Training in progress, step 161, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf54f14b533ce25d582ebc87923c3c750c6835b7083a549f225c3cffd228604
+oid sha256:2267a83d32a0f01d30923eeed6c884962b2f437b656b6249999fc429308c3dd5
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab66d502b5f8c2dc2ceb8ca53c17a074f1572f2650ed0e15984091aad6ea18c
+oid sha256:5fb34ade9628a496d6c957ac6c86838398fb54323d091af3a2be98780466dc57
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c41a6a22c8d7bbe44b37cc084e6e293948fa0399c9dee6cb51f3061351eefb
+oid sha256:639b9048e564ee3bfbba8e4d7783ec4589b5f1c852988b29842fc930d46c52bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77fecceef02880a4146c504aef986e50a2aa79b7ebef5c03c12015958eb0af66
+oid sha256:60772f64231e90f8ab464fc52a2e99407881e390f96f20fa87b685c94fc274b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.854687690734863,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.803738317757009,
+  "epoch": 3.0093457943925235,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 161,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,83 @@
       "eval_samples_per_second": 711.858,
       "eval_steps_per_second": 181.919,
       "step": 150
+    },
+    {
+      "epoch": 2.822429906542056,
+      "grad_norm": 0.27185508608818054,
+      "learning_rate": 1.0782481637284013e-06,
+      "loss": 6.842,
+      "step": 151
+    },
+    {
+      "epoch": 2.8411214953271027,
+      "grad_norm": 0.34425657987594604,
+      "learning_rate": 8.739801888871469e-07,
+      "loss": 6.8271,
+      "step": 152
+    },
+    {
+      "epoch": 2.8598130841121496,
+      "grad_norm": 0.30129221081733704,
+      "learning_rate": 6.909760573925561e-07,
+      "loss": 6.8476,
+      "step": 153
+    },
+    {
+      "epoch": 2.878504672897196,
+      "grad_norm": 0.19908937811851501,
+      "learning_rate": 5.29314981262985e-07,
+      "loss": 6.8637,
+      "step": 154
+    },
+    {
+      "epoch": 2.897196261682243,
+      "grad_norm": 0.183157280087471,
+      "learning_rate": 3.8906693432924634e-07,
+      "loss": 6.8853,
+      "step": 155
+    },
+    {
+      "epoch": 2.9158878504672896,
+      "grad_norm": 0.17316141724586487,
+      "learning_rate": 2.702926219468882e-07,
+      "loss": 6.8954,
+      "step": 156
+    },
+    {
+      "epoch": 2.9345794392523366,
+      "grad_norm": 0.18594498932361603,
+      "learning_rate": 1.7304345472035631e-07,
+      "loss": 6.8887,
+      "step": 157
+    },
+    {
+      "epoch": 2.953271028037383,
+      "grad_norm": 0.16382110118865967,
+      "learning_rate": 9.73615262502503e-08,
+      "loss": 6.8816,
+      "step": 158
+    },
+    {
+      "epoch": 2.97196261682243,
+      "grad_norm": 0.2256663292646408,
+      "learning_rate": 4.3279594913447905e-08,
+      "loss": 6.8817,
+      "step": 159
+    },
+    {
+      "epoch": 2.9906542056074765,
+      "grad_norm": 0.2136058360338211,
+      "learning_rate": 1.082106968385288e-08,
+      "loss": 6.8499,
+      "step": 160
+    },
+    {
+      "epoch": 3.0093457943925235,
+      "grad_norm": 0.29850977659225464,
+      "learning_rate": 0.0,
+      "loss": 10.9924,
+      "step": 161
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1189,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2880981295104.0,
+  "total_flos": 3091228053504.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null