Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ed64ac6583a62a12345bef16a0ea8a61f451882f31b268aedd5c21e5cd6393
+oid sha256:bc24af07de4cd279c33afbd45367e5132a29eef069059375662aab2130ceb5d2
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86e3aae1258d43a8c6e871e7e79834570f7da24ab6b3ba448862d31edf3ed2f2
+oid sha256:b07f67d4b74b0e94f0869a35c994342a129ba18ddc1de799783ac1a233609fa5
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3ee690ad88b56c8223e3bf83d50e37e8f858cadaf0e44c5eac6f2d3f098a1f
+oid sha256:0224f484e5bfbab7c30ddcc29fc1c1bfdbd095d7e88be12d43d0cd40c26c884f
 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": 1.3241080045700073,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.16553246275519587,
+  "best_metric": 1.3223226070404053,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.18392495861688432,
   "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": 17.499,
       "eval_steps_per_second": 4.386,
       "step": 450
+    },
+    {
+      "epoch": 0.16921096192753357,
+      "grad_norm": 0.7751836776733398,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 1.4373,
+      "step": 460
+    },
+    {
+      "epoch": 0.17288946109987124,
+      "grad_norm": 0.7827539443969727,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 1.3386,
+      "step": 470
+    },
+    {
+      "epoch": 0.17656796027220895,
+      "grad_norm": 0.7729030847549438,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 1.3196,
+      "step": 480
+    },
+    {
+      "epoch": 0.18024645944454662,
+      "grad_norm": 0.8775790333747864,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 1.2671,
+      "step": 490
+    },
+    {
+      "epoch": 0.18392495861688432,
+      "grad_norm": 1.0807873010635376,
+      "learning_rate": 0.0,
+      "loss": 1.2471,
+      "step": 500
+    },
+    {
+      "epoch": 0.18392495861688432,
+      "eval_loss": 1.3223226070404053,
+      "eval_runtime": 65.3468,
+      "eval_samples_per_second": 17.522,
+      "eval_steps_per_second": 4.392,
+      "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": 7.9981238550528e+16,
+  "total_flos": 8.886804283392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null