Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae4b6dca450b054be9de0dc97d3e5454d618b1444b3549e97c7c9d5f3224851
+oid sha256:8ad157a729c8103a1c945f03a5d17a8b6aed148db9b5a33c9bfc06011cc6dcef
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4c88504c7d60a03f993e7d3e042134a3faac7f1837367d2df62fe4a89bd853
+oid sha256:733bb37a4d0fa3e2d803c690c458282be75475ca8c3d8d16941ce5b0437dd14f
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98a6b5e5080fcd87c6a71760f39ee427f007e05c9baeb1b6f06079a9b067c8ff
+oid sha256:6256954562b6e49efdca9d22d196476cde069d8d31c9e637b0ef7dd3ca3e1827
 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": 1.4081313610076904,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00260061114361875,
+  "best_metric": 1.397467017173767,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0039009167154281255,
   "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": 23.779,
       "eval_steps_per_second": 5.947,
       "step": 20
+    },
+    {
+      "epoch": 0.002730641700799688,
+      "grad_norm": 0.1603408008813858,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.3965,
+      "step": 21
+    },
+    {
+      "epoch": 0.0031207333723425007,
+      "grad_norm": 0.17872142791748047,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.3831,
+      "step": 24
+    },
+    {
+      "epoch": 0.003250763929523438,
+      "eval_loss": 1.3993861675262451,
+      "eval_runtime": 273.2238,
+      "eval_samples_per_second": 23.706,
+      "eval_steps_per_second": 5.929,
+      "step": 25
+    },
+    {
+      "epoch": 0.003510825043885313,
+      "grad_norm": 0.17172136902809143,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.3969,
+      "step": 27
+    },
+    {
+      "epoch": 0.0039009167154281255,
+      "grad_norm": 0.18617106974124908,
+      "learning_rate": 0.0,
+      "loss": 1.3943,
+      "step": 30
+    },
+    {
+      "epoch": 0.0039009167154281255,
+      "eval_loss": 1.397467017173767,
+      "eval_runtime": 273.6499,
+      "eval_samples_per_second": 23.669,
+      "eval_steps_per_second": 5.92,
+      "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": 2645194394566656.0,
+  "total_flos": 3951463231389696.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null