Training in progress, step 39500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59cf012cca14e7c479066e2ff0a5e1f204267b57f9816ba1aa6ee55cc5d6f9bf
+oid sha256:2d6825f4a17e39ca3df3effbf21d7f32ed1545ec9aec9ba20098846041083574
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0416e5725a213d2dafe05a9938222b9ad2625ab52c5100cdd7de652f9a9f5a
+oid sha256:0af944c7c9c469f7aebd311567f3c33ffe63ef9f70efd93e8822e7921c3f2d6f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f668cec0befb5905f1774c4110fe903320e1b8e768261c233cddbf5d15f6e2
+oid sha256:b4c593e409771c80e1808ae19146aa7f37f9ced1b60ef046ea440f1301bf278a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a87a8feee502953668db6e272529785853c44ef4f1789f772c9d4e4c1dd6e44
-size 14567
+oid sha256:e1f11ec8ea1e825f20e5a35c769fb841763170d6306b3c0372ecf458faeb41f5
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e19363ce1cc072264c627cb668ae2097c1f0e504b938ed74dfd1914e30a16032
+oid sha256:a189e23788ccc3257b3ab439e9ae8abe94cccbaa26260dabcde4a1d95c4991b3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.45969269627447,
+  "epoch": 16.62807829930541,
   "eval_steps": 100,
-  "global_step": 39100,
+  "global_step": 39500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6263,6 +6263,70 @@
       "eval_samples_per_second": 25.066,
       "eval_steps_per_second": 3.134,
       "step": 39100
+    },
+    {
+      "epoch": 16.5,
+      "grad_norm": 2.213913679122925,
+      "learning_rate": 2.2662897526501766e-05,
+      "loss": 0.7423,
+      "step": 39200
+    },
+    {
+      "epoch": 16.5,
+      "eval_cer": 0.3694517226545696,
+      "eval_loss": 1.7742842435836792,
+      "eval_runtime": 396.973,
+      "eval_samples_per_second": 23.876,
+      "eval_steps_per_second": 2.985,
+      "step": 39200
+    },
+    {
+      "epoch": 16.54,
+      "grad_norm": 3.6008243560791016,
+      "learning_rate": 2.2592226148409894e-05,
+      "loss": 0.731,
+      "step": 39300
+    },
+    {
+      "epoch": 16.54,
+      "eval_cer": 0.36915842164952484,
+      "eval_loss": 1.7430915832519531,
+      "eval_runtime": 370.2202,
+      "eval_samples_per_second": 25.601,
+      "eval_steps_per_second": 3.201,
+      "step": 39300
+    },
+    {
+      "epoch": 16.59,
+      "grad_norm": 2.914562463760376,
+      "learning_rate": 2.2521554770318022e-05,
+      "loss": 0.7409,
+      "step": 39400
+    },
+    {
+      "epoch": 16.59,
+      "eval_cer": 0.36913153572406243,
+      "eval_loss": 1.8427553176879883,
+      "eval_runtime": 393.2137,
+      "eval_samples_per_second": 24.104,
+      "eval_steps_per_second": 3.014,
+      "step": 39400
+    },
+    {
+      "epoch": 16.63,
+      "grad_norm": 4.166165828704834,
+      "learning_rate": 2.245088339222615e-05,
+      "loss": 0.7502,
+      "step": 39500
+    },
+    {
+      "epoch": 16.63,
+      "eval_cer": 0.366770462633452,
+      "eval_loss": 1.7825747728347778,
+      "eval_runtime": 387.4051,
+      "eval_samples_per_second": 24.465,
+      "eval_steps_per_second": 3.059,
+      "step": 39500
     }
   ],
   "logging_steps": 100,
@@ -6270,7 +6334,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.284622492226139e+20,
+  "total_flos": 4.3287004594488685e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null