Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbec2fd4afd82e2174d8e90843450aa9cfec17114609e0daaec109e20feb58b9
+oid sha256:76a97a1e96f8482415c65bd89a97b0c8bef1f0ba36491dc5c791eb6383fb2c93
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdef43d2b373c43f94b1dfcbd9016d90a7c196769b7519c0951291dc44b8ca91
+oid sha256:154c4e79ae0c1642bec0689b387f356f510f9f2125163f429d2f1e99318872a4
 size 15814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
+oid sha256:642f45901353083874dd4ccdc81e607e878e0b3cdd199252b432047c32c37076
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066ba65f4953fa1b75b645f57a930b28fbba82ba12586f9907c767ebd5948500
+oid sha256:f80e8870b8e62250be6500873da286447839553cb3b0143c2f041e1ffce40d01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.5687203791469194,
+  "epoch": 0.7582938388625592,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -39,6 +39,14 @@
       "eval_samples_per_second": 167.381,
       "eval_steps_per_second": 5.478,
       "step": 60
+    },
+    {
+      "epoch": 0.7582938388625592,
+      "eval_loss": 11.5,
+      "eval_runtime": 1.0634,
+      "eval_samples_per_second": 258.61,
+      "eval_steps_per_second": 8.464,
+      "step": 80
     }
   ],
   "logging_steps": 100,
@@ -53,7 +61,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -67,7 +75,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 31876605542400.0,
+  "total_flos": 38251926650880.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null