Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6183daeaae998ee28966f271a9e12d64e048a821bf0377f3d72b35a5336557d4
+oid sha256:139ab6e5023084853c3e1924182df8c69cf704345d8c898fb95958f7aba1b8e7
 size 402688040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80fa70c246f7016ef9ecb84d4f979702c7717728f4406b304d8c8f7fd8e2ea71
+oid sha256:e4251560ef29a8f119fe0eace77d6bb195c4763c070f00c4213d607a7d5c34f0
 size 204773972

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051026a9a89da9ad154cdff56d593da82bc617cc802089275f8d69463f4fd42b
+oid sha256:8fdf170ffdaff47ea36e8e2d34c14091e0093717e3ac6253a2fd93c559c89d35
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
+oid sha256:4f23fa0ef01cbb776456cad40209cd1c0c6a02d9fdf8c0632982552f2f542168
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7834962606430054,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.055699962866691426,
+  "epoch": 0.061888847629657136,
   "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": 21.721,
       "eval_steps_per_second": 5.434,
       "step": 450
+    },
+    {
+      "epoch": 0.056937739819284565,
+      "grad_norm": 0.48121166229248047,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 3.2537,
+      "step": 460
+    },
+    {
+      "epoch": 0.05817551677187771,
+      "grad_norm": 0.5190563201904297,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 3.4487,
+      "step": 470
+    },
+    {
+      "epoch": 0.05941329372447085,
+      "grad_norm": 0.6063217520713806,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 3.6391,
+      "step": 480
+    },
+    {
+      "epoch": 0.060651070677063997,
+      "grad_norm": 0.644209086894989,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 3.5162,
+      "step": 490
+    },
+    {
+      "epoch": 0.061888847629657136,
+      "grad_norm": 1.317447543144226,
+      "learning_rate": 0.0,
+      "loss": 3.8812,
+      "step": 500
+    },
+    {
+      "epoch": 0.061888847629657136,
+      "eval_loss": 1.7836123704910278,
+      "eval_runtime": 157.1333,
+      "eval_samples_per_second": 21.65,
+      "eval_steps_per_second": 5.416,
+      "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": 5.064444069543936e+16,
+  "total_flos": 5.632902077349888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null