Training in progress, step 54500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:261f5aa29d796648d142454d356754c0daa58ea249148b27851231430a96995c
+oid sha256:d18b1ffc01be06a7d955de27541e116d684fa2a9a6af297dbb7f02ff2552fcb9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e6973bc5c3aceef25441e3d061e46116955f4cf9ff95f3edcc89fd5823832b
+oid sha256:2b88e4c89ab318c14f3a49bcac249af4939619e98fce1829a0711517576dfb87
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b57c1cb981aa093ad536532c531f30dd1534cd1ce4054df1e5da8e31c553687
+oid sha256:c1e7d9c1caa0d1b3d5c6725d4b4337ebc28a60d58662fcc30551cee24b6f8682
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c9224ba23bc6336e062987353c9877aacd7d8246979cd20e730d3da7787040
-size 14567
+oid sha256:683cc9fc24d2ae77adc186a85857b0c580cacfda070070405742dd40f4a6f6bb
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1d6f240808a249e74b97cfcaffd4c82e145821d5e3022d1fd6a98866547498c
+oid sha256:6284b9930aef0581c1cf4c3684706693afb2aa3723205627204c06ef0b42946b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.858345611450222,
+  "epoch": 22.942538412965693,
   "eval_steps": 100,
-  "global_step": 54300,
+  "global_step": 54500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8695,6 +8695,38 @@
       "eval_samples_per_second": 23.999,
       "eval_steps_per_second": 3.0,
       "step": 54300
+    },
+    {
+      "epoch": 22.9,
+      "grad_norm": 4.459865570068359,
+      "learning_rate": 1.1925088339222615e-05,
+      "loss": 0.3105,
+      "step": 54400
+    },
+    {
+      "epoch": 22.9,
+      "eval_cer": 0.33500596378710257,
+      "eval_loss": 2.3388936519622803,
+      "eval_runtime": 432.3816,
+      "eval_samples_per_second": 21.92,
+      "eval_steps_per_second": 2.741,
+      "step": 54400
+    },
+    {
+      "epoch": 22.94,
+      "grad_norm": 2.0811266899108887,
+      "learning_rate": 1.1854416961130743e-05,
+      "loss": 0.3078,
+      "step": 54500
+    },
+    {
+      "epoch": 22.94,
+      "eval_cer": 0.3347126627820578,
+      "eval_loss": 2.5939130783081055,
+      "eval_runtime": 402.0697,
+      "eval_samples_per_second": 23.573,
+      "eval_steps_per_second": 2.947,
+      "step": 54500
     }
   ],
   "logging_steps": 100,
@@ -8702,7 +8734,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.949889515390252e+20,
+  "total_flos": 5.971614270421255e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null