Training in progress, step 280, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409ca06d3faf294e4a34f4ace5a8b787da94856f596eb04a7c15162528103a5e
+oid sha256:a2e1190afdf08e6d245aebf19748bf09f95e5346d047e995a020fa32d7ee65af
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac0747dd422173fac3fd619d51b47649d7b7a36450ae4e81fe21d34d415a0370
+oid sha256:f27951f81528848db415822bf71fb9a83a227168152ca7c9b4634214b845ff2a
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897059aa7cfff37e377cd99d24d93981715ca9c34289bdce7a0cfd4e8e57e3e6
+oid sha256:9a4c5e895fc749303e186af008c616cc4691ee11e5379819a9cef8abc9244ae4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f95e5cbb6fb06bf7ed50b639c404486199a6ebf7da6a6f5f39500844da24e03
+oid sha256:bcff232e369592911db2b4e3df034b850aaaa5664b471617ca7ce83896190c8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.83989538224705e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-260",
-  "epoch": 1.7508417508417509,
+  "best_metric": 4.489497769100126e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-280",
+  "epoch": 1.8855218855218854,
   "eval_steps": 20,
-  "global_step": 260,
+  "global_step": 280,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,14 @@
       "eval_samples_per_second": 28.64,
       "eval_steps_per_second": 0.916,
       "step": 260
+    },
+    {
+      "epoch": 1.8855218855218854,
+      "eval_loss": 4.489497769100126e-07,
+      "eval_runtime": 4.3601,
+      "eval_samples_per_second": 28.669,
+      "eval_steps_per_second": 0.917,
+      "step": 280
     }
   ],
   "logging_steps": 100,
@@ -161,7 +169,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0980709852250112e+17,
+  "total_flos": 1.1825582935375872e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null