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:aa3ac03a9726225ffa24f979e6b3eff20b0b9cebcd8327673a8d1975b6f94211
+oid sha256:56a3b937e821706119d998cc0c19a950933e4be23fc0ac869f30c140768b7771
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d926d1efcab59711dfc929d355e1236f8bad71f15baa81ed0353468ad848ed
+oid sha256:6158f12f04f067f509af016d34ba2c1c407dc9ab0753c97e70fcb9e3bb158ee8
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d414eadf39302d8ec0219af438e287bb7b20fa850e733f546b8f98e5ed72641b
+oid sha256:610bc13fcb17b2c654a1a8a0116abfd6bf67a64c697b07f17d249de06418163e
 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": 2.349881649017334,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004232132465746178,
+  "best_metric": 2.304311990737915,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.006348198698619267,
   "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": 7.489,
       "eval_steps_per_second": 3.744,
       "step": 20
+    },
+    {
+      "epoch": 0.004443739089033487,
+      "grad_norm": 5.530812740325928,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 9.1007,
+      "step": 21
+    },
+    {
+      "epoch": 0.005078558958895413,
+      "grad_norm": 4.739592552185059,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 9.1675,
+      "step": 24
+    },
+    {
+      "epoch": 0.0052901655821827225,
+      "eval_loss": 2.312439203262329,
+      "eval_runtime": 265.7188,
+      "eval_samples_per_second": 7.489,
+      "eval_steps_per_second": 3.745,
+      "step": 25
+    },
+    {
+      "epoch": 0.00571337882875734,
+      "grad_norm": 6.098222255706787,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 9.2889,
+      "step": 27
+    },
+    {
+      "epoch": 0.006348198698619267,
+      "grad_norm": 5.108956813812256,
+      "learning_rate": 0.0,
+      "loss": 8.6635,
+      "step": 30
+    },
+    {
+      "epoch": 0.006348198698619267,
+      "eval_loss": 2.304311990737915,
+      "eval_runtime": 265.7683,
+      "eval_samples_per_second": 7.488,
+      "eval_steps_per_second": 3.744,
+      "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": 5777796587520000.0,
+  "total_flos": 8738917338624000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null