Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4399f2b8219f203fdaad0f9c026e0c6bdec19a3283e8c5839e1396ac590c724c
+oid sha256:60785f177735d89c1aa210c0fc7c60467b33fdd3489c125722e02abc248d138d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6458b473c4311ad0dfa21470d979034b5e47c65cf2fbb9f75196e9c0d2041931
+oid sha256:f4e820bd566d77fdddce49519cfa5b3486563e5a9ec099437bef16c37454f92a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5016d318ca8e3d6b8ca4b2a60622ca780cb9ab30c6b1c3967b8626d3aa409c3
+oid sha256:cac8f850acca46a552006ff5c648e435d49743086920a562138c2052b8f6ea77
 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": 0.6153923273086548,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00565171317555634,
+  "best_metric": 0.6096845865249634,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.008477569763334511,
   "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": 4.035,
       "eval_steps_per_second": 2.017,
       "step": 20
+    },
+    {
+      "epoch": 0.0059342988343341575,
+      "grad_norm": 1.9146122932434082,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.4474,
+      "step": 21
+    },
+    {
+      "epoch": 0.006782055810667609,
+      "grad_norm": 1.4940017461776733,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.5059,
+      "step": 24
+    },
+    {
+      "epoch": 0.007064641469445425,
+      "eval_loss": 0.6112915277481079,
+      "eval_runtime": 369.4846,
+      "eval_samples_per_second": 4.033,
+      "eval_steps_per_second": 2.016,
+      "step": 25
+    },
+    {
+      "epoch": 0.0076298127870010595,
+      "grad_norm": 1.4474186897277832,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.4497,
+      "step": 27
+    },
+    {
+      "epoch": 0.008477569763334511,
+      "grad_norm": 1.4451892375946045,
+      "learning_rate": 0.0,
+      "loss": 2.4351,
+      "step": 30
+    },
+    {
+      "epoch": 0.008477569763334511,
+      "eval_loss": 0.6096845865249634,
+      "eval_runtime": 369.4916,
+      "eval_samples_per_second": 4.033,
+      "eval_steps_per_second": 2.016,
+      "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": 1.406260607975424e+16,
+  "total_flos": 2.109390911963136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null