Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fad8af9b1a684c0a1513ff3972ec6ec341b4677b2e63a1a4a751278d70d8da
+oid sha256:d29fede0f9aa4ec65bb8a24612f2f54e6794fb83b8339aaee9f7a05b707b2d59
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d91c9621b9d46e49ffa01fb304bd2395a33fb94f8818fd3f6f99b57078be1df6
-size 170920084
+oid sha256:2e55b5366313248d2716c4642760cc12e61afa21d9f780915b37f512e24a19d0
+size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e222c759bd3e8885d01f80f8ae9354be3426b1a8f5b586fab68f27a11091665f
+oid sha256:20ffebf7b659fadf5edcf5590d56cf6357bd324720bac92824401509b738cb39
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce54f61503edf00b56f4cd65020ab3a18bbd43c84561899444870908675e793
+oid sha256:74485e67705dc36efbfb69b1e54f842e1ff07894d01bb0e36d6d2526a318b300
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1232517957687378,
   "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 2.487562189054726,
+  "epoch": 2.9850746268656714,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 7.374,
       "eval_steps_per_second": 1.876,
       "step": 250
+    },
+    {
+      "epoch": 2.587064676616915,
+      "grad_norm": 4.624186992645264,
+      "learning_rate": 9.242458032904311e-06,
+      "loss": 2.8715,
+      "step": 260
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 6.473374366760254,
+      "learning_rate": 5.2346828817197655e-06,
+      "loss": 1.3872,
+      "step": 270
+    },
+    {
+      "epoch": 2.7860696517412933,
+      "grad_norm": 4.681886196136475,
+      "learning_rate": 2.3379444289913342e-06,
+      "loss": 1.8138,
+      "step": 280
+    },
+    {
+      "epoch": 2.8855721393034823,
+      "grad_norm": 5.433272361755371,
+      "learning_rate": 5.862042845640403e-07,
+      "loss": 1.9018,
+      "step": 290
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 3.1172711849212646,
+      "learning_rate": 0.0,
+      "loss": 1.2011,
+      "step": 300
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_loss": 1.1773170232772827,
+      "eval_runtime": 22.8856,
+      "eval_samples_per_second": 7.385,
+      "eval_steps_per_second": 1.879,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -244,7 +287,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -253,12 +296,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.574355575335813e+17,
+  "total_flos": 7.893381799823278e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null