Training in progress, step 32900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc051f6398a756522cc490f0a8f154f42b3f2b30d98bf7d60f11ac1888cdb3da
+oid sha256:43cf24c50a2fb90dff7e6f39ca95373b4b3a194b6e7b5ea3450b567d1cf2acd4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02021cbbbec3246b6712aecc4cd14c4d4dfc08e3dbc00c5473d548a791306375
+oid sha256:4045e3043dff6c75ceb1ceaf8651a36ad38e032419f1934e6b35b395ed37e495
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1539346c05dd0db53e003a5edfb0638d6fd9baf85cb3d6708792dcf6b2d6967
+oid sha256:830da9de182f0cddc597083bf4f5e081033ce68dba8352d3fc4bd7b82acf4629
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c999f4c1d5bb7ee3e6b99ed7a27056b2b32e84ae4ae775052bdec993bdba558
+oid sha256:66bf72c9582e89b0605330cab03a1ed6574afa16c96e8aa002547f90558e0a41
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f278373e69e9ebd2b300373366d8c349b14d9205b631b0731c93a52b7c91f8b
+oid sha256:fea4ba0cc40f8b6ca722c0ae8b27293a5270b2e8eb60bc080bc213006fdf44bc
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.765523047779414,
+  "epoch": 13.849715849294885,
   "eval_steps": 100,
-  "global_step": 32700,
+  "global_step": 32900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5239,6 +5239,38 @@
       "eval_samples_per_second": 25.63,
       "eval_steps_per_second": 3.204,
       "step": 32700
+    },
+    {
+      "epoch": 13.81,
+      "grad_norm": 1.3860234022140503,
+      "learning_rate": 2.718515901060071e-05,
+      "loss": 1.7756,
+      "step": 32800
+    },
+    {
+      "epoch": 13.81,
+      "eval_cer": 0.41578839310156035,
+      "eval_loss": 2.565376043319702,
+      "eval_runtime": 390.8183,
+      "eval_samples_per_second": 24.252,
+      "eval_steps_per_second": 3.032,
+      "step": 32800
+    },
+    {
+      "epoch": 13.85,
+      "grad_norm": 9.211983680725098,
+      "learning_rate": 2.7114487632508833e-05,
+      "loss": 1.0164,
+      "step": 32900
+    },
+    {
+      "epoch": 13.85,
+      "eval_cer": 0.39727621133315083,
+      "eval_loss": 2.448713779449463,
+      "eval_runtime": 372.957,
+      "eval_samples_per_second": 25.413,
+      "eval_steps_per_second": 3.177,
+      "step": 32900
     }
   ],
   "logging_steps": 100,
@@ -5246,7 +5278,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.582774517736169e+20,
+  "total_flos": 3.6049959871612964e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null