Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3f3076e5c0732b70b5a115ae1b17e428c2a7b76e315a586f0b2b01cc0b8df9
+oid sha256:32109b6c86ef56f551c4cdfccce5bd77f3da11b5a56bbc97d53ebb10b7335ee0
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a2d269a9b4c72e0e32e0131d8a013b909fa8659ba95b5f2396985b0bcc9e68
+oid sha256:2742bbbebe6ca762c9cc8bc898ab53555ff5c3c4edb439b9aa88972acfadee10
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbb4bd5a0ca2e3e75d2f8acc05aac16ce5a53f54d837f188dbe78b7c432e38a
+oid sha256:7717065921c4dea76a36dd746d970dc9a6ce20f30c2c780cc5516f57bde442a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.0717053413391113,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.052321778940483975,
+  "epoch": 0.06540222367560497,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 22.796,
       "eval_steps_per_second": 11.469,
       "step": 20
+    },
+    {
+      "epoch": 0.05493786788750817,
+      "grad_norm": 340.34808349609375,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 12.0801,
+      "step": 21
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 299.4101867675781,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 12.436,
+      "step": 22
+    },
+    {
+      "epoch": 0.060170045781556575,
+      "grad_norm": 365.0613098144531,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 13.1997,
+      "step": 23
+    },
+    {
+      "epoch": 0.06278613472858077,
+      "grad_norm": 272.857177734375,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.977,
+      "step": 24
+    },
+    {
+      "epoch": 0.06540222367560497,
+      "grad_norm": 500.1920166015625,
+      "learning_rate": 0.0,
+      "loss": 11.1673,
+      "step": 25
+    },
+    {
+      "epoch": 0.06540222367560497,
+      "eval_loss": 3.082658290863037,
+      "eval_runtime": 7.2336,
+      "eval_samples_per_second": 22.257,
+      "eval_steps_per_second": 11.198,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 73650803834880.0,
+  "total_flos": 93597896540160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null