Training in progress, step 94, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad448a2f72ed52d2c8b1e7ed9e8d15bd83219a3166062c0452fe0e9c12497e95
+oid sha256:4e1803fb1954671637cc0b0cca2b45c0e008d5d989c4cec4476a6633c6ad5e7e
 size 226530600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb78729f22fdf036909165b06a3e24395746a41d917597e301c39b7445ef71b
+oid sha256:23314cf085c944e7e11e1e4e39aaff66c6202fae9d91da18c779c730b85ada5d
 size 115354708

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed81e91b1d8e129108d84ea210e875c7a9ace2a5142ac5d6c89c432cd1f6cd1
+oid sha256:6208cfdf8c4e8a1ec2abce6a023c8a24a68d76563ca4165b4381eeb369457ac5
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c8c147e1fe7513a3e72b46b8b3c1e7f3b1004b680485178b6ad50625fde2b3
+oid sha256:4bc2ecafca3c346e8e52d1384a8ca96fad6b06a6bb514f10bb0c1cdbddf9f50c
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b974eff5f448b71d2a535f223f46feebc9f2990db044859bc107adbe4dcd0f34
+oid sha256:d011052707634a20c9a6031f2a8e6d72ce4f6641f28b167bfc893795bf8f0c60
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e698ec51c47f1b98cbf6f3b1c08ee0c47af054428910dc1112fcdc16ed378f49
+oid sha256:32a9619d6ff21b84a72698076e98ae9e76cbebb2176307849480b5a0e99a5e48
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b854d8cf49b9ceb47677523a5e83e042f4c08fd8e1230b87c991731ad3bea661
+oid sha256:c4a94f5bb1498693a066e5bf93ffbd5717952f9cb17d05ed0a2e8d92afb767f2
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3620ac1a1c313f97a79d8c2a366ef3f6f1a85a48d7717e96039e26136d30c2
+oid sha256:23f9c0a0006f95e06f162000e6848e3b039d97396f9660fc6a8cb8e71778b18a
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6d2016b54a623a06fcb79dd0dc1370476374101ead59a4949599794305828b
+oid sha256:ef96ff931f328cc1462c27545ff012f27f83f55e4cbd1c8771d540325488c3d4
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a2be7038a3fdc68df9bfd8e24be9321b4c5abdc5054fb1ff50504ab10db693
+oid sha256:ca681567d2dce0aa394e1601f1e55d898b7855e3bb7b1a9bc80168d79d738272
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb07bf9b3fb2656d49e7c9a66904014d612801f10c569079a3a3ec9280672f8
+oid sha256:b912ead5903a0906a733eb009427ce9d23cefc1a3d65b7794ee32cd6d73d4349
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.1337220668792725,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.5873015873015874,
+  "epoch": 2.984126984126984,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 94,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,314 @@
       "eval_samples_per_second": 201.374,
       "eval_steps_per_second": 6.681,
       "step": 50
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.45410627126693726,
+      "learning_rate": 5.653782008805976e-05,
+      "loss": 2.2446,
+      "step": 51
+    },
+    {
+      "epoch": 1.6507936507936507,
+      "grad_norm": 0.41431552171707153,
+      "learning_rate": 5.45e-05,
+      "loss": 2.3145,
+      "step": 52
+    },
+    {
+      "epoch": 1.6825396825396826,
+      "grad_norm": 0.47648075222969055,
+      "learning_rate": 5.246217991194026e-05,
+      "loss": 2.0731,
+      "step": 53
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.5698195099830627,
+      "learning_rate": 5.0427209899539885e-05,
+      "loss": 2.1394,
+      "step": 54
+    },
+    {
+      "epoch": 1.746031746031746,
+      "grad_norm": 0.6480918526649475,
+      "learning_rate": 4.839793605236973e-05,
+      "loss": 2.2599,
+      "step": 55
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.6323531270027161,
+      "learning_rate": 4.637719649339849e-05,
+      "loss": 1.9002,
+      "step": 56
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.5675813555717468,
+      "learning_rate": 4.436781740962116e-05,
+      "loss": 1.9179,
+      "step": 57
+    },
+    {
+      "epoch": 1.8412698412698414,
+      "grad_norm": 0.3834620714187622,
+      "learning_rate": 4.237260909938087e-05,
+      "loss": 2.0767,
+      "step": 58
+    },
+    {
+      "epoch": 1.873015873015873,
+      "grad_norm": 0.525580108165741,
+      "learning_rate": 4.039436204191262e-05,
+      "loss": 2.0866,
+      "step": 59
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.5951598286628723,
+      "learning_rate": 3.843584299460572e-05,
+      "loss": 2.1633,
+      "step": 60
+    },
+    {
+      "epoch": 1.9365079365079365,
+      "grad_norm": 0.6223026514053345,
+      "learning_rate": 3.649979112344341e-05,
+      "loss": 2.1433,
+      "step": 61
+    },
+    {
+      "epoch": 1.9682539682539684,
+      "grad_norm": 0.5904918909072876,
+      "learning_rate": 3.458891417203147e-05,
+      "loss": 1.9242,
+      "step": 62
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6642892360687256,
+      "learning_rate": 3.270588467457413e-05,
+      "loss": 2.5825,
+      "step": 63
+    },
+    {
+      "epoch": 2.0317460317460316,
+      "grad_norm": 0.32559293508529663,
+      "learning_rate": 3.0853336218093084e-05,
+      "loss": 1.7258,
+      "step": 64
+    },
+    {
+      "epoch": 2.0634920634920633,
+      "grad_norm": 0.4587280750274658,
+      "learning_rate": 2.903385975911812e-05,
+      "loss": 2.3208,
+      "step": 65
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.565092921257019,
+      "learning_rate": 2.7250000000000015e-05,
+      "loss": 2.194,
+      "step": 66
+    },
+    {
+      "epoch": 2.126984126984127,
+      "grad_norm": 0.6108811497688293,
+      "learning_rate": 2.5504251829914166e-05,
+      "loss": 2.1169,
+      "step": 67
+    },
+    {
+      "epoch": 2.1587301587301586,
+      "grad_norm": 0.6142228841781616,
+      "learning_rate": 2.3799056835532598e-05,
+      "loss": 2.0625,
+      "step": 68
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.6467757821083069,
+      "learning_rate": 2.213679988624417e-05,
+      "loss": 1.9029,
+      "step": 69
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.3613305687904358,
+      "learning_rate": 2.0519805798699028e-05,
+      "loss": 1.6734,
+      "step": 70
+    },
+    {
+      "epoch": 2.253968253968254,
+      "grad_norm": 0.41251838207244873,
+      "learning_rate": 1.8950336085342414e-05,
+      "loss": 2.2353,
+      "step": 71
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.5022515654563904,
+      "learning_rate": 1.7430585791484883e-05,
+      "loss": 2.0696,
+      "step": 72
+    },
+    {
+      "epoch": 2.317460317460317,
+      "grad_norm": 0.5805606245994568,
+      "learning_rate": 1.5962680425333164e-05,
+      "loss": 2.0047,
+      "step": 73
+    },
+    {
+      "epoch": 2.3492063492063493,
+      "grad_norm": 0.5866724252700806,
+      "learning_rate": 1.4548672985274478e-05,
+      "loss": 1.9632,
+      "step": 74
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.668701708316803,
+      "learning_rate": 1.3190541088572804e-05,
+      "loss": 1.8914,
+      "step": 75
+    },
+    {
+      "epoch": 2.4126984126984126,
+      "grad_norm": 0.41800686717033386,
+      "learning_rate": 1.1890184205492376e-05,
+      "loss": 1.5903,
+      "step": 76
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.39929744601249695,
+      "learning_rate": 1.0649421002716576e-05,
+      "loss": 2.1196,
+      "step": 77
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.5325944423675537,
+      "learning_rate": 9.46998679977829e-06,
+      "loss": 2.0817,
+      "step": 78
+    },
+    {
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.5891134738922119,
+      "learning_rate": 8.353531142058515e-06,
+      "loss": 2.1,
+      "step": 79
+    },
+    {
+      "epoch": 2.5396825396825395,
+      "grad_norm": 0.6240812540054321,
+      "learning_rate": 7.301615493748091e-06,
+      "loss": 2.0559,
+      "step": 80
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.6424437165260315,
+      "learning_rate": 6.315711053998774e-06,
+      "loss": 1.9652,
+      "step": 81
+    },
+    {
+      "epoch": 2.6031746031746033,
+      "grad_norm": 0.4992195963859558,
+      "learning_rate": 5.397196699318163e-06,
+      "loss": 1.7574,
+      "step": 82
+    },
+    {
+      "epoch": 2.634920634920635,
+      "grad_norm": 0.3789694607257843,
+      "learning_rate": 4.547357055086298e-06,
+      "loss": 1.9254,
+      "step": 83
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.4895634949207306,
+      "learning_rate": 3.7673806988908747e-06,
+      "loss": 2.1383,
+      "step": 84
+    },
+    {
+      "epoch": 2.6984126984126986,
+      "grad_norm": 0.7421378493309021,
+      "learning_rate": 3.0583584981939674e-06,
+      "loss": 2.122,
+      "step": 85
+    },
+    {
+      "epoch": 2.7301587301587302,
+      "grad_norm": 0.6015245914459229,
+      "learning_rate": 2.421282084655327e-06,
+      "loss": 2.0425,
+      "step": 86
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.6372620463371277,
+      "learning_rate": 1.857042467245783e-06,
+      "loss": 1.9019,
+      "step": 87
+    },
+    {
+      "epoch": 2.7936507936507935,
+      "grad_norm": 0.7627705931663513,
+      "learning_rate": 1.3664287860906128e-06,
+      "loss": 1.9153,
+      "step": 88
+    },
+    {
+      "epoch": 2.825396825396825,
+      "grad_norm": 0.3627667725086212,
+      "learning_rate": 9.501272087857891e-07,
+      "loss": 1.7647,
+      "step": 89
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.4342782497406006,
+      "learning_rate": 6.087199707304955e-07,
+      "loss": 2.194,
+      "step": 90
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.5292289853096008,
+      "learning_rate": 3.426845608182781e-07,
+      "loss": 2.058,
+      "step": 91
+    },
+    {
+      "epoch": 2.9206349206349205,
+      "grad_norm": 0.5725750923156738,
+      "learning_rate": 1.5239305362568295e-07,
+      "loss": 1.9702,
+      "step": 92
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.6080511808395386,
+      "learning_rate": 3.8111589032275855e-08,
+      "loss": 2.005,
+      "step": 93
+    },
+    {
+      "epoch": 2.984126984126984,
+      "grad_norm": 0.6713661551475525,
+      "learning_rate": 0.0,
+      "loss": 1.8249,
+      "step": 94
     }
   ],
   "logging_steps": 1,
@@ -396,12 +704,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.077440327712768e+17,
+  "total_flos": 2.025587816100004e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null