Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552171d36178e0f37f6a27475161147d57a0dbeac2624bf29f6c566431b4a6d7
+oid sha256:6be4cb24ff59f0e2b6f124eb67dedb1c25e6d77622b986e0579e85cb83e551ed
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22f8385a5f84d72cac1f8a0612a2c595bf3bb489ae90e3cb9de72a41afab01a
+oid sha256:f9ac564c54aa90ef9b6a54d4030e0797a637ab1cb0628e2f0673688fdff99dff
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36023d83828db86d8a053d500ce5d643eedfde8b879e596eeda08ddb29af1109
+oid sha256:92a807a3bd5c9d9c0a1533fdd9d34897d9e3a04bf0159f5901038370fc8f606a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4411721229553223,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.03751875937968985,
+  "best_metric": 1.4395215511322021,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.041687510421877606,
   "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": 17.108,
       "eval_steps_per_second": 4.279,
       "step": 450
+    },
+    {
+      "epoch": 0.038352509588127394,
+      "grad_norm": 1.432081699371338,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 2.6117,
+      "step": 460
+    },
+    {
+      "epoch": 0.03918625979656495,
+      "grad_norm": 1.6217148303985596,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 2.6554,
+      "step": 470
+    },
+    {
+      "epoch": 0.0400200100050025,
+      "grad_norm": 2.4671072959899902,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 3.0135,
+      "step": 480
+    },
+    {
+      "epoch": 0.04085376021344005,
+      "grad_norm": 3.2890851497650146,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 2.8535,
+      "step": 490
+    },
+    {
+      "epoch": 0.041687510421877606,
+      "grad_norm": 5.924061298370361,
+      "learning_rate": 0.0,
+      "loss": 3.2508,
+      "step": 500
+    },
+    {
+      "epoch": 0.041687510421877606,
+      "eval_loss": 1.4395215511322021,
+      "eval_runtime": 294.2333,
+      "eval_samples_per_second": 17.163,
+      "eval_steps_per_second": 4.293,
+      "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": 7.791715878017434e+16,
+  "total_flos": 8.664853729876378e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null