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:ae7dc84329ebc64fba08ac0aa481e6719b283d96897e704ed634c8fbeecad5c2
+oid sha256:86059f0649f3b8bc848259bf7055cf8acb8c0b5cae22003b44159c6caabeeeeb
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdbfad0b0db14e162b330df6af00770a64daa5e2f6bcafc23e4b3a887a6583ac
+oid sha256:275f47e65e05c43899acb7aced0c9036fd5136452cfabf245620d55d4aa99fba
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e49fbb104ba2ba53b0e3999d9c7107cec1afec9c6fa9908017da03654a5c6e6a
+oid sha256:a34dab0366d6df4bd4c0671ec4920b7cbf242752341e00902f490b726983b4e3
 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": 1.7960519790649414,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07149240393208221,
+  "best_metric": 1.7647408246994019,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.10723860589812333,
   "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": 7.801,
       "eval_steps_per_second": 1.95,
       "step": 20
+    },
+    {
+      "epoch": 0.07506702412868632,
+      "grad_norm": 7.885202407836914,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.0055,
+      "step": 21
+    },
+    {
+      "epoch": 0.08579088471849866,
+      "grad_norm": 6.037095069885254,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.7882,
+      "step": 24
+    },
+    {
+      "epoch": 0.08936550491510277,
+      "eval_loss": 1.770914912223816,
+      "eval_runtime": 30.9115,
+      "eval_samples_per_second": 7.635,
+      "eval_steps_per_second": 1.909,
+      "step": 25
+    },
+    {
+      "epoch": 0.09651474530831099,
+      "grad_norm": 5.651801109313965,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.0168,
+      "step": 27
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "grad_norm": 4.951616287231445,
+      "learning_rate": 0.0,
+      "loss": 6.2873,
+      "step": 30
+    },
+    {
+      "epoch": 0.10723860589812333,
+      "eval_loss": 1.7647408246994019,
+      "eval_runtime": 30.3902,
+      "eval_samples_per_second": 7.766,
+      "eval_steps_per_second": 1.941,
+      "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": 1.227781774848e+16,
+  "total_flos": 1.8055614336e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null