Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df40decb696bdc7a8c851e118f0cf174c2ec1f493301f7b064828bbd041efec
+oid sha256:2604bc54b3a50a282cc81851ffdc302efc33b76021df8ab35b4e4a69d86a5352
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c775f80541f359d703a3df128154f7ca5649ec61190d6a6a68c0e11f33780ae
+oid sha256:b0ac393f9e15758334369f422b57c6c20d2b502a471fd8ea6873af22dd9daf68
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 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": 0.79096919298172,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07476635514018691,
+  "best_metric": 0.7853652834892273,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11214953271028037,
   "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": 6.786,
       "eval_steps_per_second": 3.423,
       "step": 20
+    },
+    {
+      "epoch": 0.07850467289719626,
+      "grad_norm": 4.945610046386719,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.1776,
+      "step": 21
+    },
+    {
+      "epoch": 0.08971962616822429,
+      "grad_norm": 5.950798034667969,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.4026,
+      "step": 24
+    },
+    {
+      "epoch": 0.09345794392523364,
+      "eval_loss": 0.7868967652320862,
+      "eval_runtime": 16.6554,
+      "eval_samples_per_second": 6.785,
+      "eval_steps_per_second": 3.422,
+      "step": 25
+    },
+    {
+      "epoch": 0.10093457943925234,
+      "grad_norm": 4.506432056427002,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.3116,
+      "step": 27
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "grad_norm": 5.6557793617248535,
+      "learning_rate": 0.0,
+      "loss": 3.1075,
+      "step": 30
+    },
+    {
+      "epoch": 0.11214953271028037,
+      "eval_loss": 0.7853652834892273,
+      "eval_runtime": 16.6506,
+      "eval_samples_per_second": 6.787,
+      "eval_steps_per_second": 3.423,
+      "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": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null