Training in progress, step 10900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f48962b77a0ffadd466c017fcd32bec6946f7ff9c2a2e74009ea84a13a26ac
+oid sha256:925ca6a7a657be372a1ede2493cfd96a2f133c25e9867ec4da48475676fa164f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd244e0c641e9fc420b274487550a5fd81f515433393f446ae69f4eb95c66400
+oid sha256:f27c0cb6141c94d0dacfc876e294ea98c7799ee63d706b3da7170f154c3148ea
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5da71c3972cdf1c8ca47cfca858d3f5eebd3ddd0bbfffc533b99224dfc911ff
+oid sha256:89e99b8e65f7bf166bd10fd6d514d5c480e8db3676f1ced31fa5161b09b6df98
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e5ea2f8b945220efdb684f11b1780e2edefdb156c009e8c72ef7983c62a8e2
+oid sha256:327dc357355df114a69c34bffd061d4e755c0d795f133172f85021369d644224
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3e3c26689da313cb94037cbfc3a7e856b1f0f65c3a0e23766260d8fd9feabe
+oid sha256:5da37cafd44a01d142bb7be841997aa67fccdece5e8c01b177bc8c267b367398
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.504314881077668,
+  "epoch": 4.588507682593138,
   "eval_steps": 100,
-  "global_step": 10700,
+  "global_step": 10900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1719,6 +1719,38 @@
       "eval_samples_per_second": 26.262,
       "eval_steps_per_second": 3.283,
       "step": 10700
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 3.434525966644287,
+      "learning_rate": 4.272791519434629e-05,
+      "loss": 1.605,
+      "step": 10800
+    },
+    {
+      "epoch": 4.55,
+      "eval_cer": 0.4771103007312972,
+      "eval_loss": 3.0746238231658936,
+      "eval_runtime": 370.845,
+      "eval_samples_per_second": 25.558,
+      "eval_steps_per_second": 3.195,
+      "step": 10800
+    },
+    {
+      "epoch": 4.59,
+      "grad_norm": 6.7493815422058105,
+      "learning_rate": 4.265724381625442e-05,
+      "loss": 2.153,
+      "step": 10900
+    },
+    {
+      "epoch": 4.59,
+      "eval_cer": 0.4859728794337335,
+      "eval_loss": 2.0545401573181152,
+      "eval_runtime": 361.9049,
+      "eval_samples_per_second": 26.189,
+      "eval_steps_per_second": 3.274,
+      "step": 10900
     }
   ],
   "logging_steps": 100,
@@ -1726,7 +1758,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.1715979719910262e+20,
+  "total_flos": 1.1931430816580592e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null