Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48e831562e26657d2e58a4dab26702ae65b2a5647e6d590148409d8fbf373eb1
+oid sha256:ad8f237619c28eadf87264eb374d1e19d202af7d1fccf61c1f313596b5ff28dd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f63fcd9a8609e9e11239ba33ac91e9a274b7b98279c39fba64103879003395f
+oid sha256:5962acbee94f0f04e3fcc2a509c8b9ec4d391d4ecb3dc1fa1636361713e6af79
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae184646e5fd289353aeabc7a666b3a81d12e72ee226fa1bc7384eb0371befb
+oid sha256:7f022f3ee7b0b20719b3effd332f0ac19987fadb876a170addfc7f5f32c45fba
 size 14308

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": 0.22399407625198364,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.27590435315757206,
+  "best_metric": 0.22088730335235596,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.30656039239730226,
   "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": 16.178,
       "eval_steps_per_second": 4.05,
       "step": 450
+    },
+    {
+      "epoch": 0.2820355610055181,
+      "grad_norm": 0.8298888802528381,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 0.2218,
+      "step": 460
+    },
+    {
+      "epoch": 0.28816676885346415,
+      "grad_norm": 0.9988222122192383,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 0.2328,
+      "step": 470
+    },
+    {
+      "epoch": 0.29429797670141017,
+      "grad_norm": 0.8386346101760864,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 0.217,
+      "step": 480
+    },
+    {
+      "epoch": 0.30042918454935624,
+      "grad_norm": 0.7417736053466797,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 0.1874,
+      "step": 490
+    },
+    {
+      "epoch": 0.30656039239730226,
+      "grad_norm": 2.6463584899902344,
+      "learning_rate": 0.0,
+      "loss": 0.3353,
+      "step": 500
+    },
+    {
+      "epoch": 0.30656039239730226,
+      "eval_loss": 0.22088730335235596,
+      "eval_runtime": 42.3398,
+      "eval_samples_per_second": 16.226,
+      "eval_steps_per_second": 4.062,
+      "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": 8.494817090312602e+16,
+  "total_flos": 9.437638077028762e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null