Training in progress, step 18800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05600eb332380574b52f500b4d9acf6495af5b8f8c8a80d16d05132a35dbdde4
+oid sha256:cb4a32dca6535b97ec9d409e1a20428735a6caf1a07d9a581e33bfebdd98da98
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4566bb143a9221c476166298783b072e2d5600fad5a694751515835f2329e9
+oid sha256:deeb9007a2105b9fb534ca944aa12eb54abb9e830e8010cc6a86bc5057ba3f51
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5217e8be28535efa2a4e60fd1aa4e2ad60fdba5e79e0caffb56d99a0213dd6ae
+oid sha256:56b60272ee229edfde841bdf64339526be164c159e635b4cca6a36b012e8b8f8
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e574121cd2f48fe3779fc12e2fc48d6f0347b202db10a57a0f0ac24a750e3f
-size 14567
+oid sha256:76df4b30fe1f8da5a7cc93cde7f754197127ebb58da2a061a690a113c1c8f092
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848b9d4191f57596a67ed77f7f652c25002d270d8cdf8a0d9e34a780cddc39f5
+oid sha256:86f6690eee3cc7efd55068f6778b0cdb2acd34211dc189d0a8d254cc2fc4d966
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.82993054093875,
+  "epoch": 7.91412334245422,
   "eval_steps": 100,
-  "global_step": 18600,
+  "global_step": 18800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2983,6 +2983,38 @@
       "eval_samples_per_second": 25.775,
       "eval_steps_per_second": 3.223,
       "step": 18600
+    },
+    {
+      "epoch": 7.87,
+      "grad_norm": 2.091411590576172,
+      "learning_rate": 3.714628975265018e-05,
+      "loss": 1.7498,
+      "step": 18700
+    },
+    {
+      "epoch": 7.87,
+      "eval_cer": 0.44587129951898635,
+      "eval_loss": 2.4873616695404053,
+      "eval_runtime": 381.5796,
+      "eval_samples_per_second": 24.839,
+      "eval_steps_per_second": 3.106,
+      "step": 18700
+    },
+    {
+      "epoch": 7.91,
+      "grad_norm": 2.1210122108459473,
+      "learning_rate": 3.7075618374558305e-05,
+      "loss": 1.4463,
+      "step": 18800
+    },
+    {
+      "epoch": 7.91,
+      "eval_cer": 0.4508696374799578,
+      "eval_loss": 2.1447994709014893,
+      "eval_runtime": 360.7307,
+      "eval_samples_per_second": 26.274,
+      "eval_steps_per_second": 3.285,
+      "step": 18800
     }
   ],
   "logging_steps": 100,
@@ -2990,7 +3022,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.0376121366581146e+20,
+  "total_flos": 2.0599593093311608e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null