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:abb62aef33627499dca733a616b812dba96fb7c57de587944683a4b439772725
+oid sha256:b8369151b1e9c729988696d48a5a7bb8a10bad12a6c247528def7586aecc0980
 size 377538512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7820b270c78e8c92a6776bcc51b4ae3a250702f904ac636cc9616ace8bbf338
+oid sha256:0639e85056c7ed4de65de6324ab5d534010ebf95c4d019fe4f650f829fc2c2c1
 size 192144980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4c1953abeb2acb7e6d632aabc233a01c7622fa568813d31b5b31934a1336156
+oid sha256:97697fa90535d3219bbcbf79c89a308e303f420579ec879dbce7a99639a9f4fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18572f0adae215b3259455cf96083d95e78dc1ab7af393890cd3753bf61cc9f4
+oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6434217095375061,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.01685878658883527,
+  "epoch": 0.01896613491243968,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 17.427,
       "eval_steps_per_second": 4.358,
       "step": 400
+    },
+    {
+      "epoch": 0.01728025625355615,
+      "grad_norm": 3.92277193069458,
+      "learning_rate": 2.0435181601880635e-05,
+      "loss": 0.6158,
+      "step": 410
+    },
+    {
+      "epoch": 0.017701725918277032,
+      "grad_norm": 2.673832893371582,
+      "learning_rate": 1.625885371126242e-05,
+      "loss": 0.6602,
+      "step": 420
+    },
+    {
+      "epoch": 0.018123195582997912,
+      "grad_norm": 2.5034871101379395,
+      "learning_rate": 1.2524607564094813e-05,
+      "loss": 0.7164,
+      "step": 430
+    },
+    {
+      "epoch": 0.018544665247718795,
+      "grad_norm": 2.5820553302764893,
+      "learning_rate": 9.250636032241695e-06,
+      "loss": 0.6318,
+      "step": 440
+    },
+    {
+      "epoch": 0.01896613491243968,
+      "grad_norm": 4.127530574798584,
+      "learning_rate": 6.45288957590781e-06,
+      "loss": 0.7689,
+      "step": 450
+    },
+    {
+      "epoch": 0.01896613491243968,
+      "eval_loss": 0.6436655521392822,
+      "eval_runtime": 571.8197,
+      "eval_samples_per_second": 17.471,
+      "eval_steps_per_second": 4.369,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -373,7 +416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.56713365880832e+16,
+  "total_flos": 5.136761399279616e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null