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:b1c2dff47746eb27372f0cfaf92b07ddf77235b5dea5d4b584cdfbd6a0e68ebd
+oid sha256:35aa84d2c65b5a8ae37918b0e81ec3ed13569ed7ad64ba4dfa6a283d90a4f9c7
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0e06d084433df0cf5823e8911c494cf45d9da1f3bdf5d1dc1a8f1d4ec31be5
+oid sha256:66f926f8d8475f5832c399ee0de66127482c07a8f0f362c080dd7127abaa8348
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4f7f46ce9f2a991d9a947996a834f2a3d46d64a84535948c375ff36bf095f2
+oid sha256:e0a7373dd0da620e7783f9f8ce3e7af30a929105599f24bab69465f69336deaa
 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": 0.8632563352584839,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "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": 6.622,
       "eval_steps_per_second": 1.673,
       "step": 150
+    },
+    {
+      "epoch": 2.6814159292035398,
+      "grad_norm": 1.3277695178985596,
+      "learning_rate": 3.4392532620598216e-06,
+      "loss": 0.33,
+      "step": 151
+    },
+    {
+      "epoch": 2.6991150442477876,
+      "grad_norm": 1.3910033702850342,
+      "learning_rate": 3.0904332038757977e-06,
+      "loss": 0.3814,
+      "step": 152
+    },
+    {
+      "epoch": 2.7168141592920354,
+      "grad_norm": 1.2756978273391724,
+      "learning_rate": 2.759697676656098e-06,
+      "loss": 0.2763,
+      "step": 153
+    },
+    {
+      "epoch": 2.734513274336283,
+      "grad_norm": 1.615118145942688,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.5316,
+      "step": 154
+    },
+    {
+      "epoch": 2.752212389380531,
+      "grad_norm": 1.4810477495193481,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 0.4607,
+      "step": 155
+    },
+    {
+      "epoch": 2.769911504424779,
+      "grad_norm": 1.2083476781845093,
+      "learning_rate": 1.8772381773176417e-06,
+      "loss": 0.3965,
+      "step": 156
+    },
+    {
+      "epoch": 2.7876106194690267,
+      "grad_norm": 1.4224122762680054,
+      "learning_rate": 1.620045381987012e-06,
+      "loss": 0.4466,
+      "step": 157
+    },
+    {
+      "epoch": 2.8053097345132745,
+      "grad_norm": 1.1904553174972534,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.3303,
+      "step": 158
+    },
+    {
+      "epoch": 2.823008849557522,
+      "grad_norm": 1.8643724918365479,
+      "learning_rate": 1.1617059339563807e-06,
+      "loss": 0.2957,
+      "step": 159
+    },
+    {
+      "epoch": 2.84070796460177,
+      "grad_norm": 1.446276307106018,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3413,
+      "step": 160
+    },
+    {
+      "epoch": 2.8584070796460175,
+      "grad_norm": 1.2475237846374512,
+      "learning_rate": 7.786715955054203e-07,
+      "loss": 0.2997,
+      "step": 161
+    },
+    {
+      "epoch": 2.8761061946902657,
+      "grad_norm": 1.1617192029953003,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.288,
+      "step": 162
+    },
+    {
+      "epoch": 2.893805309734513,
+      "grad_norm": 1.2316638231277466,
+      "learning_rate": 4.715329778211375e-07,
+      "loss": 0.3284,
+      "step": 163
+    },
+    {
+      "epoch": 2.911504424778761,
+      "grad_norm": 1.2865647077560425,
+      "learning_rate": 3.465771522536854e-07,
+      "loss": 0.3033,
+      "step": 164
+    },
+    {
+      "epoch": 2.9292035398230087,
+      "grad_norm": 1.2015645503997803,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 0.2449,
+      "step": 165
+    },
+    {
+      "epoch": 2.9469026548672566,
+      "grad_norm": 1.321933627128601,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.4011,
+      "step": 166
+    },
+    {
+      "epoch": 2.9646017699115044,
+      "grad_norm": 1.2619785070419312,
+      "learning_rate": 8.671949076420882e-08,
+      "loss": 0.3557,
+      "step": 167
+    },
+    {
+      "epoch": 2.982300884955752,
+      "grad_norm": 1.5023789405822754,
+      "learning_rate": 3.8548187963854956e-08,
+      "loss": 0.4547,
+      "step": 168
+    },
+    {
+      "epoch": 3.004424778761062,
+      "grad_norm": 4.348768711090088,
+      "learning_rate": 9.637975896759077e-09,
+      "loss": 0.6441,
+      "step": 169
+    },
+    {
+      "epoch": 3.02212389380531,
+      "grad_norm": 1.0477544069290161,
+      "learning_rate": 0.0,
+      "loss": 0.2443,
+      "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": 2.018651406336e+17,
+  "total_flos": 2.2878049271808e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null