Training in progress, step 14100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb04ec4f3d36dd72f1880e67e379df925d69c4c1ee3be76fa1a43897ef9b16aa
+oid sha256:c687e1d18d37b98cc3685c02de3ed0c4572f0e8600102167b26d1c1780a6edaf
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c667ab0a8a130f4910409ed5385aecf8d04f340e0b73bf61de9998e419ee5ef
+oid sha256:a83bc02a2443eeb53634fea4453c212f298686f5c1891b5c5cb4209798e8aaa5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d91ae259b3415ae409d9b1aee3a858751c6d1e1cb5fb402436da9dbabb9012
+oid sha256:4e964c133b070afbed08f3ca32ca2670faf41bdc59e39b051dcf0fc33af0121a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b368cb744e028a8d7ec06984741ea4d567105d2c13b979cf5f116c73e24cca3
+oid sha256:5416a7b3a6d3cb418f6138347bcbabc33a0662041a00f66de497a1c8ca331973
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b01cc7e72200b1387dbf60d697bf53f87ac3009f238952d98a6ef44ab1024b0
+oid sha256:54e7a079f92a1bd85f80ccfb5ee98154d535f91421f908722bb451cef9b9d8b4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.8513997053251945,
+  "epoch": 5.935592506840665,
   "eval_steps": 100,
-  "global_step": 13900,
+  "global_step": 14100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2231,6 +2231,38 @@
       "eval_samples_per_second": 25.913,
       "eval_steps_per_second": 3.24,
       "step": 13900
+    },
+    {
+      "epoch": 5.89,
+      "grad_norm": 4.99106502532959,
+      "learning_rate": 4.0466431095406356e-05,
+      "loss": 1.7663,
+      "step": 14000
+    },
+    {
+      "epoch": 5.89,
+      "eval_cer": 0.4712345039302335,
+      "eval_loss": 2.6297221183776855,
+      "eval_runtime": 401.5004,
+      "eval_samples_per_second": 23.606,
+      "eval_steps_per_second": 2.951,
+      "step": 14000
+    },
+    {
+      "epoch": 5.94,
+      "grad_norm": 4.448285102844238,
+      "learning_rate": 4.039575971731449e-05,
+      "loss": 1.842,
+      "step": 14100
+    },
+    {
+      "epoch": 5.94,
+      "eval_cer": 0.46505562942395684,
+      "eval_loss": 2.5416791439056396,
+      "eval_runtime": 383.7378,
+      "eval_samples_per_second": 24.699,
+      "eval_steps_per_second": 3.088,
+      "step": 14100
     }
   ],
   "logging_steps": 100,
@@ -2238,7 +2270,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.523070949553679e+20,
+  "total_flos": 1.5450260168151686e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null