Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02316dca9c3b5be6191a2d286fdb0070cc8a335dc5b42fe2c711189d45690daa
+oid sha256:2697b0103f3e9a84d56d702845b9ab9e0674b90e040a7763cbd8a01bbeb3aa78
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a247eece61ef3ceffde76ba136be55a3e918ed7cc7028608e9966866496f83b
+oid sha256:23c6f5fb498cfcc23a8591ef372f36052fe34ce1134acce53126104d8962bd9a
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a996b0afeb762013a5d1bbc12322068270ba60f6975cd7e0cb0252d24278e9
+oid sha256:f108ec767e229a767e3d8a697ef9ce2b2a773115cacb416ea44871e02516790e
 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": 2.244985580444336,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.023781212841854936,
+  "best_metric": 1.9199856519699097,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.04756242568370987,
   "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": 37.789,
       "eval_steps_per_second": 18.894,
       "step": 10
+    },
+    {
+      "epoch": 0.028537455410225922,
+      "grad_norm": 3.0050437450408936,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.2602,
+      "step": 12
+    },
+    {
+      "epoch": 0.0356718192627824,
+      "grad_norm": 2.746276617050171,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.1064,
+      "step": 15
+    },
+    {
+      "epoch": 0.0356718192627824,
+      "eval_loss": 2.0495896339416504,
+      "eval_runtime": 4.977,
+      "eval_samples_per_second": 35.764,
+      "eval_steps_per_second": 17.882,
+      "step": 15
+    },
+    {
+      "epoch": 0.04280618311533888,
+      "grad_norm": 2.704167127609253,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.1799,
+      "step": 18
+    },
+    {
+      "epoch": 0.04756242568370987,
+      "eval_loss": 1.9199856519699097,
+      "eval_runtime": 4.7375,
+      "eval_samples_per_second": 37.573,
+      "eval_steps_per_second": 18.786,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180238575206400.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null