Training in progress, step 41600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a24d4d54212b7695bf8a287d4f8eb9270a6d60d13f9a931c5779f13538973f
+oid sha256:b086fa26ee47712401c3d69c87257d0d3f9613e9fb8680b69a5ee540ff3f53a6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c05975af95ab79acf8a310695dfc38749b93829e001cc546ee9d4792a95bad7
+oid sha256:cf6e22001dd4affa8cf530d079935dfa59fa8df9907239c9cb39bc28fc66e6dd
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe48223f5c90918abbcc4c7259c7f6f8efbe538b78aea4ef8ef1741ac5a2fe8c
+oid sha256:a63d464ec4e4df145ecc44e97b395647a4d55c9c0c375c6832518e3c2c7c1beb
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d26f522d8cbc1a8729bb0644c4ccc57cbd2a2a52d55e5adac8c2487f5ed38e
+oid sha256:9b10c96a9898d522aa6fb3a44fee850c880dc53d26180c9dd1f3c0328eebd110
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc876a1c5dec1820929e730793e2c174c8e91d009bdd7e30b3f49cc015882f56
+oid sha256:d5e3847532555a54ee57194f9293c52c4e634134b9b1f3b1e9b28031e9951cd6
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.42790991370238,
+  "epoch": 17.51210271521785,
   "eval_steps": 100,
-  "global_step": 41400,
+  "global_step": 41600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6631,6 +6631,38 @@
       "eval_samples_per_second": 24.814,
       "eval_steps_per_second": 3.102,
       "step": 41400
+    },
+    {
+      "epoch": 17.47,
+      "grad_norm": 2.586341142654419,
+      "learning_rate": 2.1038162544169613e-05,
+      "loss": 0.6534,
+      "step": 41500
+    },
+    {
+      "epoch": 17.47,
+      "eval_cer": 0.36276690391459077,
+      "eval_loss": 1.7679296731948853,
+      "eval_runtime": 404.4195,
+      "eval_samples_per_second": 23.436,
+      "eval_steps_per_second": 2.93,
+      "step": 41500
+    },
+    {
+      "epoch": 17.51,
+      "grad_norm": 12.988226890563965,
+      "learning_rate": 2.096749116607774e-05,
+      "loss": 0.655,
+      "step": 41600
+    },
+    {
+      "epoch": 17.51,
+      "eval_cer": 0.3648982245512495,
+      "eval_loss": 1.7326639890670776,
+      "eval_runtime": 382.6806,
+      "eval_samples_per_second": 24.767,
+      "eval_steps_per_second": 3.097,
+      "step": 41600
     }
   ],
   "logging_steps": 100,
@@ -6638,7 +6670,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.5372888758914744e+20,
+  "total_flos": 4.559345589900353e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null