Training in progress, step 46300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:777938124b8f08a6fc51de91ba4f6a248e0db6ecac962b10d96fb7af7371d947
+oid sha256:910ecd859a8d0f32e129cb369bc21dd817ab4778aab303a77df38a75142b51b4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426caf72cf84a12bb83fee44c5ab19d9a2c05db3c88c152eeba1f77afb9c94e6
+oid sha256:807d8fc0cd6b048948b226e59c943374d2cd199c6af744483c8f646a6e1f1672
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e181b4508fa0c0aef068c5ce9add7596cdd91480b74f68ef60dd67316c6f7a0c
+oid sha256:f44160a285c7e249f016d0e21e83db493778843b94be95b839943989b935239a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2667702793407db19d3728855aeacbfeb7c14b67574cd2f6c8c45fc93cc266
+oid sha256:eb3b2642d68c442cbe013ded4c0016af936b97de48da28f05df95d93cbf16db5
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac30970e8a48e7dc94fd4d8f03dc31e7111fa8cfb4c3ecd5d2ab0fbdb55b042
+oid sha256:b8541f60b5d8dccf40450d6d85c1815ea0602e8747955d9567362b4052680b42
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.322247947800463,
+  "epoch": 19.490633550831404,
   "eval_steps": 100,
-  "global_step": 45900,
+  "global_step": 46300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7351,6 +7351,70 @@
       "eval_samples_per_second": 25.625,
       "eval_steps_per_second": 3.204,
       "step": 45900
+    },
+    {
+      "epoch": 19.36,
+      "grad_norm": 2.3827292919158936,
+      "learning_rate": 1.7860070671378094e-05,
+      "loss": 0.471,
+      "step": 46000
+    },
+    {
+      "epoch": 19.36,
+      "eval_cer": 0.3508588831097728,
+      "eval_loss": 2.3617963790893555,
+      "eval_runtime": 380.0492,
+      "eval_samples_per_second": 24.939,
+      "eval_steps_per_second": 3.118,
+      "step": 46000
+    },
+    {
+      "epoch": 19.41,
+      "grad_norm": 1.383456826210022,
+      "learning_rate": 1.778939929328622e-05,
+      "loss": 0.494,
+      "step": 46100
+    },
+    {
+      "epoch": 19.41,
+      "eval_cer": 0.3493679363341285,
+      "eval_loss": 2.267214298248291,
+      "eval_runtime": 370.4047,
+      "eval_samples_per_second": 25.588,
+      "eval_steps_per_second": 3.199,
+      "step": 46100
+    },
+    {
+      "epoch": 19.45,
+      "grad_norm": 5.505711555480957,
+      "learning_rate": 1.7718727915194347e-05,
+      "loss": 0.4749,
+      "step": 46200
+    },
+    {
+      "epoch": 19.45,
+      "eval_cer": 0.3519318759532283,
+      "eval_loss": 3.048175573348999,
+      "eval_runtime": 386.8635,
+      "eval_samples_per_second": 24.5,
+      "eval_steps_per_second": 3.063,
+      "step": 46200
+    },
+    {
+      "epoch": 19.49,
+      "grad_norm": 11.937617301940918,
+      "learning_rate": 1.7648056537102475e-05,
+      "loss": 0.4895,
+      "step": 46300
+    },
+    {
+      "epoch": 19.49,
+      "eval_cer": 0.3529168784951703,
+      "eval_loss": 2.974360942840576,
+      "eval_runtime": 369.5199,
+      "eval_samples_per_second": 25.65,
+      "eval_steps_per_second": 3.207,
+      "step": 46300
     }
   ],
   "logging_steps": 100,
@@ -7358,7 +7422,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.030211590848743e+20,
+  "total_flos": 5.0742971232760116e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null