Training in progress, step 24700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562e4a9f15032cff37840fc99c24b36c2938f6824c4ca58590bc282b9eceefae
+oid sha256:ced1d4dde33aefe5dc39b13645ee47a4fd8e1770aa5a898de3b845e505ff1c54
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efa372ea2585805112312160143a4a2b5f3a5057ba30e3e0eeff9dd31782e88f
+oid sha256:66f1f55268dc994db0d05cb94152e6bf792c2200b525e6387d02aaf9ae9bccf5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cf928a2adfc5e5cc511e1fa21a7d847528c68010f1f44667b1fe6fd9def055
+oid sha256:5119a87747b87e471b8a600bd8ac1f15b46eea46cd11df632ac6499078f8b490
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff48e968f7fe23fe47e4973cf98e3ccc5305e7ef8b406ef287a82f2825196c0
-size 14567
+oid sha256:e25c2ae242c4ef3e74feef24b9532eb46e95b0eb0e303649bd76f8613a1702b0
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006849dff6df46bbddfe5a9b04e68547e9c816ca6762fb11abd57f00f2fd9546
+oid sha256:9e7497143a450b0fe1b393b84fb43e48289b6099fa5e2bc00a016595988f9227
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.313618185645128,
+  "epoch": 10.397810987160598,
   "eval_steps": 100,
-  "global_step": 24500,
+  "global_step": 24700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3927,6 +3927,38 @@
       "eval_samples_per_second": 25.689,
       "eval_steps_per_second": 3.212,
       "step": 24500
+    },
+    {
+      "epoch": 10.36,
+      "grad_norm": 2.029782295227051,
+      "learning_rate": 3.297809187279152e-05,
+      "loss": 1.1697,
+      "step": 24600
+    },
+    {
+      "epoch": 10.36,
+      "eval_cer": 0.42697293809393455,
+      "eval_loss": 1.4594690799713135,
+      "eval_runtime": 389.4322,
+      "eval_samples_per_second": 24.338,
+      "eval_steps_per_second": 3.043,
+      "step": 24600
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 2.0395631790161133,
+      "learning_rate": 3.290742049469965e-05,
+      "loss": 1.1793,
+      "step": 24700
+    },
+    {
+      "epoch": 10.4,
+      "eval_cer": 0.42983506706816316,
+      "eval_loss": 1.475653886795044,
+      "eval_runtime": 374.0567,
+      "eval_samples_per_second": 25.338,
+      "eval_steps_per_second": 3.168,
+      "step": 24700
     }
   ],
   "logging_steps": 100,
@@ -3934,7 +3966,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.6839589636223064e+20,
+  "total_flos": 2.7057203744998287e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null