Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525eea3f2c93217aef6f42d2b143a65e63d7ab0ec67ae2667a54acc1c89b2a45
+oid sha256:5b4dcb2706bab7a28b96ef55d0d42911d7edbba511570f431a40b2cceb989805
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a119d6761d4a53c7777ebe6af48109b36c740bc207a47858a068048ae26b4643
+oid sha256:2bbe3c276dcd52c80215bd55f5c295d7263190d91cd59664f0aa38115bf2e678
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f8c1634877b7d4e3c74a0e50d2917fe957a0d933a5540aa6509d62f047bd85
+oid sha256:105471c0e963247bb5a376815822bac2cc6125692c7954ca52a2f8dcca22d474
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.277400493621826,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.0010789697996353082,
+  "best_metric": 3.1820225715637207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0014386263995137443,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 2.892,
       "eval_steps_per_second": 1.446,
       "step": 75
+    },
+    {
+      "epoch": 0.0010933560636304457,
+      "grad_norm": 5.396302223205566,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 2.4818,
+      "step": 76
+    },
+    {
+      "epoch": 0.001107742327625583,
+      "grad_norm": 4.9067301750183105,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 2.6765,
+      "step": 77
+    },
+    {
+      "epoch": 0.0011221285916207205,
+      "grad_norm": 5.162796497344971,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 2.6254,
+      "step": 78
+    },
+    {
+      "epoch": 0.001136514855615858,
+      "grad_norm": 5.922882556915283,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 3.3523,
+      "step": 79
+    },
+    {
+      "epoch": 0.0011509011196109953,
+      "grad_norm": 5.30287504196167,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 3.2716,
+      "step": 80
+    },
+    {
+      "epoch": 0.0011652873836061328,
+      "grad_norm": 5.643162250518799,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.5917,
+      "step": 81
+    },
+    {
+      "epoch": 0.0011796736476012704,
+      "grad_norm": 9.638242721557617,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 3.8924,
+      "step": 82
+    },
+    {
+      "epoch": 0.0011940599115964077,
+      "grad_norm": 7.516237735748291,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 3.5587,
+      "step": 83
+    },
+    {
+      "epoch": 0.0012084461755915452,
+      "grad_norm": 7.148532867431641,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 2.6055,
+      "step": 84
+    },
+    {
+      "epoch": 0.0012228324395866827,
+      "grad_norm": 6.535606384277344,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 2.5346,
+      "step": 85
+    },
+    {
+      "epoch": 0.00123721870358182,
+      "grad_norm": 7.571803569793701,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 2.7083,
+      "step": 86
+    },
+    {
+      "epoch": 0.0012516049675769575,
+      "grad_norm": 7.3511881828308105,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 3.5115,
+      "step": 87
+    },
+    {
+      "epoch": 0.001265991231572095,
+      "grad_norm": 6.102956771850586,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 3.0957,
+      "step": 88
+    },
+    {
+      "epoch": 0.0012803774955672325,
+      "grad_norm": 7.065240859985352,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 2.9476,
+      "step": 89
+    },
+    {
+      "epoch": 0.0012947637595623698,
+      "grad_norm": 10.024836540222168,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 4.0562,
+      "step": 90
+    },
+    {
+      "epoch": 0.0013091500235575073,
+      "grad_norm": 6.252835750579834,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 3.0513,
+      "step": 91
+    },
+    {
+      "epoch": 0.0013235362875526448,
+      "grad_norm": 8.234208106994629,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 3.3823,
+      "step": 92
+    },
+    {
+      "epoch": 0.0013379225515477821,
+      "grad_norm": 8.580864906311035,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 3.2553,
+      "step": 93
+    },
+    {
+      "epoch": 0.0013523088155429196,
+      "grad_norm": 9.852059364318848,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 4.1037,
+      "step": 94
+    },
+    {
+      "epoch": 0.0013666950795380571,
+      "grad_norm": 15.760644912719727,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 2.7196,
+      "step": 95
+    },
+    {
+      "epoch": 0.0013810813435331944,
+      "grad_norm": 8.547517776489258,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 3.8778,
+      "step": 96
+    },
+    {
+      "epoch": 0.001395467607528332,
+      "grad_norm": 9.558707237243652,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 3.362,
+      "step": 97
+    },
+    {
+      "epoch": 0.0014098538715234695,
+      "grad_norm": 6.9549455642700195,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 2.8635,
+      "step": 98
+    },
+    {
+      "epoch": 0.0014242401355186068,
+      "grad_norm": 11.047368049621582,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 3.9017,
+      "step": 99
+    },
+    {
+      "epoch": 0.0014386263995137443,
+      "grad_norm": 10.734683990478516,
+      "learning_rate": 0.0,
+      "loss": 3.2839,
+      "step": 100
+    },
+    {
+      "epoch": 0.0014386263995137443,
+      "eval_loss": 3.1820225715637207,
+      "eval_runtime": 10123.1923,
+      "eval_samples_per_second": 2.891,
+      "eval_steps_per_second": 1.446,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.052684203327488e+17,
+  "total_flos": 1.403578937769984e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null