Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2626fe35e6f83de99f058fbe7858cfb48ff4077837213d14a418ba4721bfb4ae
+oid sha256:fff52d18fd3720d6c57ba0215230f43ae3b31950334273821c9769bdd3c87f2b
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94f83497f051a6aefa1401f944ba5ae9c11134faca09b09cb64d72d9ff8c979
+oid sha256:e3b59b04315a89e1df4f3154c6f1ab8b960a1a3ccee1f8b7e31db94ce2944ec1
 size 74090938

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb21cbb22e6af7a5398ea007cced10baef621a5b7ab52ee9cbe09f3a9941c3d
+oid sha256:e4f01f48df822ac93510ce23ec308f3426185194a3baa88c94e047d3edea0445
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2963515520095825,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00909090909090909,
+  "best_metric": 1.2940274477005005,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.011363636363636364,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 12.084,
       "eval_steps_per_second": 6.049,
       "step": 20
+    },
+    {
+      "epoch": 0.009545454545454546,
+      "grad_norm": 0.27244335412979126,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.2956,
+      "step": 21
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.329553484916687,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0757,
+      "step": 22
+    },
+    {
+      "epoch": 0.010454545454545454,
+      "grad_norm": 0.3100622296333313,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1361,
+      "step": 23
+    },
+    {
+      "epoch": 0.01090909090909091,
+      "grad_norm": 0.2915355861186981,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.0331,
+      "step": 24
+    },
+    {
+      "epoch": 0.011363636363636364,
+      "grad_norm": 0.293474018573761,
+      "learning_rate": 0.0,
+      "loss": 1.4389,
+      "step": 25
+    },
+    {
+      "epoch": 0.011363636363636364,
+      "eval_loss": 1.2940274477005005,
+      "eval_runtime": 82.6057,
+      "eval_samples_per_second": 11.222,
+      "eval_steps_per_second": 5.617,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1045861883707392.0,
+  "total_flos": 1313407946981376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null