Training in progress, step 45700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba72df5975c8b99cbc6d6a6d24dea915763e37bcfeeb094b07a32702d90892df
+oid sha256:8dcae94e0ba5659a94762126ca017500f9640d109bedc1a86e16f7c3a364e9f5
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9bc26a5cbbbc20d7fd8697e5046c3103c37dc49f7a44a61a5442d759e5639da
+oid sha256:a4dca8d70c56075bf2982f5f2b6c6bc3e36a911dffcbaf478a2abecf931e8e68
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911113640d61c316fc766e86411da7bb59e1d0e3ce7f49e464f18e99ea654517
+oid sha256:194585cbf7d9cfd62136cd29e1512102cdc3ce800cad797ad714867a01a807e3
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea78b13ed690a2241b4d959d7b6ee1a7ec9311794f20d4d9c39e9088e224fc5e
+oid sha256:01cb821d23c120c3f2fb4bfd56f972b2f4b5203cf129d2966782cb58aafc588a
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388522323e4003fdf0f1aab6ae314ad13e012d10187ec9e801314752b5856b73
+oid sha256:b83145c90d97eef0fc9a5597e2a0947d443830911cd43cef4159f379916f7334
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.15386234476952,
+  "epoch": 19.238055146284992,
   "eval_steps": 100,
-  "global_step": 45500,
+  "global_step": 45700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7287,6 +7287,38 @@
       "eval_samples_per_second": 25.903,
       "eval_steps_per_second": 3.239,
       "step": 45500
+    },
+    {
+      "epoch": 19.2,
+      "grad_norm": 5.378861427307129,
+      "learning_rate": 1.8142756183745585e-05,
+      "loss": 0.4807,
+      "step": 45600
+    },
+    {
+      "epoch": 19.2,
+      "eval_cer": 0.35123773024128896,
+      "eval_loss": 2.7749032974243164,
+      "eval_runtime": 380.1844,
+      "eval_samples_per_second": 24.93,
+      "eval_steps_per_second": 3.117,
+      "step": 45600
+    },
+    {
+      "epoch": 19.24,
+      "grad_norm": 1.9357730150222778,
+      "learning_rate": 1.807208480565371e-05,
+      "loss": 0.4868,
+      "step": 45700
+    },
+    {
+      "epoch": 19.24,
+      "eval_cer": 0.35421473544249343,
+      "eval_loss": 2.5809061527252197,
+      "eval_runtime": 368.1076,
+      "eval_samples_per_second": 25.748,
+      "eval_steps_per_second": 3.219,
+      "step": 45700
     }
   ],
   "logging_steps": 100,
@@ -7294,7 +7326,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.9862113247753096e+20,
+  "total_flos": 5.008227787418482e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null