Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9692744b48db18fa4e4208eca6c93f9c09bf94a432e0e61f592cb15c2ce7b8ed
+oid sha256:449464db766d63860123fe585eb2ea917a236cabadecd7c6c7a38b33a67a1128
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e5bb09298c4244d44cfbf7a5d6da5b4b2009c455fa622da155c3110db955846
+oid sha256:5b6a2a7a6ef3cc7ec0da7330f4cbbf8c921fc40740eb8aa8fc148cef03435478
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4169c04cb7870f2b433cea736eca37c4197f487fcf83cf802a73d112dbe27f
+oid sha256:c9222f49813f2d37090b6c3ba6ddf1267525395ace62444cf594c70d8427f4f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd52d52fe0f0348e0615f49790d582d99bc965e6e8d769157b68f404ab1ba391
+oid sha256:367bcdbb471387c2c2f46f68f85951017299d77f7594d07a196d5f5b5d01911a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.20296970009803772,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 1.5466408893185113,
+  "epoch": 2.0106331561140647,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,224 @@
       "eval_samples_per_second": 6.839,
       "eval_steps_per_second": 6.839,
       "step": 100
+    },
+    {
+      "epoch": 1.5621072982116964,
+      "grad_norm": 0.1923961192369461,
+      "learning_rate": 4.1193844348156886e-05,
+      "loss": 0.1462,
+      "step": 101
+    },
+    {
+      "epoch": 1.5775737071048814,
+      "grad_norm": 0.18478325009346008,
+      "learning_rate": 3.852827617839084e-05,
+      "loss": 0.1648,
+      "step": 102
+    },
+    {
+      "epoch": 1.5930401159980667,
+      "grad_norm": 0.30043265223503113,
+      "learning_rate": 3.593910515999536e-05,
+      "loss": 0.1844,
+      "step": 103
+    },
+    {
+      "epoch": 1.6085065248912518,
+      "grad_norm": 0.5838200449943542,
+      "learning_rate": 3.342810578145436e-05,
+      "loss": 0.2355,
+      "step": 104
+    },
+    {
+      "epoch": 1.623972933784437,
+      "grad_norm": 0.5884765386581421,
+      "learning_rate": 3.099699895631474e-05,
+      "loss": 0.2287,
+      "step": 105
+    },
+    {
+      "epoch": 1.6394393426776221,
+      "grad_norm": 0.4631075859069824,
+      "learning_rate": 2.8647450843757897e-05,
+      "loss": 0.2004,
+      "step": 106
+    },
+    {
+      "epoch": 1.6549057515708072,
+      "grad_norm": 0.3879186809062958,
+      "learning_rate": 2.6381071706697644e-05,
+      "loss": 0.1996,
+      "step": 107
+    },
+    {
+      "epoch": 1.6703721604639923,
+      "grad_norm": 0.2909069359302521,
+      "learning_rate": 2.4199414808186406e-05,
+      "loss": 0.1985,
+      "step": 108
+    },
+    {
+      "epoch": 1.6858385693571774,
+      "grad_norm": 0.34202706813812256,
+      "learning_rate": 2.210397534688617e-05,
+      "loss": 0.1848,
+      "step": 109
+    },
+    {
+      "epoch": 1.7013049782503624,
+      "grad_norm": 0.3348611295223236,
+      "learning_rate": 2.009618943233419e-05,
+      "loss": 0.2004,
+      "step": 110
+    },
+    {
+      "epoch": 1.7167713871435475,
+      "grad_norm": 0.4890515208244324,
+      "learning_rate": 1.8177433100705207e-05,
+      "loss": 0.2107,
+      "step": 111
+    },
+    {
+      "epoch": 1.7322377960367326,
+      "grad_norm": 0.560546875,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 0.2933,
+      "step": 112
+    },
+    {
+      "epoch": 1.7477042049299178,
+      "grad_norm": 0.5725692510604858,
+      "learning_rate": 1.4612207347520938e-05,
+      "loss": 0.2927,
+      "step": 113
+    },
+    {
+      "epoch": 1.763170613823103,
+      "grad_norm": 0.33504927158355713,
+      "learning_rate": 1.2968181353609852e-05,
+      "loss": 0.1681,
+      "step": 114
+    },
+    {
+      "epoch": 1.7786370227162882,
+      "grad_norm": 0.34945377707481384,
+      "learning_rate": 1.1418070123306989e-05,
+      "loss": 0.1594,
+      "step": 115
+    },
+    {
+      "epoch": 1.7941034316094733,
+      "grad_norm": 0.31711897253990173,
+      "learning_rate": 9.962936025419754e-06,
+      "loss": 0.1475,
+      "step": 116
+    },
+    {
+      "epoch": 1.8095698405026583,
+      "grad_norm": 0.25584596395492554,
+      "learning_rate": 8.603776336173235e-06,
+      "loss": 0.1476,
+      "step": 117
+    },
+    {
+      "epoch": 1.8250362493958434,
+      "grad_norm": 0.34091395139694214,
+      "learning_rate": 7.34152255572697e-06,
+      "loss": 0.1856,
+      "step": 118
+    },
+    {
+      "epoch": 1.8405026582890285,
+      "grad_norm": 0.3409639894962311,
+      "learning_rate": 6.1770397697710414e-06,
+      "loss": 0.1982,
+      "step": 119
+    },
+    {
+      "epoch": 1.8559690671822135,
+      "grad_norm": 0.2535560131072998,
+      "learning_rate": 5.11112605663977e-06,
+      "loss": 0.1881,
+      "step": 120
+    },
+    {
+      "epoch": 1.8714354760753986,
+      "grad_norm": 0.26184314489364624,
+      "learning_rate": 4.144511940348516e-06,
+      "loss": 0.1976,
+      "step": 121
+    },
+    {
+      "epoch": 1.886901884968584,
+      "grad_norm": 0.28429871797561646,
+      "learning_rate": 3.2778598899291465e-06,
+      "loss": 0.1938,
+      "step": 122
+    },
+    {
+      "epoch": 1.902368293861769,
+      "grad_norm": 0.23394553363323212,
+      "learning_rate": 2.511763865406824e-06,
+      "loss": 0.1655,
+      "step": 123
+    },
+    {
+      "epoch": 1.917834702754954,
+      "grad_norm": 0.36569544672966003,
+      "learning_rate": 1.8467489107293509e-06,
+      "loss": 0.2076,
+      "step": 124
+    },
+    {
+      "epoch": 1.9333011116481393,
+      "grad_norm": 0.38919389247894287,
+      "learning_rate": 1.2832707939284427e-06,
+      "loss": 0.1977,
+      "step": 125
+    },
+    {
+      "epoch": 1.9333011116481393,
+      "eval_loss": 0.18706867098808289,
+      "eval_runtime": 7.3048,
+      "eval_samples_per_second": 6.845,
+      "eval_steps_per_second": 6.845,
+      "step": 125
+    },
+    {
+      "epoch": 1.9487675205413244,
+      "grad_norm": 0.2989993989467621,
+      "learning_rate": 8.217156947590064e-07,
+      "loss": 0.2162,
+      "step": 126
+    },
+    {
+      "epoch": 1.9642339294345095,
+      "grad_norm": 0.41685956716537476,
+      "learning_rate": 4.623999400308054e-07,
+      "loss": 0.2151,
+      "step": 127
+    },
+    {
+      "epoch": 1.9797003383276945,
+      "grad_norm": 0.2608714699745178,
+      "learning_rate": 2.05569786813925e-07,
+      "loss": 0.2491,
+      "step": 128
+    },
+    {
+      "epoch": 1.9951667472208796,
+      "grad_norm": 0.4548462927341461,
+      "learning_rate": 5.1401253666411016e-08,
+      "loss": 0.333,
+      "step": 129
+    },
+    {
+      "epoch": 2.0106331561140647,
+      "grad_norm": 0.17462550103664398,
+      "learning_rate": 0.0,
+      "loss": 0.1465,
+      "step": 130
     }
   ],
   "logging_steps": 1,
@@ -770,12 +988,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.579466434711388e+17,
+  "total_flos": 2.052912237505413e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null