Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4883121b510ed551f839790b7a29a9316f24e3e5c7c6c1356be133e3f076c19d
+oid sha256:87e5b960b5c75173433b14f7e1893b2e8d5393d3bf4e2d103a4c20181755c2ba
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa9b111fd917e19acdee5b89b287031222e9c09e3b3704d0e39c589e9be2f1f
+oid sha256:b582a8df9d729a8b161e29da7f19b2be9fcd6ce03aa67d52a7bca80ac0983bd6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:551e095e1e9cd74728411123c4dd140596880ba8fd559502809ce92b3a4c22f8
+oid sha256:1be35aeac4bcb7316e89773cf05ebc5ff781542bd8c887bcfda1b418cdc670c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3193468749523163,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07797270955165692,
+  "best_metric": 0.31632593274116516,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.09746588693957114,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 4.92,
       "eval_steps_per_second": 2.46,
       "step": 20
+    },
+    {
+      "epoch": 0.08187134502923976,
+      "grad_norm": 0.37978965044021606,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.3882,
+      "step": 21
+    },
+    {
+      "epoch": 0.08576998050682261,
+      "grad_norm": 0.3311784565448761,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.3009,
+      "step": 22
+    },
+    {
+      "epoch": 0.08966861598440545,
+      "grad_norm": 0.3548380136489868,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.2982,
+      "step": 23
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 0.34436410665512085,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.3098,
+      "step": 24
+    },
+    {
+      "epoch": 0.09746588693957114,
+      "grad_norm": 0.384309321641922,
+      "learning_rate": 0.0,
+      "loss": 0.366,
+      "step": 25
+    },
+    {
+      "epoch": 0.09746588693957114,
+      "eval_loss": 0.31632593274116516,
+      "eval_runtime": 21.7761,
+      "eval_samples_per_second": 4.96,
+      "eval_steps_per_second": 2.48,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7678045118791680.0,
+  "total_flos": 9419457413775360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null