Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b41f147f74741cbbafb1775d5bcc6d7cca5c3f8cf889779063a29fbca855ba6
+oid sha256:997fbebd379cc607bb1c4f6b46d6a63d2c5674a7d3cb9bf62788787342cb5904
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5abdd673ffa721322e47dd1f2ddbda83a355871d1346a545842307ce324090a5
+oid sha256:18d4e6e703c3ae58a7ee1d7e3186ec008025663ef080e3fc3a5e35825dfbf0aa
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6400b71c58d8852d97ee274f2c0c19d268ee7995aa59f21416a02749a9c55550
+oid sha256:48c3d0371c6ea16c11e51847c0e9252ab1cb3c98c2217205c5579fd2e2e6bfda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3780980110168457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003699593044765076,
+  "best_metric": 2.1492695808410645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007399186089530152,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 10.864,
       "eval_steps_per_second": 5.437,
       "step": 10
+    },
+    {
+      "epoch": 0.004069552349241583,
+      "grad_norm": 1.9337842464447021,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 8.7787,
+      "step": 11
+    },
+    {
+      "epoch": 0.004439511653718091,
+      "grad_norm": 2.108654737472534,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 9.1597,
+      "step": 12
+    },
+    {
+      "epoch": 0.004809470958194599,
+      "grad_norm": 1.804977536201477,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 8.2654,
+      "step": 13
+    },
+    {
+      "epoch": 0.005179430262671106,
+      "grad_norm": 2.0446128845214844,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 9.4629,
+      "step": 14
+    },
+    {
+      "epoch": 0.005549389567147614,
+      "grad_norm": 1.792378306388855,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.666,
+      "step": 15
+    },
+    {
+      "epoch": 0.005549389567147614,
+      "eval_loss": 2.193725824356079,
+      "eval_runtime": 107.7566,
+      "eval_samples_per_second": 10.57,
+      "eval_steps_per_second": 5.29,
+      "step": 15
+    },
+    {
+      "epoch": 0.0059193488716241215,
+      "grad_norm": 2.1119868755340576,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 9.1084,
+      "step": 16
+    },
+    {
+      "epoch": 0.006289308176100629,
+      "grad_norm": 1.9483788013458252,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 8.5385,
+      "step": 17
+    },
+    {
+      "epoch": 0.006659267480577136,
+      "grad_norm": 1.958540439605713,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 8.3581,
+      "step": 18
+    },
+    {
+      "epoch": 0.007029226785053644,
+      "grad_norm": 2.1146419048309326,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 8.3837,
+      "step": 19
+    },
+    {
+      "epoch": 0.007399186089530152,
+      "grad_norm": 2.071730852127075,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 8.3191,
+      "step": 20
+    },
+    {
+      "epoch": 0.007399186089530152,
+      "eval_loss": 2.1492695808410645,
+      "eval_runtime": 104.3323,
+      "eval_samples_per_second": 10.917,
+      "eval_steps_per_second": 5.463,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 917953377730560.0,
+  "total_flos": 1835906755461120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null