Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdb6b0392e49eb49b58e0fb4f543f26ec0767a1accb7f356da15ae2cf51ae7f
+oid sha256:82592257541f166b7f6678bb1a4815ab83363a620190de1381ef271bc5178147
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f97a8729fd968f72c85dd44be3284868b7af5e01be558f35c219938e3af9f1e
+oid sha256:745dccfbc58b704660060532cbc4f8f9761ad67c7c69c81bcee58125b5aaed82
 size 341314196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2ae29239509559eec01c645b731dcf81c9c74579b19db533df11fa076dee9b
+oid sha256:50ea30d9115dfa78c890c24369b41013c87cb05c1eebeb5d3a7800080b5cceaa
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03510c6cf7e971d9952a74f175320714230c881a9860922558474122aabe1532
+oid sha256:7732b6191d41c03edb04114a2892473ded1337c75ce472441f0158d1dfebedb5
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8824ab68485d2938a99458911aa7f7b037c4bf649ebb0672b8a19b2b23a8bf
+oid sha256:1cae75ae1669fbdd8d700b2814919cefe2541bbc777fe474515d27fb93fd91a7
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80fc45f21cd9595a1ed0e2efb8f5a95397f41b20ada3fb3c56fad2593a6f75ac
+oid sha256:676ad7d4bce3d4cc3092bc6ff99442b6304ba495054b357124f8228d1e8a3fb9
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f969ed41d9b4713b8d805b1345dcd990c410c619a80dcb3d91a5819b844ca978
+oid sha256:b88f092309835dd73c1cbfc15e605526c4b384e69950f75bac9ed24ea512bf9a
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7636ed803ab77b72f36f9227843b448e06774f4ee994b8815e9f2a237423e166
+oid sha256:1d23d1d13e4aaf0766648c6e278dbf1adb9ff5cc4f9f8e4a103e02dc265c34b8
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8229b55f3e8492cf06b8503851197f88106af10e687b9b83f5898dc8d791443e
+oid sha256:14fed10d5db9e9035b5ce587f68e4f95adc2343803656c35ebfc887a3ab2009b
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecf3ae5cdc7262ff9770b0a4afeedcc19e66bcec1b6bf7de0cd4a6ac4f57a79
+oid sha256:f3c18235841f5a14d9ecb4708920dbec365edfb5bce02def4dd8b306162f287b
 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": 0.500893771648407,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.487408610885459,
+  "best_metric": 0.4971354603767395,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.6498781478472786,
   "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": 120.686,
       "eval_steps_per_second": 3.785,
       "step": 150
+    },
+    {
+      "epoch": 0.49065800162469536,
+      "grad_norm": 0.663077175617218,
+      "learning_rate": 2.6047368421052634e-05,
+      "loss": 1.4541,
+      "step": 151
+    },
+    {
+      "epoch": 0.4939073923639318,
+      "grad_norm": 0.8141458034515381,
+      "learning_rate": 2.5515789473684213e-05,
+      "loss": 1.7101,
+      "step": 152
+    },
+    {
+      "epoch": 0.49715678310316813,
+      "grad_norm": 0.9676505327224731,
+      "learning_rate": 2.4984210526315788e-05,
+      "loss": 1.9742,
+      "step": 153
+    },
+    {
+      "epoch": 0.5004061738424046,
+      "grad_norm": 1.1361451148986816,
+      "learning_rate": 2.445263157894737e-05,
+      "loss": 2.1574,
+      "step": 154
+    },
+    {
+      "epoch": 0.503655564581641,
+      "grad_norm": 1.4020987749099731,
+      "learning_rate": 2.3921052631578946e-05,
+      "loss": 2.2212,
+      "step": 155
+    },
+    {
+      "epoch": 0.5069049553208773,
+      "grad_norm": 2.2447288036346436,
+      "learning_rate": 2.3389473684210528e-05,
+      "loss": 2.2826,
+      "step": 156
+    },
+    {
+      "epoch": 0.5101543460601138,
+      "grad_norm": 1.6583353281021118,
+      "learning_rate": 2.2857894736842106e-05,
+      "loss": 1.4546,
+      "step": 157
+    },
+    {
+      "epoch": 0.5134037367993501,
+      "grad_norm": 0.8053531050682068,
+      "learning_rate": 2.2326315789473685e-05,
+      "loss": 1.7827,
+      "step": 158
+    },
+    {
+      "epoch": 0.5166531275385865,
+      "grad_norm": 0.9444765448570251,
+      "learning_rate": 2.1794736842105264e-05,
+      "loss": 1.949,
+      "step": 159
+    },
+    {
+      "epoch": 0.5199025182778229,
+      "grad_norm": 1.0987521409988403,
+      "learning_rate": 2.1263157894736842e-05,
+      "loss": 2.0987,
+      "step": 160
+    },
+    {
+      "epoch": 0.5231519090170593,
+      "grad_norm": 1.3520469665527344,
+      "learning_rate": 2.073157894736842e-05,
+      "loss": 2.1702,
+      "step": 161
+    },
+    {
+      "epoch": 0.5264012997562957,
+      "grad_norm": 1.977528691291809,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 2.3078,
+      "step": 162
+    },
+    {
+      "epoch": 0.529650690495532,
+      "grad_norm": 2.550848960876465,
+      "learning_rate": 1.966842105263158e-05,
+      "loss": 1.679,
+      "step": 163
+    },
+    {
+      "epoch": 0.5329000812347685,
+      "grad_norm": 0.8038365244865417,
+      "learning_rate": 1.913684210526316e-05,
+      "loss": 1.7397,
+      "step": 164
+    },
+    {
+      "epoch": 0.5361494719740049,
+      "grad_norm": 0.9397936463356018,
+      "learning_rate": 1.8605263157894736e-05,
+      "loss": 1.9464,
+      "step": 165
+    },
+    {
+      "epoch": 0.5393988627132412,
+      "grad_norm": 1.1106864213943481,
+      "learning_rate": 1.8073684210526318e-05,
+      "loss": 2.1317,
+      "step": 166
+    },
+    {
+      "epoch": 0.5426482534524777,
+      "grad_norm": 1.3086658716201782,
+      "learning_rate": 1.7542105263157897e-05,
+      "loss": 2.1368,
+      "step": 167
+    },
+    {
+      "epoch": 0.545897644191714,
+      "grad_norm": 1.788801670074463,
+      "learning_rate": 1.7010526315789475e-05,
+      "loss": 2.3036,
+      "step": 168
+    },
+    {
+      "epoch": 0.5491470349309504,
+      "grad_norm": 2.4834604263305664,
+      "learning_rate": 1.6478947368421054e-05,
+      "loss": 1.8618,
+      "step": 169
+    },
+    {
+      "epoch": 0.5523964256701869,
+      "grad_norm": 0.7303159236907959,
+      "learning_rate": 1.5947368421052633e-05,
+      "loss": 1.5978,
+      "step": 170
+    },
+    {
+      "epoch": 0.5556458164094232,
+      "grad_norm": 0.8802539110183716,
+      "learning_rate": 1.541578947368421e-05,
+      "loss": 1.8807,
+      "step": 171
+    },
+    {
+      "epoch": 0.5588952071486596,
+      "grad_norm": 1.0369060039520264,
+      "learning_rate": 1.4884210526315788e-05,
+      "loss": 2.047,
+      "step": 172
+    },
+    {
+      "epoch": 0.5621445978878961,
+      "grad_norm": 1.2004215717315674,
+      "learning_rate": 1.4352631578947369e-05,
+      "loss": 2.1124,
+      "step": 173
+    },
+    {
+      "epoch": 0.5653939886271324,
+      "grad_norm": 1.6219362020492554,
+      "learning_rate": 1.3821052631578949e-05,
+      "loss": 2.2972,
+      "step": 174
+    },
+    {
+      "epoch": 0.5686433793663688,
+      "grad_norm": 2.9119997024536133,
+      "learning_rate": 1.3289473684210526e-05,
+      "loss": 2.1111,
+      "step": 175
+    },
+    {
+      "epoch": 0.5718927701056052,
+      "grad_norm": 0.6864357590675354,
+      "learning_rate": 1.2757894736842106e-05,
+      "loss": 1.5427,
+      "step": 176
+    },
+    {
+      "epoch": 0.5751421608448416,
+      "grad_norm": 0.8761265277862549,
+      "learning_rate": 1.2226315789473685e-05,
+      "loss": 1.9088,
+      "step": 177
+    },
+    {
+      "epoch": 0.578391551584078,
+      "grad_norm": 1.000681757926941,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 2.0116,
+      "step": 178
+    },
+    {
+      "epoch": 0.5816409423233144,
+      "grad_norm": 1.1264008283615112,
+      "learning_rate": 1.1163157894736842e-05,
+      "loss": 2.1357,
+      "step": 179
+    },
+    {
+      "epoch": 0.5848903330625508,
+      "grad_norm": 1.4033488035202026,
+      "learning_rate": 1.0631578947368421e-05,
+      "loss": 2.1847,
+      "step": 180
+    },
+    {
+      "epoch": 0.5881397238017871,
+      "grad_norm": 2.3456692695617676,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 2.2616,
+      "step": 181
+    },
+    {
+      "epoch": 0.5913891145410236,
+      "grad_norm": 1.9166276454925537,
+      "learning_rate": 9.56842105263158e-06,
+      "loss": 1.45,
+      "step": 182
+    },
+    {
+      "epoch": 0.59463850528026,
+      "grad_norm": 0.8226500153541565,
+      "learning_rate": 9.036842105263159e-06,
+      "loss": 1.8469,
+      "step": 183
+    },
+    {
+      "epoch": 0.5978878960194963,
+      "grad_norm": 0.9651978611946106,
+      "learning_rate": 8.505263157894738e-06,
+      "loss": 1.9721,
+      "step": 184
+    },
+    {
+      "epoch": 0.6011372867587328,
+      "grad_norm": 1.1123151779174805,
+      "learning_rate": 7.973684210526316e-06,
+      "loss": 2.1579,
+      "step": 185
+    },
+    {
+      "epoch": 0.6043866774979691,
+      "grad_norm": 1.3884251117706299,
+      "learning_rate": 7.442105263157894e-06,
+      "loss": 2.2652,
+      "step": 186
+    },
+    {
+      "epoch": 0.6076360682372055,
+      "grad_norm": 2.057554244995117,
+      "learning_rate": 6.9105263157894745e-06,
+      "loss": 2.3265,
+      "step": 187
+    },
+    {
+      "epoch": 0.6108854589764419,
+      "grad_norm": 2.2101337909698486,
+      "learning_rate": 6.378947368421053e-06,
+      "loss": 1.4899,
+      "step": 188
+    },
+    {
+      "epoch": 0.6141348497156783,
+      "grad_norm": 0.7804029583930969,
+      "learning_rate": 5.847368421052632e-06,
+      "loss": 1.739,
+      "step": 189
+    },
+    {
+      "epoch": 0.6173842404549147,
+      "grad_norm": 0.9255872964859009,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 1.9584,
+      "step": 190
+    },
+    {
+      "epoch": 0.620633631194151,
+      "grad_norm": 1.0721971988677979,
+      "learning_rate": 4.78421052631579e-06,
+      "loss": 2.0831,
+      "step": 191
+    },
+    {
+      "epoch": 0.6238830219333875,
+      "grad_norm": 1.3093819618225098,
+      "learning_rate": 4.252631578947369e-06,
+      "loss": 2.2101,
+      "step": 192
+    },
+    {
+      "epoch": 0.6271324126726239,
+      "grad_norm": 1.7907172441482544,
+      "learning_rate": 3.721052631578947e-06,
+      "loss": 2.3666,
+      "step": 193
+    },
+    {
+      "epoch": 0.6303818034118602,
+      "grad_norm": 2.6148416996002197,
+      "learning_rate": 3.1894736842105266e-06,
+      "loss": 1.8086,
+      "step": 194
+    },
+    {
+      "epoch": 0.6336311941510967,
+      "grad_norm": 0.736183226108551,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 1.6694,
+      "step": 195
+    },
+    {
+      "epoch": 0.6368805848903331,
+      "grad_norm": 0.9078429341316223,
+      "learning_rate": 2.1263157894736844e-06,
+      "loss": 1.9222,
+      "step": 196
+    },
+    {
+      "epoch": 0.6401299756295694,
+      "grad_norm": 1.0417286157608032,
+      "learning_rate": 1.5947368421052633e-06,
+      "loss": 2.0774,
+      "step": 197
+    },
+    {
+      "epoch": 0.6433793663688059,
+      "grad_norm": 1.198705792427063,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 2.2244,
+      "step": 198
+    },
+    {
+      "epoch": 0.6466287571080422,
+      "grad_norm": 1.611803650856018,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 2.3064,
+      "step": 199
+    },
+    {
+      "epoch": 0.6498781478472786,
+      "grad_norm": 2.893977165222168,
+      "learning_rate": 0.0,
+      "loss": 2.0551,
+      "step": 200
+    },
+    {
+      "epoch": 0.6498781478472786,
+      "eval_loss": 0.4971354603767395,
+      "eval_runtime": 34.2352,
+      "eval_samples_per_second": 121.074,
+      "eval_steps_per_second": 3.797,
+      "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": 1.8349744251669053e+18,
+  "total_flos": 2.446274663685292e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null