Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:841e2a7963690e840f9e8c0ff88a8c8ba0dc65bfd2072cd38c647ba3df2232bc
+oid sha256:b0cac7dd1d23aeca450d590dd363c342e041f8f454c11413224b81d145ce7de1
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b07c17f132ea29dc958f6fd789dcb9de8e39674ea36f3e6717fab2c71152c1
+oid sha256:d29a94ce954837e5f097c2848413e378f16e2f954256c2fb45cb44f9a21ce97b
 size 29091284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf5047ce0cd92f6ae940c79a07a1afdbeee8fbdb29b67dddf76d5b11ef7f6b4e
+oid sha256:328bd3fe7939a56439b9a2f90f2358861d49dc223102da438b6523b2c9683732
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
+oid sha256:2c9718e38efb2d48aaa61791c4fc8b4a7f9cfd08f355dda43ae7de9f2cb195d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4904224872589111,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.03800836183960471,
+  "best_metric": 1.4900296926498413,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.04223151315511635,
   "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": 23.417,
       "eval_steps_per_second": 5.858,
       "step": 450
+    },
+    {
+      "epoch": 0.03885299210270704,
+      "grad_norm": 0.2755116820335388,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 1.4975,
+      "step": 460
+    },
+    {
+      "epoch": 0.039697622365809364,
+      "grad_norm": 0.25559327006340027,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 1.4252,
+      "step": 470
+    },
+    {
+      "epoch": 0.040542252628911694,
+      "grad_norm": 0.29182490706443787,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 1.4583,
+      "step": 480
+    },
+    {
+      "epoch": 0.04138688289201402,
+      "grad_norm": 0.272938996553421,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 1.48,
+      "step": 490
+    },
+    {
+      "epoch": 0.04223151315511635,
+      "grad_norm": 0.3512996733188629,
+      "learning_rate": 0.0,
+      "loss": 1.5623,
+      "step": 500
+    },
+    {
+      "epoch": 0.04223151315511635,
+      "eval_loss": 1.4900296926498413,
+      "eval_runtime": 212.6997,
+      "eval_samples_per_second": 23.437,
+      "eval_steps_per_second": 5.863,
+      "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": 2.926582086972211e+16,
+  "total_flos": 3.252845418853171e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null