Training in progress, step 850, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b38eab253dba5b0deb684b9be7be55b35fccfa203ed22bec471b3d2aa494879
+oid sha256:da079b9d8ca9edec5c19d40185ac34a5d967b988536e67ab8c54c5fc8c3731b0
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2706762d78364c391d070350d7079727bc3b17acaff24aa2d513f2e945c300f
+oid sha256:2d536b0da6ed2281687c34137ae7211c81201040fd7f921085d915c4552739c2
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a211653fa38f3820ad08baeef7bf2217831b7fa32c8abb08f12aef6c9bf3c4f
+oid sha256:69b86e924bddef11293e860631f6e1e1350720b1f64e7f8977d7267e36a24ee7
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9213080fe2b45399b87036ca9ff9164533abe6b368e5c828136ee184486749d4
+oid sha256:86a2aa7bca84d2b8e7dd4e04a286714ba9169af11c46c739950a52df4c45259f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462c3770d14e466903ac3cbb8d02a07b05bb99c1e78e9ab65cd1a8165b933c02
+oid sha256:9109740607103fa260f8765f6910df83c4ef7244fe0858cce09056260804c468
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.04996876951905059,
+  "epoch": 0.05309181761399125,
   "eval_steps": 50,
-  "global_step": 800,
+  "global_step": 850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -704,6 +704,49 @@
       "eval_samples_per_second": 15.331,
       "eval_steps_per_second": 15.331,
       "step": 800
+    },
+    {
+      "epoch": 0.05059337913803873,
+      "grad_norm": 1072.0,
+      "learning_rate": 0.004453175712928476,
+      "loss": 8.6992,
+      "step": 810
+    },
+    {
+      "epoch": 0.05121798875702686,
+      "grad_norm": 3584.0,
+      "learning_rate": 0.004011658237794877,
+      "loss": 7.6904,
+      "step": 820
+    },
+    {
+      "epoch": 0.051842598376014994,
+      "grad_norm": 121.5,
+      "learning_rate": 0.003591274243710277,
+      "loss": 8.3538,
+      "step": 830
+    },
+    {
+      "epoch": 0.05246720799500312,
+      "grad_norm": 524.0,
+      "learning_rate": 0.0031924470217222834,
+      "loss": 7.6898,
+      "step": 840
+    },
+    {
+      "epoch": 0.05309181761399125,
+      "grad_norm": 516.0,
+      "learning_rate": 0.002815578157036303,
+      "loss": 8.4977,
+      "step": 850
+    },
+    {
+      "epoch": 0.05309181761399125,
+      "eval_loss": 8.241488456726074,
+      "eval_runtime": 55.3183,
+      "eval_samples_per_second": 15.239,
+      "eval_steps_per_second": 15.239,
+      "step": 850
     }
   ],
   "logging_steps": 10,
@@ -718,7 +761,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 16
+        "early_stopping_patience_counter": 17
       }
     },
     "TrainerControl": {
@@ -732,7 +775,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.267697311744e+16,
+  "total_flos": 3.471928393728e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null