Training in progress, step 20400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da8b304c458a518082aa8726d59c13923b22bcbfafb8c9974ba081498990923
+oid sha256:424006b63705ff8d128ce03cf112d0f0202b9b53563618c80069b74aadf6b121
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d579f962773a873e990bf64f2ef77b2bda2450b161ecf4daba9ef7ab67c9e1e
+oid sha256:486219a9cbd763fd42552ee2a1a2647b831dc1b08e3f181c8b5b51fe133f0228
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05592761d986af7a947218805add8c50c1c8d6fdee22c120c1dc80c2d3c678c3
+oid sha256:0908165977f8c3d9489a849f85d9268f712bef0a616c664c5b76ba43a71c7f3d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:514e6bb8aa1fefb3e31c68440ba01eb2833533f9f34d13f635293e87198bd4a2
+oid sha256:ae9aa79a869a104ab7e27c688f3cfabb1a5b016e6c0d9194e567985352b95f11
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:505d5d43fa0ef4ab6941e01c5cac91243ad894a08db7c0784e965134236be7af
+oid sha256:006c5e8305ef9dc1fe3403e1173068b8cb7f990d0fc5d4b955050dc8157ec06d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.503472953062513,
+  "epoch": 8.587665754577984,
   "eval_steps": 100,
-  "global_step": 20200,
+  "global_step": 20400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3239,6 +3239,38 @@
       "eval_samples_per_second": 26.116,
       "eval_steps_per_second": 3.265,
       "step": 20200
+    },
+    {
+      "epoch": 8.55,
+      "grad_norm": 6.447911262512207,
+      "learning_rate": 3.6016254416961133e-05,
+      "loss": 2.11,
+      "step": 20300
+    },
+    {
+      "epoch": 8.55,
+      "eval_cer": 0.43633657267998904,
+      "eval_loss": 3.3446898460388184,
+      "eval_runtime": 385.9035,
+      "eval_samples_per_second": 24.561,
+      "eval_steps_per_second": 3.071,
+      "step": 20300
+    },
+    {
+      "epoch": 8.59,
+      "grad_norm": 2.172891139984131,
+      "learning_rate": 3.5945583038869255e-05,
+      "loss": 1.4999,
+      "step": 20400
+    },
+    {
+      "epoch": 8.59,
+      "eval_cer": 0.4393355754565719,
+      "eval_loss": 3.0930521488189697,
+      "eval_runtime": 363.4753,
+      "eval_samples_per_second": 26.076,
+      "eval_steps_per_second": 3.26,
+      "step": 20400
     }
   ],
   "logging_steps": 100,
@@ -3246,7 +3278,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.2137141360320797e+20,
+  "total_flos": 2.2352658822253032e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null