Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ffdb8629ce2fe066238cffbf8cea7e4787bfdd9840b2a8751fc175f24431cd
+oid sha256:656b318f48ee0a4b5308418cccacb43a11eb4738080db57cad0a305b4b864281
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81044b76e6a031e5c98e93b98b4809bd70f97a39c9707b7ca40499561b5e4db5
+oid sha256:17f75237f35c1929e1b2d93f3b4c0785df49270384cf6a32aa2410b375015259
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d8a6753bf9eff5b67e540a93f6cf1b00d8cc12cceceee564b133c4134fc898
+oid sha256:421c20132010ecc809a284cebf4e311f6264a3372cba268cebada7aacbc800b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1930021047592163,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.023583051646883107,
+  "best_metric": 1.1896018981933594,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.026203390718759007,
   "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": 16.422,
       "eval_steps_per_second": 4.106,
       "step": 450
+    },
+    {
+      "epoch": 0.02410711946125829,
+      "grad_norm": 1.3619661331176758,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 1.077,
+      "step": 460
+    },
+    {
+      "epoch": 0.024631187275633466,
+      "grad_norm": 1.5200282335281372,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 1.0089,
+      "step": 470
+    },
+    {
+      "epoch": 0.025155255090008648,
+      "grad_norm": 1.4571294784545898,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 1.0334,
+      "step": 480
+    },
+    {
+      "epoch": 0.025679322904383826,
+      "grad_norm": 2.3840417861938477,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 1.0615,
+      "step": 490
+    },
+    {
+      "epoch": 0.026203390718759007,
+      "grad_norm": 9.744729995727539,
+      "learning_rate": 0.0,
+      "loss": 1.8475,
+      "step": 500
+    },
+    {
+      "epoch": 0.026203390718759007,
+      "eval_loss": 1.1896018981933594,
+      "eval_runtime": 488.1331,
+      "eval_samples_per_second": 16.461,
+      "eval_steps_per_second": 4.116,
+      "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": 8.48538888044544e+16,
+  "total_flos": 9.4282098671616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null