Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719928d15e3878f3afcfe1609105d01248224f0d6ed3c93d8ec6c0a8910dc581
+oid sha256:3f621b3053c29d0c5672e00fd75f1ee93bfd6a54ff102fd3a0cff27843979f04
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c22698a0b320a6d45ffeed96830461cc5b143aba7cd4efe6fdbae2b0e55cc9
+oid sha256:d8c4fa57e0c50a9ebed8593500050e529c00f5bc32499d2046f5c3ca6b617f57
 size 40178148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bc1028a94f9b9910c5fb265e3dd361de766cab41d3de074d532673eb6d04cb
+oid sha256:0a8aaed42384413b519c4f5d8254b3cf86b8efb41949850a55d91d89e7d4fe91
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
+oid sha256:4f23fa0ef01cbb776456cad40209cd1c0c6a02d9fdf8c0632982552f2f542168
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.028611183166504,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.023405195953501677,
+  "best_metric": 1.0285351276397705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.02600577328166853,
   "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": 41.775,
       "eval_steps_per_second": 10.444,
       "step": 450
+    },
+    {
+      "epoch": 0.023925311419135047,
+      "grad_norm": 0.19935743510723114,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 0.9743,
+      "step": 460
+    },
+    {
+      "epoch": 0.024445426884768418,
+      "grad_norm": 0.20279110968112946,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 1.0289,
+      "step": 470
+    },
+    {
+      "epoch": 0.024965542350401788,
+      "grad_norm": 0.2163035273551941,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 1.0602,
+      "step": 480
+    },
+    {
+      "epoch": 0.02548565781603516,
+      "grad_norm": 0.21532097458839417,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 1.0253,
+      "step": 490
+    },
+    {
+      "epoch": 0.02600577328166853,
+      "grad_norm": 0.26831209659576416,
+      "learning_rate": 0.0,
+      "loss": 1.0653,
+      "step": 500
+    },
+    {
+      "epoch": 0.02600577328166853,
+      "eval_loss": 1.0285351276397705,
+      "eval_runtime": 192.6922,
+      "eval_samples_per_second": 42.015,
+      "eval_steps_per_second": 10.504,
+      "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": 2663769688768512.0,
+  "total_flos": 2957340594143232.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null