Training in progress, step 20000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13d9360e86d6728b712f59c7c4708bbf9b1a6e025cbe69d32a8c222aedcfc489
+oid sha256:69774389453b3ace50a775638e2f5918335f227e54490308f1ecc9f049c680b9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d17c27964e0a9bb4db1d4e8f9a66d19db2579e7d1a4682579269e4387b23ca
+oid sha256:8eb25e6a96a19cf513e1cbf5b186f74f8277610735262c93589f5210fe9a995e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb443bec736266f1308adc945a429fcbd90b82f2937dc6e73185a9dc0e104218
+oid sha256:b9f40b795846ead1c0623ee579805fb3cfc72061e674100f80e71e636c069d35
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad3bce82b1ec9d0e105b84287a1d9a5af1cdbaae50b9ee14dce6c13e9ad62a7
-size 14567
+oid sha256:88808367e8c9aa08f2d1d94fe210aa146f1db378f3f747361538dc647479930a
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8004b4b6a8c520e4ed293ea3a4cb135c114f118b79d1b79d758805030484f7fb
+oid sha256:1b0d9587951dad3129d971e7ba722052a3740ec7e6470902edd12e67fb1998ca
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.335087350031571,
+  "epoch": 8.419280151547042,
   "eval_steps": 100,
-  "global_step": 19800,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3175,6 +3175,38 @@
       "eval_samples_per_second": 26.038,
       "eval_steps_per_second": 3.255,
       "step": 19800
+    },
+    {
+      "epoch": 8.38,
+      "grad_norm": 1.848604679107666,
+      "learning_rate": 3.629893992932862e-05,
+      "loss": 2.2543,
+      "step": 19900
+    },
+    {
+      "epoch": 8.38,
+      "eval_cer": 0.4581728325055727,
+      "eval_loss": 1.8045251369476318,
+      "eval_runtime": 381.1374,
+      "eval_samples_per_second": 24.868,
+      "eval_steps_per_second": 3.109,
+      "step": 19900
+    },
+    {
+      "epoch": 8.42,
+      "grad_norm": 34.23902893066406,
+      "learning_rate": 3.622826855123675e-05,
+      "loss": 1.313,
+      "step": 20000
+    },
+    {
+      "epoch": 8.42,
+      "eval_cer": 0.4448887411520864,
+      "eval_loss": 2.140085458755493,
+      "eval_runtime": 364.9023,
+      "eval_samples_per_second": 25.974,
+      "eval_steps_per_second": 3.247,
+      "step": 20000
     }
   ],
   "logging_steps": 100,
@@ -3182,7 +3214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.169673140779638e+20,
+  "total_flos": 2.1918019268617958e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null