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:c0351d1d11c0dcf403ae9adc13daaeeed027d42fa62b64e3ec1f545e27630a18
+oid sha256:142e9efadb1556fe29a24193a9115b4a2cd99b3e7c6e6a78e5493e250e822816
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d069c9320c7eec38ecc267e437fd250615b21bfb3013c2e7f7823b0a08550db9
+oid sha256:49232695cdc22f6d6e1f5c80efb8afa3ff44509ed885524e703554fb24c7922c
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dacb351634cadf8731b37769aa65f8d189619347a642a1e44a84b8345b1b587
+oid sha256:7e09a1d7755414f4cd678315a0c28a4f52599b9a0a8c7cbe611e828b919b0c8f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
+oid sha256:dc6d7a4e5542db8278bbb08501029d28a2952cf2860b91c35fe25fb2510ba81c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.10635092109441757,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.24483133841131666,
+  "best_metric": 0.10595488548278809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.2720348204570185,
   "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": 5.826,
       "eval_steps_per_second": 1.46,
       "step": 450
+    },
+    {
+      "epoch": 0.250272034820457,
+      "grad_norm": 0.14279238879680634,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 0.1664,
+      "step": 460
+    },
+    {
+      "epoch": 0.25571273122959737,
+      "grad_norm": 0.6236724853515625,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 0.2752,
+      "step": 470
+    },
+    {
+      "epoch": 0.2611534276387378,
+      "grad_norm": 0.802135169506073,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 0.2971,
+      "step": 480
+    },
+    {
+      "epoch": 0.26659412404787813,
+      "grad_norm": 0.7756718993186951,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 0.3215,
+      "step": 490
+    },
+    {
+      "epoch": 0.2720348204570185,
+      "grad_norm": 0.9758143424987793,
+      "learning_rate": 0.0,
+      "loss": 0.4517,
+      "step": 500
+    },
+    {
+      "epoch": 0.2720348204570185,
+      "eval_loss": 0.10595488548278809,
+      "eval_runtime": 66.4878,
+      "eval_samples_per_second": 5.821,
+      "eval_steps_per_second": 1.459,
+      "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": 1.2083271532806144e+17,
+  "total_flos": 1.3049289243623424e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null