Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df78edf93ed7c5c330c23a4b8c0f91d5ca32b1e0f14867c271c87ed1e7c0b9e
+oid sha256:fd33c7d979d41f502b1b9a11034a294bc102fdc0a227d771031bb85c1458de81
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60684086fa16f968bc1b61aa50eeb85c182d0a012f38e5cd87c5147af02487e5
+oid sha256:0e30feffe824059d40bf021a3d5d1d7dfc71121b1db3cd576f71dd4372335a85
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:6bfe317d44b8f3bf2eb130aa26c2579199f2fbb7a32f4bcba4bfcd17b18d14b2
 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": 1.3193284273147583,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012366671819446591,
+  "best_metric": 1.2900359630584717,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.018550007729169888,
   "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": 7.571,
       "eval_steps_per_second": 3.791,
       "step": 20
+    },
+    {
+      "epoch": 0.01298500541041892,
+      "grad_norm": 1.2019850015640259,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2235,
+      "step": 21
+    },
+    {
+      "epoch": 0.01484000618333591,
+      "grad_norm": 1.4664053916931152,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.3314,
+      "step": 24
+    },
+    {
+      "epoch": 0.015458339774308239,
+      "eval_loss": 1.2940338850021362,
+      "eval_runtime": 89.7811,
+      "eval_samples_per_second": 7.585,
+      "eval_steps_per_second": 3.798,
+      "step": 25
+    },
+    {
+      "epoch": 0.016695006956252898,
+      "grad_norm": 1.2575082778930664,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.254,
+      "step": 27
+    },
+    {
+      "epoch": 0.018550007729169888,
+      "grad_norm": 1.3184213638305664,
+      "learning_rate": 0.0,
+      "loss": 1.1453,
+      "step": 30
+    },
+    {
+      "epoch": 0.018550007729169888,
+      "eval_loss": 1.2900359630584717,
+      "eval_runtime": 89.8528,
+      "eval_samples_per_second": 7.579,
+      "eval_steps_per_second": 3.795,
+      "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": 7418872835604480.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null