Training in progress, step 53, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00c7e2ca2f7201416ee0db7548754ff0b7dad3573e16f5759f340b0edf91035
+oid sha256:708c6aadb9f8e545ae09f3bba3ce8a552f118e32dfe7c81df3bcce7d994d683e
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80645b0c4593e3ffa5f299466cc99572408a8e260842bda9dc94271f7e380e52
+oid sha256:22f988dddbf3a0b9f9e83b72b1af9a63168ed0e2c88f9190a770903f57b79541
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59a5254780d448320ee839ee90bfa0ce534a45ff625b1caabb810d268fac3ee
+oid sha256:0b4464714bdff05cee69b1f8c55cac8fa8134b444386c23de5a63fd21314eaab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7e76384fe2e1907e44b199e48722ea251cbbcfea1285f875115318fffa6d887
+oid sha256:62186d98e2e1a228b1a77580a02e85af5559d427fe6308d24fc721da049c3720
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.704846203327179,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.857142857142857,
+  "epoch": 3.0285714285714285,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 53,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,27 @@
       "eval_samples_per_second": 7.18,
       "eval_steps_per_second": 1.915,
       "step": 50
+    },
+    {
+      "epoch": 2.914285714285714,
+      "grad_norm": 0.2923741936683655,
+      "learning_rate": 5.328315962444874e-07,
+      "loss": 0.6826,
+      "step": 51
+    },
+    {
+      "epoch": 2.9714285714285715,
+      "grad_norm": 0.29426372051239014,
+      "learning_rate": 1.333858168224178e-07,
+      "loss": 0.6043,
+      "step": 52
+    },
+    {
+      "epoch": 3.0285714285714285,
+      "grad_norm": 0.29648035764694214,
+      "learning_rate": 0.0,
+      "loss": 0.6566,
+      "step": 53
     }
   ],
   "logging_steps": 1,
@@ -428,12 +449,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.92436412350464e+16,
+  "total_flos": 2.0398259709149184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null