Training in progress, step 1600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c92440fc3b9b45e7e0e4a9674fa19fce3f0fd3fe7cb24d9f6f901b47afe242b
+oid sha256:8288a02283f86e9ba638fcdafdad6ac55a5bf4c5099f8ee42ed13013ea826eb4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:683c3f3779f4ddf18b57367326dc993b25b896ad4a4cbeefdf56cfcf9e7b0fa7
+oid sha256:5a97f66c1c28574e6392a73fea8effb2b5863a86aaab48224adfe1b025bb3191
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e04da75fa32b96fe88ee2245cd789a7ab34640f3c20d52935f88c9d082271e
+oid sha256:98cc6c42135d5fdae0950a750eaccd195bb5b28087533bf97a0e88b169b95efd
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e0150d5c1434dee8facf0d33346f4c9f38cdcf44d6e76bcb3fd3b20f9d35c64
+oid sha256:e44798068a9718e8bcfd56ffc9856739f99cbd9473873a0e9a358ac7d41155d6
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b996914f3debd8e889aa6e874dd0cf4525660561cc81e5c6b8e85e3aadef0c
+oid sha256:270b38fcc20aa3dd5713b96e8eb52fafaafc66915212800045170780fba378bf
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5893496106082929,
+  "epoch": 0.6735424121237634,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,38 @@
       "eval_samples_per_second": 27.872,
       "eval_steps_per_second": 3.485,
       "step": 1400
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.837653875350952,
+      "learning_rate": 4.929752650176679e-05,
+      "loss": 2.6865,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "eval_cer": 0.5574918853388604,
+      "eval_loss": 3.5201330184936523,
+      "eval_runtime": 351.432,
+      "eval_samples_per_second": 26.97,
+      "eval_steps_per_second": 3.372,
+      "step": 1500
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.9047458171844482,
+      "learning_rate": 4.922685512367491e-05,
+      "loss": 2.4105,
+      "step": 1600
+    },
+    {
+      "epoch": 0.67,
+      "eval_cer": 0.5886624496499941,
+      "eval_loss": 3.5269789695739746,
+      "eval_runtime": 347.023,
+      "eval_samples_per_second": 27.312,
+      "eval_steps_per_second": 3.415,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -238,7 +270,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.5334531543694647e+19,
+  "total_flos": 1.752021221030171e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null