Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c13b4bb684e58547d7caddcb687698fe3eff6e5d5b40ed155c4b1fb50a8001e
+oid sha256:6265f445046190619845cea109ee427d37eee0f2ab61719eeaabb70903d6472c
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f05ff467629f5e2cf3bf75768ac1b89242e030cef2b5a76f17d5b4ae7389b16
+oid sha256:bfe019dff0bd6b36689008f65e061ea67bd7598cae5a51f0c2f2cd8def3f9d5a
 size 13005370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7df6bf58b77fa0076f446f1f43ed7bccf4e646a2b1b005aa9e5da142e7c846
+oid sha256:4427beaeac36b979afda96d09557802e1ea60b6f59b7f3341e894978bf50533c
 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": 2.8470160961151123,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.004344593877019029,
+  "best_metric": 2.8458566665649414,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.004827326530021144,
   "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": 69.032,
       "eval_steps_per_second": 17.258,
       "step": 450
+    },
+    {
+      "epoch": 0.004441140407619453,
+      "grad_norm": 12.585321426391602,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 5.103,
+      "step": 460
+    },
+    {
+      "epoch": 0.004537686938219875,
+      "grad_norm": 12.552547454833984,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 5.1533,
+      "step": 470
+    },
+    {
+      "epoch": 0.004634233468820298,
+      "grad_norm": 13.851476669311523,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 5.6343,
+      "step": 480
+    },
+    {
+      "epoch": 0.004730779999420721,
+      "grad_norm": 20.92866325378418,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 6.2419,
+      "step": 490
+    },
+    {
+      "epoch": 0.004827326530021144,
+      "grad_norm": 93.0564956665039,
+      "learning_rate": 0.0,
+      "loss": 6.9058,
+      "step": 500
+    },
+    {
+      "epoch": 0.004827326530021144,
+      "eval_loss": 2.8458566665649414,
+      "eval_runtime": 599.551,
+      "eval_samples_per_second": 72.741,
+      "eval_steps_per_second": 18.185,
+      "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": 4695013057363968.0,
+  "total_flos": 5203897601753088.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null