Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cabbf0358b6ae7037832406af074a145020c26a154b886180ec7b0321323ae
+oid sha256:7d1aa454c44d402fc8b3a06d32d432b2507402431abc39861dc666baa38590f5
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29070380fa76f1a540d411e124bb4125ac5bed5f4686080cad2c4f556423474d
+oid sha256:04c7e0f6f447943989ca60a48de7096798a58f2406180a726afb12334a20271e
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:705deedf796b313cb76cd6c14cb7b94da899d809f9d9c1109db82fbb592f3b6c
 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": 3.5884788036346436,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003429355281207133,
+  "best_metric": 3.548567771911621,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0051440329218107,
   "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": 49.24,
       "eval_steps_per_second": 24.62,
       "step": 20
+    },
+    {
+      "epoch": 0.00360082304526749,
+      "grad_norm": 65.02677917480469,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 14.097,
+      "step": 21
+    },
+    {
+      "epoch": 0.00411522633744856,
+      "grad_norm": 76.67129516601562,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 13.7619,
+      "step": 24
+    },
+    {
+      "epoch": 0.0042866941015089165,
+      "eval_loss": 3.5535809993743896,
+      "eval_runtime": 48.946,
+      "eval_samples_per_second": 50.178,
+      "eval_steps_per_second": 25.089,
+      "step": 25
+    },
+    {
+      "epoch": 0.004629629629629629,
+      "grad_norm": 60.97380447387695,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 13.284,
+      "step": 27
+    },
+    {
+      "epoch": 0.0051440329218107,
+      "grad_norm": 59.055320739746094,
+      "learning_rate": 0.0,
+      "loss": 14.099,
+      "step": 30
+    },
+    {
+      "epoch": 0.0051440329218107,
+      "eval_loss": 3.548567771911621,
+      "eval_runtime": 52.3268,
+      "eval_samples_per_second": 46.936,
+      "eval_steps_per_second": 23.468,
+      "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": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null