Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ed23aadbdac3a4625bb723f6a73adebc98dd00d5b375874b228d2623240c06
+oid sha256:0f1b2a741613b7b9667b12873f267b40a46b89f29ebba82ff36d2931a9767190
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eeb99e4f15afe47e24243281bf05c9ae612bbf83adb5f348dcdb4268dd4f386a
+oid sha256:44efb3c6a43a0b2d6baced26d9907d4162e9fa2974f83de35d82c525bfafc586
 size 48843956

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:678a5384192c74f38dac63d392031fba04f9327271855ccf295f133b78f8aeb4
+oid sha256:b0bf58e46326ba44fb46e406611cb20e8a28eaee12cce4e234e812eec11a75f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
+oid sha256:200a199971193d5b4ec602093f689606117a65db31ca244b618fc0f0cd969846
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2521640062332153,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.04170335016913025,
+  "best_metric": 1.2492706775665283,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.04633705574347806,
   "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": 28.651,
       "eval_steps_per_second": 7.163,
       "step": 450
+    },
+    {
+      "epoch": 0.04263009128399981,
+      "grad_norm": 8.084239959716797,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 3.6936,
+      "step": 460
+    },
+    {
+      "epoch": 0.04355683239886938,
+      "grad_norm": 11.500914573669434,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 3.4893,
+      "step": 470
+    },
+    {
+      "epoch": 0.04448357351373894,
+      "grad_norm": 14.991345405578613,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 3.1834,
+      "step": 480
+    },
+    {
+      "epoch": 0.0454103146286085,
+      "grad_norm": 10.201809883117676,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 3.3994,
+      "step": 490
+    },
+    {
+      "epoch": 0.04633705574347806,
+      "grad_norm": 12.510831832885742,
+      "learning_rate": 0.0,
+      "loss": 3.0099,
+      "step": 500
+    },
+    {
+      "epoch": 0.04633705574347806,
+      "eval_loss": 1.2492706775665283,
+      "eval_runtime": 159.1369,
+      "eval_samples_per_second": 28.554,
+      "eval_steps_per_second": 7.139,
+      "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": 3.688764724268237e+16,
+  "total_flos": 4.10259132776448e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null