Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:305100552e48ba23623a2e714f3591341db275b115a7748a3c1e54fbb1718faf
+oid sha256:c4a31322ac77da1938731bbcd97448dc4f4c2d3ef83015f7ee559d9cd6e61df7
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1856d2a7e33bdd9972b3745ef2b0d4bfcd326fad86fa04fde544064cac9707d
+oid sha256:431070ecf967a3c3d2414a8824c1e35d0a22102a2b667b129f0a4e246aecfe1a
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf1fc5b56a62737787ac054c4058edbb175d16d4950ba722810b681ea8f6197
+oid sha256:e7039ad488ecad79c244d578e72d1880cc11807f12526e5d67ce8157a576adbe
 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": 11.931222915649414,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00022024733776030483,
+  "best_metric": 11.931078910827637,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00044049467552060965,
   "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": 73.895,
       "eval_steps_per_second": 36.948,
       "step": 10
+    },
+    {
+      "epoch": 0.0002642968053123658,
+      "grad_norm": 0.007844880223274231,
+      "learning_rate": 0.000163742398974869,
+      "loss": 11.9314,
+      "step": 12
+    },
+    {
+      "epoch": 0.0003303710066404572,
+      "grad_norm": 0.010503560304641724,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9316,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003303710066404572,
+      "eval_loss": 11.931129455566406,
+      "eval_runtime": 258.176,
+      "eval_samples_per_second": 74.05,
+      "eval_steps_per_second": 37.025,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003964452079685487,
+      "grad_norm": 0.010184229351580143,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 11.9315,
+      "step": 18
+    },
+    {
+      "epoch": 0.00044049467552060965,
+      "eval_loss": 11.931078910827637,
+      "eval_runtime": 259.3667,
+      "eval_samples_per_second": 73.71,
+      "eval_steps_per_second": 36.855,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5527339008.0,
+  "total_flos": 9274687488.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null