Training in progress, step 41400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f31e821b74dd2aecadf4a49ced761482cb24335fa070340f440dfac62ebd15
+oid sha256:d8a24d4d54212b7695bf8a287d4f8eb9270a6d60d13f9a931c5779f13538973f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6ee0aff95bbd15a39f1188865d0051383c510dd4594f6c062ec608c68dc92c
+oid sha256:8c05975af95ab79acf8a310695dfc38749b93829e001cc546ee9d4792a95bad7
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:440e01e057f577e2f701487c44c7f69aaeaa1240bf4c1499312f3532285ec4eb
+oid sha256:fe48223f5c90918abbcc4c7259c7f6f8efbe538b78aea4ef8ef1741ac5a2fe8c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b009d8e28cf1d32b3e47f2da155cb0f031794cbe7f69274b2edda21d846b19
+oid sha256:52d26f522d8cbc1a8729bb0644c4ccc57cbd2a2a52d55e5adac8c2487f5ed38e
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ddc5f7d6b9326460646ca0179f41d1dca732c5948fbb1407ab5e2beb6ca76c2
+oid sha256:bc876a1c5dec1820929e730793e2c174c8e91d009bdd7e30b3f49cc015882f56
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.259524310671438,
+  "epoch": 17.42790991370238,
   "eval_steps": 100,
-  "global_step": 41000,
+  "global_step": 41400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6567,6 +6567,70 @@
       "eval_samples_per_second": 25.165,
       "eval_steps_per_second": 3.146,
       "step": 41000
+    },
+    {
+      "epoch": 17.3,
+      "grad_norm": 5.671442031860352,
+      "learning_rate": 2.1320848056537103e-05,
+      "loss": 0.6544,
+      "step": 41100
+    },
+    {
+      "epoch": 17.3,
+      "eval_cer": 0.3657659066911736,
+      "eval_loss": 1.7072508335113525,
+      "eval_runtime": 397.2129,
+      "eval_samples_per_second": 23.861,
+      "eval_steps_per_second": 2.983,
+      "step": 41100
+    },
+    {
+      "epoch": 17.34,
+      "grad_norm": 1.6116443872451782,
+      "learning_rate": 2.125017667844523e-05,
+      "loss": 0.6304,
+      "step": 41200
+    },
+    {
+      "epoch": 17.34,
+      "eval_cer": 0.36735950881858354,
+      "eval_loss": 2.110800266265869,
+      "eval_runtime": 379.2769,
+      "eval_samples_per_second": 24.99,
+      "eval_steps_per_second": 3.124,
+      "step": 41200
+    },
+    {
+      "epoch": 17.39,
+      "grad_norm": 2.9379818439483643,
+      "learning_rate": 2.117950530035336e-05,
+      "loss": 0.6426,
+      "step": 41300
+    },
+    {
+      "epoch": 17.39,
+      "eval_cer": 0.3644313871182199,
+      "eval_loss": 2.184722900390625,
+      "eval_runtime": 397.6084,
+      "eval_samples_per_second": 23.838,
+      "eval_steps_per_second": 2.98,
+      "step": 41300
+    },
+    {
+      "epoch": 17.43,
+      "grad_norm": 2.8842365741729736,
+      "learning_rate": 2.1108833922261484e-05,
+      "loss": 0.6913,
+      "step": 41400
+    },
+    {
+      "epoch": 17.43,
+      "eval_cer": 0.36425785069023503,
+      "eval_loss": 1.9356818199157715,
+      "eval_runtime": 381.9605,
+      "eval_samples_per_second": 24.814,
+      "eval_steps_per_second": 3.102,
+      "step": 41400
     }
   ],
   "logging_steps": 100,
@@ -6574,7 +6638,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.49389546173303e+20,
+  "total_flos": 4.5372888758914744e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null