Training in progress, step 47900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c737cef3e8496bd78bd7ec0023f68befe3d9a9c05598534030ccd26c85918ac6
+oid sha256:1adfcc7c1f34a33f4a2bfbac3eb295bc3f331ec01a66d851a4cfb6f83c1aff40
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2723715a10a82482c591b82cb51edd59abae6401d5ba96ea07090b181b9d643
+oid sha256:ed007356b71ab84b0e8369afe1f731d7b87590e01e741341a30fabb57ea24819
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b283c3ae87191de5fca07697a3974a9d234e69848cf8838bc28bee17cf75ce3
+oid sha256:f9f402496bd178d4de64e033a566a7386cd249090a2d60c9e41debb84daa8866
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392684c134f5cf29a9c14bb0a154c1d7d4d520741978198c633be27f537faa31
+oid sha256:f110e151f1624ce1e56568b61663aad2f2940177db6d8936e6a6eed4b8851d5b
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9916ddee38224af3ba1b5cf7e13befa56143fa30905487537b8489305fe5fcae
+oid sha256:23f550947596db3e46a433785e4ed8ccd479a0748ceb41ef26d7a8a3b5971eb4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.079983161439696,
+  "epoch": 20.164175962955166,
   "eval_steps": 100,
-  "global_step": 47700,
+  "global_step": 47900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7639,6 +7639,38 @@
       "eval_samples_per_second": 24.789,
       "eval_steps_per_second": 3.099,
       "step": 47700
+    },
+    {
+      "epoch": 20.12,
+      "grad_norm": 2.015397071838379,
+      "learning_rate": 1.6587985865724383e-05,
+      "loss": 0.4211,
+      "step": 47800
+    },
+    {
+      "epoch": 20.12,
+      "eval_cer": 0.3458312150482969,
+      "eval_loss": 2.9953062534332275,
+      "eval_runtime": 408.1484,
+      "eval_samples_per_second": 23.222,
+      "eval_steps_per_second": 2.903,
+      "step": 47800
+    },
+    {
+      "epoch": 20.16,
+      "grad_norm": 7.887564182281494,
+      "learning_rate": 1.651731448763251e-05,
+      "loss": 0.415,
+      "step": 47900
+    },
+    {
+      "epoch": 20.16,
+      "eval_cer": 0.3473783778499081,
+      "eval_loss": 3.28759765625,
+      "eval_runtime": 390.4889,
+      "eval_samples_per_second": 24.272,
+      "eval_steps_per_second": 3.035,
+      "step": 47900
     }
   ],
   "logging_steps": 100,
@@ -7646,7 +7678,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.227217240325222e+20,
+  "total_flos": 5.249064179783837e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null