Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339fcb57c6ff14e069d684dd9d7c1dd791a3bca783c6692c68f686194b3c5eb1
+oid sha256:baf7a609f40810267d2096fa9719ac592f62ef82a1e2b53052107b9c0d44433f
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8958667ef34de15b926bbc9d14c4963ccfb7e2bf03151362da5471d427722fa3
-size 341314196
+oid sha256:e24a59c35b3bbe5ac43e7443f14ffe139c3ebb725d79143a559de8dcf94c4337
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa36029be4f20f75ac36f4261d1754b4e77c776ae7c76dd378f9c3aec7ab9827
+oid sha256:88954c2f228c82fcdb3a7e1ecffc2796614a2fbc1dc6e6146b94cf5dacd451e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180579b18c9e708a5cf9b411c96230bb3cb8d2c4c87c23004deaa70e5c990f72
+oid sha256:eb7fb5f22874147e56941b0c2b0e6e106f9317ff78b343462a5df511f2b8d1e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.669979989528656,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.04701015419330575,
+  "best_metric": 0.6255946755409241,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.056412185031966905,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 16.639,
       "eval_steps_per_second": 4.16,
       "step": 250
+    },
+    {
+      "epoch": 0.048890560361037984,
+      "grad_norm": 1.8978098630905151,
+      "learning_rate": 0.00011652775287473745,
+      "loss": 1.3589,
+      "step": 260
+    },
+    {
+      "epoch": 0.050770966528770216,
+      "grad_norm": 1.964809536933899,
+      "learning_rate": 0.00010918189690211387,
+      "loss": 1.1163,
+      "step": 270
+    },
+    {
+      "epoch": 0.05265137269650245,
+      "grad_norm": 1.9690378904342651,
+      "learning_rate": 0.00010181810309788618,
+      "loss": 1.1062,
+      "step": 280
+    },
+    {
+      "epoch": 0.05453177886423467,
+      "grad_norm": 2.6126410961151123,
+      "learning_rate": 9.447224712526258e-05,
+      "loss": 1.0986,
+      "step": 290
+    },
+    {
+      "epoch": 0.056412185031966905,
+      "grad_norm": 3.1689352989196777,
+      "learning_rate": 8.718011725613886e-05,
+      "loss": 1.1686,
+      "step": 300
+    },
+    {
+      "epoch": 0.056412185031966905,
+      "eval_loss": 0.6255946755409241,
+      "eval_runtime": 133.189,
+      "eval_samples_per_second": 16.818,
+      "eval_steps_per_second": 4.205,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.50764880174121e+16,
+  "total_flos": 5.40202356399145e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null