Training in progress, step 36700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212fd85a8f0771f83e70fda3fe36ae1286fc6ca154640d937c6b46050c337f8f
+oid sha256:a2e7d744e605fdeb47c357c118df95f001014156b76f00db93fae8270b36d782
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705d5ee447293f9a70d2f66760196b2c46343eca0cdcd5524ec4f3b449b70b84
+oid sha256:4a0e0ccb6fbb91ed7c1319992741aa3473b384fd1962f0a2bdef33fd8f0424a5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b3b70c810545bf21d9ddf057aebcb724eb6e9a8a7e6c91016e8f0e815ec023
+oid sha256:f2329d5a7fedc8f15c09d69541a87944d288c3f9c2684c5d81d7725abd374732
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a5b2fbf1a12d8205cee3894c54223b35a4a80e438d87a963917ccf699aca0e2
-size 14503
+oid sha256:792ef05d47d8fddd57baa2e5e4c79c5f1008526305f0fc51b7e4b0ff90c07793
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764ca9ef7fae34c6a8cba4f8df83adaaaca50ef1ca45f561d696e2b2507c6419
+oid sha256:28baba878695b471c12cd9b5814de5f1bb170226354cdd018df9f14201aec249
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.280993475057883,
+  "epoch": 15.449379078088823,
   "eval_steps": 100,
-  "global_step": 36300,
+  "global_step": 36700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5815,6 +5815,70 @@
       "eval_samples_per_second": 25.394,
       "eval_steps_per_second": 3.175,
       "step": 36300
+    },
+    {
+      "epoch": 15.32,
+      "grad_norm": 4.485095024108887,
+      "learning_rate": 2.4641696113074207e-05,
+      "loss": 0.8412,
+      "step": 36400
+    },
+    {
+      "epoch": 15.32,
+      "eval_cer": 0.3884747370067655,
+      "eval_loss": 2.459603786468506,
+      "eval_runtime": 390.2769,
+      "eval_samples_per_second": 24.285,
+      "eval_steps_per_second": 3.036,
+      "step": 36400
+    },
+    {
+      "epoch": 15.37,
+      "grad_norm": 7.8216471672058105,
+      "learning_rate": 2.4571024734982335e-05,
+      "loss": 0.8567,
+      "step": 36500
+    },
+    {
+      "epoch": 15.37,
+      "eval_cer": 0.3837354816002503,
+      "eval_loss": 3.254591226577759,
+      "eval_runtime": 377.582,
+      "eval_samples_per_second": 25.102,
+      "eval_steps_per_second": 3.138,
+      "step": 36500
+    },
+    {
+      "epoch": 15.41,
+      "grad_norm": 2.479659080505371,
+      "learning_rate": 2.450035335689046e-05,
+      "loss": 0.8539,
+      "step": 36600
+    },
+    {
+      "epoch": 15.41,
+      "eval_cer": 0.3853241953775762,
+      "eval_loss": 1.766408085823059,
+      "eval_runtime": 396.6796,
+      "eval_samples_per_second": 23.893,
+      "eval_steps_per_second": 2.987,
+      "step": 36600
+    },
+    {
+      "epoch": 15.45,
+      "grad_norm": 3.3775389194488525,
+      "learning_rate": 2.4429681978798587e-05,
+      "loss": 0.8428,
+      "step": 36700
+    },
+    {
+      "epoch": 15.45,
+      "eval_cer": 0.3814917289116577,
+      "eval_loss": 1.7772597074508667,
+      "eval_runtime": 373.2028,
+      "eval_samples_per_second": 25.396,
+      "eval_steps_per_second": 3.175,
+      "step": 36700
     }
   ],
   "logging_steps": 100,
@@ -5822,7 +5886,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.9789875911390396e+20,
+  "total_flos": 4.022627751818035e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null