Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a8620853eb5f2150be145f968ccf9428b97c191294e6cffd6f5bbd08a35bea
+oid sha256:66e222da317a682ba421b1872cd8880d1668ca875b489418135b4a53c5d86b10
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:896155c353cf0ad796164e838a645db5ae8607b29799b5a5734ab995e1b9901d
+oid sha256:a5ccb45e75545e44f4b332b96df39c24b8e0d9b8a967fb00b5e04d96851171ad
 size 335810490

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 sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5280091762542725,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007979413114165454,
+  "best_metric": 1.4976978302001953,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0011969119671248179,
   "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": 7.541,
       "eval_steps_per_second": 3.77,
       "step": 20
+    },
+    {
+      "epoch": 0.0008378383769873726,
+      "grad_norm": 0.6277047395706177,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.531,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "grad_norm": 0.6077454090118408,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4596,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009974266392706816,
+      "eval_loss": 1.5027270317077637,
+      "eval_runtime": 1399.9411,
+      "eval_samples_per_second": 7.539,
+      "eval_steps_per_second": 3.769,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010772207704123362,
+      "grad_norm": 0.6708080768585205,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4892,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011969119671248179,
+      "grad_norm": 0.6865500211715698,
+      "learning_rate": 0.0,
+      "loss": 1.4852,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011969119671248179,
+      "eval_loss": 1.4976978302001953,
+      "eval_runtime": 1397.2014,
+      "eval_samples_per_second": 7.554,
+      "eval_steps_per_second": 3.777,
+      "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": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null