Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b39f0d00a6ad653a37273b08acd155f65d9bb6824cc5c7298ba93a3f8499f2
+oid sha256:33439d50bdafb6a186a49b1a9646d3b4b87b8e2c210de72c2cce77858e862178
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc592481b118a6c1ba8f5fbd0875b0a458f9d1b8668422da2b997ca77945573f
+oid sha256:825acdfe64c1726cfd56584ba36c77b961baa25891a3ee114c25c9e13f3dfa70
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776c795d5ce00acdc5c227779c9000600f2c67c8f31649cef8f2748ee86585da
+oid sha256:ec84973a8c4546012ec27d66888bce107d62db391365a89b423e98fa2bb4e15b
 size 14244

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": 1.2887566089630127,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.062107515009316126,
+  "best_metric": 1.2874583005905151,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.06900835001035126,
   "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": 15.722,
       "eval_steps_per_second": 3.932,
       "step": 450
+    },
+    {
+      "epoch": 0.06348768200952315,
+      "grad_norm": 1.1596732139587402,
+      "learning_rate": 3.912568710229791e-06,
+      "loss": 0.9878,
+      "step": 460
+    },
+    {
+      "epoch": 0.06486784900973018,
+      "grad_norm": 1.447120189666748,
+      "learning_rate": 2.2070923258856255e-06,
+      "loss": 1.279,
+      "step": 470
+    },
+    {
+      "epoch": 0.0662480160099372,
+      "grad_norm": 1.357725739479065,
+      "learning_rate": 9.829250571013935e-07,
+      "loss": 1.2906,
+      "step": 480
+    },
+    {
+      "epoch": 0.06762818301014423,
+      "grad_norm": 1.5343546867370605,
+      "learning_rate": 2.4603092375775605e-07,
+      "loss": 1.3415,
+      "step": 490
+    },
+    {
+      "epoch": 0.06900835001035126,
+      "grad_norm": 1.877431869506836,
+      "learning_rate": 0.0,
+      "loss": 1.4312,
+      "step": 500
+    },
+    {
+      "epoch": 0.06900835001035126,
+      "eval_loss": 1.2874583005905151,
+      "eval_runtime": 194.3711,
+      "eval_samples_per_second": 15.697,
+      "eval_steps_per_second": 3.925,
+      "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": 8.862517275131904e+16,
+  "total_flos": 9.84305110131671e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null