Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7090855172c3a21e61af7972b141d178c0646fb77708244cb15eb254bf2cd344
+oid sha256:27e2852914d6d4c5766f9a28cb2feefc344b2e5a197f566499c8bdded2eff545
 size 94422368

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fb77b473d4eec64dde853209f3886189c9571e307b3705574fc06610b2a834
+oid sha256:3f27e9dd07d0abac926bfdc1bb987731c35752e821eb2d77663345dcd3775a4f
 size 189066386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3dba61893a1e71cf8f6a23883bf4b372892166e8d0959b298428f95c7822d2
+oid sha256:ceed9f290bc02e6a37dc4466bd2b7f9348e81a95d696a722345aaf274aa77c62
 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": 2.6216320991516113,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.1652892561983471,
+  "best_metric": 1.8933956623077393,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.3305785123966942,
   "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": 9.849,
       "eval_steps_per_second": 2.511,
       "step": 10
+    },
+    {
+      "epoch": 0.19834710743801653,
+      "grad_norm": 6.966921329498291,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.0435,
+      "step": 12
+    },
+    {
+      "epoch": 0.24793388429752067,
+      "grad_norm": 8.361279487609863,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.4061,
+      "step": 15
+    },
+    {
+      "epoch": 0.24793388429752067,
+      "eval_loss": 1.9922754764556885,
+      "eval_runtime": 5.1278,
+      "eval_samples_per_second": 9.946,
+      "eval_steps_per_second": 2.535,
+      "step": 15
+    },
+    {
+      "epoch": 0.2975206611570248,
+      "grad_norm": 5.423651218414307,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.1216,
+      "step": 18
+    },
+    {
+      "epoch": 0.3305785123966942,
+      "eval_loss": 1.8933956623077393,
+      "eval_runtime": 4.9153,
+      "eval_samples_per_second": 10.376,
+      "eval_steps_per_second": 2.645,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3546293678899200.0,
+  "total_flos": 7158259462963200.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null