Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd846e2c1856e770f4db01416ea8b97cc2d9e83e2f7353f10d200508e4f4b0d
+oid sha256:1dd8b783f3dfc6ffe4eb308ece1db36be3c280666048ac50b28770adbcdfd2b3
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92957458d7f18d474879e88183cbcf8df20889536d7cf98ad03443c164d1516c
+oid sha256:aa9254c034215d622dc239b53395c5295ace9c53213ea9a1b78b33415156f8b2
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d563021eee7fc49a9a529ffb8fa25c77ffd1461e9d730bab66a305aae1d6f14f
+oid sha256:c7bce148323040dd557a1e8acc593e31ebe8a78e78f6a2bd49e21af997949574
 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": 2.1939339637756348,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005295908910366741,
+  "best_metric": 1.6363563537597656,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.010591817820733483,
   "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": 18.276,
       "eval_steps_per_second": 4.575,
       "step": 10
+    },
+    {
+      "epoch": 0.00635509069244009,
+      "grad_norm": 2.1099212169647217,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.6025,
+      "step": 12
+    },
+    {
+      "epoch": 0.007943863365550112,
+      "grad_norm": 2.824223041534424,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7027,
+      "step": 15
+    },
+    {
+      "epoch": 0.007943863365550112,
+      "eval_loss": 1.879441499710083,
+      "eval_runtime": 86.9668,
+      "eval_samples_per_second": 18.283,
+      "eval_steps_per_second": 4.576,
+      "step": 15
+    },
+    {
+      "epoch": 0.009532636038660135,
+      "grad_norm": 1.6235729455947876,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.8063,
+      "step": 18
+    },
+    {
+      "epoch": 0.010591817820733483,
+      "eval_loss": 1.6363563537597656,
+      "eval_runtime": 86.9975,
+      "eval_samples_per_second": 18.276,
+      "eval_steps_per_second": 4.575,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3292692008140800.0,
+  "total_flos": 6585384016281600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null