Training in progress, step 169, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc0033e7ed9e9f3c87a4cab42a9ee85e479936ff0f23f1ac27e4617bb606d679
+oid sha256:9281616733c882764c606bb7b1b53e1a36649ff5d169eb26f6ae38a63771cfa6
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec47d103af5bbc661ffdf0a81d105e608db8913372cc21daab8047d360ec6c00
+oid sha256:9fdeea9d8580ad2b65f136213a35ea6a409825d78ea61688f7dfa1f0ade87ad5
 size 159641092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473932356fbc514d613e8f16239146240be6ba1a2e795d5ef42cc52bb2517c10
+oid sha256:44dfc825fd884465811bf40f6405494044a8fc0c1881f38b28a1153fa4c4cae0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6147e9f76e26f4103407c773313a9a6a0e0cd5a4bb067ee04e892a28437c5001
+oid sha256:7d87009f3cc1770dc6c0f8ea9809e51a1ce242970478e0b9070b4eeaa0a149ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03540904074907303,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.663716814159292,
+  "epoch": 3.004424778761062,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 169,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,139 @@
       "eval_samples_per_second": 7.024,
       "eval_steps_per_second": 1.774,
       "step": 150
+    },
+    {
+      "epoch": 2.6814159292035398,
+      "grad_norm": 0.2015472650527954,
+      "learning_rate": 3.441918637623351e-06,
+      "loss": 0.0061,
+      "step": 151
+    },
+    {
+      "epoch": 2.6991150442477876,
+      "grad_norm": 0.18059758841991425,
+      "learning_rate": 3.073611222760698e-06,
+      "loss": 0.0066,
+      "step": 152
+    },
+    {
+      "epoch": 2.7168141592920354,
+      "grad_norm": 0.22959595918655396,
+      "learning_rate": 2.7255750092938926e-06,
+      "loss": 0.0067,
+      "step": 153
+    },
+    {
+      "epoch": 2.734513274336283,
+      "grad_norm": 0.3204856514930725,
+      "learning_rate": 2.3979458647912667e-06,
+      "loss": 0.0031,
+      "step": 154
+    },
+    {
+      "epoch": 2.752212389380531,
+      "grad_norm": 0.7649920582771301,
+      "learning_rate": 2.0908516902397413e-06,
+      "loss": 0.0231,
+      "step": 155
+    },
+    {
+      "epoch": 2.769911504424779,
+      "grad_norm": 0.22219803929328918,
+      "learning_rate": 1.8044123701143611e-06,
+      "loss": 0.0115,
+      "step": 156
+    },
+    {
+      "epoch": 2.7876106194690267,
+      "grad_norm": 0.24046052992343903,
+      "learning_rate": 1.5387397255774088e-06,
+      "loss": 0.0082,
+      "step": 157
+    },
+    {
+      "epoch": 2.8053097345132745,
+      "grad_norm": 0.15456032752990723,
+      "learning_rate": 1.2939374708252589e-06,
+      "loss": 0.0053,
+      "step": 158
+    },
+    {
+      "epoch": 2.823008849557522,
+      "grad_norm": 0.17919683456420898,
+      "learning_rate": 1.0701011726000832e-06,
+      "loss": 0.0049,
+      "step": 159
+    },
+    {
+      "epoch": 2.84070796460177,
+      "grad_norm": 0.30687618255615234,
+      "learning_rate": 8.673182128821744e-07,
+      "loss": 0.0105,
+      "step": 160
+    },
+    {
+      "epoch": 2.8584070796460175,
+      "grad_norm": 0.18591438233852386,
+      "learning_rate": 6.856677547774926e-07,
+      "loss": 0.0054,
+      "step": 161
+    },
+    {
+      "epoch": 2.8761061946902657,
+      "grad_norm": 0.38478103280067444,
+      "learning_rate": 5.252207116136426e-07,
+      "loss": 0.007,
+      "step": 162
+    },
+    {
+      "epoch": 2.893805309734513,
+      "grad_norm": 0.2328488826751709,
+      "learning_rate": 3.860397192565696e-07,
+      "loss": 0.0082,
+      "step": 163
+    },
+    {
+      "epoch": 2.911504424778761,
+      "grad_norm": 0.13028258085250854,
+      "learning_rate": 2.681791116584731e-07,
+      "loss": 0.0028,
+      "step": 164
+    },
+    {
+      "epoch": 2.9292035398230087,
+      "grad_norm": 0.16649429500102997,
+      "learning_rate": 1.7168489964679735e-07,
+      "loss": 0.0048,
+      "step": 165
+    },
+    {
+      "epoch": 2.9469026548672566,
+      "grad_norm": 0.15426984429359436,
+      "learning_rate": 9.659475296232567e-08,
+      "loss": 0.0045,
+      "step": 166
+    },
+    {
+      "epoch": 2.9646017699115044,
+      "grad_norm": 0.13245390355587006,
+      "learning_rate": 4.2937985553548884e-08,
+      "loss": 0.0041,
+      "step": 167
+    },
+    {
+      "epoch": 2.982300884955752,
+      "grad_norm": 0.1312681883573532,
+      "learning_rate": 1.0735544133004261e-08,
+      "loss": 0.0034,
+      "step": 168
+    },
+    {
+      "epoch": 3.004424778761062,
+      "grad_norm": 0.3671550452709198,
+      "learning_rate": 0.0,
+      "loss": 0.0091,
+      "step": 169
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1245,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.07616338231296e+16,
+  "total_flos": 6.845810744072602e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null