Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:634856382964ad884b5cb0e39c8a78aa46afe605ba6c9c16679ae3019fa5cced
+oid sha256:a7603b8f2c0d375e477066e332892181d53de56a16b9fa86c2103226518aa34a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bbfee61ec6b58ae140b18174bf67af33194ebac6bcd77a6543737b23697c05
+oid sha256:36183f59e3b36dd30372475cbd64202881ada8f5ee14b42728112a18428c29d7
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
+oid sha256:315f214c6e0b8fd03acec16280ddc948e89968dbe8e150005ce6867f765b6871
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.217616558074951,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.044370493621741544,
+  "best_metric": 4.198707103729248,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.05546311702717693,
   "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": 5.648,
       "eval_steps_per_second": 2.824,
       "step": 20
+    },
+    {
+      "epoch": 0.04658901830282862,
+      "grad_norm": 4.145676136016846,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 3.9516,
+      "step": 21
+    },
+    {
+      "epoch": 0.048807542983915694,
+      "grad_norm": 3.771132469177246,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 3.8903,
+      "step": 22
+    },
+    {
+      "epoch": 0.051026067665002776,
+      "grad_norm": 2.8407840728759766,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 3.9793,
+      "step": 23
+    },
+    {
+      "epoch": 0.05324459234608985,
+      "grad_norm": 2.948822498321533,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 3.5158,
+      "step": 24
+    },
+    {
+      "epoch": 0.05546311702717693,
+      "grad_norm": 4.163925647735596,
+      "learning_rate": 0.0,
+      "loss": 3.9669,
+      "step": 25
+    },
+    {
+      "epoch": 0.05546311702717693,
+      "eval_loss": 4.198707103729248,
+      "eval_runtime": 33.5933,
+      "eval_samples_per_second": 5.656,
+      "eval_steps_per_second": 2.828,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null