Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e29faaabd86f4af31161a97e83b91b4a8f8ef3b433eae8163a48cf1d436680
+oid sha256:85bedbd461e9179d34712240ec26a83260273217c8ff797ecb69a15f5f289bef
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbd7d5703070b42a7a5cee749f0c716c4d1b8b44832e118c116d75ee053848f4
+oid sha256:aa745748d75a31358d3e8982d3155c790bb81033facb334f1c3fd753fb74464c
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525e5fa24400d869f9fc3537701e89d57b364b765a64417b7c484690fabcff66
+oid sha256:1a2a88e24916e66748ee76d72facab6ee1e97630003c9511a4f04221fafc3f10
 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": 2.541001081466675,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 2.536858081817627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "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": 16.151,
       "eval_steps_per_second": 8.076,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 1.8993418216705322,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.1311,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 3.285736083984375,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.3098,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 2.537450075149536,
+      "eval_runtime": 30.4782,
+      "eval_samples_per_second": 16.077,
+      "eval_steps_per_second": 8.039,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 3.5203537940979004,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.6445,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 2.378814935684204,
+      "learning_rate": 0.0,
+      "loss": 10.5218,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 2.536858081817627,
+      "eval_runtime": 30.6248,
+      "eval_samples_per_second": 16.0,
+      "eval_steps_per_second": 8.0,
+      "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": 1893182157619200.0,
+  "total_flos": 2839773236428800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null