Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ae42795da762d57e91bc69f878cd228b0d33d8c7ddef1118343cb5abc278046
+oid sha256:a354d5612638437d1435fa8c6a6bbceb5ae0d93c056a4a91a4233c30b5572430
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdc647c3abc8dd079c58ddea42b3b9101a6889e4a73d8e5963e67058367b062
+oid sha256:8dd7bd1175931213422c4474948a85c47efd528e0f6ec422e608864bcebbf082
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd474099de92dc845d40d5927f170b424592df7fa8ed3e362e00c4d62a05861
+oid sha256:d49593ae7e22d09a07a09f52967b7e9139e11dc8b7b2354bdf8719302bca62c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
+oid sha256:200a199971193d5b4ec602093f689606117a65db31ca244b618fc0f0cd969846
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.072546362876892,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.31424581005586594,
+  "best_metric": 1.0717943906784058,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.34916201117318435,
   "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": 11.664,
       "eval_steps_per_second": 2.921,
       "step": 450
+    },
+    {
+      "epoch": 0.32122905027932963,
+      "grad_norm": 0.3935563862323761,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 0.8383,
+      "step": 460
+    },
+    {
+      "epoch": 0.32821229050279327,
+      "grad_norm": 0.3855022192001343,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 0.7788,
+      "step": 470
+    },
+    {
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.4132440984249115,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 0.7524,
+      "step": 480
+    },
+    {
+      "epoch": 0.34217877094972066,
+      "grad_norm": 0.4790831208229065,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 0.8183,
+      "step": 490
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "grad_norm": 1.258919596672058,
+      "learning_rate": 0.0,
+      "loss": 2.1397,
+      "step": 500
+    },
+    {
+      "epoch": 0.34916201117318435,
+      "eval_loss": 1.0717943906784058,
+      "eval_runtime": 52.0261,
+      "eval_samples_per_second": 11.59,
+      "eval_steps_per_second": 2.902,
+      "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": 1.2681469712400384e+17,
+  "total_flos": 1.408558478917632e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null