Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6d35b6f1e3b1b7c1e09abe0d9e02493bf0acd5e2efe551a8bd364e7e3b3074
+oid sha256:5588a95e191602177fe9e72bc0859b695931bdfb0282fac420a01d4e6527609b
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da7126affbfc3bce9eca5b2011e85ac1006bfe45bfda49b0825e90593a69573
+oid sha256:765b36ee020bf27b737db48f2acae16d156fc975aaf59b05351589c8e7c76a7a
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449e1ad9277cc345b26150303ab1d00fa8d31d8552de022060a6372b037df491
+oid sha256:2abdf2abada856d35ae8bc928ccdc37f1effa00be5fd4bbdf4e554f6e9ec8cd5
 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": 1.3293501138687134,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.002146037877568539,
+  "best_metric": 1.1837564706802368,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004292075755137078,
   "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": 5.346,
       "eval_steps_per_second": 1.336,
       "step": 10
+    },
+    {
+      "epoch": 0.002575245453082247,
+      "grad_norm": 1.227637529373169,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.2881,
+      "step": 12
+    },
+    {
+      "epoch": 0.003219056816352809,
+      "grad_norm": 1.231693148612976,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2856,
+      "step": 15
+    },
+    {
+      "epoch": 0.003219056816352809,
+      "eval_loss": 1.2313477993011475,
+      "eval_runtime": 733.9654,
+      "eval_samples_per_second": 5.346,
+      "eval_steps_per_second": 1.337,
+      "step": 15
+    },
+    {
+      "epoch": 0.00386286817962337,
+      "grad_norm": 1.0194306373596191,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.2727,
+      "step": 18
+    },
+    {
+      "epoch": 0.004292075755137078,
+      "eval_loss": 1.1837564706802368,
+      "eval_runtime": 734.1115,
+      "eval_samples_per_second": 5.345,
+      "eval_steps_per_second": 1.336,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8236125420257280.0,
+  "total_flos": 1.647225084051456e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null