Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ef0253218918712a9c83ef07b8fb9d7868f8767ce85c99843403dda49efa6a
+oid sha256:1cc6b349c88584d928ec74d7781121867cc6d3470865240ac4c43353e69478db
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dfd64e751c21b2f81adb5481031af12aac734bc588c60648086ff6a3f67d9d2
+oid sha256:b516410cfd0d9b327416c6b57ebad8a9c539bc9d5cb63c86951bab13fac1bbbc
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c44b964d93b0fc5fee5d5af65dde8558cbf37e361379af884005f24d828778
+oid sha256:13afc7b396ae81bcf059d4e0773a0bc122616b0208baad9f4c6e29d04eea6f2e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5443201661109924,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.03508771929824561,
+  "best_metric": 0.505159854888916,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.07017543859649122,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 15.112,
       "eval_steps_per_second": 3.778,
       "step": 10
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 2.1932902336120605,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.126,
+      "step": 12
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 2.2802176475524902,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1705,
+      "step": 15
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": 0.522257924079895,
+      "eval_runtime": 15.921,
+      "eval_samples_per_second": 15.074,
+      "eval_steps_per_second": 3.769,
+      "step": 15
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 2.212062120437622,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.0907,
+      "step": 18
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 0.505159854888916,
+      "eval_runtime": 15.9222,
+      "eval_samples_per_second": 15.073,
+      "eval_steps_per_second": 3.768,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7207077361483776.0,
+  "total_flos": 1.4238372348297216e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null