Training in progress, step 620, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e0f9fcdf48f487a1c9001825e5051f82f66679b2a25912d3b21503f2d4a1c4
+oid sha256:7be70d8683f52dfd6ab8a831dd123d31825f4f46f3d60ff6ff495756b2423892
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347cd973f6654ee2258a2954d44bb5fc9959a63600a404728a5f3d3feda03a7d
+oid sha256:7cef13c342042cdffc93928dccbe66ef17dc59173c61c71746512d665ecab28c
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3775aa2a57ceedad86a9060869357a0158ad85ec662a59802338adbc33ed6fc5
+oid sha256:f1da8f1783ffd6f503df78c842d3af807c7c31d93c07e493d90c00923c143bb4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f4ffe4ed9bff96a333b247dd3c9b5dfaf8c2768b6a1ee83b674ec988b0833c
+oid sha256:74f685c1f5a24a54cae2add4213dad1550d2eddd5d044f686e315a3bdf3dd38b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6435236577526666e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-600",
-  "epoch": 4.040404040404041,
+  "best_metric": 2.6299875344193424e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-620",
+  "epoch": 4.175084175084175,
   "eval_steps": 20,
-  "global_step": 600,
+  "global_step": 620,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -297,6 +297,14 @@
       "eval_samples_per_second": 28.244,
       "eval_steps_per_second": 0.904,
       "step": 600
+    },
+    {
+      "epoch": 4.175084175084175,
+      "eval_loss": 2.6299875344193424e-07,
+      "eval_runtime": 4.3837,
+      "eval_samples_per_second": 28.514,
+      "eval_steps_per_second": 0.912,
+      "step": 620
     }
   ],
   "logging_steps": 100,
@@ -325,7 +333,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5335631580233728e+17,
+  "total_flos": 2.6180504663359488e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null