Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cc175137431626882adc09c49fa4de5b523abea2e13838e3a62b937a32e101
+oid sha256:53e07334cf803e8c55cc21f5bc4c61949af29682d86d526a08d4fa4df7981e33
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f437222b236920343e8f12cd729961ba83f3ff3ef7f01931fb69e0e812b3035b
+oid sha256:137de887f7ae75e0d37bd2b68159a9ff95622f2abd5d71cca9caa80cb6375e21
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3e9f2a322aa4a6909429a3a033cc8e74c578c2ecf9ea8a7389170a8f7efffb
+oid sha256:25fa7b3f1605fa59a36bb896fa96a5cc4483614cb90114208981dd46184ab095
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275a3f467a10238121d3751994e96dac39b01caeff52940c5c443f8040986af4
+oid sha256:2b9e64598e5491bb996b411334acd2cefa3c30b5e20788d80cc38bcc4e5e5001
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4367404580116272,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.02868617326448652,
+  "best_metric": 0.4364141821861267,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.031873525849429464,
   "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": 9.493,
       "eval_steps_per_second": 2.374,
       "step": 450
+    },
+    {
+      "epoch": 0.029323643781475107,
+      "grad_norm": 0.3007957339286804,
+      "learning_rate": 4.164367686630719e-06,
+      "loss": 0.4225,
+      "step": 460
+    },
+    {
+      "epoch": 0.029961114298463695,
+      "grad_norm": 0.2977583110332489,
+      "learning_rate": 2.3491329211158885e-06,
+      "loss": 0.4111,
+      "step": 470
+    },
+    {
+      "epoch": 0.030598584815452284,
+      "grad_norm": 0.29993608593940735,
+      "learning_rate": 1.046182610281186e-06,
+      "loss": 0.3988,
+      "step": 480
+    },
+    {
+      "epoch": 0.031236055332440876,
+      "grad_norm": 0.28918012976646423,
+      "learning_rate": 2.6186459706889876e-07,
+      "loss": 0.3953,
+      "step": 490
+    },
+    {
+      "epoch": 0.031873525849429464,
+      "grad_norm": 0.33532270789146423,
+      "learning_rate": 0.0,
+      "loss": 0.5542,
+      "step": 500
+    },
+    {
+      "epoch": 0.031873525849429464,
+      "eval_loss": 0.4364141821861267,
+      "eval_runtime": 696.1613,
+      "eval_samples_per_second": 9.489,
+      "eval_steps_per_second": 2.373,
+      "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": 1.557108689385554e+17,
+  "total_flos": 1.7292469676172902e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null