Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be6cacbfe0bffb0581b05fb6e7e86c191cc5c1365998549000135c11b2798ed
+oid sha256:88fca79a42acb59b9e675e977d8c76b3a3a39358c5966d94ad7487c57dfcb663
 size 406863720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b56a8bb8f43f4b17be951955ca96528e7e51ba728e844e939fb1680832a3294
+oid sha256:3e2ce69c45f8295d0908ef7b217c7d08054e77bae04cad2bbe75ef384979f143
 size 207014276

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e2e78d3593dae83c2a9fe33598195e178cbb065d93f50bd4c4fd19bda92231
+oid sha256:924139522dce457886c928c98870770cf9779d23e131ca21cd44f268e6ee466e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9625978469848633,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.16213294901819492,
+  "best_metric": 1.9572868347167969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.18014772113132768,
   "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": 18.449,
       "eval_steps_per_second": 4.624,
       "step": 450
+    },
+    {
+      "epoch": 0.16573590344082148,
+      "grad_norm": 0.5630381107330322,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 2.0962,
+      "step": 460
+    },
+    {
+      "epoch": 0.16933885786344802,
+      "grad_norm": 0.5653451681137085,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 1.948,
+      "step": 470
+    },
+    {
+      "epoch": 0.17294181228607458,
+      "grad_norm": 0.528786838054657,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 1.9981,
+      "step": 480
+    },
+    {
+      "epoch": 0.17654476670870115,
+      "grad_norm": 0.5580498576164246,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 1.8072,
+      "step": 490
+    },
+    {
+      "epoch": 0.18014772113132768,
+      "grad_norm": 1.0382150411605835,
+      "learning_rate": 0.0,
+      "loss": 1.8913,
+      "step": 500
+    },
+    {
+      "epoch": 0.18014772113132768,
+      "eval_loss": 1.9572868347167969,
+      "eval_runtime": 63.3164,
+      "eval_samples_per_second": 18.463,
+      "eval_steps_per_second": 4.628,
+      "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": 6.29334470688768e+16,
+  "total_flos": 7.000556687327232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null