Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058530e4eca99670ba0055d082a2a4d9f5f1ec55158c626ecd381ff8c1e3ad4e
+oid sha256:17ed18ddb023a3395a41a23181578cfeba8e7519d1310b3a40b04942780145f0
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a5e427456baf8da92567a0350f1723ab6595d58be597a7b216854a05d2d9f4
-size 102864548
+oid sha256:c80c1f04c65f4b069b9b7ca9cb4de410727a589a5ee29e5712e78cdaa8a8d7bc
+size 102864868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7131b70fc7ebdd91a4fdaf6a201da7ae892386e8abcc9ed2410b4cbcda1633cf
+oid sha256:827aa64c8faf16952bd9662def653a65b68fa9797cf29fca95f2cd42c5fffb53
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc544fc67f1b8a2b1db90f19b38ff839ccead6d1b6c5672460d1acb014ba0c1
+oid sha256:a987734371c39c6974f0e478c7d6a4ed2064b15a4162308e0d41fa113d63e748
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.10329132527112961,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 1.2654867256637168,
+  "epoch": 1.5183312262958282,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -90,6 +90,21 @@
       "eval_samples_per_second": 176.766,
       "eval_steps_per_second": 5.574,
       "step": 250
+    },
+    {
+      "epoch": 1.5183312262958282,
+      "grad_norm": 0.07207214087247849,
+      "learning_rate": 0.000203,
+      "loss": 0.1043,
+      "step": 300
+    },
+    {
+      "epoch": 1.5183312262958282,
+      "eval_loss": 0.10684775561094284,
+      "eval_runtime": 7.5158,
+      "eval_samples_per_second": 177.228,
+      "eval_steps_per_second": 5.588,
+      "step": 300
     }
   ],
   "logging_steps": 50,
@@ -104,7 +119,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -113,12 +128,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0708402219411046e+17,
+  "total_flos": 1.2841550071883366e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null