Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f06810a76c54ec643ce74dc6079a2bf5355a0e563ab27059178720c3d30a9b7
+oid sha256:5ae4b6dca450b054be9de0dc97d3e5454d618b1444b3549e97c7c9d5f3224851
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:183e4d25126f37e019da6541b08c5eb3de23f23837b306aa4fc1367fdc0b23e0
+oid sha256:fc4c88504c7d60a03f993e7d3e042134a3faac7f1837367d2df62fe4a89bd853
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe5df6d694ec27c5c0cf866253f1b6e988c03c2b38ae43d7112f30f0983dfdc
+oid sha256:98a6b5e5080fcd87c6a71760f39ee427f007e05c9baeb1b6f06079a9b067c8ff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4525096416473389,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.001300305571809375,
+  "best_metric": 1.4081313610076904,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00260061114361875,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 23.78,
       "eval_steps_per_second": 5.948,
       "step": 10
+    },
+    {
+      "epoch": 0.0015603666861712503,
+      "grad_norm": 0.16580092906951904,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.408,
+      "step": 12
+    },
+    {
+      "epoch": 0.0019504583577140628,
+      "grad_norm": 0.15052564442157745,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3837,
+      "step": 15
+    },
+    {
+      "epoch": 0.0019504583577140628,
+      "eval_loss": 1.4265315532684326,
+      "eval_runtime": 272.3667,
+      "eval_samples_per_second": 23.78,
+      "eval_steps_per_second": 5.948,
+      "step": 15
+    },
+    {
+      "epoch": 0.0023405500292568754,
+      "grad_norm": 0.24706414341926575,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.3752,
+      "step": 18
+    },
+    {
+      "epoch": 0.00260061114361875,
+      "eval_loss": 1.4081313610076904,
+      "eval_runtime": 272.3861,
+      "eval_samples_per_second": 23.779,
+      "eval_steps_per_second": 5.947,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1338925557743616.0,
+  "total_flos": 2645194394566656.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null