Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ddf1e3f9798acd73020fd3308769fe0b13879a448fe014be8a734e7f751d030
+oid sha256:408ef6eec6b4f59699c999d01c9d0fad974965f611a6d10454664f38667fdcd6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370a7e459d49a0b2d9a8350808e1f353e8d2276b08220cbcb888b146cd7069fe
+oid sha256:c953dd08ab36d0b3d76b4e3653c0525b34deff42d3bc7f7dc60b5b5f0cfcbfdc
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b8f3c2d3598a9a04a5ea7aeb36b1fc836c4e69963500b30df13ecb47949b07
+oid sha256:095670adb63b208497762df0b96a90171bea703270c605fd50bd872eca7637a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.806941270828247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04810583283223091,
+  "best_metric": 1.7848981618881226,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07215874924834637,
   "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": 4.797,
       "eval_steps_per_second": 2.412,
       "step": 20
+    },
+    {
+      "epoch": 0.050511124473842456,
+      "grad_norm": 0.4743472933769226,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.4983,
+      "step": 21
+    },
+    {
+      "epoch": 0.05772699939867709,
+      "grad_norm": 0.7433637976646423,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.6693,
+      "step": 24
+    },
+    {
+      "epoch": 0.06013229104028864,
+      "eval_loss": 1.7883085012435913,
+      "eval_runtime": 36.4746,
+      "eval_samples_per_second": 4.798,
+      "eval_steps_per_second": 2.413,
+      "step": 25
+    },
+    {
+      "epoch": 0.06494287432351173,
+      "grad_norm": 0.36506912112236023,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.5368,
+      "step": 27
+    },
+    {
+      "epoch": 0.07215874924834637,
+      "grad_norm": 0.35806649923324585,
+      "learning_rate": 0.0,
+      "loss": 1.5179,
+      "step": 30
+    },
+    {
+      "epoch": 0.07215874924834637,
+      "eval_loss": 1.7848981618881226,
+      "eval_runtime": 36.5171,
+      "eval_samples_per_second": 4.792,
+      "eval_steps_per_second": 2.41,
+      "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": 1.2612083820527616e+16,
+  "total_flos": 1.9381805283016704e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null