Training in progress, step 44200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f19dba491a25d75f15b6159fc5e7396e6bf275bfe74583181dbd07998d1cbb4
+oid sha256:a6e41fc808d9972ae9a0dfa1a3483f519eb67e999b70042d921835bc59638489
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a09b882ac57021f3360f6b46e6c48150eb4d27559cafc0c4506d26a72a0f1b
+oid sha256:66d5afb964bb98cac56c816782061036a702eff99b6e3d495ef2fdcf08b01c92
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74903110a4522efbf4d997a1acdcf357239e6610d383186fe076ffb850c8f85
+oid sha256:6dd9d6c48cfa65f5b93370ff7f40f7ce3b03a44f928109b20c95774f503d25ee
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1f556843d94bb8d13387eff57fa2cf17353ff9625e171f8ad00a37c074b58a
+oid sha256:4b51cbb9afcdf6c15a06208b1901272a0f842bc0bb257500541e033fcecde1b3
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2949bea6872ed29b16b472ed73eddb49bd8e0598e7413d431d5a4600941bd043
+oid sha256:62651611c38fd3a93cb59175e5b537ae65eaf6fa69019b3e8cf5975bd5eadf40
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.522416333403495,
+  "epoch": 18.606609134918966,
   "eval_steps": 100,
-  "global_step": 44000,
+  "global_step": 44200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7047,6 +7047,38 @@
       "eval_samples_per_second": 24.927,
       "eval_steps_per_second": 3.117,
       "step": 44000
+    },
+    {
+      "epoch": 18.56,
+      "grad_norm": 2.2667276859283447,
+      "learning_rate": 1.9202120141342757e-05,
+      "loss": 0.5645,
+      "step": 44100
+    },
+    {
+      "epoch": 18.56,
+      "eval_cer": 0.35216651675726407,
+      "eval_loss": 1.9949140548706055,
+      "eval_runtime": 407.2675,
+      "eval_samples_per_second": 23.272,
+      "eval_steps_per_second": 2.91,
+      "step": 44100
+    },
+    {
+      "epoch": 18.61,
+      "grad_norm": 2.5292446613311768,
+      "learning_rate": 1.9131448763250885e-05,
+      "loss": 0.5488,
+      "step": 44200
+    },
+    {
+      "epoch": 18.61,
+      "eval_cer": 0.35419029369207305,
+      "eval_loss": 1.832000732421875,
+      "eval_runtime": 383.3497,
+      "eval_samples_per_second": 24.724,
+      "eval_steps_per_second": 3.091,
+      "step": 44200
     }
   ],
   "logging_steps": 100,
@@ -7054,7 +7086,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.821751474533075e+20,
+  "total_flos": 4.843579747142292e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null