Training in progress, step 3800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91eeb91e22ee51b1c65e0c04b8e6cabb537d7c0caf4d077f5e1e69eb940968b
+oid sha256:cda231612e7da9ba6fe5b73580b35ba57a5509163e110e5e0eba0e5b73599828
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3fa62a4ee19ff913d4188ef73821370b4351489d9e353c373367e718c41ac6e
+oid sha256:7b7bf19e287139c8acae351b1673a21b2058f7cec0fcff727e026d3c46270716
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6075a74dcc3a31b11a7f90c9467bb390ebde2f5281e9b62844ebc5a11f042c
+oid sha256:a5f5a1c77820b7bbc317c1aff8a45aed6a8560151a804ae0da402a849cde98b3
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902f08a8f6cb2d34977202b642aa8ca1da1a7e05061f8a4675f56789cb56a1ae
-size 14567
+oid sha256:ba629318d7b57f286219027aeead93614853054919718b951849895b202cb795
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c69799836d793c36bf22d6ba3fabc8c8590dabdbaf72f82cc4a147403fd5ff1
+oid sha256:9fd2fb3de96e6243302ce77c9c01fd7c31f2ad88c6a97730bbe44948db0ff021
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5154704272784678,
+  "epoch": 1.599663228793938,
   "eval_steps": 100,
-  "global_step": 3600,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -583,6 +583,38 @@
       "eval_samples_per_second": 27.434,
       "eval_steps_per_second": 3.43,
       "step": 3600
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.648332357406616,
+      "learning_rate": 4.77434628975265e-05,
+      "loss": 1.74,
+      "step": 3700
+    },
+    {
+      "epoch": 1.56,
+      "eval_cer": 0.5568441789527199,
+      "eval_loss": 3.1145806312561035,
+      "eval_runtime": 362.0538,
+      "eval_samples_per_second": 26.178,
+      "eval_steps_per_second": 3.273,
+      "step": 3700
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 17.834945678710938,
+      "learning_rate": 4.767279151943463e-05,
+      "loss": 1.7586,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6,
+      "eval_cer": 0.5344653122678034,
+      "eval_loss": 1.8897360563278198,
+      "eval_runtime": 345.2891,
+      "eval_samples_per_second": 27.449,
+      "eval_steps_per_second": 3.432,
+      "step": 3800
     }
   ],
   "logging_steps": 100,
@@ -590,7 +622,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.957301946059647e+19,
+  "total_flos": 4.173960303853909e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null