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:e9c0b534542c403f52162c8352fe5a2d0226a270d058eff62c50fa2d83685bb5
+oid sha256:80682d54417bf88de1de03f5d8c8cf57465aeba111e57454818be5f2ef19d57c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58809080169625e0aaf12dcb5cee2fc94e64d32a94abe366253fecdd50c0ef7
+oid sha256:3cabb70e3eb243ce888b252b21f02a10b78e425379a815712980b6cdff69fe85
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac6304c3d282c68b3b54b02e10f7ccb87b4af7f30bf7c763231322312d8a778
+oid sha256:4f474396eecfe9e2fdb32279c7633ecfaa4a13ca05fa0d113fea1216d0a56fc5
 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": 0.6643534302711487,
   "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07319304666056725,
+  "epoch": 0.09149130832570906,
   "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": 5.283,
       "eval_steps_per_second": 2.664,
       "step": 20
+    },
+    {
+      "epoch": 0.0768526989935956,
+      "grad_norm": 1.0972665548324585,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7126,
+      "step": 21
+    },
+    {
+      "epoch": 0.08051235132662397,
+      "grad_norm": 0.5327695608139038,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.606,
+      "step": 22
+    },
+    {
+      "epoch": 0.08417200365965233,
+      "grad_norm": 1.9314485788345337,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.8752,
+      "step": 23
+    },
+    {
+      "epoch": 0.0878316559926807,
+      "grad_norm": 1.509268045425415,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.7843,
+      "step": 24
+    },
+    {
+      "epoch": 0.09149130832570906,
+      "grad_norm": 0.6228687763214111,
+      "learning_rate": 0.0,
+      "loss": 0.5933,
+      "step": 25
+    },
+    {
+      "epoch": 0.09149130832570906,
+      "eval_loss": 0.676060140132904,
+      "eval_runtime": 21.8701,
+      "eval_samples_per_second": 5.258,
+      "eval_steps_per_second": 2.652,
+      "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": 3295645846732800.0,
+  "total_flos": 4119557308416000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null