Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46201983b5a46f21c2cf47c938caaca7aaaab131faa946e654f2dc46ddba1a4b
+oid sha256:2343932dc9f467c552a05f4f42ad1f00522e970a21f404c0d34f439b11f110d3
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade04989d9666d7017a5192dd38f0949183ee6886364d11c4fab8303a028d47e
+oid sha256:ba2d329041d8d1f36d2142eea86f5efc2d289fc8405d222b886991ed8f5f3b16
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3346ddd98d51004b1bf1c84a10dbc456b6f0ed2c47354b53e9497c1347ce254
+oid sha256:309ed8187c26794765c48c908a5ffa54f398031a8d5f717c5f098779ed419ab9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
+oid sha256:b617d9f149fb11f5d9825dc6193f0b55aa7bf4899d1811982c0c93a389d7300b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.489604949951172,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.390625,
+  "best_metric": 10.487534523010254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.4340277777777778,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 197.866,
       "eval_steps_per_second": 49.772,
       "step": 450
+    },
+    {
+      "epoch": 0.3993055555555556,
+      "grad_norm": 0.6133874654769897,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 20.9323,
+      "step": 460
+    },
+    {
+      "epoch": 0.4079861111111111,
+      "grad_norm": 0.734044075012207,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 20.9398,
+      "step": 470
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.5548656582832336,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 20.9857,
+      "step": 480
+    },
+    {
+      "epoch": 0.4253472222222222,
+      "grad_norm": 0.6384900808334351,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 21.0152,
+      "step": 490
+    },
+    {
+      "epoch": 0.4340277777777778,
+      "grad_norm": 1.009379267692566,
+      "learning_rate": 0.0,
+      "loss": 21.0878,
+      "step": 500
+    },
+    {
+      "epoch": 0.4340277777777778,
+      "eval_loss": 10.487534523010254,
+      "eval_runtime": 2.4822,
+      "eval_samples_per_second": 195.392,
+      "eval_steps_per_second": 49.15,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8299021860864.0,
+  "total_flos": 9229801881600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null