Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44dc3fbbe13a71f5b9b2dc1dfdb312c59d3da6c2aadea975e4e891d129fe19ac
+oid sha256:89eb5ed31f068bc725e624783d234176de8048f66689a875c94baaf8827824d1
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a781e6a58c1422569909ae38392e9af98cd2f9f39226137c88c8236db19da2
+oid sha256:e1f96d78be725272a2591e5c297aa5c9d02ffe12ab6f1c4717c4aea99d8b900e
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08bf2b2538bcf5289702f665cdf547aa18a0c25852676d00d65e9fa80ae6c966
+oid sha256:317bf1310bd01646e56bfd3b55b274ccfeeb7ef1eee3cbee4a51268b2b021418
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2585527896881104,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0721370604147881,
+  "best_metric": 2.131821632385254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.10820559062218214,
   "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": 12.446,
       "eval_steps_per_second": 6.276,
       "step": 20
+    },
+    {
+      "epoch": 0.0757439134355275,
+      "grad_norm": 111.02490997314453,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.2688,
+      "step": 21
+    },
+    {
+      "epoch": 0.08656447249774572,
+      "grad_norm": 195.60818481445312,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 8.6093,
+      "step": 24
+    },
+    {
+      "epoch": 0.09017132551848513,
+      "eval_loss": 2.1531364917755127,
+      "eval_runtime": 9.4091,
+      "eval_samples_per_second": 12.435,
+      "eval_steps_per_second": 6.271,
+      "step": 25
+    },
+    {
+      "epoch": 0.09738503155996393,
+      "grad_norm": 3.565056800842285,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 8.3193,
+      "step": 27
+    },
+    {
+      "epoch": 0.10820559062218214,
+      "grad_norm": 22.954635620117188,
+      "learning_rate": 0.0,
+      "loss": 8.2484,
+      "step": 30
+    },
+    {
+      "epoch": 0.10820559062218214,
+      "eval_loss": 2.131821632385254,
+      "eval_runtime": 9.4155,
+      "eval_samples_per_second": 12.426,
+      "eval_steps_per_second": 6.266,
+      "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": 489185718829056.0,
+  "total_flos": 750843196342272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null