Training in progress, step 56300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab4065c03764effc8670cef485e7172138b847944296ddc1d4ac63592bb57b3
+oid sha256:c1932436298b8fb538e4cf80bed7163defd092b6328eb4bbc212e7fb308846d2
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c6c84b58be65267870df3ab069b46c0ec0719004b480fb2a5a41f9b2c0d5b5
+oid sha256:cc9f7d35cf87748eddf9bf58f61c5ba700e389c31489d78a290697c06c313346
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83b49b95053c311733c21b0f1a9bbdd3669c30e7fc3caf207b5862e66e32be6c
+oid sha256:0ec88f79f8a5c3ad18d543cea65ddcfd2fe9aa517c23d778574b571f8236405d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00cb33b6fce6dba04a33d05c1cb2d3d6d099ac011324c13a509e8848d1669b14
-size 14503
+oid sha256:a56a788fea959cad8157c6c6dc5342a179f5cfb4ced637d221d4c0e4c02d4c3c
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1305d66ef8f2afa8554deae5dd51afcd829f2485cde50c618b4fe4df3ce6276
+oid sha256:8b6a938385f789102516706256ee22f9b98b3e9613d4f67c8346e35dc285e21c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.616080825089455,
+  "epoch": 23.700273626604925,
   "eval_steps": 100,
-  "global_step": 56100,
+  "global_step": 56300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8983,6 +8983,38 @@
       "eval_samples_per_second": 23.624,
       "eval_steps_per_second": 2.954,
       "step": 56100
+    },
+    {
+      "epoch": 23.66,
+      "grad_norm": 1.4341765642166138,
+      "learning_rate": 1.0653003533568904e-05,
+      "loss": 0.26,
+      "step": 56200
+    },
+    {
+      "epoch": 23.66,
+      "eval_cer": 0.33526260216651677,
+      "eval_loss": 2.6399149894714355,
+      "eval_runtime": 433.4463,
+      "eval_samples_per_second": 21.867,
+      "eval_steps_per_second": 2.734,
+      "step": 56200
+    },
+    {
+      "epoch": 23.7,
+      "grad_norm": 1.7979743480682373,
+      "learning_rate": 1.0582332155477032e-05,
+      "loss": 0.2688,
+      "step": 56300
+    },
+    {
+      "epoch": 23.7,
+      "eval_cer": 0.3343387040006257,
+      "eval_loss": 2.507894515991211,
+      "eval_runtime": 402.3559,
+      "eval_samples_per_second": 23.556,
+      "eval_steps_per_second": 2.945,
+      "step": 56300
     }
   ],
   "logging_steps": 100,
@@ -8990,7 +9022,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.14754805865386e+20,
+  "total_flos": 6.169297958480331e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null