Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51aecfda6474cb6a9b18f5791c3aaaf3acb18e3a1e1fbe9f7c03a16227adffd1
+oid sha256:c4d92f7cf3d125c77485240a3ccb68e99b2b17771713eeec576360975ac5dcae
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f2b321408f80c5b7da62d5bc1d90eba1b78c01f43da87aca60a93ef035f55d5
+oid sha256:253a2f5227b75b9ffe98d8454d6d307067214fcf250fe30601ebb5758d35a01e
 size 253144

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0cc8ba5206a542e4c95cba0207e3a9f589b91302dc09503c2e30d95b064505
+oid sha256:f25a5ccc1ca4546abd6e30a91a49baeaa6716a31c7d6906ff0ea5665d3f62239
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7184dd553de40442c66a0b4be61349dc886675cd2d150cd8fbe2e7df1b661ae
+oid sha256:5b07e555a202593c63f6bac44dc3ea733353ba121d904da5294b277396f02756
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7947821c9733f73670dbd8ff0eb6f44ea83cfe36954785f5919b9c3b439ad73
+oid sha256:35ece4076973bfc656e10c2c38d727539b6dded448b44541d432443f239670b3
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eddacce13425537aa9c75a8aee346199db36cbbf17ea255fd73a213b41da414c
+oid sha256:cbc55ea3a6e12149d64e9abc924964458d7ef2fc1939f8757720e216c510a8e8
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173eabd058f5ee6f255592920e905e9b49eb2a91d4cece530013279f0c161aeb
+oid sha256:902c91f73a954181ac570dea9820f0687bd92f4de3b0bbe519ad70a1c507f363
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8a32fcfe96cac63eadb87ec409bdc937af10221a7c7294aad11aa65d8e1dbe
+oid sha256:146af54b4d071cddf617c52272c0917a2a2ea3bad5e391b72c86a030f659ab7b
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df54088d52aa2dfc9d948fbf20e67c24427dcbb70e6b8cea0ce9804f575d50fb
+oid sha256:70813af7402255b82860edb4e44f49a505840fd9cdb1f2426932f9d9118cb397
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40f736708561b62ee56dd40d22ea9270a0ff7419cd30a58808d0501f0af4606
+oid sha256:4a91180062622ae9ca6c35d3e5235a4f0cf949b4705bfe1ffcafa768acb9a8b2
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d606eeb1aa97b417de3c30d0a970be83ac979e2c7cc0fa41135c63d459909e5
+oid sha256:ba4af3b1b4fa156d60adeec70df709d1741ac2f3147c676ab2805007313fc707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.319371223449707,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.8771929824561403,
+  "best_metric": 10.318848609924316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 1.1695906432748537,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,364 @@
       "eval_samples_per_second": 2799.918,
       "eval_steps_per_second": 87.535,
       "step": 150
+    },
+    {
+      "epoch": 0.8830409356725146,
+      "grad_norm": 0.04753561317920685,
+      "learning_rate": 2.6047368421052634e-05,
+      "loss": 10.3198,
+      "step": 151
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.04506006836891174,
+      "learning_rate": 2.5515789473684213e-05,
+      "loss": 10.3201,
+      "step": 152
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.04640384018421173,
+      "learning_rate": 2.4984210526315788e-05,
+      "loss": 10.3192,
+      "step": 153
+    },
+    {
+      "epoch": 0.9005847953216374,
+      "grad_norm": 0.04677899554371834,
+      "learning_rate": 2.445263157894737e-05,
+      "loss": 10.322,
+      "step": 154
+    },
+    {
+      "epoch": 0.9064327485380117,
+      "grad_norm": 0.0557510182261467,
+      "learning_rate": 2.3921052631578946e-05,
+      "loss": 10.3253,
+      "step": 155
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.04363035410642624,
+      "learning_rate": 2.3389473684210528e-05,
+      "loss": 10.323,
+      "step": 156
+    },
+    {
+      "epoch": 0.9181286549707602,
+      "grad_norm": 0.057154517620801926,
+      "learning_rate": 2.2857894736842106e-05,
+      "loss": 10.3214,
+      "step": 157
+    },
+    {
+      "epoch": 0.9239766081871345,
+      "grad_norm": 0.048275310546159744,
+      "learning_rate": 2.2326315789473685e-05,
+      "loss": 10.3178,
+      "step": 158
+    },
+    {
+      "epoch": 0.9298245614035088,
+      "grad_norm": 0.0417465940117836,
+      "learning_rate": 2.1794736842105264e-05,
+      "loss": 10.3195,
+      "step": 159
+    },
+    {
+      "epoch": 0.935672514619883,
+      "grad_norm": 0.05189359560608864,
+      "learning_rate": 2.1263157894736842e-05,
+      "loss": 10.3207,
+      "step": 160
+    },
+    {
+      "epoch": 0.9415204678362573,
+      "grad_norm": 0.05150682479143143,
+      "learning_rate": 2.073157894736842e-05,
+      "loss": 10.3242,
+      "step": 161
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.04391467198729515,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 10.3223,
+      "step": 162
+    },
+    {
+      "epoch": 0.9532163742690059,
+      "grad_norm": 0.04629657045006752,
+      "learning_rate": 1.966842105263158e-05,
+      "loss": 10.3191,
+      "step": 163
+    },
+    {
+      "epoch": 0.9590643274853801,
+      "grad_norm": 0.05460255220532417,
+      "learning_rate": 1.913684210526316e-05,
+      "loss": 10.3183,
+      "step": 164
+    },
+    {
+      "epoch": 0.9649122807017544,
+      "grad_norm": 0.049161266535520554,
+      "learning_rate": 1.8605263157894736e-05,
+      "loss": 10.3224,
+      "step": 165
+    },
+    {
+      "epoch": 0.9707602339181286,
+      "grad_norm": 0.03662397339940071,
+      "learning_rate": 1.8073684210526318e-05,
+      "loss": 10.323,
+      "step": 166
+    },
+    {
+      "epoch": 0.9766081871345029,
+      "grad_norm": 0.05333482101559639,
+      "learning_rate": 1.7542105263157897e-05,
+      "loss": 10.3214,
+      "step": 167
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.04198982194066048,
+      "learning_rate": 1.7010526315789475e-05,
+      "loss": 10.3223,
+      "step": 168
+    },
+    {
+      "epoch": 0.9883040935672515,
+      "grad_norm": 0.04948439076542854,
+      "learning_rate": 1.6478947368421054e-05,
+      "loss": 10.3231,
+      "step": 169
+    },
+    {
+      "epoch": 0.9941520467836257,
+      "grad_norm": 0.03972179442644119,
+      "learning_rate": 1.5947368421052633e-05,
+      "loss": 10.3224,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.048699554055929184,
+      "learning_rate": 1.541578947368421e-05,
+      "loss": 10.322,
+      "step": 171
+    },
+    {
+      "epoch": 1.0058479532163742,
+      "grad_norm": 0.037639688700437546,
+      "learning_rate": 1.4884210526315788e-05,
+      "loss": 10.3192,
+      "step": 172
+    },
+    {
+      "epoch": 1.0116959064327484,
+      "grad_norm": 0.050600651651620865,
+      "learning_rate": 1.4352631578947369e-05,
+      "loss": 10.3184,
+      "step": 173
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 0.05240437388420105,
+      "learning_rate": 1.3821052631578949e-05,
+      "loss": 10.3229,
+      "step": 174
+    },
+    {
+      "epoch": 1.023391812865497,
+      "grad_norm": 0.0477156937122345,
+      "learning_rate": 1.3289473684210526e-05,
+      "loss": 10.3211,
+      "step": 175
+    },
+    {
+      "epoch": 1.0292397660818713,
+      "grad_norm": 0.042833827435970306,
+      "learning_rate": 1.2757894736842106e-05,
+      "loss": 10.3241,
+      "step": 176
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.0383039191365242,
+      "learning_rate": 1.2226315789473685e-05,
+      "loss": 10.3228,
+      "step": 177
+    },
+    {
+      "epoch": 1.04093567251462,
+      "grad_norm": 0.04826338216662407,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 10.3221,
+      "step": 178
+    },
+    {
+      "epoch": 1.0467836257309941,
+      "grad_norm": 0.06094099208712578,
+      "learning_rate": 1.1163157894736842e-05,
+      "loss": 10.3195,
+      "step": 179
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.05548038333654404,
+      "learning_rate": 1.0631578947368421e-05,
+      "loss": 10.3206,
+      "step": 180
+    },
+    {
+      "epoch": 1.0584795321637426,
+      "grad_norm": 0.050352051854133606,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 10.3214,
+      "step": 181
+    },
+    {
+      "epoch": 1.064327485380117,
+      "grad_norm": 0.0544871911406517,
+      "learning_rate": 9.56842105263158e-06,
+      "loss": 10.3221,
+      "step": 182
+    },
+    {
+      "epoch": 1.0701754385964912,
+      "grad_norm": 0.047093939036130905,
+      "learning_rate": 9.036842105263159e-06,
+      "loss": 10.3198,
+      "step": 183
+    },
+    {
+      "epoch": 1.0760233918128654,
+      "grad_norm": 0.05518404394388199,
+      "learning_rate": 8.505263157894738e-06,
+      "loss": 10.3179,
+      "step": 184
+    },
+    {
+      "epoch": 1.0818713450292399,
+      "grad_norm": 0.047170720994472504,
+      "learning_rate": 7.973684210526316e-06,
+      "loss": 10.3168,
+      "step": 185
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 0.0469110831618309,
+      "learning_rate": 7.442105263157894e-06,
+      "loss": 10.3187,
+      "step": 186
+    },
+    {
+      "epoch": 1.0935672514619883,
+      "grad_norm": 0.04719029366970062,
+      "learning_rate": 6.9105263157894745e-06,
+      "loss": 10.3205,
+      "step": 187
+    },
+    {
+      "epoch": 1.0994152046783625,
+      "grad_norm": 0.059677038341760635,
+      "learning_rate": 6.378947368421053e-06,
+      "loss": 10.3213,
+      "step": 188
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.0459284782409668,
+      "learning_rate": 5.847368421052632e-06,
+      "loss": 10.3205,
+      "step": 189
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.04358220845460892,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 10.3201,
+      "step": 190
+    },
+    {
+      "epoch": 1.1169590643274854,
+      "grad_norm": 0.04509731009602547,
+      "learning_rate": 4.78421052631579e-06,
+      "loss": 10.3174,
+      "step": 191
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 0.03762376680970192,
+      "learning_rate": 4.252631578947369e-06,
+      "loss": 10.3202,
+      "step": 192
+    },
+    {
+      "epoch": 1.128654970760234,
+      "grad_norm": 0.05426834896206856,
+      "learning_rate": 3.721052631578947e-06,
+      "loss": 10.3242,
+      "step": 193
+    },
+    {
+      "epoch": 1.1345029239766082,
+      "grad_norm": 0.04800776019692421,
+      "learning_rate": 3.1894736842105266e-06,
+      "loss": 10.3216,
+      "step": 194
+    },
+    {
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.055790722370147705,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 10.3274,
+      "step": 195
+    },
+    {
+      "epoch": 1.1461988304093567,
+      "grad_norm": 0.05108264833688736,
+      "learning_rate": 2.1263157894736844e-06,
+      "loss": 10.3213,
+      "step": 196
+    },
+    {
+      "epoch": 1.1520467836257309,
+      "grad_norm": 0.05039351433515549,
+      "learning_rate": 1.5947368421052633e-06,
+      "loss": 10.3196,
+      "step": 197
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.06291382759809494,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 10.3192,
+      "step": 198
+    },
+    {
+      "epoch": 1.1637426900584795,
+      "grad_norm": 0.038250647485256195,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 10.3209,
+      "step": 199
+    },
+    {
+      "epoch": 1.1695906432748537,
+      "grad_norm": 0.03914465755224228,
+      "learning_rate": 0.0,
+      "loss": 10.3201,
+      "step": 200
+    },
+    {
+      "epoch": 1.1695906432748537,
+      "eval_loss": 10.318848609924316,
+      "eval_runtime": 0.8319,
+      "eval_samples_per_second": 2768.309,
+      "eval_steps_per_second": 86.547,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1470,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 143760913858560.0,
+  "total_flos": 191978686906368.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null