Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000f8d59e91398b299db62a0b970ec4c5e4be9dc03572c086d75b63bc702a18c
+oid sha256:34e0441628bbc29a4bda068f89acb4d4ca15354ac93f9b5153d816467c7b7b0e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde24050a1800b37cafa7c993ea8124ffde66a948d31eca58f18fe1536ef4c8a
+oid sha256:adfa179bab632f23d8a4138c0a83fe939f552452751b42e136a29b9a4e20e0ef
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d210b5a0f985fad87fbe764348781a2d914602ba6d39d457cd70061e51a223e
+oid sha256:28b039862ad1fd757ec428712bbb21e04d974f29e0b2df4fddfbd07926b6a766
 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": 0.6699627041816711,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005028600163429505,
+  "best_metric": 0.6556719541549683,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007542900245144258,
   "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": 2.333,
       "eval_steps_per_second": 1.167,
       "step": 20
+    },
+    {
+      "epoch": 0.005280030171600981,
+      "grad_norm": 0.5908681750297546,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.1488,
+      "step": 21
+    },
+    {
+      "epoch": 0.006034320196115406,
+      "grad_norm": 0.44172340631484985,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.1604,
+      "step": 24
+    },
+    {
+      "epoch": 0.006285750204286881,
+      "eval_loss": 0.6572626233100891,
+      "eval_runtime": 718.6909,
+      "eval_samples_per_second": 2.331,
+      "eval_steps_per_second": 1.166,
+      "step": 25
+    },
+    {
+      "epoch": 0.006788610220629833,
+      "grad_norm": 0.2915555536746979,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.1682,
+      "step": 27
+    },
+    {
+      "epoch": 0.007542900245144258,
+      "grad_norm": 0.2986396849155426,
+      "learning_rate": 0.0,
+      "loss": 3.0264,
+      "step": 30
+    },
+    {
+      "epoch": 0.007542900245144258,
+      "eval_loss": 0.6556719541549683,
+      "eval_runtime": 717.7915,
+      "eval_samples_per_second": 2.334,
+      "eval_steps_per_second": 1.167,
+      "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": 1.306929288708096e+16,
+  "total_flos": 1.960393933062144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null