Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:737d472a67ff9c9b55b56cd208439fc90f42a30908fae53d02a894f1218ca0df
+oid sha256:a2129890bcf670f63c2819639673f43c245c8000361e03a9ab691f10c85dcb75
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f38956f6d86475cb8621672884b51406f85c2da18fec549f2ab23ffa1e515fc
+oid sha256:7309ffa3745d2196cf8de9df55271bbe4320f3b6d993dedc960a3aa886684dd1
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07dab736b3075ce98828a811a78ccfdb0cd5a7ca7d25ebab7795f48f6968c3a
+oid sha256:95c0c7638e35469b49f0eaa64e7745e31a6e3a85bba74e33104c1b8b6c731b4f
 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": 0.49475958943367004,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08461827754795036,
+  "best_metric": 0.48943638801574707,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.0940203083866115,
   "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": 16.766,
       "eval_steps_per_second": 4.191,
       "step": 450
+    },
+    {
+      "epoch": 0.08649868371568259,
+      "grad_norm": 1.6609992980957031,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 1.0254,
+      "step": 460
+    },
+    {
+      "epoch": 0.08837908988341482,
+      "grad_norm": 1.700790524482727,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 0.9438,
+      "step": 470
+    },
+    {
+      "epoch": 0.09025949605114705,
+      "grad_norm": 1.5010980367660522,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 0.897,
+      "step": 480
+    },
+    {
+      "epoch": 0.09213990221887927,
+      "grad_norm": 1.916372537612915,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 0.9306,
+      "step": 490
+    },
+    {
+      "epoch": 0.0940203083866115,
+      "grad_norm": 3.343224048614502,
+      "learning_rate": 0.0,
+      "loss": 1.0691,
+      "step": 500
+    },
+    {
+      "epoch": 0.0940203083866115,
+      "eval_loss": 0.48943638801574707,
+      "eval_runtime": 134.0884,
+      "eval_samples_per_second": 16.705,
+      "eval_steps_per_second": 4.176,
+      "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": 8.094091598364672e+16,
+  "total_flos": 8.988466360614912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null