Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43b4d22e9fe8759919a2dcf5bdfee438bb82075f15ac088a7e6dfa6649a9877
+oid sha256:d12a20de3b3bdfb23f2bfeef920a566c393b9ffca57524683026c3eb65352ae7
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc1d6743b86dae9dc522dcb1f8319663caa231971f779c4c10fc23096120af2
+oid sha256:fb4271b9f3041795d08064ec09a7a1885dfe299b6ef6f67b3117741d699a52ce
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bd3c8eac99cfe03ea97487f09615b6736a11a3f04705f1e66b02c0dac6031d9
+oid sha256:8df93e475c978bb90c42073d7f1c0dc5b9889e9ca554318e10093ebd811d8abd
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
+oid sha256:dc6d7a4e5542db8278bbb08501029d28a2952cf2860b91c35fe25fb2510ba81c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.867518663406372,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.2234359483614697,
+  "epoch": 0.24826216484607747,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 49.863,
       "eval_steps_per_second": 12.466,
       "step": 450
+    },
+    {
+      "epoch": 0.22840119165839126,
+      "grad_norm": 0.5695914626121521,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 2.7279,
+      "step": 460
+    },
+    {
+      "epoch": 0.2333664349553128,
+      "grad_norm": 0.8601140379905701,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 2.8374,
+      "step": 470
+    },
+    {
+      "epoch": 0.23833167825223436,
+      "grad_norm": 0.8914629220962524,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 2.8793,
+      "step": 480
+    },
+    {
+      "epoch": 0.24329692154915591,
+      "grad_norm": 1.0856658220291138,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 2.8706,
+      "step": 490
+    },
+    {
+      "epoch": 0.24826216484607747,
+      "grad_norm": 2.727520227432251,
+      "learning_rate": 0.0,
+      "loss": 2.9716,
+      "step": 500
+    },
+    {
+      "epoch": 0.24826216484607747,
+      "eval_loss": 2.8689327239990234,
+      "eval_runtime": 17.1961,
+      "eval_samples_per_second": 49.314,
+      "eval_steps_per_second": 12.328,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4465410700738560.0,
+  "total_flos": 4965572746936320.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null