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:d6a0a5b55534350d56712884ba104a70662f3037e676f23fc4409aeb22caeccd
+oid sha256:1323e4c66ab01f137cf11290a4b1d0aef25e01ac5af65c0b085a874b12a853d7
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8e96f4a50676171d1e42c954a30811a105697cca5914f838c82970b37e9b2f
+oid sha256:b415862c2334d14020edf6e41780f447b9ef678ebc0d1861a8a2b86226b9dc21
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1dcbd4ca11878e182b2a443ac16eb53a385e713b9af55f8a27917cd0d74d93
+oid sha256:2e21f265f27a77a4f1136ee5037572c9b1fa7c9b1169d41749c1135ac8d59210
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
+oid sha256:b3488300cc890b0bf0becbfdd6a3cc8770e6656a66feed4ec387a72a2b445721
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.29808175563812256,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.3938730853391685,
+  "best_metric": 0.29707786440849304,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.437636761487965,
   "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": 10.037,
       "eval_steps_per_second": 2.525,
       "step": 450
+    },
+    {
+      "epoch": 0.4026258205689278,
+      "grad_norm": 0.4591379463672638,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 0.6904,
+      "step": 460
+    },
+    {
+      "epoch": 0.4113785557986871,
+      "grad_norm": 0.2666955292224884,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 0.5246,
+      "step": 470
+    },
+    {
+      "epoch": 0.4201312910284464,
+      "grad_norm": 0.004976064432412386,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 0.0667,
+      "step": 480
+    },
+    {
+      "epoch": 0.4288840262582057,
+      "grad_norm": 0.0005102211725898087,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 0.0005,
+      "step": 490
+    },
+    {
+      "epoch": 0.437636761487965,
+      "grad_norm": 0.05553697422146797,
+      "learning_rate": 0.0,
+      "loss": 0.0007,
+      "step": 500
+    },
+    {
+      "epoch": 0.437636761487965,
+      "eval_loss": 0.29707786440849304,
+      "eval_runtime": 47.9196,
+      "eval_samples_per_second": 10.038,
+      "eval_steps_per_second": 2.525,
+      "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": 1.4734321501863936e+17,
+  "total_flos": 1.6342833077157888e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null