Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c087ce17a696837556063aec57c18d646a449241e4e28d5d8c5588bdf05d48e
+oid sha256:535a71a142f150adf231a329959859a386bf2c9d9d4e750c9f3369da76a64e71
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:969f75fda8c013419f4c36b0ed729483e222ff27b3800deb55ac192b60a65df3
+oid sha256:ced5709ab8c595709f22364f75479b0c82a12ab0e9bb7626b6dd087eb1a2bff8
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c4eea830611a420fa1076c55ae8f111677eaed3c271436fa849d412ba54791e
+oid sha256:5c3a376f4b4c8e9d4b2aca90a714f2f9a30d0d8843cecdd594acaa7c3e464359
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.05220973491668701,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.06570781923048843,
+  "epoch": 0.07300868803387603,
   "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": 14.162,
       "eval_steps_per_second": 3.541,
       "step": 450
+    },
+    {
+      "epoch": 0.06716799299116595,
+      "grad_norm": 0.19294171035289764,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 0.0983,
+      "step": 460
+    },
+    {
+      "epoch": 0.06862816675184347,
+      "grad_norm": 0.24596017599105835,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 0.0224,
+      "step": 470
+    },
+    {
+      "epoch": 0.070088340512521,
+      "grad_norm": 0.2332233190536499,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 0.0176,
+      "step": 480
+    },
+    {
+      "epoch": 0.07154851427319851,
+      "grad_norm": 0.5431348085403442,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 0.0331,
+      "step": 490
+    },
+    {
+      "epoch": 0.07300868803387603,
+      "grad_norm": 0.009749150834977627,
+      "learning_rate": 0.0,
+      "loss": 0.0201,
+      "step": 500
+    },
+    {
+      "epoch": 0.07300868803387603,
+      "eval_loss": 0.052996329963207245,
+      "eval_runtime": 203.6393,
+      "eval_samples_per_second": 14.162,
+      "eval_steps_per_second": 3.541,
+      "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": 1.0108214238511104e+17,
+  "total_flos": 1.1239592345940787e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null