Training in progress, step 118, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23b7052f6442b5e57e061a9ec12c4555b1a66baaea0bf2e069f4de2dcc01771
+oid sha256:63cfee5878ab65db5b705ec6ea806281ca700988be1b3e3e74c211ea2647b1db
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade28142ea9fd87d7fa415e1c947dd73351736915da0c3a90896180c9cab1afb
+oid sha256:9ad4e2fd44e8e8e8a558ec913b02829bdfa4e69a7c97eb3a8f9f3aabfad67de0
 size 40177764

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44b3e4b73abe7a23907fe168d7be6e78eb1a98f65b325b6165b1cf3630ff28c
+oid sha256:43e6292cda0efeb1e6132b0ec0fcb77f2d4b70b28c60fedc3fc6b80f99b24306
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bd5b05b92519d2726ffee16e42808f69da54027b63672bcf6975fb353217e4
+oid sha256:0b3bcdc466eb73eebfd9675632f258530c2eeec6e827633f8970adfddd0de13c
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e25f604c47c60866866955f607de55bfd3c9d658f41f3b624581a08f7ae974bd
+oid sha256:3774654a80525f2e7d0c05903fae9492ccc0d6b1e76f91d989b07516a151da74
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2768b22c9df76071dac580ad1afc0b8998c425a269dfebe53b087908a30a23ec
+oid sha256:3c289fbc2df42c6cb2efdede3def967473268adb1bf30caae90bc8595eaee2fe
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c92cf1bacb12b4d4201ed0d262a3916ea3cb93177659a32fa587afa665a707
+oid sha256:29cb203e73a43b847447a70852c414e0fe34eee7702678e59166287df8b6db17
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177e7c915929fd7e70aa37d949f3a428f0cb3365b8fcc1d2447a644a0521a136
+oid sha256:54f91fff101b03e8a32a3a388ec5c325dc89247d0110173a8d3b338bbdac0636
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6e6d9fae51bf6acdae853662ca2a80b8f4008cb3fe3616c8fed9e7feeb766b
+oid sha256:008f47c4841f931098e95b821c0d31865adfff64150cb817ae3d0b7a9f8422c0
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60e032504bc328692f846fde4443e0fee942c216f6f265dfe78ed063fc7efd5e
+oid sha256:a74062505e8d2d852ceb1243ee3149c6fcb8e05e0cc708541e00acc50125aa0b
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1565be9b29d4ad530db38223d84b3671e6b3a1aabac8097e44e5c246994c335a
+oid sha256:9b03eaaf9606b705beb16eda7d7500cdc94d6c1e550ef8fa1f732c8309e781a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7587078809738159,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.5316455696202533,
+  "epoch": 2.9873417721518987,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 118,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,132 @@
       "eval_samples_per_second": 474.105,
       "eval_steps_per_second": 15.207,
       "step": 100
+    },
+    {
+      "epoch": 2.5569620253164556,
+      "grad_norm": 0.0875733345746994,
+      "learning_rate": 6.469124876274007e-06,
+      "loss": 0.7216,
+      "step": 101
+    },
+    {
+      "epoch": 2.5822784810126582,
+      "grad_norm": 0.12728005647659302,
+      "learning_rate": 5.743837422535743e-06,
+      "loss": 0.7692,
+      "step": 102
+    },
+    {
+      "epoch": 2.607594936708861,
+      "grad_norm": 0.15928637981414795,
+      "learning_rate": 5.059379500020903e-06,
+      "loss": 0.7668,
+      "step": 103
+    },
+    {
+      "epoch": 2.632911392405063,
+      "grad_norm": 0.40893128514289856,
+      "learning_rate": 4.41633022846521e-06,
+      "loss": 0.7803,
+      "step": 104
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.2984897792339325,
+      "learning_rate": 3.815233691751582e-06,
+      "loss": 0.7272,
+      "step": 105
+    },
+    {
+      "epoch": 2.6835443037974684,
+      "grad_norm": 0.19053974747657776,
+      "learning_rate": 3.2565984775609507e-06,
+      "loss": 0.727,
+      "step": 106
+    },
+    {
+      "epoch": 2.708860759493671,
+      "grad_norm": 0.13291624188423157,
+      "learning_rate": 2.7408972470561695e-06,
+      "loss": 0.7532,
+      "step": 107
+    },
+    {
+      "epoch": 2.7341772151898733,
+      "grad_norm": 0.12510888278484344,
+      "learning_rate": 2.2685663349635993e-06,
+      "loss": 0.745,
+      "step": 108
+    },
+    {
+      "epoch": 2.759493670886076,
+      "grad_norm": 0.13656283915042877,
+      "learning_rate": 1.840005380390317e-06,
+      "loss": 0.7622,
+      "step": 109
+    },
+    {
+      "epoch": 2.7848101265822782,
+      "grad_norm": 0.2949647009372711,
+      "learning_rate": 1.4555769886895145e-06,
+      "loss": 0.7986,
+      "step": 110
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.33257901668548584,
+      "learning_rate": 1.1156064246602202e-06,
+      "loss": 0.7223,
+      "step": 111
+    },
+    {
+      "epoch": 2.8354430379746836,
+      "grad_norm": 0.2141508013010025,
+      "learning_rate": 8.203813373407668e-07,
+      "loss": 0.725,
+      "step": 112
+    },
+    {
+      "epoch": 2.8607594936708862,
+      "grad_norm": 0.133058562874794,
+      "learning_rate": 5.701515166289986e-07,
+      "loss": 0.7342,
+      "step": 113
+    },
+    {
+      "epoch": 2.8860759493670884,
+      "grad_norm": 0.06634331494569778,
+      "learning_rate": 3.6512868193507675e-07,
+      "loss": 0.74,
+      "step": 114
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 0.17949539422988892,
+      "learning_rate": 2.0548630304574055e-07,
+      "loss": 0.7621,
+      "step": 115
+    },
+    {
+      "epoch": 2.9367088607594938,
+      "grad_norm": 0.2013615071773529,
+      "learning_rate": 9.135945335151851e-08,
+      "loss": 0.7554,
+      "step": 116
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.2054380476474762,
+      "learning_rate": 2.2844695561167638e-08,
+      "loss": 0.7493,
+      "step": 117
+    },
+    {
+      "epoch": 2.9873417721518987,
+      "grad_norm": 0.1201392188668251,
+      "learning_rate": 0.0,
+      "loss": 0.7322,
+      "step": 118
     }
   ],
   "logging_steps": 1,
@@ -754,12 +880,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.00864304201728e+16,
+  "total_flos": 2.368962701348045e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null