Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36572c137b1d8c96f1e00a71c832b2a779eac3730a313984fed46a085fcad8e3
+oid sha256:b382667af2cc431ee4ee3731153dad6d001ef60ad5fc30f8ee5d3f562c4614ee
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e633e89b8932ccd22cd4eaeaa7d3a8a30d57e2c9c40bbe70d079fa844e781c
+oid sha256:6d877c845caca307619c8594d31a818ff9881eb05a9ae8fa0839c75f78a90989
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f77f55897c8bda578064e6179328ae1db2a437c75d4e7808f4292255b9e0eab
+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": 1.8922895193099976,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.011368480886741509,
+  "best_metric": 1.8816559314727783,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.014210601108426887,
   "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": 6.586,
       "eval_steps_per_second": 3.297,
       "step": 20
+    },
+    {
+      "epoch": 0.011936904931078584,
+      "grad_norm": 2.4007904529571533,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.2827,
+      "step": 21
+    },
+    {
+      "epoch": 0.01250532897541566,
+      "grad_norm": 1.4869282245635986,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.9821,
+      "step": 22
+    },
+    {
+      "epoch": 0.013073753019752736,
+      "grad_norm": 2.110950469970703,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.3384,
+      "step": 23
+    },
+    {
+      "epoch": 0.013642177064089812,
+      "grad_norm": 1.8079794645309448,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.7424,
+      "step": 24
+    },
+    {
+      "epoch": 0.014210601108426887,
+      "grad_norm": 1.7480032444000244,
+      "learning_rate": 0.0,
+      "loss": 1.6511,
+      "step": 25
+    },
+    {
+      "epoch": 0.014210601108426887,
+      "eval_loss": 1.8816559314727783,
+      "eval_runtime": 109.8328,
+      "eval_samples_per_second": 6.747,
+      "eval_steps_per_second": 3.378,
+      "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": 3837845814902784.0,
+  "total_flos": 4808867045179392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null