Training in progress, step 440, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60cc159fecd96d4d214eaf81c728f774bec2e6e29e769b1f160149eabc252f8
+oid sha256:52b78623973eb2794c0a49a2cec63bfb0dd4b26992ffac1dec31ca41cc19e923
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b6bd8b8c4b54ceb06e7fc33a5d20ec2c1f7514e2fa7d118a661c0d4fab0288
+oid sha256:6feb5a14d31c0796d533286dea3f6e3b3ce9a31fd701942e2cc4f56c02504dd4
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750b68fb260444bdc0ecba0e943e015a259b04d2544fd13bbd08cb83b9380b85
+oid sha256:df7c724a3e6764e5b735a889ce37cba056b96f3333312e703ca050d56cda9d41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79449a9403c9f2944251cd2bf4582f6ae8d416fb028a5dcf58f150b03db7a8e3
+oid sha256:46f4240f17505bd53f967c1c31fbb076003c5cff63798cacf8ef30309a9af1de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.13235887006158e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-420",
-  "epoch": 2.8282828282828283,
+  "best_metric": 3.009457714142627e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-440",
+  "epoch": 2.962962962962963,
   "eval_steps": 20,
-  "global_step": 420,
+  "global_step": 440,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -211,6 +211,14 @@
       "eval_samples_per_second": 28.482,
       "eval_steps_per_second": 0.911,
       "step": 420
+    },
+    {
+      "epoch": 2.962962962962963,
+      "eval_loss": 3.009457714142627e-07,
+      "eval_runtime": 4.3984,
+      "eval_samples_per_second": 28.419,
+      "eval_steps_per_second": 0.909,
+      "step": 440
     }
   ],
   "logging_steps": 100,
@@ -239,7 +247,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7737054288871424e+17,
+  "total_flos": 1.8581927371997184e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null