Training in progress, step 44800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae988bcf1e80d64fc3c50daaef60bc1bad12fb87f548e09dc40aad3485bc941
+oid sha256:d986491485545d732d2543b339c31a259dcb270837f25d91f6c0b31f3ac46e38
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d962bf48fdb22f97a263b871d805534e31f88c562fea1fd3091e25ec9fe6fca5
+oid sha256:af17d7c2b3c7bf2b538b3ba90686b2f4e4ed09dd4b9a9afb1fe76d2905f4f613
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f7df543c28f7b1d4e237537e55af3a1c5c2f2ab50783f01bbf2aff73580c05
+oid sha256:33f3fc9081c7129e45e682bf733c743600617e1c0e5a4ea79dca6c91a1e29f04
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:341280b36e33bee4b43d726478793b13fc021522a0fb4ba6c0b4344e30e91f0e
-size 14503
+oid sha256:1ffd4ac7d16e7a8d42ef9c4f13d915aa5d41769606ce52a3a1031a916b016bf9
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e165bf74ae366b7834cfc96ebc1c64c1b63d8ca28272d2793ae0769f087d7fdf
+oid sha256:0e3647f0c4181d85f62ad117eca30124a1bd2379804c9e34d325ea3a74a4ab0d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.774994737949907,
+  "epoch": 18.859187539465374,
   "eval_steps": 100,
-  "global_step": 44600,
+  "global_step": 44800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7143,6 +7143,38 @@
       "eval_samples_per_second": 24.629,
       "eval_steps_per_second": 3.079,
       "step": 44600
+    },
+    {
+      "epoch": 18.82,
+      "grad_norm": 8.04695987701416,
+      "learning_rate": 1.877879858657244e-05,
+      "loss": 0.5773,
+      "step": 44700
+    },
+    {
+      "epoch": 18.82,
+      "eval_cer": 0.35235960658558524,
+      "eval_loss": 2.419173002243042,
+      "eval_runtime": 407.1529,
+      "eval_samples_per_second": 23.279,
+      "eval_steps_per_second": 2.91,
+      "step": 44700
+    },
+    {
+      "epoch": 18.86,
+      "grad_norm": 2.3344297409057617,
+      "learning_rate": 1.8708127208480567e-05,
+      "loss": 0.658,
+      "step": 44800
+    },
+    {
+      "epoch": 18.86,
+      "eval_cer": 0.3527897813929842,
+      "eval_loss": 2.6321187019348145,
+      "eval_runtime": 378.5146,
+      "eval_samples_per_second": 25.04,
+      "eval_steps_per_second": 3.131,
+      "step": 44800
     }
   ],
   "logging_steps": 100,
@@ -7150,7 +7182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.8869923018175506e+20,
+  "total_flos": 4.909167843123271e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null