Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e51e3f469608d7041546a0fe1f9ccfd6ce80cf4f37fea575fb5a2a1fd3f6cfb
+oid sha256:8bdc0b02dfe52f22fd3eeccfedc11bb2407d82c43ef81e3d0bd0e0e5ed21e810
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e983642348abf8fcb0c0723d46771129bf6cb56c11d878c3d0c8263778fa8d40
+oid sha256:0f9d94a1d7f4e6d86730bfefce5bb3ca0e566a709e8cb4d197d3f4de9f50f90c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11fb9af2ad792f8aab0c3cf5e3137f46301e102dd75fa9c7e47ab9066811401
+oid sha256:f1a7f329094ae02f8da988c57a6d1db8cb958c3b9a92425b4878dae590398dad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7455750703811646,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.000842948211369264,
+  "best_metric": 0.7370086908340454,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.001264422317053896,
   "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": 7.081,
       "eval_steps_per_second": 3.54,
       "step": 20
+    },
+    {
+      "epoch": 0.0008850956219377273,
+      "grad_norm": 0.3990568220615387,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.7123,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010115378536431168,
+      "grad_norm": 0.40452733635902405,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6895,
+      "step": 24
+    },
+    {
+      "epoch": 0.00105368526421158,
+      "eval_loss": 0.7386215329170227,
+      "eval_runtime": 1409.4228,
+      "eval_samples_per_second": 7.088,
+      "eval_steps_per_second": 3.544,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011379800853485065,
+      "grad_norm": 0.3756769299507141,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.7225,
+      "step": 27
+    },
+    {
+      "epoch": 0.001264422317053896,
+      "grad_norm": 0.43550705909729004,
+      "learning_rate": 0.0,
+      "loss": 0.6535,
+      "step": 30
+    },
+    {
+      "epoch": 0.001264422317053896,
+      "eval_loss": 0.7370086908340454,
+      "eval_runtime": 1410.0596,
+      "eval_samples_per_second": 7.085,
+      "eval_steps_per_second": 3.542,
+      "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": 7604344656494592.0,
+  "total_flos": 1.1591988805632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null