Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849a72ff52b8bc2a8af5552ebd0ed2478fe51ed93c8fb606267f44f9b03cecde
+oid sha256:bf8de0b9d3080ee98ccc11a58a45a1e11422848c54785519aa6f5c1eb163d6b3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a41500702f93a35f81c9c800c4666d6633e5ce1f21dda2691d9fd9c1ef13790
+oid sha256:e17e7d08457cb8ea37635ee2e62601da2b7e1873166890ec7e055dfc28c13d30
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da087fd5b2cc926e4168efc7d258313d88f010a602804a95e7662b97eb818aa
+oid sha256:7e74afa3128c9edb7bc1c68eb675fdbb61872728a4a30240263a5f615acb7155
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44be7752e8f250f5c645b94c737a086e3ba6f8529fa94bf2d0ed1a0911f14f5a
+oid sha256:08c6d9b93a9a31eb6ebeb3ab3dc09ba23202435e453d5c3be3fefb3bbf21d637
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7514146566390991,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.007861017215627703,
+  "best_metric": 1.688521385192871,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.010481356287503603,
   "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": 16.425,
       "eval_steps_per_second": 4.107,
       "step": 150
+    },
+    {
+      "epoch": 0.008385085030002883,
+      "grad_norm": 1.7102468013763428,
+      "learning_rate": 0.0001753726596345424,
+      "loss": 1.3199,
+      "step": 160
+    },
+    {
+      "epoch": 0.008909152844378062,
+      "grad_norm": 1.9763778448104858,
+      "learning_rate": 0.00017025132184860355,
+      "loss": 1.2008,
+      "step": 170
+    },
+    {
+      "epoch": 0.009433220658753242,
+      "grad_norm": 1.650948405265808,
+      "learning_rate": 0.00016479747048321714,
+      "loss": 1.1192,
+      "step": 180
+    },
+    {
+      "epoch": 0.009957288473128423,
+      "grad_norm": 2.9453556537628174,
+      "learning_rate": 0.00015903767615401616,
+      "loss": 1.2746,
+      "step": 190
+    },
+    {
+      "epoch": 0.010481356287503603,
+      "grad_norm": 14.243999481201172,
+      "learning_rate": 0.000153,
+      "loss": 2.1821,
+      "step": 200
+    },
+    {
+      "epoch": 0.010481356287503603,
+      "eval_loss": 1.688521385192871,
+      "eval_runtime": 488.6728,
+      "eval_samples_per_second": 16.442,
+      "eval_steps_per_second": 4.111,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.82846296014848e+16,
+  "total_flos": 3.77128394686464e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null