Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b68249116728351764382805db7836289acae47e225c5a75421b679b0b94507
+oid sha256:edffa4b49f1e0685b0634b81566079ba27410cbe25e3b0770749e6933a0ac47a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038525db58b3e7db9ef89d982ed5b480bd74032b6cacd8b72857a38e1faf02a6
+oid sha256:df94add130901cae04e784f56e4c656aa966644125d6f4552a439fe26e6d725f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
+oid sha256:e04d45842b4f57f7bc47c4b705d580a46ba323787f21a23ed4c2131d727599bb
 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": 0.6794732809066772,
   "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": 7.124,
       "eval_steps_per_second": 3.593,
       "step": 20
+    },
+    {
+      "epoch": 0.0768526989935956,
+      "grad_norm": 1.2884169816970825,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7178,
+      "step": 21
+    },
+    {
+      "epoch": 0.08051235132662397,
+      "grad_norm": 0.535166323184967,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.6209,
+      "step": 22
+    },
+    {
+      "epoch": 0.08417200365965233,
+      "grad_norm": 2.09920334815979,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.9255,
+      "step": 23
+    },
+    {
+      "epoch": 0.0878316559926807,
+      "grad_norm": 1.7739763259887695,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.7789,
+      "step": 24
+    },
+    {
+      "epoch": 0.09149130832570906,
+      "grad_norm": 0.6234230995178223,
+      "learning_rate": 0.0,
+      "loss": 0.5827,
+      "step": 25
+    },
+    {
+      "epoch": 0.09149130832570906,
+      "eval_loss": 0.6813143491744995,
+      "eval_runtime": 16.3123,
+      "eval_samples_per_second": 7.05,
+      "eval_steps_per_second": 3.556,
+      "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