Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32cab2610720bba8b4a8f7c60081ef3dfd45f5657c749f2e861066ee303425b7
+oid sha256:1620fe2e989e1dc6fbcfd1ec6e7112b3eb8d0aa515f3ddad849354ebc65ad483
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4295bb3cbedc031617295b1213f5e9b070058c3b99b1f821ec455695827fe419
+oid sha256:7597ae5b841425d3d3d1bacf00220af4c3fc75d9f491288ef25b7422409a8722
 size 5561210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0298ba40ec329a95853fd2a861a525ce6fe426db89829b6542b575e9ec389041
+oid sha256:5c0892ff64ee164eb45df7018e1c5eaa013998f0490b92833b1135a7e3da2bbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c0cbab52df187d8502a1b66e46607ea8ce4ac36a84891208388bc9974f53e8
+oid sha256:2e87d47519e32af310d5ce258e0454d331221391a1b9ee9143859120658f7a9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7665436267852783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.04608058983154984,
+  "best_metric": 1.7662434577941895,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.05120065536838871,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 25.171,
       "eval_steps_per_second": 12.586,
       "step": 450
+    },
+    {
+      "epoch": 0.04710460293891762,
+      "grad_norm": 1.1416006088256836,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 6.9583,
+      "step": 460
+    },
+    {
+      "epoch": 0.04812861604628539,
+      "grad_norm": 1.2712125778198242,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 7.2235,
+      "step": 470
+    },
+    {
+      "epoch": 0.04915262915365317,
+      "grad_norm": 1.4268357753753662,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 6.9579,
+      "step": 480
+    },
+    {
+      "epoch": 0.05017664226102094,
+      "grad_norm": 1.1501182317733765,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 7.2944,
+      "step": 490
+    },
+    {
+      "epoch": 0.05120065536838871,
+      "grad_norm": 1.6461912393569946,
+      "learning_rate": 0.0,
+      "loss": 6.912,
+      "step": 500
+    },
+    {
+      "epoch": 0.05120065536838871,
+      "eval_loss": 1.7662434577941895,
+      "eval_runtime": 163.4563,
+      "eval_samples_per_second": 25.157,
+      "eval_steps_per_second": 12.578,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1886064491888640.0,
+  "total_flos": 2096704656506880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null