Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c6d7ad096547f84cf33043753b89323bf518e796812286d91745ff696c6d48
+oid sha256:49e25866beae8ac978a755a832c0cea39b051dadaedad9748c5708e002187b3c
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc4a9797364eb871e7d488879ae8a975cfe75ff77e28d53be9c3ec4730aac1e
+oid sha256:4feb206f04fd9b72dca0a4b183708ad02f494f5969d444d94504d49cb7882e62
 size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:912f61cab3ca37aaf1de8089bce634938ef8fab87fda54825cf8494660342bf7
+oid sha256:b255b85e22f5bb242ec6ac976de589bef1855406897e9675d213d4ebf8af3892
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.584151268005371,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.12789540997584198,
+  "best_metric": 1.581818699836731,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.14210601108426887,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 9.078,
       "eval_steps_per_second": 2.279,
       "step": 450
+    },
+    {
+      "epoch": 0.13073753019752735,
+      "grad_norm": 1.6380475759506226,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 1.8687,
+      "step": 460
+    },
+    {
+      "epoch": 0.13357965041921274,
+      "grad_norm": 2.9882168769836426,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 1.6105,
+      "step": 470
+    },
+    {
+      "epoch": 0.1364217706408981,
+      "grad_norm": 2.9621737003326416,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 1.3014,
+      "step": 480
+    },
+    {
+      "epoch": 0.13926389086258348,
+      "grad_norm": 2.3243489265441895,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 1.2292,
+      "step": 490
+    },
+    {
+      "epoch": 0.14210601108426887,
+      "grad_norm": 25.126081466674805,
+      "learning_rate": 0.0,
+      "loss": 2.1817,
+      "step": 500
+    },
+    {
+      "epoch": 0.14210601108426887,
+      "eval_loss": 1.581818699836731,
+      "eval_runtime": 82.2236,
+      "eval_samples_per_second": 9.012,
+      "eval_steps_per_second": 2.262,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.83983944138752e+16,
+  "total_flos": 8.66508569837568e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null