Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfd49f31e605dec4e34f0f55409b1035e32deb035451a2c6cbe0e9ce20f7857
+oid sha256:9416bdf7c24b193b624601c5346d3dfcfb5452b66940659d8fcd6104603f4713
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5bbd8eaf0ff4f1f51ee239c21031b73da42c2e9ede46c64a17ea92266f843f
+oid sha256:7b4419459c53e2ed095898c9d3176effa420d9f698102c78515a8f92e256c611
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211d7d81e929ad9ef8e16e32063cbebc88efae2e1356f1601b52a62e0452f2ee
+oid sha256:be5db24f9f5608d1b1f118efd534d1b3a17e0299b11c73616675244c532ceaf0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4542734622955322,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05685856432125089,
+  "best_metric": 2.4453086853027344,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.08528784648187633,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 63.592,
       "eval_steps_per_second": 16.059,
       "step": 20
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 0.6524438858032227,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.4109,
+      "step": 21
+    },
+    {
+      "epoch": 0.06823027718550106,
+      "grad_norm": 0.744140088558197,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.4404,
+      "step": 24
+    },
+    {
+      "epoch": 0.07107320540156362,
+      "eval_loss": 2.446140766143799,
+      "eval_runtime": 4.6715,
+      "eval_samples_per_second": 63.577,
+      "eval_steps_per_second": 16.055,
+      "step": 25
+    },
+    {
+      "epoch": 0.0767590618336887,
+      "grad_norm": 0.6780519485473633,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.3144,
+      "step": 27
+    },
+    {
+      "epoch": 0.08528784648187633,
+      "grad_norm": 0.7910773754119873,
+      "learning_rate": 0.0,
+      "loss": 2.5072,
+      "step": 30
+    },
+    {
+      "epoch": 0.08528784648187633,
+      "eval_loss": 2.4453086853027344,
+      "eval_runtime": 4.6682,
+      "eval_samples_per_second": 63.621,
+      "eval_steps_per_second": 16.066,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1935445139128320.0,
+  "total_flos": 2903167708692480.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null