Training in progress, step 20200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69774389453b3ace50a775638e2f5918335f227e54490308f1ecc9f049c680b9
+oid sha256:1da8b304c458a518082aa8726d59c13923b22bcbfafb8c9974ba081498990923
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb25e6a96a19cf513e1cbf5b186f74f8277610735262c93589f5210fe9a995e
+oid sha256:5d579f962773a873e990bf64f2ef77b2bda2450b161ecf4daba9ef7ab67c9e1e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f40b795846ead1c0623ee579805fb3cfc72061e674100f80e71e636c069d35
+oid sha256:05592761d986af7a947218805add8c50c1c8d6fdee22c120c1dc80c2d3c678c3
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88808367e8c9aa08f2d1d94fe210aa146f1db378f3f747361538dc647479930a
-size 14503
+oid sha256:514e6bb8aa1fefb3e31c68440ba01eb2833533f9f34d13f635293e87198bd4a2
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0d9587951dad3129d971e7ba722052a3740ec7e6470902edd12e67fb1998ca
+oid sha256:505d5d43fa0ef4ab6941e01c5cac91243ad894a08db7c0784e965134236be7af
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.419280151547042,
+  "epoch": 8.503472953062513,
   "eval_steps": 100,
-  "global_step": 20000,
+  "global_step": 20200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3207,6 +3207,38 @@
       "eval_samples_per_second": 25.974,
       "eval_steps_per_second": 3.247,
       "step": 20000
+    },
+    {
+      "epoch": 8.46,
+      "grad_norm": 1.8063780069351196,
+      "learning_rate": 3.615759717314488e-05,
+      "loss": 2.0001,
+      "step": 20100
+    },
+    {
+      "epoch": 8.46,
+      "eval_cer": 0.44904628289859605,
+      "eval_loss": 3.0254170894622803,
+      "eval_runtime": 380.5352,
+      "eval_samples_per_second": 24.907,
+      "eval_steps_per_second": 3.114,
+      "step": 20100
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 4.191483974456787,
+      "learning_rate": 3.6086925795053005e-05,
+      "loss": 1.2751,
+      "step": 20200
+    },
+    {
+      "epoch": 8.5,
+      "eval_cer": 0.4562517109225294,
+      "eval_loss": 4.0329742431640625,
+      "eval_runtime": 362.926,
+      "eval_samples_per_second": 26.116,
+      "eval_steps_per_second": 3.265,
+      "step": 20200
     }
   ],
   "logging_steps": 100,
@@ -3214,7 +3246,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.1918019268617958e+20,
+  "total_flos": 2.2137141360320797e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null