Training in progress, step 51300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc94c256078d60ae60c29652217c2629d9b9f6461e83c504a29f2ff2d758717
+oid sha256:0840e5b81106618e117773e1a9e46982326d5ef4a4376f8f91884378562a9093
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82a0535ceb94588d81de04a572d016f4ae08f4ed23493fe6e58cef9b9b99eef
+oid sha256:fb3ddfda4162ba8509efb41a733e19dbd95c0d6e0e8081c1227b99cdf29a4920
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5931c1deaa9accec9ce16ef413a75648d348abcbfbaeca5ad9ddeaba52d1ff7
+oid sha256:350d3e5875623b979435692aeda728979a132c77413bd449e25e3d20ae0234e7
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafedcdde0154a6bd325b96ceffadec13f91f8224b1692d8e35fbd99757a6c2c
+oid sha256:05f6e0293bbf3f1668750a9d5b5151fa82c485734c4a7e5502f70e556472e25e
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c69be6938fe5dd8ba71aa4b3717263a23a1baa9c26c2e9c021d17a37e3a94bd
+oid sha256:f9e1cfa7c07b2a4f4036b4175c9d726fa25f567b5351fc720a65fdcaf21b2d3e
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.511260787202694,
+  "epoch": 21.595453588718165,
   "eval_steps": 100,
-  "global_step": 51100,
+  "global_step": 51300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8183,6 +8183,38 @@
       "eval_samples_per_second": 24.453,
       "eval_steps_per_second": 3.057,
       "step": 51100
+    },
+    {
+      "epoch": 21.55,
+      "grad_norm": 2.3857908248901367,
+      "learning_rate": 1.4185865724381625e-05,
+      "loss": 0.3469,
+      "step": 51200
+    },
+    {
+      "epoch": 21.55,
+      "eval_cer": 0.3406764498846349,
+      "eval_loss": 2.440829277038574,
+      "eval_runtime": 418.2267,
+      "eval_samples_per_second": 22.662,
+      "eval_steps_per_second": 2.833,
+      "step": 51200
+    },
+    {
+      "epoch": 21.6,
+      "grad_norm": 1.5880221128463745,
+      "learning_rate": 1.4115194346289753e-05,
+      "loss": 0.3514,
+      "step": 51300
+    },
+    {
+      "epoch": 21.6,
+      "eval_cer": 0.34056157365765904,
+      "eval_loss": 2.3072359561920166,
+      "eval_runtime": 388.3106,
+      "eval_samples_per_second": 24.408,
+      "eval_steps_per_second": 3.052,
+      "step": 51300
     }
   ],
   "logging_steps": 100,
@@ -8190,7 +8222,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.6001325221620836e+20,
+  "total_flos": 5.621976956469394e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null