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:cd74738c4823ebe5d6ef8531d4aa468df7ddbb5c84c0639c5cf6466194177ba0
+oid sha256:4a511695045b625bfffa6f112801797fe08609cfbd30465e860c9963d8f8c639
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f66b43f55d296c38470154eabf82e3f79b87c172cc9dd7641f9f9fa20146f0
+oid sha256:ce54d97a826bf2307cb9bbd75ea032fa6959bbb620649ffde2a4ea807ae1c440
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e77cb26c5e81c86384eb2d4b3edda97766d2a7fc967a1dd2392dac4e5c28b9
+oid sha256:f4d10cefe9976c7f508f9d8e06d7587239a8c8673a878618976f7436e27616f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
+oid sha256:b3488300cc890b0bf0becbfdd6a3cc8770e6656a66feed4ec387a72a2b445721
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6946857571601868,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.03216123499142367,
+  "best_metric": 0.6936941742897034,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.0357347055460263,
   "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": 21.679,
       "eval_steps_per_second": 5.42,
       "step": 450
+    },
+    {
+      "epoch": 0.032875929102344194,
+      "grad_norm": 0.5253943204879761,
+      "learning_rate": 3.931937862260632e-06,
+      "loss": 1.1963,
+      "step": 460
+    },
+    {
+      "epoch": 0.033590623213264725,
+      "grad_norm": 0.5864456295967102,
+      "learning_rate": 2.2180185255187225e-06,
+      "loss": 1.3404,
+      "step": 470
+    },
+    {
+      "epoch": 0.03430531732418525,
+      "grad_norm": 0.8669192790985107,
+      "learning_rate": 9.877910227306082e-07,
+      "loss": 1.4906,
+      "step": 480
+    },
+    {
+      "epoch": 0.035020011435105775,
+      "grad_norm": 0.977800726890564,
+      "learning_rate": 2.472488986278439e-07,
+      "loss": 1.4202,
+      "step": 490
+    },
+    {
+      "epoch": 0.0357347055460263,
+      "grad_norm": 1.68795907497406,
+      "learning_rate": 0.0,
+      "loss": 1.6401,
+      "step": 500
+    },
+    {
+      "epoch": 0.0357347055460263,
+      "eval_loss": 0.6936941742897034,
+      "eval_runtime": 273.0352,
+      "eval_samples_per_second": 21.58,
+      "eval_steps_per_second": 5.395,
+      "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": 1.496822241558528e+17,
+  "total_flos": 1.66313582395392e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null