Training in progress, step 38300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0e4d057edfb8f7f24491b899369f7b93228a9e17e1354d5f644333b4e1576d
+oid sha256:28ca21937cf2d822209b3c05259b3ccf17f101b2990d8d77f4f382436b31f814
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfe756275a5388124bc2228feeaaf7ef82b935e701eb728a6a11413b046929db
+oid sha256:51b1bd241413fe670b447d5fde039c29e6fd164bd0971b9a810ec7e6e9644b5a
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d38f9132e2085616601917cca2b9dcaa50f30da1f10838a4c93930581540ab0
+oid sha256:e5f33e40ef0be0f68a21ea1be25305932b46c0041756190634386e045512b523
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f87a00bf8137824c3bb0753019893bcf791dd44d13ce34dc225bf7f0963a1806
-size 14567
+oid sha256:49898aff321bba13610449837ec6d94a8745b9be57e0cd4bf6c2fa192326186c
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe3a461b22634f6c029dd4cb55ac1a5510596e6da69170fbde554202a3b4b05
+oid sha256:32bd40b48ca3b96bc4530717bd2eed9f4f0e2a6be042cb204a84f6ce13b0abc0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.038728688697116,
+  "epoch": 16.122921490212587,
   "eval_steps": 100,
-  "global_step": 38100,
+  "global_step": 38300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6103,6 +6103,38 @@
       "eval_samples_per_second": 24.934,
       "eval_steps_per_second": 3.117,
       "step": 38100
+    },
+    {
+      "epoch": 16.08,
+      "grad_norm": 3.238290786743164,
+      "learning_rate": 2.3369611307420495e-05,
+      "loss": 0.738,
+      "step": 38200
+    },
+    {
+      "epoch": 16.08,
+      "eval_cer": 0.37189589769660947,
+      "eval_loss": 1.8234237432479858,
+      "eval_runtime": 391.4385,
+      "eval_samples_per_second": 24.213,
+      "eval_steps_per_second": 3.027,
+      "step": 38200
+    },
+    {
+      "epoch": 16.12,
+      "grad_norm": 3.291322708129883,
+      "learning_rate": 2.3298939929328624e-05,
+      "loss": 0.7327,
+      "step": 38300
+    },
+    {
+      "epoch": 16.12,
+      "eval_cer": 0.3755817136600055,
+      "eval_loss": 1.935049057006836,
+      "eval_runtime": 376.3761,
+      "eval_samples_per_second": 25.182,
+      "eval_steps_per_second": 3.148,
+      "step": 38300
     }
   ],
   "logging_steps": 100,
@@ -6110,7 +6142,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.175077130259511e+20,
+  "total_flos": 4.196836719020362e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null