Training in progress, step 55900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:785057a17e70302c21c007e0ef0b0f57a36cfb96718c31c8f395b008e214458d
+oid sha256:5350a3d670e63e0e724e9a948f10fee13c3e2f281c6e2cbb34e1e8d199bcddd6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19609ff9aeb7b6551ed81c17110b29191a5d741f3df4560f9d420d2d58bce8b9
+oid sha256:c30ad926c245886d2d7b37d4b9f136480894a256273517a47903a260a6350a0f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:293accb5c9dbd84af2034bf699ee6c8b6fc3c17f88796b7449387a733eaff90c
+oid sha256:0dc2cf3451e42ae8925d9cbf46fea6e10421c2853d0ff857ca4521a7443ec2ed
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cde67baa4dd7f0279761a9f5a42adbc49a7e57ab6ad2ad6773f0f379f28031b
+oid sha256:ffe56cb4545356428f0c754a6c3b227de992c60c335c1b79bf625d3be68349b6
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d431db1e058e7753d522d0aa651c6ef43b7fbfb259f3bade675c44750e1cb84
+oid sha256:86566b254e3e5928bcfd37fb46ba4a9e0762d9834543bb6f29fbaab70f97de5d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.447695222058513,
+  "epoch": 23.531888023573984,
   "eval_steps": 100,
-  "global_step": 55700,
+  "global_step": 55900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8919,6 +8919,38 @@
       "eval_samples_per_second": 23.49,
       "eval_steps_per_second": 2.937,
       "step": 55700
+    },
+    {
+      "epoch": 23.49,
+      "grad_norm": 1.8252880573272705,
+      "learning_rate": 1.0935689045936397e-05,
+      "loss": 0.2634,
+      "step": 55800
+    },
+    {
+      "epoch": 23.49,
+      "eval_cer": 0.3340087403699503,
+      "eval_loss": 2.7159037590026855,
+      "eval_runtime": 426.7576,
+      "eval_samples_per_second": 22.209,
+      "eval_steps_per_second": 2.777,
+      "step": 55800
+    },
+    {
+      "epoch": 23.53,
+      "grad_norm": 1.250098466873169,
+      "learning_rate": 1.0865017667844523e-05,
+      "loss": 0.2592,
+      "step": 55900
+    },
+    {
+      "epoch": 23.53,
+      "eval_cer": 0.3338596456923859,
+      "eval_loss": 2.6912946701049805,
+      "eval_runtime": 397.5959,
+      "eval_samples_per_second": 23.838,
+      "eval_steps_per_second": 2.98,
+      "step": 55900
     }
   ],
   "logging_steps": 100,
@@ -8926,7 +8958,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.103646459472622e+20,
+  "total_flos": 6.12582004081098e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null