Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691f994acfc59c7aca800d00d8b8e367902fb73123ddc0b51f8e84f579ecf237
+oid sha256:ff35e84e01f1386ebac587ae0cb8f62443ce9bfbcaf664da61c9fb02006570c0
 size 528526760

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9657073a58fefe7c01ef61fb07920f3088ef5ed4b3bf0ebb5157b21f93e50935
+oid sha256:6e22ca59118b10b5eb52fb341cd120c1968f04534206e934f766d9a6e8dec217
 size 141172038

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c45f92507a90bf7fbfb993e80ae13367813ee0eb21f64eb3e7039d42171134db
+oid sha256:e3048ecfad89600ff1c80bedbf89688a52e92cfd26e80e4cb6be8f6aab7986d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4609325e348c0ce76168f551d26f091fd1a57160aa92a5ffe7283ff60aa63ba8
+oid sha256:53869905448aa5dcb85f704ccd358f2990095cda7a0cb40de61a3fe333d56cc8
 size 2080

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.450434923171997,
   "best_model_checkpoint": "miner_id_24/checkpoint-1200",
-  "epoch": 0.05431567104101803,
+  "epoch": 0.05819536182966217,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1107,6 +1107,84 @@
       "eval_samples_per_second": 4.015,
       "eval_steps_per_second": 2.017,
       "step": 1400
+    },
+    {
+      "epoch": 0.05470364011988244,
+      "grad_norm": 4.387486934661865,
+      "learning_rate": 0.00019984273239970207,
+      "loss": 10.1819,
+      "step": 1410
+    },
+    {
+      "epoch": 0.05509160919874686,
+      "grad_norm": 5.688685894012451,
+      "learning_rate": 0.00019984044774901122,
+      "loss": 8.8118,
+      "step": 1420
+    },
+    {
+      "epoch": 0.055479578277611276,
+      "grad_norm": 5.5436835289001465,
+      "learning_rate": 0.00019983814854640514,
+      "loss": 9.8809,
+      "step": 1430
+    },
+    {
+      "epoch": 0.055867547356475686,
+      "grad_norm": 6.585811614990234,
+      "learning_rate": 0.00019983583479188383,
+      "loss": 9.4094,
+      "step": 1440
+    },
+    {
+      "epoch": 0.0562555164353401,
+      "grad_norm": 9.564101219177246,
+      "learning_rate": 0.00019983349193353206,
+      "loss": 10.8473,
+      "step": 1450
+    },
+    {
+      "epoch": 0.05664348551420452,
+      "grad_norm": 3.8079373836517334,
+      "learning_rate": 0.00019983113452326506,
+      "loss": 9.3833,
+      "step": 1460
+    },
+    {
+      "epoch": 0.05703145459306893,
+      "grad_norm": 4.716315269470215,
+      "learning_rate": 0.00019982877711299807,
+      "loss": 9.0148,
+      "step": 1470
+    },
+    {
+      "epoch": 0.057419423671933346,
+      "grad_norm": 5.183149337768555,
+      "learning_rate": 0.0001998263760469854,
+      "loss": 10.1636,
+      "step": 1480
+    },
+    {
+      "epoch": 0.05780739275079776,
+      "grad_norm": 7.416577339172363,
+      "learning_rate": 0.00019982398953288794,
+      "loss": 10.1869,
+      "step": 1490
+    },
+    {
+      "epoch": 0.05819536182966217,
+      "grad_norm": 10.7798433303833,
+      "learning_rate": 0.0001998215593630448,
+      "loss": 10.5461,
+      "step": 1500
+    },
+    {
+      "epoch": 0.05819536182966217,
+      "eval_loss": 2.462498426437378,
+      "eval_runtime": 51.1983,
+      "eval_samples_per_second": 4.043,
+      "eval_steps_per_second": 2.031,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -1121,7 +1199,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1130,12 +1208,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.0812918834222694e+17,
+  "total_flos": 2.2296408461785498e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null