Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591b9763b6c967d86eace01643d81d618683a0c4e10755cc402fbf76fe40a9a8
+oid sha256:ceb17e147a5c0ab0de38cf303a2780f76609913526ad0a33365e8972ab75c668
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f095f992ef0fb5baaf455527579731b5057a14810d9873f540dd0bd326f3c7f
+oid sha256:9ec72efbf28f030ce90f48e2934393765c76e450212764bfc1d10918f37dfddb
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa485e232164a5ba1536876dcd7a5a7513956687c389d75a0c55af3c2b7e026
+oid sha256:a0409d91a296bee4df6209abe19b95c896e2d11912338e862fb29c9ca6ec6fe3
 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": 2.2716472148895264,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003656474244709539,
+  "best_metric": 2.203942060470581,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005484711367064308,
   "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": 16.034,
       "eval_steps_per_second": 4.009,
       "step": 20
+    },
+    {
+      "epoch": 0.0038392979569450156,
+      "grad_norm": 1.3212151527404785,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2734,
+      "step": 21
+    },
+    {
+      "epoch": 0.0043877690936514465,
+      "grad_norm": 1.073264241218567,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.204,
+      "step": 24
+    },
+    {
+      "epoch": 0.004570592805886923,
+      "eval_loss": 2.2155237197875977,
+      "eval_runtime": 287.2747,
+      "eval_samples_per_second": 16.037,
+      "eval_steps_per_second": 4.01,
+      "step": 25
+    },
+    {
+      "epoch": 0.0049362402303578775,
+      "grad_norm": 1.0860651731491089,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.1908,
+      "step": 27
+    },
+    {
+      "epoch": 0.005484711367064308,
+      "grad_norm": 1.1522129774093628,
+      "learning_rate": 0.0,
+      "loss": 2.2658,
+      "step": 30
+    },
+    {
+      "epoch": 0.005484711367064308,
+      "eval_loss": 2.203942060470581,
+      "eval_runtime": 286.8526,
+      "eval_samples_per_second": 16.061,
+      "eval_steps_per_second": 4.016,
+      "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": 1.5529610821238784e+16,
+  "total_flos": 2.3198554436665344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null