Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b882ebee58f6b40be573ecb6f366e2ec49ee018dd2d695336f2444187ea91f
+oid sha256:b39dc826225acdeacf629ddf7f5ec80ef46c7bc14cf8752f566f5aba1e3e7a60
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17dd53c796ab2ea2d2379c6a5d8250166de88050ffb945505d5f9d07c1dda7c9
+oid sha256:070123f3613fde15c9f7ff4e6ec35e3e6f693c3e452a43aea6efbf086fe73069
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9d9e169e94fca4b8974ac069cd6054eb9406ff260f6ef065c41d763eacf448
+oid sha256:b5756f1f5319abc83666198e60bf73a1acf49326848e9cfa00c84d93e181a9c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8226829767227173,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07319304666056725,
+  "best_metric": 0.8054594993591309,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.10978956999085086,
   "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": 4.243,
       "eval_steps_per_second": 2.14,
       "step": 20
+    },
+    {
+      "epoch": 0.0768526989935956,
+      "grad_norm": 0.5138906240463257,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.9201,
+      "step": 21
+    },
+    {
+      "epoch": 0.0878316559926807,
+      "grad_norm": 0.4305804371833801,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 0.8424,
+      "step": 24
+    },
+    {
+      "epoch": 0.09149130832570906,
+      "eval_loss": 0.807555615901947,
+      "eval_runtime": 27.1058,
+      "eval_samples_per_second": 4.243,
+      "eval_steps_per_second": 2.14,
+      "step": 25
+    },
+    {
+      "epoch": 0.09881061299176579,
+      "grad_norm": 0.4798426330089569,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.8389,
+      "step": 27
+    },
+    {
+      "epoch": 0.10978956999085086,
+      "grad_norm": 0.43901804089546204,
+      "learning_rate": 0.0,
+      "loss": 0.8383,
+      "step": 30
+    },
+    {
+      "epoch": 0.10978956999085086,
+      "eval_loss": 0.8054594993591309,
+      "eval_runtime": 27.1169,
+      "eval_samples_per_second": 4.241,
+      "eval_steps_per_second": 2.139,
+      "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": 6610941168844800.0,
+  "total_flos": 9916411753267200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null