Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738db6e87dbdc652185665fc158be6fd9ea2a0182ce005e8cd70c603d7d0ba8f
+oid sha256:5d0853ccbc49c74ed52d86573779397092af38d6770ea7340c36f0d76555e3c4
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d0ec3da3829ab1403028082b4fa7f87c27e2f4f73466535f064dcf46407e206
+oid sha256:a4561c456d651b8a435f898c6b533102771df8f28fda2e9c0d6ba23759fcf1ed
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dee4d5b27e291e54604657b0419725531a46b79101c42b4fcc524425de489f6
+oid sha256:2984c51083c54f2a93eb7c7b2418dea66d8f3c5351ed7e42b1e0477edc7c96a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0547163486480713,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.10526315789473684,
+  "best_metric": 0.9311612844467163,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.21052631578947367,
   "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": 23.726,
       "eval_steps_per_second": 11.863,
       "step": 10
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 1.323952555656433,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 4.3055,
+      "step": 12
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 1.4276947975158691,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.7414,
+      "step": 15
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "eval_loss": 0.9728013277053833,
+      "eval_runtime": 1.7105,
+      "eval_samples_per_second": 23.386,
+      "eval_steps_per_second": 11.693,
+      "step": 15
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 1.4990589618682861,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.9735,
+      "step": 18
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 0.9311612844467163,
+      "eval_runtime": 1.6769,
+      "eval_samples_per_second": 23.853,
+      "eval_steps_per_second": 11.926,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 600937731194880.0,
+  "total_flos": 1201875462389760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null