Training in progress, step 44000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ee0ab11786b912c2f0f9e3b57f5ffbe9d0694ec931e2307992de1c69fcc6067
+oid sha256:2f19dba491a25d75f15b6159fc5e7396e6bf275bfe74583181dbd07998d1cbb4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e55e361ac64d7291febab7443b2f6a44b10aa8eab4266d488df2b631e69bb9
+oid sha256:e8a09b882ac57021f3360f6b46e6c48150eb4d27559cafc0c4506d26a72a0f1b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:523b100723d242bcd643f3d25fa3179a70891cdcb5922df989d44d3134b47c80
+oid sha256:d74903110a4522efbf4d997a1acdcf357239e6610d383186fe076ffb850c8f85
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bc8b57edba631898d0c329c841283aca0c73672887396826c194a70381d9299
+oid sha256:9c1f556843d94bb8d13387eff57fa2cf17353ff9625e171f8ad00a37c074b58a
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504183be9a2961ad91183bbca527d7ccf44c7b7d7af7b2247d4cb4fe8fc9255e
+oid sha256:2949bea6872ed29b16b472ed73eddb49bd8e0598e7413d431d5a4600941bd043
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.438223531888024,
+  "epoch": 18.522416333403495,
   "eval_steps": 100,
-  "global_step": 43800,
+  "global_step": 44000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7015,6 +7015,38 @@
       "eval_samples_per_second": 24.997,
       "eval_steps_per_second": 3.125,
       "step": 43800
+    },
+    {
+      "epoch": 18.48,
+      "grad_norm": 8.040356636047363,
+      "learning_rate": 1.93434628975265e-05,
+      "loss": 0.5427,
+      "step": 43900
+    },
+    {
+      "epoch": 18.48,
+      "eval_cer": 0.3585995854679129,
+      "eval_loss": 2.0755696296691895,
+      "eval_runtime": 399.7267,
+      "eval_samples_per_second": 23.711,
+      "eval_steps_per_second": 2.965,
+      "step": 43900
+    },
+    {
+      "epoch": 18.52,
+      "grad_norm": 7.321507930755615,
+      "learning_rate": 1.927279151943463e-05,
+      "loss": 0.5651,
+      "step": 44000
+    },
+    {
+      "epoch": 18.52,
+      "eval_cer": 0.35462046849947204,
+      "eval_loss": 2.0843379497528076,
+      "eval_runtime": 380.2237,
+      "eval_samples_per_second": 24.927,
+      "eval_steps_per_second": 3.117,
+      "step": 44000
     }
   ],
   "logging_steps": 100,
@@ -7022,7 +7054,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.799417110573236e+20,
+  "total_flos": 4.821751474533075e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null