Training in progress, step 29500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50232d939f78d5740a41fd81bf023712c5c693d778097c79e55298face0f025b
+oid sha256:74c74ecbee4e1a8242a17d4c2cfc3c46f09bdf3ff948db845e0287939b975dea
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db3e991dfe1a936d6ef65c495ee9761ff54d03321f26e0e255697576ef10d891
+oid sha256:ceb3b24b62b8f81ad58f841e1018bf034218bd58f9bdd1f410c406e08bcdd920
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998edb77418ff8b92315111e002be1e2e7d45d4fb7abc865004a01191ced046e
+oid sha256:fb0467bc8c50dfe57f4bcbd8fc88cea7ba636d0b36b1de300428fb502e231787
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a86fe569935bf8228ce07fba57b2a527aee99754700b112dc1c3845b5131fc
+oid sha256:80f2285403a1ec740056f3337347a8efaeed42b939a0542107a6039f7778e7dd
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8281fbededb748303e66d7421871c4aa440861dfbc8b82b3df124b186a19421d
+oid sha256:148cfef2b67149a381f9c475314fcab86d5e5e65400d90bb5d47c1b39f20affa
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.334245422016417,
+  "epoch": 12.418438223531888,
   "eval_steps": 100,
-  "global_step": 29300,
+  "global_step": 29500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4695,6 +4695,38 @@
       "eval_samples_per_second": 25.691,
       "eval_steps_per_second": 3.212,
       "step": 29300
+    },
+    {
+      "epoch": 12.38,
+      "grad_norm": 2.1881866455078125,
+      "learning_rate": 2.9587279151943463e-05,
+      "loss": 1.0462,
+      "step": 29400
+    },
+    {
+      "epoch": 12.38,
+      "eval_cer": 0.40699180712525906,
+      "eval_loss": 1.977940320968628,
+      "eval_runtime": 389.1348,
+      "eval_samples_per_second": 24.357,
+      "eval_steps_per_second": 3.045,
+      "step": 29400
+    },
+    {
+      "epoch": 12.42,
+      "grad_norm": 2.38139009475708,
+      "learning_rate": 2.951660777385159e-05,
+      "loss": 1.0711,
+      "step": 29500
+    },
+    {
+      "epoch": 12.42,
+      "eval_cer": 0.4067278362207188,
+      "eval_loss": 1.981135606765747,
+      "eval_runtime": 374.3024,
+      "eval_samples_per_second": 25.322,
+      "eval_steps_per_second": 3.166,
+      "step": 29500
     }
   ],
   "logging_steps": 100,
@@ -4702,7 +4734,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.21083173107527e+20,
+  "total_flos": 3.232564742637217e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null