Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336ee389d8e28d7da97166f3e6542f4af321d550f875685757edc3e3b6450ac1
+oid sha256:6d5ac93ed6a938c1b32a5c42a3260267d3221a59f23d460ddf0afa0fabb87145
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c090174020e14167c5ff3a19587ceaebf25fd6d904145548b04306ef2050a7b
+oid sha256:1ccef7dee44bfd169bf32ddcb88bff9d0748b03d26aab4f0ca761249d2cb8b6f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0eb5af9db0e507734d039e8150b1d74c78fa93b1b6f4328d9efa52a20c50c2b
+oid sha256:7b362a0f9206f50744ad3d91894f7ac7b2751f29b8976ecdd39441ca9506c460
 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": 1.9345818758010864,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005848808305307793,
+  "best_metric": 1.7933586835861206,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011697616610615587,
   "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": 4.458,
       "eval_steps_per_second": 2.229,
       "step": 10
+    },
+    {
+      "epoch": 0.007018569966369352,
+      "grad_norm": 1.275268793106079,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.8981,
+      "step": 12
+    },
+    {
+      "epoch": 0.00877321245796169,
+      "grad_norm": 0.8033922910690308,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5351,
+      "step": 15
+    },
+    {
+      "epoch": 0.00877321245796169,
+      "eval_loss": 1.8322913646697998,
+      "eval_runtime": 163.0438,
+      "eval_samples_per_second": 4.416,
+      "eval_steps_per_second": 2.208,
+      "step": 15
+    },
+    {
+      "epoch": 0.010527854949554029,
+      "grad_norm": 1.3494081497192383,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 1.7886,
+      "step": 18
+    },
+    {
+      "epoch": 0.011697616610615587,
+      "eval_loss": 1.7933586835861206,
+      "eval_runtime": 162.0286,
+      "eval_samples_per_second": 4.444,
+      "eval_steps_per_second": 2.222,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4080380059582464.0,
+  "total_flos": 7882552387829760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null