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:f23d0780064bbab1ccdb905633151564803f8906ba910ccef298b9cef97f2812
+oid sha256:086c2895ac8e0d672b8f98be63c38e65d2ac8212e447feae93cd7aeb59bf059e
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07bbcc8c827083fddbb7316a1c3dfff70d03ebe42ece58f6f5091d6a660ef41
+oid sha256:0974bbf23be9e93934fb63e1afe90e90d291ac89bc874e24b0f7fc1b2c412bba
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:740b4d5b5706c9b622ccec788006a80e3bb923be218c04c7170c76a352dd6003
+oid sha256:070bdad6e7a6bcf08418efe6977e6e26c1dccf17e3ba16b2882b37a28bdc9794
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b638125345eee66261d2423c36c01b02453186ef536e9a5b8085fc8faa3a2a46
+oid sha256:5ca13c3530cb36506b3692f740061cffec6ee384ba8c3a08d5aff4eb57c1361e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7266805171966553,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.02031832035218422,
+  "best_metric": 2.7254714965820312,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.02257591150242691,
   "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": 50.135,
       "eval_steps_per_second": 12.537,
       "step": 450
+    },
+    {
+      "epoch": 0.020769838582232757,
+      "grad_norm": 3.088073968887329,
+      "learning_rate": 3.970676166322313e-06,
+      "loss": 2.602,
+      "step": 460
+    },
+    {
+      "epoch": 0.021221356812281295,
+      "grad_norm": 3.8279261589050293,
+      "learning_rate": 2.239870924784917e-06,
+      "loss": 2.5787,
+      "step": 470
+    },
+    {
+      "epoch": 0.021672875042329835,
+      "grad_norm": 4.529348373413086,
+      "learning_rate": 9.97522953989038e-07,
+      "loss": 2.6237,
+      "step": 480
+    },
+    {
+      "epoch": 0.022124393272378372,
+      "grad_norm": 4.052964210510254,
+      "learning_rate": 2.4968484836801973e-07,
+      "loss": 2.7617,
+      "step": 490
+    },
+    {
+      "epoch": 0.02257591150242691,
+      "grad_norm": 6.235555171966553,
+      "learning_rate": 0.0,
+      "loss": 2.8884,
+      "step": 500
+    },
+    {
+      "epoch": 0.02257591150242691,
+      "eval_loss": 2.7254714965820312,
+      "eval_runtime": 185.5313,
+      "eval_samples_per_second": 50.266,
+      "eval_steps_per_second": 12.569,
+      "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": 4059873906524160.0,
+  "total_flos": 4510470344540160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null