Training in progress, step 19600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39536b07857e96674098336d821ff35749a8ecafb4e064cb918e9fbf3d7ba9c4
+oid sha256:00654abbd49ab7c1b06ad13bd92392598e97365698af5ae035f055dddc563eb6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d85220a081ebf7ba5f24dcf36d455607c800e07075731fc0438ed7d721838b8
+oid sha256:f3534c0d0d6c087dbb36cf99338a3d176fcf9d951caf7ff8a6cd9a35560fb3bb
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2feee5f579bc8ff01696c6cde6f4789c3b844b14e975ef180da8d549e0fe33b
+oid sha256:e7c5fb04aed7fd947c3154b620a13560df67c92576c5a2785bb106f21c7b1026
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b560c73f8c11664695f9a90d9d927dbe3811353bb8caf7abe8872e3b37b7585
-size 14567
+oid sha256:fe9be4631163448c85f4cf45e9e6c457c57ffe835d72fe349f9f924bacc75fc4
+size 14631

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee31d8b929c9d8d36d66b3500c5c4c93de524b8757148ff9ad30057ceaeb53d
+oid sha256:9df926b58d6c14520abeb8fe058a9df1dd12fab7b21c8130e728596730b0a1e5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.166701747000632,
+  "epoch": 8.250894548516102,
   "eval_steps": 100,
-  "global_step": 19400,
+  "global_step": 19600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3111,6 +3111,38 @@
       "eval_samples_per_second": 25.989,
       "eval_steps_per_second": 3.249,
       "step": 19400
+    },
+    {
+      "epoch": 8.21,
+      "grad_norm": 1.623938798904419,
+      "learning_rate": 3.6580918727915195e-05,
+      "loss": 1.2988,
+      "step": 19500
+    },
+    {
+      "epoch": 8.21,
+      "eval_cer": 0.4476164404990028,
+      "eval_loss": 2.2084550857543945,
+      "eval_runtime": 384.5947,
+      "eval_samples_per_second": 24.644,
+      "eval_steps_per_second": 3.081,
+      "step": 19500
+    },
+    {
+      "epoch": 8.25,
+      "grad_norm": 3.2966043949127197,
+      "learning_rate": 3.6510954063604243e-05,
+      "loss": 1.5739,
+      "step": 19600
+    },
+    {
+      "epoch": 8.25,
+      "eval_cer": 0.451500234640804,
+      "eval_loss": 1.4389057159423828,
+      "eval_runtime": 366.8675,
+      "eval_samples_per_second": 25.835,
+      "eval_steps_per_second": 3.23,
+      "step": 19600
     }
   ],
   "logging_steps": 100,
@@ -3118,7 +3150,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.1255543863355028e+20,
+  "total_flos": 2.1473444214428877e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null