Training in progress, step 41800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b086fa26ee47712401c3d69c87257d0d3f9613e9fb8680b69a5ee540ff3f53a6
+oid sha256:16df4d6de6762c1f1db0594493c5dbe4807fbb7aeb4ffb34555825a9d9d04146
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6e22001dd4affa8cf530d079935dfa59fa8df9907239c9cb39bc28fc66e6dd
+oid sha256:ab626964d3a443836bb0b91fb446a151856aea70c73efd8f48b4c8d2ea0d0396
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63d464ec4e4df145ecc44e97b395647a4d55c9c0c375c6832518e3c2c7c1beb
+oid sha256:53e26564465c0e121b7bea0b1e6e7ce1fd43de5ee568c559280ebef58a187e5d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b10c96a9898d522aa6fb3a44fee850c880dc53d26180c9dd1f3c0328eebd110
+oid sha256:68121decba33fc890b293e4256e209b83c963a48989e0b33e6ef62cd27e6b943
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e3847532555a54ee57194f9293c52c4e634134b9b1f3b1e9b28031e9951cd6
+oid sha256:0c93fb241eedaa94832e6d27b22d2591980d2a3312c84d793dfe2f6489464b54
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.51210271521785,
+  "epoch": 17.59629551673332,
   "eval_steps": 100,
-  "global_step": 41600,
+  "global_step": 41800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6663,6 +6663,38 @@
       "eval_samples_per_second": 24.767,
       "eval_steps_per_second": 3.097,
       "step": 41600
+    },
+    {
+      "epoch": 17.55,
+      "grad_norm": 3.8716864585876465,
+      "learning_rate": 2.0896819787985865e-05,
+      "loss": 0.6464,
+      "step": 41700
+    },
+    {
+      "epoch": 17.55,
+      "eval_cer": 0.36285245004106215,
+      "eval_loss": 2.095261573791504,
+      "eval_runtime": 400.7202,
+      "eval_samples_per_second": 23.652,
+      "eval_steps_per_second": 2.957,
+      "step": 41700
+    },
+    {
+      "epoch": 17.6,
+      "grad_norm": 1.966536521911621,
+      "learning_rate": 2.0826148409893993e-05,
+      "loss": 0.6675,
+      "step": 41800
+    },
+    {
+      "epoch": 17.6,
+      "eval_cer": 0.3588268937468226,
+      "eval_loss": 1.8380521535873413,
+      "eval_runtime": 382.7754,
+      "eval_samples_per_second": 24.761,
+      "eval_steps_per_second": 3.096,
+      "step": 41800
     }
   ],
   "logging_steps": 100,
@@ -6670,7 +6702,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.559345589900353e+20,
+  "total_flos": 4.5813049896121755e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null