Training in progress, step 800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d425e498e6ea5e98cfd459b2b2df78bf5605bd551cc2b2f19d2ed0d145ae61dc
+oid sha256:7b38eab253dba5b0deb684b9be7be55b35fccfa203ed22bec471b3d2aa494879
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76be76af91f29063bfcebef649f23fc116d070cd4e8c608c922d67c1dcaa32d
+oid sha256:a2706762d78364c391d070350d7079727bc3b17acaff24aa2d513f2e945c300f
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad29f8cf4ebaa4c54604266e6a8a1d5d0769f2cc214c8d151ac79b0bbc731b0a
+oid sha256:6a211653fa38f3820ad08baeef7bf2217831b7fa32c8abb08f12aef6c9bf3c4f
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83fe17529e572dff2734bb21512b28dd7cf5d20ef0e84688f5068ffbf24e765
+oid sha256:9213080fe2b45399b87036ca9ff9164533abe6b368e5c828136ee184486749d4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1144fac8f856c755e44dc152ccdb65401daaed44242a933fe7be5d965bad4096
+oid sha256:462c3770d14e466903ac3cbb8d02a07b05bb99c1e78e9ab65cd1a8165b933c02
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.046845721424109935,
+  "epoch": 0.04996876951905059,
   "eval_steps": 50,
-  "global_step": 750,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -661,6 +661,49 @@
       "eval_samples_per_second": 16.087,
       "eval_steps_per_second": 16.087,
       "step": 750
+    },
+    {
+      "epoch": 0.047470331043098064,
+      "grad_norm": 117.5,
+      "learning_rate": 0.006961486195636613,
+      "loss": 8.5237,
+      "step": 760
+    },
+    {
+      "epoch": 0.048094940662086194,
+      "grad_norm": 1024.0,
+      "learning_rate": 0.006421379363065142,
+      "loss": 8.9334,
+      "step": 770
+    },
+    {
+      "epoch": 0.04871955028107433,
+      "grad_norm": 1216.0,
+      "learning_rate": 0.005899979626632835,
+      "loss": 7.7087,
+      "step": 780
+    },
+    {
+      "epoch": 0.04934415990006246,
+      "grad_norm": 1120.0,
+      "learning_rate": 0.005397811991677107,
+      "loss": 8.1393,
+      "step": 790
+    },
+    {
+      "epoch": 0.04996876951905059,
+      "grad_norm": 374.0,
+      "learning_rate": 0.0049153820984394365,
+      "loss": 9.1765,
+      "step": 800
+    },
+    {
+      "epoch": 0.04996876951905059,
+      "eval_loss": 9.214335441589355,
+      "eval_runtime": 54.987,
+      "eval_samples_per_second": 15.331,
+      "eval_steps_per_second": 15.331,
+      "step": 800
     }
   ],
   "logging_steps": 10,
@@ -675,7 +718,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 15
+        "early_stopping_patience_counter": 16
       }
     },
     "TrainerControl": {
@@ -689,7 +732,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.06346622976e+16,
+  "total_flos": 3.267697311744e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null