Training in progress, step 57100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2c1b8e9be3ed4e5e58861e55bb2300fe594045ed5ac8701cb863f8c64b3b59
+oid sha256:e346f6031cce705b7a51a894f6f6378890db177912b7be7998e56d05733b2858
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a227592c640ebf19876714d2dee94144050fa04295abb4b60c4591e30937ca39
+oid sha256:9c1028245122ba4f0c3074dff84fb7696439ffd310961493c9af148d1751f0d0
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497ed74a4b175aaa80b7d9a67f8e0c9244db6631882ee06a6b637d0107236884
+oid sha256:1480bf7de8a85342639e631f5104ad44bcd60ccdd626b0e1def4e6b1302d49f4
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be286c7fb1c7bc11fa342e9bfd940e27a4b41b2d41eb275264375a0cad4252cb
-size 14567
+oid sha256:f2354b0cf33dcdb8cc3fac9417682e1384f8242d5c4698533d6cd32a821a72d6
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5227b1a7ff1352d31f4f09975564547391e6e8a0c885a0c20e698eab002a80
+oid sha256:d4c15ce344ebb0358d0e2efa0d9ff824c7520b3efdb90c37d82fe6283bcb7100
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.952852031151338,
+  "epoch": 24.03704483266681,
   "eval_steps": 100,
-  "global_step": 56900,
+  "global_step": 57100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -9111,6 +9111,38 @@
       "eval_samples_per_second": 23.654,
       "eval_steps_per_second": 2.957,
       "step": 56900
+    },
+    {
+      "epoch": 23.99,
+      "grad_norm": 1.9022639989852905,
+      "learning_rate": 1.0087632508833924e-05,
+      "loss": 0.2657,
+      "step": 57000
+    },
+    {
+      "epoch": 23.99,
+      "eval_cer": 0.33296507762699934,
+      "eval_loss": 2.5121145248413086,
+      "eval_runtime": 423.803,
+      "eval_samples_per_second": 22.364,
+      "eval_steps_per_second": 2.796,
+      "step": 57000
+    },
+    {
+      "epoch": 24.04,
+      "grad_norm": 1.854609727859497,
+      "learning_rate": 1.001696113074205e-05,
+      "loss": 0.2253,
+      "step": 57100
+    },
+    {
+      "epoch": 24.04,
+      "eval_cer": 0.3338425364670916,
+      "eval_loss": 2.654775381088257,
+      "eval_runtime": 395.2094,
+      "eval_samples_per_second": 23.982,
+      "eval_steps_per_second": 2.998,
+      "step": 57100
     }
   ],
   "logging_steps": 100,
@@ -9118,7 +9150,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.23499754043143e+20,
+  "total_flos": 6.257522860637754e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null