Training in progress, step 56100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5350a3d670e63e0e724e9a948f10fee13c3e2f281c6e2cbb34e1e8d199bcddd6
+oid sha256:8ab4065c03764effc8670cef485e7172138b847944296ddc1d4ac63592bb57b3
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30ad926c245886d2d7b37d4b9f136480894a256273517a47903a260a6350a0f
+oid sha256:18c6c84b58be65267870df3ab069b46c0ec0719004b480fb2a5a41f9b2c0d5b5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc2cf3451e42ae8925d9cbf46fea6e10421c2853d0ff857ca4521a7443ec2ed
+oid sha256:83b49b95053c311733c21b0f1a9bbdd3669c30e7fc3caf207b5862e66e32be6c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe56cb4545356428f0c754a6c3b227de992c60c335c1b79bf625d3be68349b6
-size 14567
+oid sha256:00cb33b6fce6dba04a33d05c1cb2d3d6d099ac011324c13a509e8848d1669b14
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86566b254e3e5928bcfd37fb46ba4a9e0762d9834543bb6f29fbaab70f97de5d
+oid sha256:b1305d66ef8f2afa8554deae5dd51afcd829f2485cde50c618b4fe4df3ce6276
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.531888023573984,
+  "epoch": 23.616080825089455,
   "eval_steps": 100,
-  "global_step": 55900,
+  "global_step": 56100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8951,6 +8951,38 @@
       "eval_samples_per_second": 23.838,
       "eval_steps_per_second": 2.98,
       "step": 55900
+    },
+    {
+      "epoch": 23.57,
+      "grad_norm": 3.1888105869293213,
+      "learning_rate": 1.0794346289752651e-05,
+      "loss": 0.2537,
+      "step": 56000
+    },
+    {
+      "epoch": 23.57,
+      "eval_cer": 0.3346197841304603,
+      "eval_loss": 2.708544969558716,
+      "eval_runtime": 427.2487,
+      "eval_samples_per_second": 22.184,
+      "eval_steps_per_second": 2.774,
+      "step": 56000
+    },
+    {
+      "epoch": 23.62,
+      "grad_norm": 9.785385131835938,
+      "learning_rate": 1.0723674911660778e-05,
+      "loss": 0.2622,
+      "step": 56100
+    },
+    {
+      "epoch": 23.62,
+      "eval_cer": 0.3341309491220523,
+      "eval_loss": 2.625296115875244,
+      "eval_runtime": 401.2011,
+      "eval_samples_per_second": 23.624,
+      "eval_steps_per_second": 2.954,
+      "step": 56100
     }
   ],
   "logging_steps": 100,
@@ -8958,7 +8990,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.12582004081098e+20,
+  "total_flos": 6.14754805865386e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null