Training in progress, step 3750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cbdc2b9825166869a6fac2e63a5a97fa4b37b5b84f026246356242c3f1b4f3c
+oid sha256:15c45c6e7cae74c7c01cc815be82d11c04abfc37e552bbb2e1edeb577ca83b42
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3ccbbe76b5289cfdf27cae32ff8667d16da79bd900a109b903abe92fb00891a
+oid sha256:6cb068897f774dbfee50ed4f9898a74eb932cd172b2dae12cdd41b44fa863b09
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebc4da58173c003f7aad6d162278501a1be585d313d2d5f53369f2e219408a6
+oid sha256:f976ec367a6fae76ed6062feb3c28d822959b5991b851f1f820f4aede451cc53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0afe5275623b07807c5bf749b62f86b7a1ab63345ab37a5eef17970d4cb1036
+oid sha256:49f949a4e89c1a57ac6e6dbdd046680bfbcaae2a1fc8d3bcb9e95ba396ae344e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.898159980773926,
   "best_model_checkpoint": "miner_id_24/checkpoint-3450",
-  "epoch": 29.93762993762994,
+  "epoch": 31.185031185031185,
   "eval_steps": 150,
-  "global_step": 3600,
+  "global_step": 3750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -711,6 +711,35 @@
       "eval_samples_per_second": 225.366,
       "eval_steps_per_second": 57.446,
       "step": 3600
+    },
+    {
+      "epoch": 30.353430353430355,
+      "grad_norm": 0.07721268385648727,
+      "learning_rate": 3.956689608863522e-05,
+      "loss": 12.0689,
+      "step": 3650
+    },
+    {
+      "epoch": 30.76923076923077,
+      "grad_norm": 0.05511786788702011,
+      "learning_rate": 3.87275474231996e-05,
+      "loss": 11.8995,
+      "step": 3700
+    },
+    {
+      "epoch": 31.185031185031185,
+      "grad_norm": 0.0616980604827404,
+      "learning_rate": 3.788819875776398e-05,
+      "loss": 12.0734,
+      "step": 3750
+    },
+    {
+      "epoch": 31.185031185031185,
+      "eval_loss": 11.89826488494873,
+      "eval_runtime": 0.4524,
+      "eval_samples_per_second": 225.481,
+      "eval_steps_per_second": 57.475,
+      "step": 3750
     }
   ],
   "logging_steps": 50,
@@ -725,7 +754,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -734,12 +763,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4686500364288.0,
+  "total_flos": 4881642258432.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null