Training in progress, step 52300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a160b4e175184a931e59f6e0e078e62570ed360295c0fe949679c0e727f5eea
+oid sha256:4b49f0d391833f22a3a65f3991676e2a987a97b88cd0ad802eb1db8d1e6fe024
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362756a97ee496019c94541204764d63f92ffafe15a248f8434077d701710266
+oid sha256:87ea0d5906e0a8cad3a20b57981e4b95dcaa8043c17d437ec383528d77b70576
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af97be2351717a648f3ed627e3a5da1be85bd899722f95b48558a241429b0c7
+oid sha256:7486ea49baf77b45c7355012daf8b9a61b16da9ea0572d25ecdf994887dc4344
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5d06a7cdc46e4a528aeb9bb66bf58e9c1dcb3edea8772b30cb812147232c3dd
-size 14567
+oid sha256:dfcdd93522276fcda8f039579079d552064ebfca8be5aa43e5f90d00df30ae75
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5d1aa72f6daaa98e8456979d83438a50fc20467c64d414fc9148e60e30d500
+oid sha256:2dc85812b74cb6bb673f1e4f6b9869a44b0f2cf4d744fa3459bb02f98086cf88
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.932224794780048,
+  "epoch": 22.01641759629552,
   "eval_steps": 100,
-  "global_step": 52100,
+  "global_step": 52300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8343,6 +8343,38 @@
       "eval_samples_per_second": 24.409,
       "eval_steps_per_second": 3.052,
       "step": 52100
+    },
+    {
+      "epoch": 21.97,
+      "grad_norm": 1.7431000471115112,
+      "learning_rate": 1.3479858657243816e-05,
+      "loss": 0.3401,
+      "step": 52200
+    },
+    {
+      "epoch": 21.97,
+      "eval_cer": 0.3359225294278675,
+      "eval_loss": 2.4058258533477783,
+      "eval_runtime": 412.0183,
+      "eval_samples_per_second": 23.004,
+      "eval_steps_per_second": 2.876,
+      "step": 52200
+    },
+    {
+      "epoch": 22.02,
+      "grad_norm": 2.714993953704834,
+      "learning_rate": 1.3409187279151944e-05,
+      "loss": 0.3222,
+      "step": 52300
+    },
+    {
+      "epoch": 22.02,
+      "eval_cer": 0.33601051972938095,
+      "eval_loss": 2.8305118083953857,
+      "eval_runtime": 391.1586,
+      "eval_samples_per_second": 24.231,
+      "eval_steps_per_second": 3.029,
+      "step": 52300
     }
   ],
   "logging_steps": 100,
@@ -8350,7 +8382,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.7089616015663346e+20,
+  "total_flos": 5.7311072805771385e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null