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:dfbd4ed79f34dbb5ebf076321c0f4f3e329970a9c393eb532d1db05574b20c52
+oid sha256:11baf582a2f22eee45a402c32addc85caa10b8a6d119e2e3c586efd0ce48bbf1
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2925ae90da29ab4b9d68b2bf29a063fc6f9a4fef091e4779a9da945ed8482d
+oid sha256:66a60d8d325c61a2c151ca65f63275a60f0e090f51a7c161bf8f2d45886bdef8
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107a2111e838867c3feac9e98b4e198826002bd6fc18625eae8ef120b76d9b4b
+oid sha256:11dc50ba25204dd40ecba0ebf665a51f0363460963d143cee1ec68e4484546f8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.0252015590667725,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00019401841234733177,
+  "best_metric": 2.954017400741577,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00038803682469466355,
   "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": 10.719,
       "eval_steps_per_second": 5.359,
       "step": 10
+    },
+    {
+      "epoch": 0.00023282209481679812,
+      "grad_norm": 0.4297844171524048,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.8714,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002910276185209976,
+      "grad_norm": 0.3757598400115967,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.8659,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002910276185209976,
+      "eval_loss": 2.9789626598358154,
+      "eval_runtime": 2026.1573,
+      "eval_samples_per_second": 10.711,
+      "eval_steps_per_second": 5.355,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003492331422251972,
+      "grad_norm": 0.35646551847457886,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.8937,
+      "step": 18
+    },
+    {
+      "epoch": 0.00038803682469466355,
+      "eval_loss": 2.954017400741577,
+      "eval_runtime": 2027.9112,
+      "eval_samples_per_second": 10.702,
+      "eval_steps_per_second": 5.351,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1305053327523840.0,
+  "total_flos": 2610106655047680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null