Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822cbe05eb5d2b7c48eea57f9bcc0604768b02f91fe361a66bd8fcb5d79cad76
+oid sha256:583a0d54c47a5987b7e473f8052082fe2d23fb8cdb96e1449cd69131bf9a1291
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad73460f76e9cd71019dcba7d7f1b382123c13fb6650ee4221f1aff8c4611c6
+oid sha256:282fe03887f80241fbf89093e804d33ada5012cf3eaf7e8bbc5b77a524b0cbf0
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06045bfda977b8c794d21c92a67b76b0c15a955b90c4b3bfcb8761ed94c6587d
+oid sha256:fdd7d019df37cd84828db58e2c5c33c7bb57ed50835adbb723c01dce5ea3add2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.876220166683197,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.029332203500309618,
+  "best_metric": 0.875745415687561,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.03259133722256624,
   "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": 14.563,
       "eval_steps_per_second": 3.641,
       "step": 450
+    },
+    {
+      "epoch": 0.029984030244760942,
+      "grad_norm": 2.2378225326538086,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 0.6365,
+      "step": 460
+    },
+    {
+      "epoch": 0.030635856989212267,
+      "grad_norm": 2.819683074951172,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 0.8311,
+      "step": 470
+    },
+    {
+      "epoch": 0.03128768373366359,
+      "grad_norm": 1.4101600646972656,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 0.9517,
+      "step": 480
+    },
+    {
+      "epoch": 0.03193951047811492,
+      "grad_norm": 1.9987350702285767,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 0.8854,
+      "step": 490
+    },
+    {
+      "epoch": 0.03259133722256624,
+      "grad_norm": 5.414979934692383,
+      "learning_rate": 0.0,
+      "loss": 1.0317,
+      "step": 500
+    },
+    {
+      "epoch": 0.03259133722256624,
+      "eval_loss": 0.875745415687561,
+      "eval_runtime": 444.3276,
+      "eval_samples_per_second": 14.539,
+      "eval_steps_per_second": 3.635,
+      "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": 9.352345754271744e+16,
+  "total_flos": 1.0400815009234944e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null