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:aacc5c3eeba5b0cf2fde2b91ce7a32cfb688826789ecf63e13e133091ba571d2
+oid sha256:c10e1024f75d1532fc1fb0ecee6581d07c99a877333b8804f1a7671c18ebfa7f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d14cd3676acd58ab9074b997595553735cce336b944cfc296d947d2c269c9bfd
+oid sha256:00c9b9bcc89a9a003a6a3027797a7f6e54cbae9ccfc96a583da3a210939cedd6
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2caab57c9738a6223b66a33175b22839bf9437a089ed80e62b0e4247b5a00c6c
+oid sha256:aa475f51346237b604de04dfb5849998c82ad8e092cda930a1bc5b8d1fca410b
 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": 0.5925781726837158,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.04555808656036447,
+  "best_metric": 0.5212913155555725,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.09111617312072894,
   "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": 5.644,
       "eval_steps_per_second": 2.852,
       "step": 10
+    },
+    {
+      "epoch": 0.05466970387243736,
+      "grad_norm": 1.1079726219177246,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.3765,
+      "step": 12
+    },
+    {
+      "epoch": 0.0683371298405467,
+      "grad_norm": 0.9152125120162964,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1722,
+      "step": 15
+    },
+    {
+      "epoch": 0.0683371298405467,
+      "eval_loss": 0.5529842972755432,
+      "eval_runtime": 17.0438,
+      "eval_samples_per_second": 5.457,
+      "eval_steps_per_second": 2.758,
+      "step": 15
+    },
+    {
+      "epoch": 0.08200455580865604,
+      "grad_norm": 1.1765227317810059,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.0581,
+      "step": 18
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "eval_loss": 0.5212913155555725,
+      "eval_runtime": 17.5468,
+      "eval_samples_per_second": 5.3,
+      "eval_steps_per_second": 2.679,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2164457522331648.0,
+  "total_flos": 4467071907790848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null