Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1c4c39f85163077f6100f168c5c9840425ddb1127193fc513f427d5c2471b5
+oid sha256:44a1efc19a612e1f41fd4886f12991080634060c0018cd35ad51d3f2502c48fb
 size 9450352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a948c90424a35ef1e530cef4f2e576b120600fa34f7d7456f65f9fedc91ba7cf
+oid sha256:8fd5cc455bb271f61f168c91b6944088af0bde0725b7e24a2ec11df9e5073310
 size 18955258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff98874bc89bde6ac46b886b1e5329cd37545baaae90e1082aa46eadc75d2e2
+oid sha256:5bc0827eba7ade7dc1f4e12fd7cc1cd50f21888020b9de7d7e9096217d21a4ab
 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": 3.3627068996429443,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009538571598903063,
+  "best_metric": 3.3605213165283203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.014307857398354596,
   "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": 63.799,
       "eval_steps_per_second": 31.935,
       "step": 20
+    },
+    {
+      "epoch": 0.010015500178848218,
+      "grad_norm": 6558.29052734375,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 13.7362,
+      "step": 21
+    },
+    {
+      "epoch": 0.011446285918683676,
+      "grad_norm": 1657.87646484375,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 13.5649,
+      "step": 24
+    },
+    {
+      "epoch": 0.01192321449862883,
+      "eval_loss": 3.3596713542938232,
+      "eval_runtime": 13.9007,
+      "eval_samples_per_second": 63.522,
+      "eval_steps_per_second": 31.797,
+      "step": 25
+    },
+    {
+      "epoch": 0.012877071658519137,
+      "grad_norm": 1542.7044677734375,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 12.4871,
+      "step": 27
+    },
+    {
+      "epoch": 0.014307857398354596,
+      "grad_norm": 905.5773315429688,
+      "learning_rate": 0.0,
+      "loss": 14.9088,
+      "step": 30
+    },
+    {
+      "epoch": 0.014307857398354596,
+      "eval_loss": 3.3605213165283203,
+      "eval_runtime": 13.8459,
+      "eval_samples_per_second": 63.773,
+      "eval_steps_per_second": 31.923,
+      "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": 130106529939456.0,
+  "total_flos": 198257569431552.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null