Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146f0709257c226e4624aa25762c617f4503b5562531a5f43652e7fe3ba70d70
+oid sha256:d0cb551b3af5a87647b56d9f7796d0415eda3d2d42381649626c14ab78a79fbd
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d9163e2b1b5849c17690f4bf23cb87062e7ccc999dcbf322324b6ee24fdda18
+oid sha256:30c6ab54fc24585e148a50c756837fc221a46feaef3a3d2b6e26044583b76a9c
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f86cc369b6ccc541a840ceef6b1b6690c175a4d8260d24044952765c594b895
+oid sha256:740c6d711ce94d5833f0f43d49420935290998af391c5b95329d4c31c90d6cca
 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": 1.5855631828308105,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.028119507908611598,
+  "best_metric": 1.577901840209961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0421792618629174,
   "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": 4.35,
       "eval_steps_per_second": 1.089,
       "step": 20
+    },
+    {
+      "epoch": 0.02952548330404218,
+      "grad_norm": 0.10177566856145859,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.5537,
+      "step": 21
+    },
+    {
+      "epoch": 0.03374340949033392,
+      "grad_norm": 0.10590466111898422,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.376,
+      "step": 24
+    },
+    {
+      "epoch": 0.0351493848857645,
+      "eval_loss": 1.579613208770752,
+      "eval_runtime": 137.7471,
+      "eval_samples_per_second": 4.349,
+      "eval_steps_per_second": 1.089,
+      "step": 25
+    },
+    {
+      "epoch": 0.03796133567662566,
+      "grad_norm": 0.10410355031490326,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.4243,
+      "step": 27
+    },
+    {
+      "epoch": 0.0421792618629174,
+      "grad_norm": 0.10854054987430573,
+      "learning_rate": 0.0,
+      "loss": 1.472,
+      "step": 30
+    },
+    {
+      "epoch": 0.0421792618629174,
+      "eval_loss": 1.577901840209961,
+      "eval_runtime": 137.6591,
+      "eval_samples_per_second": 4.351,
+      "eval_steps_per_second": 1.09,
+      "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": 2.796154773307392e+16,
+  "total_flos": 4.194232159961088e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null