Training in progress, step 463, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bbe67a5221554012d1a0abe98cfef9cb3d2ce84930edd8f0bdca7f359834da
+oid sha256:a39e67628f69ceff4db6354f500c36f22f79ae661f32f9911365e2f2b0b005f2
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f6ff799ae141dfebffb5e5543de928351bdc53209182d29ccd523c130600b9
+oid sha256:1e3b456e3bacface25e2ceed9cb56f797d1f42fec018464e6dd4b922e36a9ede
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6a76e3bf01ce0abfb46b08e0e12448701dac9fdc00f5bcf08f1da2695ab7f9
+oid sha256:67cdbe4a2ca3fa88e3019c20bf61a48e617ad066ebcf184bdeb5b874c5bf6124
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ec5d18fbee4ceb79650729eac8dcbe812062dc71c315bc7032dd15edeeaee3
+oid sha256:2eb077182c12d040926d6a2a621d9a4402b4f2cd2914796b63debbc474189180
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0007766146445646882,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.9719222462203023,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 463,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,13 @@
       "eval_samples_per_second": 6.88,
       "eval_steps_per_second": 1.729,
       "step": 450
+    },
+    {
+      "epoch": 0.9935205183585313,
+      "grad_norm": 0.060769353061914444,
+      "learning_rate": 2.6557884657352427e-08,
+      "loss": 0.0049,
+      "step": 460
     }
   ],
   "logging_steps": 10,
@@ -425,12 +432,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.3232580688019456e+17,
+  "total_flos": 2.3904763809103872e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null