Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d4b9e896e08298a9fc4850e2b0f7d6f975aacbe0372798863507a40db0da1
+oid sha256:2246f52ecbc241c2d787fbf14c65515a72e095723af14503ea8f06b9f689be33
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef06f18265c83b6e7d933065cd062638c32258b35812b3fcf5fcf0ea30ef010
+oid sha256:09f1b1b3af4948a17b61118140494dbac5e0c5fc46094447346faa32f61cc11d
 size 127788756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa0d5be4cbf8607624a8cf17b3d8ef008d879e7a13d1230a5dfe5653a28c195
+oid sha256:145fdd3e0bbb0877bea68825818c4e310d8579bfec2ce3274f382e10adcce1a2
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
+oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7672083377838135,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.15387245683022738,
+  "epoch": 0.17096939647803044,
   "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": 6.757,
       "eval_steps_per_second": 1.689,
       "step": 450
+    },
+    {
+      "epoch": 0.157291844759788,
+      "grad_norm": 0.31098073720932007,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 0.7879,
+      "step": 460
+    },
+    {
+      "epoch": 0.16071123268934862,
+      "grad_norm": 6.655428886413574,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 0.9999,
+      "step": 470
+    },
+    {
+      "epoch": 0.1641306206189092,
+      "grad_norm": 4.029115200042725,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 0.9647,
+      "step": 480
+    },
+    {
+      "epoch": 0.16755000854846983,
+      "grad_norm": 0.3827471435070038,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 0.6842,
+      "step": 490
+    },
+    {
+      "epoch": 0.17096939647803044,
+      "grad_norm": 0.9424235224723816,
+      "learning_rate": 0.0,
+      "loss": 0.7972,
+      "step": 500
+    },
+    {
+      "epoch": 0.17096939647803044,
+      "eval_loss": 0.779399037361145,
+      "eval_runtime": 182.875,
+      "eval_samples_per_second": 6.737,
+      "eval_steps_per_second": 1.684,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "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": 2.4169218853306368e+17,
+  "total_flos": 2.674007469981696e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null