98056638ba875f3575284
+oid sha256:0cb3db9d2bd3bce52bd4db7c183811c68dab8410c3e736a49c6c697983dffdd9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf19318ad1b6dc72bddec929f0849bc212f2e1e8bd60f19ac70115441c83c91
+oid sha256:84b143c07e902a9dcb951619cb1986e38157fd91e3cf1bcaced4a96d3371c692
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d07a63df9aaae7d187b5731e2c4c19721e7a2e9545c19b5722e4ffda120ed9
+oid sha256:20e71314605e7678242a5a386ea35a216d449f08cf4c3ff655d23be515343b67
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815af6775e420c509219caee17b9a5516bbf2b05365eac817aa0f9a01cbd8f8d
-size 14503
+oid sha256:5293e155d2b0d2e7b914f2d40a0c1ca84ad8e4c46494c609b09f7e1634588b5b
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a1219b2614f7ac1e5741ff596a810f142ab9bd2e0d40eb1eb0d44675ea0fea
+oid sha256:4efa9e4a4746446a85030c2502426e055bf40a9b3cad17aeaecf307da12c8f64
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.943380340980845,
+  "epoch": 18.98547674173858,
   "eval_steps": 100,
-  "global_step": 45000,
+  "global_step": 45100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7207,6 +7207,22 @@
       "eval_samples_per_second": 24.544,
       "eval_steps_per_second": 3.069,
       "step": 45000
+    },
+    {
+      "epoch": 18.99,
+      "grad_norm": 2.5482892990112305,
+      "learning_rate": 1.8496113074204948e-05,
+      "loss": 0.5893,
+      "step": 45100
+    },
+    {
+      "epoch": 18.99,
+      "eval_cer": 0.3533568300027375,
+      "eval_loss": 2.9341318607330322,
+      "eval_runtime": 402.0749,
+      "eval_samples_per_second": 23.573,
+      "eval_steps_per_second": 2.947,
+      "step": 45100
     }
   ],
   "logging_steps": 100,
@@ -7214,7 +7230,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.930677119902053e+20,
+  "total_flos": 4.941606672163604e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null