Training in progress, step 33900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bdec49f5ba937575c37201bec00db52b8c3e844821eecc385ba239a33663f10
+oid sha256:d4186f3650dd2c32b5c95649922f0c731bb934e125494ff655895c62239c4ca2
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619c1c99184b876365ca973837576037ba7b39716899416a2f1019041043ea17
+oid sha256:ff80ab491126fed19c95d290404bfe1af60734b253ff71a62d4b455264686070
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0729b7a58599ea8921b314d9c9621e535f2d82f309864faa4b6d052417b8b263
+oid sha256:7977c1dc90467f2c33a0b7b407c78f8d85c3fac6707f046993eb9f84bc014848
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44661c431a879e3226aadc89367134cd0b53d52f6af54472aaa115083d69b12e
+oid sha256:cf8717eba5f8c781613f5361807f6b34d91ead5957ce05c9b325c92b9b4e28f0
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a48819e7745c34bedd45ae62b08be3d10aa46039968cd3e6efddcf11d1d5426
+oid sha256:dc335cf92591df6c603a8f2a60377fa97b6288d754e2350836d0114c03b2d445
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.186487055356768,
+  "epoch": 14.270679856872237,
   "eval_steps": 100,
-  "global_step": 33700,
+  "global_step": 33900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5399,6 +5399,38 @@
       "eval_samples_per_second": 25.278,
       "eval_steps_per_second": 3.16,
       "step": 33700
+    },
+    {
+      "epoch": 14.23,
+      "grad_norm": 2.4856455326080322,
+      "learning_rate": 2.647844522968198e-05,
+      "loss": 0.9387,
+      "step": 33800
+    },
+    {
+      "epoch": 14.23,
+      "eval_cer": 0.3982514371749247,
+      "eval_loss": 1.5301440954208374,
+      "eval_runtime": 391.5929,
+      "eval_samples_per_second": 24.204,
+      "eval_steps_per_second": 3.026,
+      "step": 33800
+    },
+    {
+      "epoch": 14.27,
+      "grad_norm": 21.76763916015625,
+      "learning_rate": 2.6407773851590107e-05,
+      "loss": 0.9334,
+      "step": 33900
+    },
+    {
+      "epoch": 14.27,
+      "eval_cer": 0.3909311329240155,
+      "eval_loss": 2.4011144638061523,
+      "eval_runtime": 373.6109,
+      "eval_samples_per_second": 25.369,
+      "eval_steps_per_second": 3.172,
+      "step": 33900
     }
   ],
   "logging_steps": 100,
@@ -5406,7 +5438,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.693186041855623e+20,
+  "total_flos": 3.715219759674186e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null