Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da54134d203dece3743a02238bf6fdce05f28508e3415ef44b2496106d8727f
+oid sha256:74db9026662325ab6047183a93102db0c360ab67821ea89e24d4488e48a557cc
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9efbfc5a18c171c1347ec7e409d1f80fb651bb029486280dddca773fda8e536c
+oid sha256:e153a32b62eaf4c95d28982df681303dbc6641b64d0f7aaf1683b128fc36d04d
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8f49ae7d1b0c7244ec5f9891b6336e8dd63d15c3a7223d7539af234aae23c3
+oid sha256:d5cc3a753cc51f866553dfadf2b52490dcd473af43bb8799d39fb22f4aadbcef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88004fe81ddcc4e2df673ef2a68c651d0c3f66e5c526887263eba26939791c56
+oid sha256:d9596e684890f5bf48408b636f8dc50022bd084571bd5fe14d342b2e016d043c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2263110727071762,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.663716814159292,
+  "epoch": 3.02212389380531,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,146 @@
       "eval_samples_per_second": 10.6,
       "eval_steps_per_second": 2.678,
       "step": 150
+    },
+    {
+      "epoch": 2.6814159292035398,
+      "grad_norm": 7.257627964019775,
+      "learning_rate": 3.4392532620598216e-06,
+      "loss": 0.2907,
+      "step": 151
+    },
+    {
+      "epoch": 2.6991150442477876,
+      "grad_norm": 2.6858301162719727,
+      "learning_rate": 3.0904332038757977e-06,
+      "loss": 0.2093,
+      "step": 152
+    },
+    {
+      "epoch": 2.7168141592920354,
+      "grad_norm": 4.403625965118408,
+      "learning_rate": 2.759697676656098e-06,
+      "loss": 0.2625,
+      "step": 153
+    },
+    {
+      "epoch": 2.734513274336283,
+      "grad_norm": 5.445953845977783,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.2808,
+      "step": 154
+    },
+    {
+      "epoch": 2.752212389380531,
+      "grad_norm": 3.8295862674713135,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 0.2573,
+      "step": 155
+    },
+    {
+      "epoch": 2.769911504424779,
+      "grad_norm": 2.5319910049438477,
+      "learning_rate": 1.8772381773176417e-06,
+      "loss": 0.1505,
+      "step": 156
+    },
+    {
+      "epoch": 2.7876106194690267,
+      "grad_norm": 2.632370710372925,
+      "learning_rate": 1.620045381987012e-06,
+      "loss": 0.1901,
+      "step": 157
+    },
+    {
+      "epoch": 2.8053097345132745,
+      "grad_norm": 4.662055969238281,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.2873,
+      "step": 158
+    },
+    {
+      "epoch": 2.823008849557522,
+      "grad_norm": 2.293377161026001,
+      "learning_rate": 1.1617059339563807e-06,
+      "loss": 0.1484,
+      "step": 159
+    },
+    {
+      "epoch": 2.84070796460177,
+      "grad_norm": 2.53718638420105,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1503,
+      "step": 160
+    },
+    {
+      "epoch": 2.8584070796460175,
+      "grad_norm": 2.226994752883911,
+      "learning_rate": 7.786715955054203e-07,
+      "loss": 0.1639,
+      "step": 161
+    },
+    {
+      "epoch": 2.8761061946902657,
+      "grad_norm": 2.434995174407959,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.1509,
+      "step": 162
+    },
+    {
+      "epoch": 2.893805309734513,
+      "grad_norm": 2.5986759662628174,
+      "learning_rate": 4.715329778211375e-07,
+      "loss": 0.1388,
+      "step": 163
+    },
+    {
+      "epoch": 2.911504424778761,
+      "grad_norm": 3.339171886444092,
+      "learning_rate": 3.465771522536854e-07,
+      "loss": 0.1941,
+      "step": 164
+    },
+    {
+      "epoch": 2.9292035398230087,
+      "grad_norm": 3.910398006439209,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 0.2387,
+      "step": 165
+    },
+    {
+      "epoch": 2.9469026548672566,
+      "grad_norm": 2.9578335285186768,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.234,
+      "step": 166
+    },
+    {
+      "epoch": 2.9646017699115044,
+      "grad_norm": 3.8173089027404785,
+      "learning_rate": 8.671949076420882e-08,
+      "loss": 0.2285,
+      "step": 167
+    },
+    {
+      "epoch": 2.982300884955752,
+      "grad_norm": 4.536461353302002,
+      "learning_rate": 3.8548187963854956e-08,
+      "loss": 0.2497,
+      "step": 168
+    },
+    {
+      "epoch": 3.004424778761062,
+      "grad_norm": 4.463059425354004,
+      "learning_rate": 9.637975896759077e-09,
+      "loss": 0.2892,
+      "step": 169
+    },
+    {
+      "epoch": 3.02212389380531,
+      "grad_norm": 2.0114989280700684,
+      "learning_rate": 0.0,
+      "loss": 0.1349,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1252,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.146497013481472e+17,
+  "total_flos": 2.4326966152790016e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null