Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b500ee2d224d4e640beaa7f56f2db84d9bd13832c9ac427b6acd1d1df324efc2
+oid sha256:99daae0827ac7ad52e18d39b353c82b0099fe8e796df0b330433491a4427588d
 size 599689368

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650dc181d12546068a1bd5e33b80d4def8681f47f948fc641d38f7390414f09b
+oid sha256:18fdcd7ea9d3fed282a9f10f5509675379f5f943a9881cc239c9dcf00c6ec00c
 size 404854808

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46783c83748053c32f6173e8a637d5570ed0cf107dec0748cd97d11efc3389ff
+oid sha256:181b317c15f0766a6b713386a1a9e20616982c39714ae506a3bc45a52693de67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de723127fb29334c1d5f5d4d0ba1d4e78fc916dfc4e8f6b4bb5846a069a13ba9
+oid sha256:9d89303aa828aaa9e241260e2ca606db088309d8b5a7ba3d79cb10ce1887994d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.450271606445312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.8490566037735849,
+  "best_metric": 3.989581823348999,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 1.1320754716981132,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 21.517,
       "eval_steps_per_second": 5.397,
       "step": 450
+    },
+    {
+      "epoch": 0.8679245283018868,
+      "grad_norm": 695.1412353515625,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 73.7925,
+      "step": 460
+    },
+    {
+      "epoch": 0.8867924528301887,
+      "grad_norm": 118.63365936279297,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 34.6368,
+      "step": 470
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 50.097171783447266,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 23.91,
+      "step": 480
+    },
+    {
+      "epoch": 0.9245283018867925,
+      "grad_norm": 127.65890502929688,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 9.4513,
+      "step": 490
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 3.7929797172546387,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 1.6077,
+      "step": 500
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "eval_loss": 4.622971534729004,
+      "eval_runtime": 41.3713,
+      "eval_samples_per_second": 21.585,
+      "eval_steps_per_second": 5.414,
+      "step": 500
+    },
+    {
+      "epoch": 0.9622641509433962,
+      "grad_norm": 320.5762634277344,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 31.4437,
+      "step": 510
+    },
+    {
+      "epoch": 0.9811320754716981,
+      "grad_norm": 46.00068664550781,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 23.0031,
+      "step": 520
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.2149858474731445,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.5552,
+      "step": 530
+    },
+    {
+      "epoch": 1.0188679245283019,
+      "grad_norm": 88.85747528076172,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 27.1639,
+      "step": 540
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "grad_norm": 45.806617736816406,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 24.8611,
+      "step": 550
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "eval_loss": 3.9979488849639893,
+      "eval_runtime": 41.4471,
+      "eval_samples_per_second": 21.546,
+      "eval_steps_per_second": 5.404,
+      "step": 550
+    },
+    {
+      "epoch": 1.0566037735849056,
+      "grad_norm": 22.6519832611084,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 22.9177,
+      "step": 560
+    },
+    {
+      "epoch": 1.0754716981132075,
+      "grad_norm": 48.2337760925293,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 3.576,
+      "step": 570
+    },
+    {
+      "epoch": 1.0943396226415094,
+      "grad_norm": 13.664042472839355,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.382,
+      "step": 580
+    },
+    {
+      "epoch": 1.1132075471698113,
+      "grad_norm": 96.89643096923828,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 25.7203,
+      "step": 590
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 19.166614532470703,
+      "learning_rate": 0.0,
+      "loss": 24.3324,
+      "step": 600
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "eval_loss": 3.989581823348999,
+      "eval_runtime": 41.5204,
+      "eval_samples_per_second": 21.507,
+      "eval_steps_per_second": 5.395,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -416,7 +545,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.469707080368128e+17,
+  "total_flos": 4.6255532515157606e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null