Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1948a1fe7b6ffe217f930dbc7092629d97c04adec70f098fa16b6dae1e3a4e28
+oid sha256:6014ebd33c503291024ec6f124d3042366a29bdbee277ffddb5fddee05ecf383
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749d38555ba580de274f55590478354e7ab395d15fb5892b188f9fd66d130b7f
+oid sha256:5c60e3cdee8c3e6c6d9f6ee834f3fe934375da61bc0e011e2e2b309a305ea4fe
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f760f9a1410cf17fff48f1f37b58e9c594f8c3f120c35016c9434be2131aa74a
+oid sha256:b2abb6a37eadaa060f9c072797c71506a0370030b9f1277990d6e4bd1fccfea2
 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": 1.5477936267852783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07136485280999108,
+  "best_metric": 1.4500839710235596,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.10704727921498662,
   "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": 9.736,
       "eval_steps_per_second": 2.434,
       "step": 20
+    },
+    {
+      "epoch": 0.07493309545049064,
+      "grad_norm": 11.966535568237305,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.785,
+      "step": 21
+    },
+    {
+      "epoch": 0.08563782337198929,
+      "grad_norm": 9.986099243164062,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.7129,
+      "step": 24
+    },
+    {
+      "epoch": 0.08920606601248884,
+      "eval_loss": 1.4632445573806763,
+      "eval_runtime": 24.1718,
+      "eval_samples_per_second": 9.763,
+      "eval_steps_per_second": 2.441,
+      "step": 25
+    },
+    {
+      "epoch": 0.09634255129348795,
+      "grad_norm": 16.059425354003906,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.0728,
+      "step": 27
+    },
+    {
+      "epoch": 0.10704727921498662,
+      "grad_norm": 14.310097694396973,
+      "learning_rate": 0.0,
+      "loss": 7.0192,
+      "step": 30
+    },
+    {
+      "epoch": 0.10704727921498662,
+      "eval_loss": 1.4500839710235596,
+      "eval_runtime": 24.1501,
+      "eval_samples_per_second": 9.772,
+      "eval_steps_per_second": 2.443,
+      "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": 1.306916403806208e+16,
+  "total_flos": 1.960374605709312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null