Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1920f8c571933f387f8ec7d606e7671d9d8d814ac7fee9d7ea0b3259c9e61db7
+oid sha256:5ee3bf8840ac90cb087d2223f83cd34ab36052add89c9b480917ac8cf925d91f
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8e1f9c2814ada4cc2941c2f239c9f875c037e65e9f8eb1533ae01078ff1a68
+oid sha256:db9696211b4df3077708caa7416b616817cb62670eea134fc2f7a1ca36d4b99b
 size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da029d306d5935dd72183ce162ddaebbaf1460e4f1049d17fe9222fec1918c1e
+oid sha256:1c662b5f0f687b4f0eff942d3b8188f63f868fb4de5b5eeed3a458db74f891da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1962662935256958,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07640067911714771,
+  "best_metric": 1.1944663524627686,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.08488964346349745,
   "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": 5.269,
       "eval_steps_per_second": 1.317,
       "step": 450
+    },
+    {
+      "epoch": 0.07809847198641766,
+      "grad_norm": 0.7613552212715149,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 1.2263,
+      "step": 460
+    },
+    {
+      "epoch": 0.07979626485568761,
+      "grad_norm": 0.7208029627799988,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 1.2039,
+      "step": 470
+    },
+    {
+      "epoch": 0.08149405772495756,
+      "grad_norm": 0.8188151121139526,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 1.2092,
+      "step": 480
+    },
+    {
+      "epoch": 0.0831918505942275,
+      "grad_norm": 0.7839704751968384,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 1.2678,
+      "step": 490
+    },
+    {
+      "epoch": 0.08488964346349745,
+      "grad_norm": 1.197765588760376,
+      "learning_rate": 0.0,
+      "loss": 1.2776,
+      "step": 500
+    },
+    {
+      "epoch": 0.08488964346349745,
+      "eval_loss": 1.1944663524627686,
+      "eval_runtime": 235.1406,
+      "eval_samples_per_second": 5.273,
+      "eval_steps_per_second": 1.318,
+      "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": 1.439229472187351e+17,
+  "total_flos": 1.589424290959196e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null