Training in progress, step 380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27dcec798f401aea531332fd52d47af4e2e2052534e106a38738f74d8310f559
+oid sha256:14c1fd6535b1947d88953614c47802dd8b81a013bb8594bc2fa89f725857c9ac
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f75e289bb3450e55503e27675a790d9ae74e663bd5176ca0036dc79eed1f7f
+oid sha256:4c946b2c89717f2d9b83962c1fea716d72aa3ccdf0862f8da941b1f3acef991a
 size 56088788

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f464ee492959ca51f31ddd6c918f5e6ed3b897ddaa5bd27211176d3e42d4533
+oid sha256:8966b15f85185715dd994ab5a2d54fa29563cc2e5c4c1515e4dbf61731e57b3f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a1a67751ef8c6e878b8ba1ee8cfd48efab59bef2ad58f80bf89ebc2ab37857
+oid sha256:8092b14896167cec4bcd41544a9706c780edac6d6d1675e384862c5b2b347c56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.503983521113696e-07,
-  "best_model_checkpoint": "miner_id_24/checkpoint-360",
-  "epoch": 2.4242424242424243,
+  "best_metric": 3.3884660410876677e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-380",
+  "epoch": 2.558922558922559,
   "eval_steps": 20,
-  "global_step": 360,
+  "global_step": 380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,6 +180,14 @@
       "eval_samples_per_second": 28.493,
       "eval_steps_per_second": 0.912,
       "step": 360
+    },
+    {
+      "epoch": 2.558922558922559,
+      "eval_loss": 3.3884660410876677e-07,
+      "eval_runtime": 4.549,
+      "eval_samples_per_second": 27.478,
+      "eval_steps_per_second": 0.879,
+      "step": 380
     }
   ],
   "logging_steps": 100,
@@ -208,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5202435039494144e+17,
+  "total_flos": 1.6047308122619904e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null