Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3c34d71fb85efa2377aeb484038b95e1c47f2ab459edc06d0c297e7b3545e3
+oid sha256:73f564cabc52ca3f1e48b7302b4cd2691bdcc0c31c102e983194005194667017
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81dc3c203c433b2e02c3d760d40e514481e0c3887b7056094a063c3007795e41
+oid sha256:cd32a7ea1c588e18b85741730f91f93f434e3d6d094a7d0b3bd55de60d6ac77d
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818d7ab5bd47bdd1a24da947800ef4c6cd90c336eb8d016638b35a139c160421
+oid sha256:979feb229ea878c876a7d97f1bd4f129fbd6ea7b2fad5a6881860b5c3a388743
 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": 0.8792083859443665,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.21500238891543239,
+  "best_metric": 0.8746353387832642,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.23889154323936931,
   "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": 71.883,
       "eval_steps_per_second": 18.011,
       "step": 450
+    },
+    {
+      "epoch": 0.21978021978021978,
+      "grad_norm": 28.86961555480957,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 1.3139,
+      "step": 460
+    },
+    {
+      "epoch": 0.22455805064500717,
+      "grad_norm": 38.519046783447266,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 1.4227,
+      "step": 470
+    },
+    {
+      "epoch": 0.22933588150979456,
+      "grad_norm": 20.339561462402344,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 1.6595,
+      "step": 480
+    },
+    {
+      "epoch": 0.23411371237458195,
+      "grad_norm": 55.318058013916016,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 1.9445,
+      "step": 490
+    },
+    {
+      "epoch": 0.23889154323936931,
+      "grad_norm": 15.225406646728516,
+      "learning_rate": 0.0,
+      "loss": 2.0612,
+      "step": 500
+    },
+    {
+      "epoch": 0.23889154323936931,
+      "eval_loss": 0.8746353387832642,
+      "eval_runtime": 12.2579,
+      "eval_samples_per_second": 71.953,
+      "eval_steps_per_second": 18.029,
+      "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": 4191310105804800.0,
+  "total_flos": 4657011228672000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null