Training in progress, step 22700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a6f6fa04efb391c7b9fbd08481c3254f51e8b2441232585f62a46a10bf14603
+oid sha256:1f673b59dec39b6208eaf91ca45400990b1ab1106cb32adb89e40289b3692b7e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d778a8ad947e1c4d0ef5534ea92304b2cc11141de4fb34b0cf684c5c48ad306b
+oid sha256:19267df07b64ec62c5070fedddb73269d34ceb079fafa1cc02aa086792ab3300
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc91affcdb5daa6221794d9599eeb12bcba1f681e61698d0b5225d19c1246f0d
+oid sha256:cc7974ef7e39b635024ed4786978103eb9d236e553fc1a70a6679023daa9296c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275755e5f99f71b688f2ecd5a64a5f85d430b909b06bf279b4dfbdc41ff3aab1
-size 14567
+oid sha256:8052a894386dd37f759deaab2c0d19acd6e44b9e9130c47c71e3f213d13e6053
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b142e6816a019f0e45a0c6af01127180a64accf85a0b47c2b9c58feab018eef9
+oid sha256:d49d336b26493b459dab233dfc32ed3bf79ed6ce889dcb67006a60f916875b97
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.471690170490422,
+  "epoch": 9.555882972005893,
   "eval_steps": 100,
-  "global_step": 22500,
+  "global_step": 22700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3607,6 +3607,38 @@
       "eval_samples_per_second": 25.533,
       "eval_steps_per_second": 3.192,
       "step": 22500
+    },
+    {
+      "epoch": 9.51,
+      "grad_norm": 2.171220302581787,
+      "learning_rate": 3.439151943462898e-05,
+      "loss": 1.2667,
+      "step": 22600
+    },
+    {
+      "epoch": 9.51,
+      "eval_cer": 0.44492784795275897,
+      "eval_loss": 1.6504524946212769,
+      "eval_runtime": 384.6648,
+      "eval_samples_per_second": 24.64,
+      "eval_steps_per_second": 3.081,
+      "step": 22600
+    },
+    {
+      "epoch": 9.56,
+      "grad_norm": 4.868325233459473,
+      "learning_rate": 3.43208480565371e-05,
+      "loss": 1.2425,
+      "step": 22700
+    },
+    {
+      "epoch": 9.56,
+      "eval_cer": 0.4337261937350905,
+      "eval_loss": 1.6726810932159424,
+      "eval_runtime": 360.9955,
+      "eval_samples_per_second": 26.255,
+      "eval_steps_per_second": 3.283,
+      "step": 22700
     }
   ],
   "logging_steps": 100,
@@ -3614,7 +3646,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.4656325068595944e+20,
+  "total_flos": 2.487348846779533e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null