Training in progress, step 29700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c74ecbee4e1a8242a17d4c2cfc3c46f09bdf3ff948db845e0287939b975dea
+oid sha256:e68ea1988adeb339de8fec3f9339ae2e610fdc78d37a899de33b92dc31a8778e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb3b24b62b8f81ad58f841e1018bf034218bd58f9bdd1f410c406e08bcdd920
+oid sha256:104344ee154889869d6dedaa406882521e8ffda57ed470d6f198a5ee48bd5eaf
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0467bc8c50dfe57f4bcbd8fc88cea7ba636d0b36b1de300428fb502e231787
+oid sha256:fc040a80a5272a21db9b6b731bb1e83dc816581c92f952fb1897abe3414cc9a7
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f2285403a1ec740056f3337347a8efaeed42b939a0542107a6039f7778e7dd
+oid sha256:359f2156e19f2ec5bc6dded0d2150c295c3c63a7ad8ee22ed71b68fed5bc2e23
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148cfef2b67149a381f9c475314fcab86d5e5e65400d90bb5d47c1b39f20affa
+oid sha256:f9221d64181d2487e327013dbd89210af652170a383b61db186b5d6c56be9471
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.418438223531888,
+  "epoch": 12.502631025047359,
   "eval_steps": 100,
-  "global_step": 29500,
+  "global_step": 29700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4727,6 +4727,38 @@
       "eval_samples_per_second": 25.322,
       "eval_steps_per_second": 3.166,
       "step": 29500
+    },
+    {
+      "epoch": 12.46,
+      "grad_norm": 13.329228401184082,
+      "learning_rate": 2.944593639575972e-05,
+      "loss": 1.041,
+      "step": 29600
+    },
+    {
+      "epoch": 12.46,
+      "eval_cer": 0.41142309647647723,
+      "eval_loss": 2.5235061645507812,
+      "eval_runtime": 396.1248,
+      "eval_samples_per_second": 23.927,
+      "eval_steps_per_second": 2.991,
+      "step": 29600
+    },
+    {
+      "epoch": 12.5,
+      "grad_norm": 3.899754524230957,
+      "learning_rate": 2.9375265017667848e-05,
+      "loss": 1.1686,
+      "step": 29700
+    },
+    {
+      "epoch": 12.5,
+      "eval_cer": 0.4094359821672989,
+      "eval_loss": 1.6854169368743896,
+      "eval_runtime": 371.974,
+      "eval_samples_per_second": 25.48,
+      "eval_steps_per_second": 3.186,
+      "step": 29700
     }
   ],
   "logging_steps": 100,
@@ -4734,7 +4766,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.232564742637217e+20,
+  "total_flos": 3.254575201001735e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null