Training in progress, step 48700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1672c0a76833a5b5822154c7fa186402def49a98de876f28ea3494cad8f8888d
+oid sha256:919479edc9c44b709a6fbc48787e8e31ae9b413ae5d1bf037e00f15a35aa7618
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36beb4b37fe86763115810c74e72bd6beb673e075cd6a49cc0bce66f1564a42e
+oid sha256:10995179ef6d151496a819060d002d0d14d0ae4946c8f3186f134f7b134c7b4c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa6ee9fb6e8b8ff058d8531424821cbaa6688b19e17750aa45dece30fa41780
+oid sha256:38b0edab5285069b45c657b2c1e8a54173d39533689345a0336372816e6ee99f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1366c26f46b0efee6d4bad587c69654e431d12bbbd1ef637f411a48b4d281d1
-size 14567
+oid sha256:8905c27bc949ca26e4d080125b36f4b021cbb40b50e21f90195179c8522e0ada
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e98968c8be08f3c058353eaf3e9c13f6c3ef943aba36fc721f7302bf66d7b2a7
+oid sha256:c5c0c262f0099d55672ec4b48865245d6b1a61a5275913739ab46d7d5cc0df15
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.41675436750158,
+  "epoch": 20.50094716901705,
   "eval_steps": 100,
-  "global_step": 48500,
+  "global_step": 48700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7767,6 +7767,38 @@
       "eval_samples_per_second": 24.334,
       "eval_steps_per_second": 3.042,
       "step": 48500
+    },
+    {
+      "epoch": 20.46,
+      "grad_norm": 4.963177680969238,
+      "learning_rate": 1.6023321554770318e-05,
+      "loss": 0.456,
+      "step": 48600
+    },
+    {
+      "epoch": 20.46,
+      "eval_cer": 0.34791120800907277,
+      "eval_loss": 2.5059995651245117,
+      "eval_runtime": 407.1464,
+      "eval_samples_per_second": 23.279,
+      "eval_steps_per_second": 2.911,
+      "step": 48600
+    },
+    {
+      "epoch": 20.5,
+      "grad_norm": 1.5969637632369995,
+      "learning_rate": 1.5952650176678446e-05,
+      "loss": 0.3946,
+      "step": 48700
+    },
+    {
+      "epoch": 20.5,
+      "eval_cer": 0.34289331664776507,
+      "eval_loss": 3.0652801990509033,
+      "eval_runtime": 388.6588,
+      "eval_samples_per_second": 24.386,
+      "eval_steps_per_second": 3.049,
+      "step": 48700
     }
   ],
   "logging_steps": 100,
@@ -7774,7 +7806,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.314599801292227e+20,
+  "total_flos": 5.336332584830473e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null