Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819e785a9980818c83c4b249bb714c2dbb71810466554b0ca9f0d2e1ec9c0c40
+oid sha256:c4e9ba1929ee972b77bcd72d468a37fe2ae415207ef7e59323b5fbe61463f4e4
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8676b70101b430215e22b340ce45cc7b617d94d343716ed381586f9b1bb225
+oid sha256:6af29e74f68512be973befebf6448552f1b28a5dcab1e75907db8bfa13fa2ff3
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113738d73b2993a738a284b6571514b8789145a9c46430bfbd59e9ec6ea0f8d7
+oid sha256:ab3d18275216c730a64e666d0a0b15c9be1210bce446ef49cbf8dbc3a28973b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b222f50cf4019bf2a4af9801ee61ced983584829f5aab356a024b6284fbfaea
+oid sha256:8a64b03d0773f91f522e81c4f703747e71530a9ddde23207251d238f2ace6db2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3906490802764893,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.05461123626186088,
+  "best_metric": 2.30838942527771,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.06826404532732609,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 35.144,
       "eval_steps_per_second": 8.786,
       "step": 400
+    },
+    {
+      "epoch": 0.06143764079459349,
+      "grad_norm": 64.72782135009766,
+      "learning_rate": 0.00025,
+      "loss": 8.8676,
+      "step": 450
+    },
+    {
+      "epoch": 0.06826404532732609,
+      "grad_norm": 61.32781219482422,
+      "learning_rate": 0.00025,
+      "loss": 8.8788,
+      "step": 500
+    },
+    {
+      "epoch": 0.06826404532732609,
+      "eval_loss": 2.30838942527771,
+      "eval_runtime": 175.6465,
+      "eval_samples_per_second": 35.116,
+      "eval_steps_per_second": 8.779,
+      "step": 500
     }
   ],
   "logging_steps": 50,
@@ -117,7 +139,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -131,7 +153,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.414505334571008e+17,
+  "total_flos": 1.76813166821376e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null