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:dfbf04843fe30f7a87da236b2195b9a1d63efd1523d83bec9f5ab40dd586e429
+oid sha256:482e8387001519c318fe93c076b3e62fdd68543d861f4f2f1bec99b7136d3c6d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcf82583fce814c959035c47dde42f44b93edb96fc23a1b729e823c7f9910af
+oid sha256:842261e18c33d5eeca4840b75e469343a9c5fa857314877967d7e427154dfc41
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
+oid sha256:579e13fd9090cbc06b882f45f73716d8bcfb23338a57dbfda55daedd755be462
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.63152813911438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0721370604147881,
+  "best_metric": 2.626811981201172,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.09017132551848513,
   "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": 9.685,
       "eval_steps_per_second": 4.884,
       "step": 20
+    },
+    {
+      "epoch": 0.0757439134355275,
+      "grad_norm": 1.4882969856262207,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 10.718,
+      "step": 21
+    },
+    {
+      "epoch": 0.0793507664562669,
+      "grad_norm": 1.4357144832611084,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 10.5072,
+      "step": 22
+    },
+    {
+      "epoch": 0.0829576194770063,
+      "grad_norm": 1.4908266067504883,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 10.5149,
+      "step": 23
+    },
+    {
+      "epoch": 0.08656447249774572,
+      "grad_norm": 1.411119818687439,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 10.5278,
+      "step": 24
+    },
+    {
+      "epoch": 0.09017132551848513,
+      "grad_norm": 1.4688230752944946,
+      "learning_rate": 0.0,
+      "loss": 10.4999,
+      "step": 25
+    },
+    {
+      "epoch": 0.09017132551848513,
+      "eval_loss": 2.626811981201172,
+      "eval_runtime": 12.1576,
+      "eval_samples_per_second": 9.624,
+      "eval_steps_per_second": 4.853,
+      "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": 6332448610713600.0,
+  "total_flos": 7994716371025920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null