Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de37fa0ffcc640e1ff40701bfd8a9e450c2fabfb066af254678d42e1973e814
+oid sha256:7274c55c927d3afc48714d91a3ae6ce57a85c2ca6d976c49994ec951c5ec7f99
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb249581fe642bb092877c3229ff71a0e08259f2968534f6bb0c0fa1df21209
+oid sha256:50ef1ac3cc0763621815f41da8edf01f21779347746dc1aa99d8385ee3aa9e56
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2cfbf75bd4762702bdf3a9445a6bbdc2eed82805837735a49a7dd8811f2f77
+oid sha256:f9a91b7b1000237604b7d2bb13fa6d3278f6427f80e66de5f4a8a7558e4d7f3b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7293239831924438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.12886597938144329,
+  "best_metric": 1.6833069324493408,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.1718213058419244,
   "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": 17.678,
       "eval_steps_per_second": 4.437,
       "step": 150
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 1.0603128671646118,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 1.7395,
+      "step": 160
+    },
+    {
+      "epoch": 0.14604810996563575,
+      "grad_norm": 1.1844924688339233,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 1.5991,
+      "step": 170
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 1.127656102180481,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 1.5951,
+      "step": 180
+    },
+    {
+      "epoch": 0.16323024054982818,
+      "grad_norm": 1.5854954719543457,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 1.5208,
+      "step": 190
+    },
+    {
+      "epoch": 0.1718213058419244,
+      "grad_norm": 3.6740827560424805,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 1.3948,
+      "step": 200
+    },
+    {
+      "epoch": 0.1718213058419244,
+      "eval_loss": 1.6833069324493408,
+      "eval_runtime": 27.6079,
+      "eval_samples_per_second": 17.749,
+      "eval_steps_per_second": 4.455,
+      "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": 2.6660412850176e+16,
+  "total_flos": 3.5547217133568e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null