Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd59cc37c01e371a95eb2d0658162ad360f53603d8c21065f49d74c625c47dd
+oid sha256:73bfbf2ac983b311095d86ba60d91641513e9d05dde15e49e1c7b5776b2e0edf
 size 608282672

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02634bdb3e98cef96461ceed468b5470bbe070408556bd4cfec2ab82673ca362
+oid sha256:fb5d5875cf5c9270eaa55da9668d1ba437ccf55f2a225357857370e8929ff32f
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5b95f764d72ed6aa17d7197e22e16e0cc217530d7d3f18f36eafb2b4ceb1e32
+oid sha256:d52950ec15e966e18aaf7209ff00250eaac59d546ed773da760f76891e528d13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a866955cff9370cd3957339d6bf23f5ca8494fc491b0c5ef9330a9273b5d4460
+oid sha256:1c8e87504e3807136188d9860a28acbec106160a24a8674e04169e93f2e42104
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.714054524898529,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1350",
-  "epoch": 2.4226110363391653,
+  "best_metric": 0.7140275239944458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
+  "epoch": 2.6917900403768504,
   "eval_steps": 150,
-  "global_step": 1350,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1032,6 +1032,119 @@
       "eval_samples_per_second": 9.861,
       "eval_steps_per_second": 1.239,
       "step": 1350
+    },
+    {
+      "epoch": 2.4405563032750113,
+      "grad_norm": 5.729117393493652,
+      "learning_rate": 6.847762393717782e-07,
+      "loss": 2.9529,
+      "step": 1360
+    },
+    {
+      "epoch": 2.458501570210857,
+      "grad_norm": 3.2370126247406006,
+      "learning_rate": 5.910696692505202e-07,
+      "loss": 2.3974,
+      "step": 1370
+    },
+    {
+      "epoch": 2.4764468371467023,
+      "grad_norm": 3.672769546508789,
+      "learning_rate": 5.041267081295648e-07,
+      "loss": 2.4916,
+      "step": 1380
+    },
+    {
+      "epoch": 2.4943921040825483,
+      "grad_norm": 3.912321090698242,
+      "learning_rate": 4.239881673794166e-07,
+      "loss": 2.6173,
+      "step": 1390
+    },
+    {
+      "epoch": 2.512337371018394,
+      "grad_norm": 4.756332874298096,
+      "learning_rate": 3.5069166434870014e-07,
+      "loss": 2.8032,
+      "step": 1400
+    },
+    {
+      "epoch": 2.5302826379542394,
+      "grad_norm": 5.58614444732666,
+      "learning_rate": 2.8427160470641255e-07,
+      "loss": 2.931,
+      "step": 1410
+    },
+    {
+      "epoch": 2.5482279048900853,
+      "grad_norm": 3.3309953212738037,
+      "learning_rate": 2.2475916629177418e-07,
+      "loss": 2.5066,
+      "step": 1420
+    },
+    {
+      "epoch": 2.566173171825931,
+      "grad_norm": 3.625159502029419,
+      "learning_rate": 1.7218228447922869e-07,
+      "loss": 2.3303,
+      "step": 1430
+    },
+    {
+      "epoch": 2.5841184387617764,
+      "grad_norm": 4.057403087615967,
+      "learning_rate": 1.2656563906545903e-07,
+      "loss": 2.6747,
+      "step": 1440
+    },
+    {
+      "epoch": 2.6020637056976224,
+      "grad_norm": 4.8578877449035645,
+      "learning_rate": 8.793064268460605e-08,
+      "loss": 2.7823,
+      "step": 1450
+    },
+    {
+      "epoch": 2.620008972633468,
+      "grad_norm": 5.646084308624268,
+      "learning_rate": 5.629543075708177e-08,
+      "loss": 2.9719,
+      "step": 1460
+    },
+    {
+      "epoch": 2.6379542395693134,
+      "grad_norm": 3.3096609115600586,
+      "learning_rate": 3.1674852976734116e-08,
+      "loss": 2.5002,
+      "step": 1470
+    },
+    {
+      "epoch": 2.6558995065051594,
+      "grad_norm": 3.604172706604004,
+      "learning_rate": 1.4080466340349318e-08,
+      "loss": 2.3697,
+      "step": 1480
+    },
+    {
+      "epoch": 2.673844773441005,
+      "grad_norm": 4.091582298278809,
+      "learning_rate": 3.520529722738086e-09,
+      "loss": 2.7008,
+      "step": 1490
+    },
+    {
+      "epoch": 2.6917900403768504,
+      "grad_norm": 4.5670952796936035,
+      "learning_rate": 0.0,
+      "loss": 2.6918,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6917900403768504,
+      "eval_loss": 0.7140275239944458,
+      "eval_runtime": 95.2168,
+      "eval_samples_per_second": 9.862,
+      "eval_steps_per_second": 1.239,
+      "step": 1500
     }
   ],
   "logging_steps": 10,
@@ -1055,12 +1168,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.50754898332536e+18,
+  "total_flos": 2.78587342489387e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null