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:bf861987e9cf010d3be7bfcfd46f8307858dc36872c1bb573a97bd5a32f1f415
+oid sha256:d1c50329c762683f0cdd63251009b78f4eb7270aa69790cfa2d4a16c82d2df55
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e73f635cf9eda432dd55ebda9db7741298e7a01b91a97a64b0027783fad2c86d
+oid sha256:b32d72b1435a33d934557edaaa13a6087b208d3a9869636fd05e74ea9504c18d
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3816115ffca8d86490c789c3fcb51dafd9ddd44dd5e0fd03ea1b926569b8d1
+oid sha256:60e2baccb756262de6ad99cf7b62b8e4035c6738812e1268d030ed7a22b411e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9942281246185303,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0008761650256825873,
+  "best_metric": 0.9854606986045837,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.001095206282103234,
   "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": 6.081,
       "eval_steps_per_second": 3.04,
       "step": 20
+    },
+    {
+      "epoch": 0.0009199732769667166,
+      "grad_norm": 0.6829021573066711,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8964,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009637815282508461,
+      "grad_norm": 0.6567800045013428,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9836,
+      "step": 22
+    },
+    {
+      "epoch": 0.0010075897795349753,
+      "grad_norm": 0.7929419875144958,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1444,
+      "step": 23
+    },
+    {
+      "epoch": 0.0010513980308191047,
+      "grad_norm": 0.8563855886459351,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9932,
+      "step": 24
+    },
+    {
+      "epoch": 0.001095206282103234,
+      "grad_norm": 0.7275117039680481,
+      "learning_rate": 0.0,
+      "loss": 0.9546,
+      "step": 25
+    },
+    {
+      "epoch": 0.001095206282103234,
+      "eval_loss": 0.9854606986045837,
+      "eval_runtime": 1581.5965,
+      "eval_samples_per_second": 6.077,
+      "eval_steps_per_second": 3.039,
+      "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": 5225019001012224.0,
+  "total_flos": 6658431293325312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null