Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:586d0dfbf68de230ed980f2b3ae5236dc15225f117b6655abfd65b754c730744
+oid sha256:bdfc0aec5993c74c8dac8c2798fdfcf3512930b67c41a44b13ccb1149007aa37
 size 1216072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c052735840a45824349bf812b4a1b576719d3f977a3bb3efcf0b227c6bad665
+oid sha256:2814a4443e9c46e42c699fd711d34f8c35ed68d3f640143febe66e98579562b7
 size 1294548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f8f032f08cf8e4fc2860b5f74ff56ac730e3b85b1795c6de8fdcf7933541f6
+oid sha256:d8490748536ec4bdf51be10ef1ab65f4ca600ab4ad57425373a4691cb13c81b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de723127fb29334c1d5f5d4d0ba1d4e78fc916dfc4e8f6b4bb5846a069a13ba9
+oid sha256:9d89303aa828aaa9e241260e2ca606db088309d8b5a7ba3d79cb10ce1887994d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 9.231368064880371,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.529567519858782,
+  "best_metric": 9.23099136352539,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.706090026478376,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 456.443,
       "eval_steps_per_second": 114.111,
       "step": 450
+    },
+    {
+      "epoch": 0.5413356869667549,
+      "grad_norm": 0.5859640836715698,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 9.2368,
+      "step": 460
+    },
+    {
+      "epoch": 0.5531038540747278,
+      "grad_norm": 0.5664204955101013,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 9.2346,
+      "step": 470
+    },
+    {
+      "epoch": 0.5648720211827007,
+      "grad_norm": 0.5508027672767639,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 9.2328,
+      "step": 480
+    },
+    {
+      "epoch": 0.5766401882906738,
+      "grad_norm": 0.5547236204147339,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 9.2273,
+      "step": 490
+    },
+    {
+      "epoch": 0.5884083553986467,
+      "grad_norm": 0.5351949334144592,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 9.2272,
+      "step": 500
+    },
+    {
+      "epoch": 0.5884083553986467,
+      "eval_loss": 9.230931282043457,
+      "eval_runtime": 3.1481,
+      "eval_samples_per_second": 454.871,
+      "eval_steps_per_second": 113.718,
+      "step": 500
+    },
+    {
+      "epoch": 0.6001765225066196,
+      "grad_norm": 0.5742395520210266,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 9.2388,
+      "step": 510
+    },
+    {
+      "epoch": 0.6119446896145925,
+      "grad_norm": 0.5664268732070923,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 9.234,
+      "step": 520
+    },
+    {
+      "epoch": 0.6237128567225655,
+      "grad_norm": 0.5586317777633667,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 9.231,
+      "step": 530
+    },
+    {
+      "epoch": 0.6354810238305384,
+      "grad_norm": 0.5682714581489563,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 9.227,
+      "step": 540
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.5156871676445007,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 9.2246,
+      "step": 550
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "eval_loss": 9.23094654083252,
+      "eval_runtime": 3.1842,
+      "eval_samples_per_second": 449.718,
+      "eval_steps_per_second": 112.429,
+      "step": 550
+    },
+    {
+      "epoch": 0.6590173580464843,
+      "grad_norm": 0.5625162124633789,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 9.2384,
+      "step": 560
+    },
+    {
+      "epoch": 0.6707855251544572,
+      "grad_norm": 0.5742562413215637,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 9.2365,
+      "step": 570
+    },
+    {
+      "epoch": 0.6825536922624301,
+      "grad_norm": 0.5625633001327515,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 9.2344,
+      "step": 580
+    },
+    {
+      "epoch": 0.694321859370403,
+      "grad_norm": 0.5586168766021729,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 9.2276,
+      "step": 590
+    },
+    {
+      "epoch": 0.706090026478376,
+      "grad_norm": 0.5523204207420349,
+      "learning_rate": 0.0,
+      "loss": 9.2266,
+      "step": 600
+    },
+    {
+      "epoch": 0.706090026478376,
+      "eval_loss": 9.23099136352539,
+      "eval_runtime": 3.1361,
+      "eval_samples_per_second": 456.613,
+      "eval_steps_per_second": 114.153,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 96345136300032.0,
+  "total_flos": 128442497236992.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null