Training in progress, step 9000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dbdc76f4c9b984be0302eb41232d54260782b41955e9f1bbf9bb95f96a58b6f
+oid sha256:bfe4d248a55091015dd44003f7230da96ba40bfc0bfb7c6c63512095fc60193b
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69884c223aa8a06685705af1b8ca9f2af295b6dc7cde4da9c00c153cdf848a1
+oid sha256:493107a5ed5fc4d8569b5f3bb1e8bf556a0daaf2ca3af4822164d14a5bcf28ac
 size 4899962

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090d2226d5becd4ac05cc146a931a60227af444a21ce770ca03c93e34c7b55cc
+oid sha256:95bd392ae4a56787ff5724cd96c68985512246001ca168d60d466f980146e191
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86795bab370d3f087ed17dee47b662a3f7e7afd3dbb186d7ada00e7f580ae03c
+oid sha256:35f0d9e5b08bcdb9ff94ecc831a9c75c033cad53fcf1082d39ad1ef8a7a6ad63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.74162483215332,
   "best_model_checkpoint": "miner_id_24/checkpoint-8500",
-  "epoch": 2.5779058306164226,
+  "epoch": 2.729547350064448,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1341,6 +1341,84 @@
       "eval_samples_per_second": 67.14,
       "eval_steps_per_second": 16.791,
       "step": 8500
+    },
+    {
+      "epoch": 2.593069982561225,
+      "grad_norm": 0.088604636490345,
+      "learning_rate": 1.3281706212767156e-06,
+      "loss": 11.7569,
+      "step": 8550
+    },
+    {
+      "epoch": 2.6082341345060276,
+      "grad_norm": 0.08613212406635284,
+      "learning_rate": 1.049882140725071e-06,
+      "loss": 11.7495,
+      "step": 8600
+    },
+    {
+      "epoch": 2.62339828645083,
+      "grad_norm": 0.09652528911828995,
+      "learning_rate": 8.041291538967689e-07,
+      "loss": 11.7611,
+      "step": 8650
+    },
+    {
+      "epoch": 2.638562438395633,
+      "grad_norm": 0.08829577267169952,
+      "learning_rate": 5.909882111579044e-07,
+      "loss": 11.7421,
+      "step": 8700
+    },
+    {
+      "epoch": 2.653726590340435,
+      "grad_norm": 0.08825016021728516,
+      "learning_rate": 4.1052570444699797e-07,
+      "loss": 11.7531,
+      "step": 8750
+    },
+    {
+      "epoch": 2.668890742285238,
+      "grad_norm": 0.09674602001905441,
+      "learning_rate": 2.627978465944208e-07,
+      "loss": 11.7567,
+      "step": 8800
+    },
+    {
+      "epoch": 2.68405489423004,
+      "grad_norm": 0.09206220507621765,
+      "learning_rate": 1.4785065381238165e-07,
+      "loss": 11.7585,
+      "step": 8850
+    },
+    {
+      "epoch": 2.699219046174843,
+      "grad_norm": 0.08380258083343506,
+      "learning_rate": 6.571993136129994e-08,
+      "loss": 11.7515,
+      "step": 8900
+    },
+    {
+      "epoch": 2.714383198119645,
+      "grad_norm": 0.0812031477689743,
+      "learning_rate": 1.6431262396651435e-08,
+      "loss": 11.7497,
+      "step": 8950
+    },
+    {
+      "epoch": 2.729547350064448,
+      "grad_norm": 0.08813946694135666,
+      "learning_rate": 0.0,
+      "loss": 11.7544,
+      "step": 9000
+    },
+    {
+      "epoch": 2.729547350064448,
+      "eval_loss": 11.74162769317627,
+      "eval_runtime": 88.5243,
+      "eval_samples_per_second": 62.74,
+      "eval_steps_per_second": 15.691,
+      "step": 9000
     }
   ],
   "logging_steps": 50,
@@ -1355,7 +1433,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -1364,12 +1442,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9372455976960000.0,
+  "total_flos": 9923764764672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null