Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af3f1da2f1e593275a9d366d198bf3fdb38c495bce77f4cd3bacbd4b70c0b29
+oid sha256:f69d5dfa3f789d9d0cbf4f26db614892e0a7c66d652669a73063ae4dbca8fa68
 size 838906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0bf638308a498a2bcb31671a993c78a75588f46808ac461de6ba190c0d7d92
+oid sha256:10437a6cc0b94f9c418ffdae4fe846e6a33e69125c8c6668c953cd6bca3a2bfc
 size 426360916

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290ca94dbc87673aeee75e8b8aee72723fd0c71ea99ebbdbc9b399cb856f9296
+oid sha256:448adbe1c0216ce3ffc4e9b91893656657b7e2e86e93182d346c14307e64ee3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a84e4a6d5f891cde98cbc1010ec1b780a9ae367fe1e922e5e6c262f5ac9f65df
+oid sha256:259dc84c23e381fbb995c8c51d7b6bf45023b2b3ae0747622e30e21b211acefc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6618533730506897,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 1.8927444794952681,
+  "epoch": 2.8391167192429023,
   "eval_steps": 150,
-  "global_step": 300,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 10.707,
       "eval_steps_per_second": 2.717,
       "step": 300
+    },
+    {
+      "epoch": 2.2082018927444795,
+      "grad_norm": 2.74511981010437,
+      "learning_rate": 0.00018173545774916627,
+      "loss": 1.9396,
+      "step": 350
+    },
+    {
+      "epoch": 2.5236593059936907,
+      "grad_norm": 1.6998424530029297,
+      "learning_rate": 0.0001754224504208647,
+      "loss": 1.68,
+      "step": 400
+    },
+    {
+      "epoch": 2.8391167192429023,
+      "grad_norm": 1.6890298128128052,
+      "learning_rate": 0.00016832032025716921,
+      "loss": 1.7147,
+      "step": 450
+    },
+    {
+      "epoch": 2.8391167192429023,
+      "eval_loss": 0.6622503995895386,
+      "eval_runtime": 12.5093,
+      "eval_samples_per_second": 10.712,
+      "eval_steps_per_second": 2.718,
+      "step": 450
     }
   ],
   "logging_steps": 50,
@@ -87,7 +116,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -101,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.315686221283328e+17,
+  "total_flos": 4.9319589407883264e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null