Training in progress, step 24500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1d86a67812950b8066ed1bd4785f9e5f74864e9e185c3c7d65a737e73412eb
+oid sha256:562e4a9f15032cff37840fc99c24b36c2938f6824c4ca58590bc282b9eceefae
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9bb1ef4ed06294b4512beffd9b8417f18d9d6c0bf30582a61d1b2418d2d7ea6
+oid sha256:efa372ea2585805112312160143a4a2b5f3a5057ba30e3e0eeff9dd31782e88f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2964d4840b876fd5ea402f55cbb3d3ecf1ccd015054120c9986b8308a80fe3b6
+oid sha256:28cf928a2adfc5e5cc511e1fa21a7d847528c68010f1f44667b1fe6fd9def055
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29deb45594f2ffe1b33e01ccb1b744191d09d4b58ab92a56ff666176b2e013c6
-size 14503
+oid sha256:eff48e968f7fe23fe47e4973cf98e3ccc5305e7ef8b406ef287a82f2825196c0
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed638b60d93524052d154552e2b26184c00d0eedea3ca18e5c2db2c0ab950927
+oid sha256:006849dff6df46bbddfe5a9b04e68547e9c816ca6762fb11abd57f00f2fd9546
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.145232582614186,
+  "epoch": 10.313618185645128,
   "eval_steps": 100,
-  "global_step": 24100,
+  "global_step": 24500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3863,6 +3863,70 @@
       "eval_samples_per_second": 25.751,
       "eval_steps_per_second": 3.22,
       "step": 24100
+    },
+    {
+      "epoch": 10.19,
+      "grad_norm": 2.6913535594940186,
+      "learning_rate": 3.3260777385159016e-05,
+      "loss": 1.2071,
+      "step": 24200
+    },
+    {
+      "epoch": 10.19,
+      "eval_cer": 0.43098382933792184,
+      "eval_loss": 1.9375296831130981,
+      "eval_runtime": 388.5754,
+      "eval_samples_per_second": 24.392,
+      "eval_steps_per_second": 3.05,
+      "step": 24200
+    },
+    {
+      "epoch": 10.23,
+      "grad_norm": 2.8861985206604004,
+      "learning_rate": 3.319010600706714e-05,
+      "loss": 1.2745,
+      "step": 24300
+    },
+    {
+      "epoch": 10.23,
+      "eval_cer": 0.43681563098822884,
+      "eval_loss": 1.8604010343551636,
+      "eval_runtime": 365.4924,
+      "eval_samples_per_second": 25.932,
+      "eval_steps_per_second": 3.242,
+      "step": 24300
+    },
+    {
+      "epoch": 10.27,
+      "grad_norm": 3.54598069190979,
+      "learning_rate": 3.3119434628975265e-05,
+      "loss": 1.3486,
+      "step": 24400
+    },
+    {
+      "epoch": 10.27,
+      "eval_cer": 0.4357133080442689,
+      "eval_loss": 1.3347864151000977,
+      "eval_runtime": 380.5736,
+      "eval_samples_per_second": 24.905,
+      "eval_steps_per_second": 3.114,
+      "step": 24400
+    },
+    {
+      "epoch": 10.31,
+      "grad_norm": 2.1198437213897705,
+      "learning_rate": 3.304876325088339e-05,
+      "loss": 1.1866,
+      "step": 24500
+    },
+    {
+      "epoch": 10.31,
+      "eval_cer": 0.4299792733956435,
+      "eval_loss": 1.308254361152649,
+      "eval_runtime": 368.9525,
+      "eval_samples_per_second": 25.689,
+      "eval_steps_per_second": 3.212,
+      "step": 24500
     }
   ],
   "logging_steps": 100,
@@ -3870,7 +3934,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.6405292408352522e+20,
+  "total_flos": 2.6839589636223064e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null