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:c4a31322ac77da1938731bbcd97448dc4f4c2d3ef83015f7ee559d9cd6e61df7
+oid sha256:2d4e7e0ef8c194decc88a8e4758030d3d6e83bdb6b4aa26b16e10a64365ca91f
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431070ecf967a3c3d2414a8824c1e35d0a22102a2b667b129f0a4e246aecfe1a
+oid sha256:8e71ac5bfb9d4e75cd7892dadba375b7961786d9618806405f8e18d56bdb6673
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7039ad488ecad79c244d578e72d1880cc11807f12526e5d67ce8157a576adbe
+oid sha256:fb4366cde00004591a22d07a897a309c5c67982376ad884b628e7e44f72990d8
 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": 11.931078910827637,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00044049467552060965,
+  "best_metric": 11.931035995483398,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0006607420132809144,
   "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": 73.71,
       "eval_steps_per_second": 36.855,
       "step": 20
+    },
+    {
+      "epoch": 0.00046251940929664014,
+      "grad_norm": 0.010106095112860203,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9302,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005285936106247316,
+      "grad_norm": 0.013225448317825794,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9327,
+      "step": 24
+    },
+    {
+      "epoch": 0.000550618344400762,
+      "eval_loss": 11.931039810180664,
+      "eval_runtime": 258.7879,
+      "eval_samples_per_second": 73.875,
+      "eval_steps_per_second": 36.938,
+      "step": 25
+    },
+    {
+      "epoch": 0.000594667811952823,
+      "grad_norm": 0.014623328112065792,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.931,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006607420132809144,
+      "grad_norm": 0.0317741297185421,
+      "learning_rate": 0.0,
+      "loss": 11.9287,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006607420132809144,
+      "eval_loss": 11.931035995483398,
+      "eval_runtime": 258.2272,
+      "eval_samples_per_second": 74.036,
+      "eval_steps_per_second": 37.018,
+      "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": 9274687488.0,
+  "total_flos": 13022035968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null