Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee54646a8d8e086da73ea4ea766d37f331724745da6db8860da669060ea0ad3
+oid sha256:9ce5384f5020e86a9a64128554a3b757a43c20aed75ce66b5b2ba9e4f0138149
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f52de36a984efd41e524a6385fb0d045ab097df06346cd62fde039dc559fb0
+oid sha256:ed848a8d649b932c38d9c82d19e0aeea9edfdc8b21ef79874f057157dc8d9e35
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b755806378981de9043df7e6fb9040a4956d482785c45c1100277e6bb6b7929
+oid sha256:e0bd87cbfefd66eec045a6015637747373f3a38ca8deaafcf82f46dc1205fa62
 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": 0.8050962686538696,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.1657153378751611,
+  "best_metric": 0.8033109903335571,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.18412815319462345,
   "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": 10.862,
       "eval_steps_per_second": 2.716,
       "step": 450
+    },
+    {
+      "epoch": 0.16939790093905358,
+      "grad_norm": 1.1936448812484741,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 1.6886,
+      "step": 460
+    },
+    {
+      "epoch": 0.17308046400294605,
+      "grad_norm": 1.1452791690826416,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 1.6843,
+      "step": 470
+    },
+    {
+      "epoch": 0.17676302706683852,
+      "grad_norm": 1.0918186902999878,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 1.6394,
+      "step": 480
+    },
+    {
+      "epoch": 0.180445590130731,
+      "grad_norm": 0.9549961686134338,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 1.7196,
+      "step": 490
+    },
+    {
+      "epoch": 0.18412815319462345,
+      "grad_norm": 1.2962521314620972,
+      "learning_rate": 0.0,
+      "loss": 1.5057,
+      "step": 500
+    },
+    {
+      "epoch": 0.18412815319462345,
+      "eval_loss": 0.8033109903335571,
+      "eval_runtime": 105.0396,
+      "eval_samples_per_second": 10.891,
+      "eval_steps_per_second": 2.723,
+      "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": 1.3587688094642995e+17,
+  "total_flos": 1.5092811439276032e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null