Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7ac6f7fc25e4f5acacfab3df1ac48d64049412249003adbb33800944b31279
+oid sha256:69c6850f8c5753872cee4ce980ab690601f49a69b9feae77086542cef9e71026
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a158ba68accba5f55f645210bf416cbe4eb7ed07fbf2f3744543c3ca9b449a46
+oid sha256:e7be7afefe571c34811e92c26c642bfdc1c127fdb07fc3b2bde6f79833c5c2f6
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330796178c89f0a970539182417e271745b4e562e5f628fb3ab81d04129143f0
+oid sha256:b05333b718c0f42708ebb8ba84e263b80dd3708563071b373694dfee958ff762
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.947441577911377,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.6531204644412192,
+  "best_metric": 1.9442715644836426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.7256894049346879,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 11.759,
       "eval_steps_per_second": 2.96,
       "step": 450
+    },
+    {
+      "epoch": 0.6676342525399129,
+      "grad_norm": 0.9019935131072998,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 1.9776,
+      "step": 460
+    },
+    {
+      "epoch": 0.6821480406386067,
+      "grad_norm": 0.8569959998130798,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 1.9456,
+      "step": 470
+    },
+    {
+      "epoch": 0.6966618287373004,
+      "grad_norm": 1.1355559825897217,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 1.9163,
+      "step": 480
+    },
+    {
+      "epoch": 0.7111756168359942,
+      "grad_norm": 1.229154109954834,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 1.9687,
+      "step": 490
+    },
+    {
+      "epoch": 0.7256894049346879,
+      "grad_norm": 3.1747612953186035,
+      "learning_rate": 0.0,
+      "loss": 1.8783,
+      "step": 500
+    },
+    {
+      "epoch": 0.7256894049346879,
+      "eval_loss": 1.9442715644836426,
+      "eval_runtime": 24.6438,
+      "eval_samples_per_second": 11.768,
+      "eval_steps_per_second": 2.962,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1634410976077414e+17,
+  "total_flos": 1.2944932147612877e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null