Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd8b783f3dfc6ffe4eb308ece1db36be3c280666048ac50b28770adbcdfd2b3
+oid sha256:00a39508e0fbf86a46ebe3876fb5eb68c78903f5e3f788cad60da26b1e330714
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9254c034215d622dc239b53395c5295ace9c53213ea9a1b78b33415156f8b2
+oid sha256:6361427e6020b021469c3077c79c62fb4a200518b9832083c145904773aad545
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7bce148323040dd557a1e8acc593e31ebe8a78e78f6a2bd49e21af997949574
+oid sha256:4e7634968b842cec52cde4462106bd4fb9b3d8c39817b197f0045e00d052051a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6363563537597656,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.010591817820733483,
+  "best_metric": 1.5616466999053955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.015887726731100223,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 18.276,
       "eval_steps_per_second": 4.575,
       "step": 20
+    },
+    {
+      "epoch": 0.011121408711770158,
+      "grad_norm": 1.313387155532837,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4939,
+      "step": 21
+    },
+    {
+      "epoch": 0.01271018138488018,
+      "grad_norm": 1.5589934587478638,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.6683,
+      "step": 24
+    },
+    {
+      "epoch": 0.013239772275916854,
+      "eval_loss": 1.5733295679092407,
+      "eval_runtime": 86.9917,
+      "eval_samples_per_second": 18.278,
+      "eval_steps_per_second": 4.575,
+      "step": 25
+    },
+    {
+      "epoch": 0.014298954057990202,
+      "grad_norm": 1.331397294998169,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.6898,
+      "step": 27
+    },
+    {
+      "epoch": 0.015887726731100223,
+      "grad_norm": 1.5433915853500366,
+      "learning_rate": 0.0,
+      "loss": 1.6671,
+      "step": 30
+    },
+    {
+      "epoch": 0.015887726731100223,
+      "eval_loss": 1.5616466999053955,
+      "eval_runtime": 87.023,
+      "eval_samples_per_second": 18.271,
+      "eval_steps_per_second": 4.574,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6585384016281600.0,
+  "total_flos": 9878076024422400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null