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:ff476ffa0821524fe14e333ea863933e1ad45c236bb668c02dca26f8e38e9257
+oid sha256:281d09d165720d44ef1ca8a9ea15bf576640e33357d43c79ae08a13e4263dfbd
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a627eebb032cb54e9cc98b4837acd719127c52c9bd55ee9357fadc1e95a5f608
+oid sha256:33ccddd447dde71a680cb9a9ca7103a3a79cf95c34a2413b7db1ff122a0a99b0
 size 250679090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be70d832a1bbff101f33c955af2006518b5495f9530a45087a280e66288a93d
+oid sha256:23ba6f4e1ddd9457b39425bc60bf390070addbb761f15a038321aac470417dab
 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": 0.48243945837020874,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03885381253035454,
+  "best_metric": 0.4723750054836273,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.04856726566294318,
   "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": 4.988,
       "eval_steps_per_second": 2.505,
       "step": 20
+    },
+    {
+      "epoch": 0.04079650315687227,
+      "grad_norm": 1.2976908683776855,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.2973,
+      "step": 21
+    },
+    {
+      "epoch": 0.042739193783389993,
+      "grad_norm": 2.772876501083374,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1802,
+      "step": 22
+    },
+    {
+      "epoch": 0.044681884409907724,
+      "grad_norm": 1.1275978088378906,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.5172,
+      "step": 23
+    },
+    {
+      "epoch": 0.04662457503642545,
+      "grad_norm": 2.216585159301758,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.9489,
+      "step": 24
+    },
+    {
+      "epoch": 0.04856726566294318,
+      "grad_norm": 1.3420172929763794,
+      "learning_rate": 0.0,
+      "loss": 1.4192,
+      "step": 25
+    },
+    {
+      "epoch": 0.04856726566294318,
+      "eval_loss": 0.4723750054836273,
+      "eval_runtime": 43.4128,
+      "eval_samples_per_second": 4.999,
+      "eval_steps_per_second": 2.511,
+      "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": 6332448610713600.0,
+  "total_flos": 7915560763392000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null