Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9e1d165d8719ec9f780eb8920883a80b63e242e51bdee30659745e50827b33
+oid sha256:c6a96fe0fa1193840a93cf68852b26b9ef4b83c26aed1c1aa27cbb92a1114463
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d83b0491c54271b98a7a8ac65d71d04b9a149eed85787a94b4873a11c78998
+oid sha256:6fcc1b30614d6509167f9fbe16fbb1244d4bc76b0b282440332ec26b019a16ff
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca1d3a29ddde696f94089676e8882cda32984390a8fca557ea6d5cc2578ecc4
+oid sha256:1a96d304a9a82c9caeab768c763cc12aade78e0014f3034a310c7ad68f23d7ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
+oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5439529418945312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05435767349157456,
+  "best_metric": 2.4248692989349365,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.07247689798876608,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 15.625,
       "eval_steps_per_second": 3.913,
       "step": 150
+    },
+    {
+      "epoch": 0.057981518391012864,
+      "grad_norm": 1.6721464395523071,
+      "learning_rate": 0.00017709199943488106,
+      "loss": 2.5641,
+      "step": 160
+    },
+    {
+      "epoch": 0.061605363290451166,
+      "grad_norm": 2.1737399101257324,
+      "learning_rate": 0.00017192045245496238,
+      "loss": 2.2523,
+      "step": 170
+    },
+    {
+      "epoch": 0.06522920818988948,
+      "grad_norm": 1.9437196254730225,
+      "learning_rate": 0.00016641313195854277,
+      "loss": 2.3634,
+      "step": 180
+    },
+    {
+      "epoch": 0.06885305308932778,
+      "grad_norm": 2.254823923110962,
+      "learning_rate": 0.0001605968690574869,
+      "loss": 2.2732,
+      "step": 190
+    },
+    {
+      "epoch": 0.07247689798876608,
+      "grad_norm": 4.65241813659668,
+      "learning_rate": 0.0001545,
+      "loss": 2.2174,
+      "step": 200
+    },
+    {
+      "epoch": 0.07247689798876608,
+      "eval_loss": 2.4248692989349365,
+      "eval_runtime": 74.2004,
+      "eval_samples_per_second": 15.66,
+      "eval_steps_per_second": 3.922,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.903888639085773e+16,
+  "total_flos": 3.884422465270579e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null