Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f23e600f9fad26718cbd615dca0737cc2bd215a75e65095e3d7cf52e01cc9a8
+oid sha256:e39e87a4adbed94a710d7612ffc749117f3c9f06b646e9651a73913e43f8ee51
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cabfc0d65a83d1fe22c72f79714294d0eecb3062dfd5977471a6446db972dfcb
+oid sha256:4da4000ad1380b6e4d1a8c8a7eeeae52a93a6d4c751a27825fc52e5834049534
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94fac44dc8c995de20631c5e197e088f33bf3b0b3901ea9028111f87bfa67634
+oid sha256:2190484cde7be8eacc78f6a3060ae47c01f6b373e3e020f3fd079582adf8cdce
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9345433712005615,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005951938099843761,
+  "best_metric": 2.918982982635498,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.007439922624804702,
   "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": 6.78,
       "eval_steps_per_second": 3.392,
       "step": 20
+    },
+    {
+      "epoch": 0.00624953500483595,
+      "grad_norm": 1.3665261268615723,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.6325,
+      "step": 21
+    },
+    {
+      "epoch": 0.006547131909828138,
+      "grad_norm": 1.5116671323776245,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.823,
+      "step": 22
+    },
+    {
+      "epoch": 0.006844728814820326,
+      "grad_norm": 1.0619993209838867,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.5133,
+      "step": 23
+    },
+    {
+      "epoch": 0.007142325719812514,
+      "grad_norm": 1.546810269355774,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.0059,
+      "step": 24
+    },
+    {
+      "epoch": 0.007439922624804702,
+      "grad_norm": 1.2780280113220215,
+      "learning_rate": 0.0,
+      "loss": 2.6926,
+      "step": 25
+    },
+    {
+      "epoch": 0.007439922624804702,
+      "eval_loss": 2.918982982635498,
+      "eval_runtime": 207.8276,
+      "eval_samples_per_second": 6.809,
+      "eval_steps_per_second": 3.407,
+      "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": 3884084921106432.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null