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:fd952bed5bc23669569654c459d0fe7f21a9ee60577528bfb5815f083d1cb0b4
+oid sha256:537cdae33dfb17e15abd578b35df3e3cf5245993f5af477313e3e0ded2fbb965
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710a2e0a605dce16668da2b981dc275d614e223f814e6806c9935b16d74ca3cb
+oid sha256:ebfc6bece643d8b60fafdb1f1cdcc60a2b9615c5ac97db9360daa71ab2e18be5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d36b99bbd18cc6de39af1ed87c8b6e35aa3d3a749446b64f99745890a089597
+oid sha256:c040ed47534ccc53a6b6c1056bf7a682a4f231d4b123f5ace620bcdd8a62ce1b
 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": 1.7831417322158813,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.013164390324173112,
+  "best_metric": 1.768334150314331,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01974658548625967,
   "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": 5.552,
       "eval_steps_per_second": 2.776,
       "step": 20
+    },
+    {
+      "epoch": 0.013822609840381767,
+      "grad_norm": 1.1832069158554077,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.7964,
+      "step": 21
+    },
+    {
+      "epoch": 0.015797268389007735,
+      "grad_norm": 1.099212884902954,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.7596,
+      "step": 24
+    },
+    {
+      "epoch": 0.01645548790521639,
+      "eval_loss": 1.7728391885757446,
+      "eval_runtime": 115.3063,
+      "eval_samples_per_second": 5.55,
+      "eval_steps_per_second": 2.775,
+      "step": 25
+    },
+    {
+      "epoch": 0.0177719269376337,
+      "grad_norm": 0.9602068662643433,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8017,
+      "step": 27
+    },
+    {
+      "epoch": 0.01974658548625967,
+      "grad_norm": 0.9222397208213806,
+      "learning_rate": 0.0,
+      "loss": 1.8021,
+      "step": 30
+    },
+    {
+      "epoch": 0.01974658548625967,
+      "eval_loss": 1.768334150314331,
+      "eval_runtime": 115.4324,
+      "eval_samples_per_second": 5.544,
+      "eval_steps_per_second": 2.772,
+      "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": 1.0108219724660736e+16,
+  "total_flos": 1.5023225645826048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null