Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ebd592846769f11383cb3f465fca322535f44a82784439b60aa651e1f306ce
+oid sha256:0d75f4e793db5a1fe363bef045f3c58fff153fb9f8d84eed6ea9cb369eb3b2e5
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11a35d6563dd9dcd6104e78b3a7f49f470feb49b2b57947a2ba6ceca71677d7
+oid sha256:e9ad05363b5d45c8187427b60bd5c48540cbc9f62af0ad749eb40d5597bcd6ad
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70617e03ad082acd3f54a3db61fac6510896f0e1efd57742c6cca947f8b939d5
+oid sha256:5ae621faf5f7b7c925100a9c32375de444af97498403cf496ff28e7876269247
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
+oid sha256:dc6d7a4e5542db8278bbb08501029d28a2952cf2860b91c35fe25fb2510ba81c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9491406679153442,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.19929140832595216,
+  "best_metric": 1.945500373840332,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.22143489813994685,
   "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": 47.83,
       "eval_steps_per_second": 11.97,
       "step": 450
+    },
+    {
+      "epoch": 0.20372010628875112,
+      "grad_norm": 5.3909220695495605,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 2.0935,
+      "step": 460
+    },
+    {
+      "epoch": 0.20814880425155005,
+      "grad_norm": 5.258525848388672,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 1.9247,
+      "step": 470
+    },
+    {
+      "epoch": 0.21257750221434898,
+      "grad_norm": 6.784404754638672,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 1.8852,
+      "step": 480
+    },
+    {
+      "epoch": 0.21700620017714792,
+      "grad_norm": 4.236598014831543,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 1.8646,
+      "step": 490
+    },
+    {
+      "epoch": 0.22143489813994685,
+      "grad_norm": 4.51641321182251,
+      "learning_rate": 0.0,
+      "loss": 1.7609,
+      "step": 500
+    },
+    {
+      "epoch": 0.22143489813994685,
+      "eval_loss": 1.945500373840332,
+      "eval_runtime": 20.2051,
+      "eval_samples_per_second": 47.067,
+      "eval_steps_per_second": 11.779,
+      "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": 4361762272444416.0,
+  "total_flos": 4844792424431616.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null