Training in progress, step 48100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1adfcc7c1f34a33f4a2bfbac3eb295bc3f331ec01a66d851a4cfb6f83c1aff40
+oid sha256:6167439d581cc395bf3088fe8ac6b11c26e4181fe551f128881e89bc4e1ce539
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed007356b71ab84b0e8369afe1f731d7b87590e01e741341a30fabb57ea24819
+oid sha256:4938e0f36333fadd4855c1934e42518090173b0a19d22feeaf6a23dda164827e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f402496bd178d4de64e033a566a7386cd249090a2d60c9e41debb84daa8866
+oid sha256:acfb4a34f27a6fb3c38894c96bbfd9bc1fd023b61822cee208fc0fb86da0a1c2
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f110e151f1624ce1e56568b61663aad2f2940177db6d8936e6a6eed4b8851d5b
-size 14503
+oid sha256:9dc98f239aaa8533c601f91ade3675472665d4acfce4d9364d5c7b75e44eee84
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f550947596db3e46a433785e4ed8ccd479a0748ceb41ef26d7a8a3b5971eb4
+oid sha256:8e4cd969c054daa76cafad7a5bcd9e1236149af3f397933e1dd3fba11510e9d1
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.164175962955166,
+  "epoch": 20.248368764470637,
   "eval_steps": 100,
-  "global_step": 47900,
+  "global_step": 48100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7671,6 +7671,38 @@
       "eval_samples_per_second": 24.272,
       "eval_steps_per_second": 3.035,
       "step": 47900
+    },
+    {
+      "epoch": 20.21,
+      "grad_norm": 2.610433578491211,
+      "learning_rate": 1.644664310954064e-05,
+      "loss": 0.4143,
+      "step": 48000
+    },
+    {
+      "epoch": 20.21,
+      "eval_cer": 0.3463151617066208,
+      "eval_loss": 2.6613733768463135,
+      "eval_runtime": 407.7959,
+      "eval_samples_per_second": 23.242,
+      "eval_steps_per_second": 2.906,
+      "step": 48000
+    },
+    {
+      "epoch": 20.25,
+      "grad_norm": 2.2651526927948,
+      "learning_rate": 1.637667844522968e-05,
+      "loss": 0.5371,
+      "step": 48100
+    },
+    {
+      "epoch": 20.25,
+      "eval_cer": 0.3461636228540143,
+      "eval_loss": 2.631626605987549,
+      "eval_runtime": 388.4014,
+      "eval_samples_per_second": 24.403,
+      "eval_steps_per_second": 3.051,
+      "step": 48100
     }
   ],
   "logging_steps": 100,
@@ -7678,7 +7710,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.249064179783837e+20,
+  "total_flos": 5.270910176053505e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null