Training in progress, step 174, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeed035ce5dcce88a233373798a9de187a66444b7065679d46eaafffdc30b49b
+oid sha256:fa4d357734fdda7036356fde4911850a42a51788ac095bec425eb881082b0bd6
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bceeef05f13bb8127977f489cebd596f044b56a22b459420d8d3913f3e8a30
+oid sha256:8475a6f622d2f8996ff69abd169f3f4d38282a43b26bbf7d9447149c7fccbad8
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e2cc68fec35eea292f2a47003384c40319897254a04e89eb1310d76e5b0b8a
+oid sha256:04492302fbc28f34f730e4ca19b43b23f39876c1af59bd98d59fa54155df39c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd09b145b84efce2be7f1cf33534415c05ffa82e2c78f38fb9db454c9c0a2d2d
+oid sha256:23fea76ad2ffea37b2ba8b48cb0de653536a9331e1198d3667a81d4423047935
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.15821892023086548,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.606060606060606,
+  "epoch": 3.0259740259740258,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 174,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,174 @@
       "eval_samples_per_second": 33.439,
       "eval_steps_per_second": 8.53,
       "step": 150
+    },
+    {
+      "epoch": 2.6233766233766236,
+      "grad_norm": 0.28441935777664185,
+      "learning_rate": 4.7749731574629196e-06,
+      "loss": 0.0847,
+      "step": 151
+    },
+    {
+      "epoch": 2.6406926406926408,
+      "grad_norm": 0.2971477210521698,
+      "learning_rate": 4.374819176172501e-06,
+      "loss": 0.1133,
+      "step": 152
+    },
+    {
+      "epoch": 2.658008658008658,
+      "grad_norm": 0.30149710178375244,
+      "learning_rate": 3.991407041832912e-06,
+      "loss": 0.0972,
+      "step": 153
+    },
+    {
+      "epoch": 2.675324675324675,
+      "grad_norm": 0.31789451837539673,
+      "learning_rate": 3.6248774448952695e-06,
+      "loss": 0.1102,
+      "step": 154
+    },
+    {
+      "epoch": 2.6926406926406927,
+      "grad_norm": 0.3588525652885437,
+      "learning_rate": 3.2753648808794503e-06,
+      "loss": 0.107,
+      "step": 155
+    },
+    {
+      "epoch": 2.70995670995671,
+      "grad_norm": 0.314968079328537,
+      "learning_rate": 2.942997601021924e-06,
+      "loss": 0.1008,
+      "step": 156
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.5025056600570679,
+      "learning_rate": 2.6278975652147875e-06,
+      "loss": 0.1122,
+      "step": 157
+    },
+    {
+      "epoch": 2.7445887445887447,
+      "grad_norm": 0.2689873278141022,
+      "learning_rate": 2.330180397253473e-06,
+      "loss": 0.1048,
+      "step": 158
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.24611997604370117,
+      "learning_rate": 2.049955342409349e-06,
+      "loss": 0.0852,
+      "step": 159
+    },
+    {
+      "epoch": 2.779220779220779,
+      "grad_norm": 0.23309774696826935,
+      "learning_rate": 1.7873252273429509e-06,
+      "loss": 0.079,
+      "step": 160
+    },
+    {
+      "epoch": 2.7965367965367967,
+      "grad_norm": 0.232229545712471,
+      "learning_rate": 1.542386422372405e-06,
+      "loss": 0.0847,
+      "step": 161
+    },
+    {
+      "epoch": 2.813852813852814,
+      "grad_norm": 0.23521187901496887,
+      "learning_rate": 1.3152288061110518e-06,
+      "loss": 0.0814,
+      "step": 162
+    },
+    {
+      "epoch": 2.8311688311688314,
+      "grad_norm": 0.25621297955513,
+      "learning_rate": 1.1059357324870455e-06,
+      "loss": 0.083,
+      "step": 163
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.2673909664154053,
+      "learning_rate": 9.145840001572537e-07,
+      "loss": 0.0838,
+      "step": 164
+    },
+    {
+      "epoch": 2.865800865800866,
+      "grad_norm": 0.28247588872909546,
+      "learning_rate": 7.41243824326504e-07,
+      "loss": 0.1066,
+      "step": 165
+    },
+    {
+      "epoch": 2.883116883116883,
+      "grad_norm": 0.27514898777008057,
+      "learning_rate": 5.859788109825793e-07,
+      "loss": 0.081,
+      "step": 166
+    },
+    {
+      "epoch": 2.9004329004329006,
+      "grad_norm": 0.29527780413627625,
+      "learning_rate": 4.48845933556441e-07,
+      "loss": 0.1017,
+      "step": 167
+    },
+    {
+      "epoch": 2.9177489177489178,
+      "grad_norm": 0.2788955569267273,
+      "learning_rate": 3.2989551201624835e-07,
+      "loss": 0.0885,
+      "step": 168
+    },
+    {
+      "epoch": 2.935064935064935,
+      "grad_norm": 0.35651448369026184,
+      "learning_rate": 2.2917119440275524e-07,
+      "loss": 0.1214,
+      "step": 169
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.31964361667633057,
+      "learning_rate": 1.4670994081297795e-07,
+      "loss": 0.104,
+      "step": 170
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.4855041205883026,
+      "learning_rate": 8.254200983794369e-08,
+      "loss": 0.1288,
+      "step": 171
+    },
+    {
+      "epoch": 2.987012987012987,
+      "grad_norm": 0.2868228554725647,
+      "learning_rate": 3.669094745950008e-08,
+      "loss": 0.1053,
+      "step": 172
+    },
+    {
+      "epoch": 3.0086580086580086,
+      "grad_norm": 0.4777703285217285,
+      "learning_rate": 9.17357841028199e-09,
+      "loss": 0.1314,
+      "step": 173
+    },
+    {
+      "epoch": 3.0259740259740258,
+      "grad_norm": 0.2728607654571533,
+      "learning_rate": 0.0,
+      "loss": 0.112,
+      "step": 174
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1280,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.0821709602816e+16,
+  "total_flos": 4.735318313926656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null