Training in progress, step 54300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9725c0510d94ab5e0140ad3201e32ed737274a6d4e461498ae6bdd113ef06849
+oid sha256:261f5aa29d796648d142454d356754c0daa58ea249148b27851231430a96995c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bf7a92a5a327d64457d7c6387c246d832fe8f59b8de59d5c1025c011c364cb
+oid sha256:35e6973bc5c3aceef25441e3d061e46116955f4cf9ff95f3edcc89fd5823832b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cea699148c2601628a445ae2b32cfee07e117de7d22a2437d44ecaff7272137
+oid sha256:8b57c1cb981aa093ad536532c531f30dd1534cd1ce4054df1e5da8e31c553687
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e358efef44d196c67f0e17e744f7c27742f90ad5db5357f0e687c4ef64d94e2c
+oid sha256:e9c9224ba23bc6336e062987353c9877aacd7d8246979cd20e730d3da7787040
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7091ad2e5c28e017a8f83466c3c7d5ebb62f0cc73aff7e61e05a5b21904f0be
+oid sha256:d1d6f240808a249e74b97cfcaffd4c82e145821d5e3022d1fd6a98866547498c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.77415280993475,
+  "epoch": 22.858345611450222,
   "eval_steps": 100,
-  "global_step": 54100,
+  "global_step": 54300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8663,6 +8663,38 @@
       "eval_samples_per_second": 24.031,
       "eval_steps_per_second": 3.004,
       "step": 54100
+    },
+    {
+      "epoch": 22.82,
+      "grad_norm": 3.5150487422943115,
+      "learning_rate": 1.206643109540636e-05,
+      "loss": 0.3035,
+      "step": 54200
+    },
+    {
+      "epoch": 22.82,
+      "eval_cer": 0.3343362598255837,
+      "eval_loss": 2.274048328399658,
+      "eval_runtime": 434.158,
+      "eval_samples_per_second": 21.831,
+      "eval_steps_per_second": 2.729,
+      "step": 54200
+    },
+    {
+      "epoch": 22.86,
+      "grad_norm": 2.194784641265869,
+      "learning_rate": 1.1995759717314487e-05,
+      "loss": 0.3109,
+      "step": 54300
+    },
+    {
+      "epoch": 22.86,
+      "eval_cer": 0.33527482304172695,
+      "eval_loss": 2.228667736053467,
+      "eval_runtime": 394.9356,
+      "eval_samples_per_second": 23.999,
+      "eval_steps_per_second": 3.0,
+      "step": 54300
     }
   ],
   "logging_steps": 100,
@@ -8670,7 +8702,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.928113111954343e+20,
+  "total_flos": 5.949889515390252e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null