Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca4a1b8de7072ae43bc0631d1ffb5d249759d5494f9186427bfa7db01f241f8
+oid sha256:bad5edc389555504b98b78beef9ddec44584cf86a8334f670f6bf29dfffdf66f
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d792d8d6232d5f7753fd3496252c5c07212da036ad6d0bc7c03c402781354b2
+oid sha256:12cf44b30dd2a3df56e1423feb6876850c08cb1951768ccfe3208b144cc34ece
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0c0666575b98e636f596a491cd3baae1cee53a60e8c84b1d7e99d6cebb0a53
+oid sha256:01ea98f3bebdda46528525ef49cd25e0b9c1e51798ae901a753912f2d86e3fef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a2f8589b19b0b3d49bfd65bba5faebaa3a097aa2636075709913e8e9b42940
+oid sha256:5fdb371b18c6b4538b2b054d4586be596e95cc5e679b6efce46bc65808638c49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.9998939037323,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.816901408450704,
+  "epoch": 3.0422535211267605,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,34 @@
       "eval_samples_per_second": 66.73,
       "eval_steps_per_second": 8.341,
       "step": 50
+    },
+    {
+      "epoch": 2.873239436619718,
+      "grad_norm": 40.0010986328125,
+      "learning_rate": 5.7132835072101486e-08,
+      "loss": 3.044,
+      "step": 51
+    },
+    {
+      "epoch": 2.9295774647887325,
+      "grad_norm": 39.7271614074707,
+      "learning_rate": 2.544639529766829e-08,
+      "loss": 2.9483,
+      "step": 52
+    },
+    {
+      "epoch": 2.9859154929577465,
+      "grad_norm": 46.26918029785156,
+      "learning_rate": 6.369713474366213e-09,
+      "loss": 3.3382,
+      "step": 53
+    },
+    {
+      "epoch": 3.0422535211267605,
+      "grad_norm": 43.628570556640625,
+      "learning_rate": 0.0,
+      "loss": 3.3172,
+      "step": 54
     }
   ],
   "logging_steps": 1,
@@ -396,12 +424,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.441007408775168e+16,
+  "total_flos": 1.555909500469248e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null