Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536270091c26545985f0b4a49f015a4d34d89e35628d561bb3c5daca719492bb
+oid sha256:4da09cba9ff3d212a6c388d07a5adb1f1b628f268c11807cd5eb8ec9629b6a3e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957090016edbdd4fc2bf7b8a540e97baf1b093de6b6094415f156f1deb72cff2
+oid sha256:e03d7c56136a42f04c19d50035463ce5e5e45c48b6bb64f74c28346bed107559
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5afc85f5d22d31bbcb902635ba8c160003572d12eb86367ff5593ce490ad2af
+oid sha256:b3543124cf942727529eb193c402eb6aa5516febd017ee74db085a7cb22b628c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2255158424377441,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.002733454060887689,
+  "best_metric": 1.2092185020446777,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.004100181091331534,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.734,
       "eval_steps_per_second": 1.868,
       "step": 20
+    },
+    {
+      "epoch": 0.0028701267639320736,
+      "grad_norm": 0.258678674697876,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.061,
+      "step": 21
+    },
+    {
+      "epoch": 0.003280144873065227,
+      "grad_norm": 0.3215930759906769,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.9596,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034168175761096113,
+      "eval_loss": 1.2115516662597656,
+      "eval_runtime": 826.0756,
+      "eval_samples_per_second": 3.73,
+      "eval_steps_per_second": 1.865,
+      "step": 25
+    },
+    {
+      "epoch": 0.0036901629821983802,
+      "grad_norm": 0.26366937160491943,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.9283,
+      "step": 27
+    },
+    {
+      "epoch": 0.004100181091331534,
+      "grad_norm": 0.3247816562652588,
+      "learning_rate": 0.0,
+      "loss": 1.1581,
+      "step": 30
+    },
+    {
+      "epoch": 0.004100181091331534,
+      "eval_loss": 1.2092185020446777,
+      "eval_runtime": 827.9915,
+      "eval_samples_per_second": 3.721,
+      "eval_steps_per_second": 1.861,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.32218823376896e+16,
+  "total_flos": 1.677526321594368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null