Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733aa2a7b5170cd8187f057ecf2d384cc0eca1b1ff01326e0947d44bf2c02764
+oid sha256:aa3ac03a9726225ffa24f979e6b3eff20b0b9cebcd8327673a8d1975b6f94211
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9750e8ab4266ed6eeacc8708b032381d5682f423d4f364231f51902a66f9c6d
+oid sha256:e6d926d1efcab59711dfc929d355e1236f8bad71f15baa81ed0353468ad848ed
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a20ac10ae460ceab98a1df5bb00959bf16cc09d5e3983169c17ecd6f52587a
+oid sha256:d414eadf39302d8ec0219af438e287bb7b20fa850e733f546b8f98e5ed72641b
 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": 2.6848888397216797,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.002116066232873089,
+  "best_metric": 2.349881649017334,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004232132465746178,
   "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": 7.489,
       "eval_steps_per_second": 3.744,
       "step": 10
+    },
+    {
+      "epoch": 0.0025392794794477066,
+      "grad_norm": 7.996623992919922,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.4054,
+      "step": 12
+    },
+    {
+      "epoch": 0.0031740993493096334,
+      "grad_norm": 6.5161848068237305,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.1166,
+      "step": 15
+    },
+    {
+      "epoch": 0.0031740993493096334,
+      "eval_loss": 2.428469657897949,
+      "eval_runtime": 265.7298,
+      "eval_samples_per_second": 7.489,
+      "eval_steps_per_second": 3.744,
+      "step": 15
+    },
+    {
+      "epoch": 0.0038089192191715603,
+      "grad_norm": 6.505863189697266,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 11.0634,
+      "step": 18
+    },
+    {
+      "epoch": 0.004232132465746178,
+      "eval_loss": 2.349881649017334,
+      "eval_runtime": 265.7323,
+      "eval_samples_per_second": 7.489,
+      "eval_steps_per_second": 3.744,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2888898293760000.0,
+  "total_flos": 5777796587520000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null