Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24dd0e1ecda8b1efcfd0a4f1510bc25459cea2335e167f7ea11ab81fc62e57cc
+oid sha256:ea05a47d6e40203ac1b2b2e132ef669a546565fb3d8417efe63ee262a23fe93e
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0ab7af3da6544fcb1231ae9d2fa50ce2f71d6b79c45e63b9f5425ccd09ed6d0
+oid sha256:b621b700c852204a7687a511c995296a1cf40606bdfde575704a8d0d5e1c42c2
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9951200f486541701fca7785235d202b2a0d67dc3607bd979cab1dfc8960ed23
+oid sha256:0202967e91f4fd0440578247b44fdb88c4af9fd94cda8a00cffecaeda930a1c7
 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": 2.6902265548706055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.016070711128967456,
+  "best_metric": 2.6543691158294678,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.024106066693451184,
   "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": 15.605,
       "eval_steps_per_second": 7.802,
       "step": 20
+    },
+    {
+      "epoch": 0.01687424668541583,
+      "grad_norm": 2.4370040893554688,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.7871,
+      "step": 21
+    },
+    {
+      "epoch": 0.019284853354760947,
+      "grad_norm": 2.2035434246063232,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.7107,
+      "step": 24
+    },
+    {
+      "epoch": 0.020088388911209322,
+      "eval_loss": 2.6591219902038574,
+      "eval_runtime": 33.7978,
+      "eval_samples_per_second": 15.504,
+      "eval_steps_per_second": 7.752,
+      "step": 25
+    },
+    {
+      "epoch": 0.021695460024106068,
+      "grad_norm": 1.9634120464324951,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.728,
+      "step": 27
+    },
+    {
+      "epoch": 0.024106066693451184,
+      "grad_norm": 1.874236822128296,
+      "learning_rate": 0.0,
+      "loss": 2.611,
+      "step": 30
+    },
+    {
+      "epoch": 0.024106066693451184,
+      "eval_loss": 2.6543691158294678,
+      "eval_runtime": 33.6148,
+      "eval_samples_per_second": 15.588,
+      "eval_steps_per_second": 7.794,
+      "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": 7668943615426560.0,
+  "total_flos": 1.150341542313984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null