Training in progress, step 157, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93517d21005be70e4c463b84e7c3e68f8c431eadd1fd10f1058fcc8d328f0fa5
+oid sha256:3e2d80b5d823d2dc0ebdf73013d3b820099340016252b1aa3b10a0b26493ac29
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d6c512d08cdfcc30f40caab3dc36006165eca1e237c4d6b8f2251cd5911b1f
+oid sha256:ae9bf77404e07ee51417901d6a1891e53c485d071f9bc130f6ab554024c31e2c
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330e5faaa3878010c9991fb905084cef46b2217cbfd5607ef9941420efefa448
+oid sha256:29c17b845947663e36e75f4014f2755820f175b35a3e2153b686f615add3cbb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c535b91583e044007e2d58e4865f12783f75470fac48c23be105e95a5f5108d
+oid sha256:18505744b03e7ab4ba61d1f55cc890333469ed381578a48998b1f2f7f10aa7ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.294066429138184,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.8708133971291865,
+  "epoch": 3.0047846889952154,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 157,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,55 @@
       "eval_samples_per_second": 428.249,
       "eval_steps_per_second": 107.062,
       "step": 150
+    },
+    {
+      "epoch": 2.889952153110048,
+      "grad_norm": 0.11171100288629532,
+      "learning_rate": 4.104993088376974e-07,
+      "loss": 10.2872,
+      "step": 151
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.0931149572134018,
+      "learning_rate": 2.851883682973233e-07,
+      "loss": 10.2623,
+      "step": 152
+    },
+    {
+      "epoch": 2.92822966507177,
+      "grad_norm": 0.09574086219072342,
+      "learning_rate": 1.8258309893965375e-07,
+      "loss": 10.4194,
+      "step": 153
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.1195647194981575,
+      "learning_rate": 1.0273036248318324e-07,
+      "loss": 10.1691,
+      "step": 154
+    },
+    {
+      "epoch": 2.9665071770334928,
+      "grad_norm": 0.1469721496105194,
+      "learning_rate": 4.566662914508579e-08,
+      "loss": 10.379,
+      "step": 155
+    },
+    {
+      "epoch": 2.985645933014354,
+      "grad_norm": 0.1375855803489685,
+      "learning_rate": 1.1417960984605458e-08,
+      "loss": 10.6679,
+      "step": 156
+    },
+    {
+      "epoch": 3.0047846889952154,
+      "grad_norm": 0.17474159598350525,
+      "learning_rate": 0.0,
+      "loss": 18.0126,
+      "step": 157
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1161,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 16732599091200.0,
+  "total_flos": 17513453715456.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null