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:b9f87dc6b75a380ed80b95bf61924458edbc33996e29822eb7a6726f816cbc2c
+oid sha256:e99166e3515d25162a07a4ba53ecead488736c85e753ef4fc02735d843617e28
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbbcdd271f0c303c4b0c747d5b833a00167e3a0c9779854591596988e47ea7b
+oid sha256:6097cd1a6460f7dbbce1a454fa9130b521524982d5a9773ef0c52e8b3b707866
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9f4f865baf06eb823312a9056f18c15ef3a4a7ab84c439f959bc428a8bda63
+oid sha256:9992fc8cb8360837abc3226b80fc40fd86910c76bd7c2f304b436c9b51562cb6
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
+oid sha256:043092824777602976966449c2a2a96527a878ad10507a3b4d0f461ea2b8d14e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0043394565582275,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.11155180961824492,
+  "best_metric": 2.0007903575897217,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.12394645513138325,
   "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": 52.34,
       "eval_steps_per_second": 13.093,
       "step": 450
+    },
+    {
+      "epoch": 0.11403073872087258,
+      "grad_norm": 4.045068740844727,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 2.1476,
+      "step": 460
+    },
+    {
+      "epoch": 0.11650966782350025,
+      "grad_norm": 3.5638298988342285,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 2.0023,
+      "step": 470
+    },
+    {
+      "epoch": 0.11898859692612791,
+      "grad_norm": 4.670226573944092,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 2.0953,
+      "step": 480
+    },
+    {
+      "epoch": 0.12146752602875557,
+      "grad_norm": 3.35652756690979,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 2.101,
+      "step": 490
+    },
+    {
+      "epoch": 0.12394645513138325,
+      "grad_norm": 3.9960343837738037,
+      "learning_rate": 0.0,
+      "loss": 1.9871,
+      "step": 500
+    },
+    {
+      "epoch": 0.12394645513138325,
+      "eval_loss": 2.0007903575897217,
+      "eval_runtime": 32.4677,
+      "eval_samples_per_second": 52.329,
+      "eval_steps_per_second": 13.09,
+      "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": 4055367942144000.0,
+  "total_flos": 4505964380160000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null