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:b21df98a6605c2b89af53c69cb420b3c9a0cff504fbbd010fd501540bf7491bc
+oid sha256:4a11f8dd59277768983f6763e96ef38fe0d7a5b72e553fa0fc684efcc19ef993
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8c352f3aaebecfbc7994a94fff678081722788149aa3ac1a5fedf8ce42f565
+oid sha256:97b0ddfad739571e5fc935c88bd42080d414fe26f07425d38722d9b038e6f745
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5567f0467a94d2ba965808d9deae03424ff67873f86a7423c669730ef7a3bef
+oid sha256:0add59cd56849238bdd29b8166c826ec1f7c0d0195f7b9509445e668bec04f12
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7775332927703857,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.38022813688212925,
+  "epoch": 0.4224757076468103,
   "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": 16.574,
       "eval_steps_per_second": 4.152,
       "step": 450
+    },
+    {
+      "epoch": 0.38867765103506546,
+      "grad_norm": 0.4057118892669678,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 0.7811,
+      "step": 460
+    },
+    {
+      "epoch": 0.3971271651880017,
+      "grad_norm": 0.649547278881073,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 0.7211,
+      "step": 470
+    },
+    {
+      "epoch": 0.4055766793409379,
+      "grad_norm": 0.7348433136940002,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 0.8406,
+      "step": 480
+    },
+    {
+      "epoch": 0.4140261934938741,
+      "grad_norm": 1.0850099325180054,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 0.8591,
+      "step": 490
+    },
+    {
+      "epoch": 0.4224757076468103,
+      "grad_norm": 2.027728319168091,
+      "learning_rate": 0.0,
+      "loss": 0.7295,
+      "step": 500
+    },
+    {
+      "epoch": 0.4224757076468103,
+      "eval_loss": 0.7784817814826965,
+      "eval_runtime": 30.0708,
+      "eval_samples_per_second": 16.594,
+      "eval_steps_per_second": 4.157,
+      "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": 8.318048809254912e+16,
+  "total_flos": 9.251163259011072e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null