Training in progress, step 38900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78672eae05411d7dfefd57b3254fa47cd72769991a6baaa5e1092236d2622db5
+oid sha256:86aedaea68068dd5c1a8b421f702958fe0acd2fbb8823da4823612fb4e7c45bf
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22915e67daad57243bf515bd80ed79bb3ec54110fd7c78d46422156d5fdcb88c
+oid sha256:727182a7c870435209c98f44944156abd6a6c3261ccb96daf87907a574c1b37b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380581ce44959c9c175fb724813187d7c36d1ce791ca3dfe21d6b0b4f80f6aaf
+oid sha256:93a07f3eb542190ed23f7b40d5f4678b80bd5b4ba91438888eb3d3cb6fc3186e
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d509fbeb2d6b8e5d595bc7a9e0a2d01ae61002e35af8526d5144d83377487f
-size 14503
+oid sha256:91e28ae43f1dd07d9a9ddf4073e22adb6e7929806ef21e48eb3b580f30a7e559
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ece92974bf15f79708e9c8cceb24d9f0629188b90b52a77e12c8501d92cc731
+oid sha256:5e9da594946dcc239f89ecda3fc48286b363af1118506368ef79741edf876cc1
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.291307093243528,
+  "epoch": 16.375499894759,
   "eval_steps": 100,
-  "global_step": 38700,
+  "global_step": 38900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6199,6 +6199,38 @@
       "eval_samples_per_second": 25.205,
       "eval_steps_per_second": 3.151,
       "step": 38700
+    },
+    {
+      "epoch": 16.33,
+      "grad_norm": 1.934323787689209,
+      "learning_rate": 2.2945583038869257e-05,
+      "loss": 0.7233,
+      "step": 38800
+    },
+    {
+      "epoch": 16.33,
+      "eval_cer": 0.3704929412224786,
+      "eval_loss": 2.179749011993408,
+      "eval_runtime": 389.749,
+      "eval_samples_per_second": 24.318,
+      "eval_steps_per_second": 3.04,
+      "step": 38800
+    },
+    {
+      "epoch": 16.38,
+      "grad_norm": 2.3759796619415283,
+      "learning_rate": 2.287491166077739e-05,
+      "loss": 0.743,
+      "step": 38900
+    },
+    {
+      "epoch": 16.38,
+      "eval_cer": 0.3723774001798913,
+      "eval_loss": 2.006964683532715,
+      "eval_runtime": 381.2342,
+      "eval_samples_per_second": 24.861,
+      "eval_steps_per_second": 3.108,
+      "step": 38900
     }
   ],
   "logging_steps": 100,
@@ -6206,7 +6238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.2406406618689883e+20,
+  "total_flos": 4.262537185081538e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null