Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72117ac5f9bf7ebb1701fb6715c32d81e70c9ebb45138961d4749a2d954cddd9
+oid sha256:d92c4bea84f9262d0234e6997c6a05af0e4fa4ad91750b3dbd291a31a94b4d54
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9feaca09ec00e3e5b1d5b633518b7d35674477b62531edc903f48064743aee37
+oid sha256:fda8ad06139ff74a1b5d387c398466ddaaeab3b0b0f7016916b3b8af0517d53b
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd082d426c5a2595f03a243a16789fbf4f16702371fd453403159dbedd3e918
+oid sha256:361ff2e447283ad07cb1410fccd645634dce3ad663bcce381597321a82fbfe95
 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": 1.9420759677886963,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00048107568523217913,
+  "best_metric": 1.8052375316619873,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0007216135278482687,
   "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": 15.679,
       "eval_steps_per_second": 3.92,
       "step": 20
+    },
+    {
+      "epoch": 0.0005051294694937881,
+      "grad_norm": 6.091856479644775,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.5995,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005772908222786149,
+      "grad_norm": 5.133573055267334,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.5864,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006013446065402239,
+      "eval_loss": 1.8254233598709106,
+      "eval_runtime": 2233.5631,
+      "eval_samples_per_second": 15.675,
+      "eval_steps_per_second": 3.919,
+      "step": 25
+    },
+    {
+      "epoch": 0.0006494521750634418,
+      "grad_norm": 14.063956260681152,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.8096,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007216135278482687,
+      "grad_norm": 6.68426513671875,
+      "learning_rate": 0.0,
+      "loss": 6.9028,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007216135278482687,
+      "eval_loss": 1.8052375316619873,
+      "eval_runtime": 2233.2894,
+      "eval_samples_per_second": 15.676,
+      "eval_steps_per_second": 3.919,
+      "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": 1.306929288708096e+16,
+  "total_flos": 1.960393933062144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null