Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4073ae6ecfb4dd3196400faa077500f4ba9b24079cb7f760756d1b8dcb693f01
+oid sha256:441d5991b7c6b1378e9dea04d5340e9883d1313e255d731fa3fb4ea3ae1b6905
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90695b9f80674a3bb92f2f1a8f285da78790a90cd125f7716bea672b1b65a62e
+oid sha256:c8ee0a70819dcd53a4097b622f9432239704753863cce424311f7154c2625add
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63e4b0558fdd27217553fdf0cf82ec203f491002d24f65f37f3400883c0715c
+oid sha256:76038f8ff2178c5a6a26d376f0b2810321247244d468de5be516366ad003d908
 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": 11.736717224121094,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.021138669673055242,
+  "best_metric": 11.736602783203125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.02348741074783916,
   "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": 54.909,
       "eval_steps_per_second": 13.727,
       "step": 450
+    },
+    {
+      "epoch": 0.021608417888012026,
+      "grad_norm": 0.07166286557912827,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 11.8053,
+      "step": 460
+    },
+    {
+      "epoch": 0.02207816610296881,
+      "grad_norm": 0.08675435185432434,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 11.8144,
+      "step": 470
+    },
+    {
+      "epoch": 0.02254791431792559,
+      "grad_norm": 0.1228862851858139,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 11.7993,
+      "step": 480
+    },
+    {
+      "epoch": 0.023017662532882375,
+      "grad_norm": 0.13015829026699066,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 11.6779,
+      "step": 490
+    },
+    {
+      "epoch": 0.02348741074783916,
+      "grad_norm": 0.17222419381141663,
+      "learning_rate": 0.0,
+      "loss": 11.5984,
+      "step": 500
+    },
+    {
+      "epoch": 0.02348741074783916,
+      "eval_loss": 11.736602783203125,
+      "eval_runtime": 162.8513,
+      "eval_samples_per_second": 55.044,
+      "eval_steps_per_second": 13.761,
+      "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": 81119379456000.0,
+  "total_flos": 89864847360000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null