Training in progress, step 340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0096943c56e6d5c858199f3d20e43a66545cfafbb05dac5dd43a4f00ef99a118
+oid sha256:c7384e6e0afd8f05180f65c96007714d18e0e6fb36424c6547b4ec71902d11c5
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae87e246941bbd07ed034fc4fce008471a5a64f84952a0a68d077c2c4799647
+oid sha256:c01ec9d1f8083459f22d7eb7f74be826665564bff8cfff1031d1dd0d4707690e
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be951e35134e38a25ddb549895edf56032d2fadab85e0bd34febb4e424907c3a
+oid sha256:75b81576a953c126a70feb1037e15d1536a41145956ed969eb430642c3a082d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f23adcb0ffe9f4db397db4bf9a51186d6924cf27594d2ce31102b42ec188074
+oid sha256:0f554738d4c98e192859c545795d9bad33dffcf55dc2610937bb10f054a491a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.925752878330968e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-320",
-  "epoch": 2.154882154882155,
+  "best_metric": 3.6971795225326787e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-340",
+  "epoch": 2.28956228956229,
   "eval_steps": 20,
-  "global_step": 320,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,14 @@
       "eval_samples_per_second": 28.562,
       "eval_steps_per_second": 0.914,
       "step": 320
+    },
+    {
+      "epoch": 2.28956228956229,
+      "eval_loss": 3.6971795225326787e-07,
+      "eval_runtime": 4.3977,
+      "eval_samples_per_second": 28.424,
+      "eval_steps_per_second": 0.91,
+      "step": 340
     }
   ],
   "logging_steps": 100,
@@ -192,7 +200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3512688873242624e+17,
+  "total_flos": 1.4357561956368384e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null