Training in progress, step 29300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd39bafad8df5816ff6b08c12be7dca52286baccaa654ea2978e0d3f02bf4e5
+oid sha256:50232d939f78d5740a41fd81bf023712c5c693d778097c79e55298face0f025b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fdf718b07a591ed57ff7ce95664e7e067c38f3eb310eba7c991b75dbb1fafa
+oid sha256:db3e991dfe1a936d6ef65c495ee9761ff54d03321f26e0e255697576ef10d891
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737d384bbb23eea51775050fd71e06d427c4606907f23670a2074c1709a9001f
+oid sha256:998edb77418ff8b92315111e002be1e2e7d45d4fb7abc865004a01191ced046e
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a57ee799b5913dee6e5865779e9212480500a11279764d115cea4398001ef0
+oid sha256:46a86fe569935bf8228ce07fba57b2a527aee99754700b112dc1c3845b5131fc
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3333223a097f72436e52b6f08ce4e75389646a8070023e25dcc110bc5f88e5d8
+oid sha256:8281fbededb748303e66d7421871c4aa440861dfbc8b82b3df124b186a19421d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.250052620500947,
+  "epoch": 12.334245422016417,
   "eval_steps": 100,
-  "global_step": 29100,
+  "global_step": 29300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4663,6 +4663,38 @@
       "eval_samples_per_second": 25.305,
       "eval_steps_per_second": 3.164,
       "step": 29100
+    },
+    {
+      "epoch": 12.29,
+      "grad_norm": 26.448299407958984,
+      "learning_rate": 2.9728621908127207e-05,
+      "loss": 1.091,
+      "step": 29200
+    },
+    {
+      "epoch": 12.29,
+      "eval_cer": 0.41021811818075166,
+      "eval_loss": 1.8954789638519287,
+      "eval_runtime": 388.9635,
+      "eval_samples_per_second": 24.367,
+      "eval_steps_per_second": 3.047,
+      "step": 29200
+    },
+    {
+      "epoch": 12.33,
+      "grad_norm": 19.144874572753906,
+      "learning_rate": 2.965795053003534e-05,
+      "loss": 1.0624,
+      "step": 29300
+    },
+    {
+      "epoch": 12.33,
+      "eval_cer": 0.41046497985999764,
+      "eval_loss": 1.6875534057617188,
+      "eval_runtime": 368.9225,
+      "eval_samples_per_second": 25.691,
+      "eval_steps_per_second": 3.212,
+      "step": 29300
     }
   ],
   "logging_steps": 100,
@@ -4670,7 +4702,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.1890627031696395e+20,
+  "total_flos": 3.21083173107527e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null