Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a09b06d5672cc3af0487a720566bb2e0f21c920af30411cfccb781ec93f1208
+oid sha256:18e7ffd682a482ff1151f4f52c4691f3f570c05ff139dc38ab32ccd4ea585e87
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a58f5aa8cdcb10c427ab588dab2fcea300b67fe3d26d8716226247cd98115c6
+oid sha256:2de8ddd015dc550f2b7b29dcd9c638b9861138e04a5323f56bdf46c5218d72f2
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
+oid sha256:f58b98283f0cf134b4005d9b921adb02a846a23631404be12129392a65cfe4e3
 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": 2.474599599838257,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04317323259579061,
+  "best_metric": 2.4719741344451904,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.053966540744738264,
   "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": 5.689,
       "eval_steps_per_second": 2.859,
       "step": 20
+    },
+    {
+      "epoch": 0.04533189422558014,
+      "grad_norm": 0.4824274480342865,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 2.461,
+      "step": 21
+    },
+    {
+      "epoch": 0.04749055585536967,
+      "grad_norm": 0.5804234147071838,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 2.3954,
+      "step": 22
+    },
+    {
+      "epoch": 0.0496492174851592,
+      "grad_norm": 0.4935641884803772,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 2.5672,
+      "step": 23
+    },
+    {
+      "epoch": 0.05180787911494873,
+      "grad_norm": 0.5770930051803589,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 2.5701,
+      "step": 24
+    },
+    {
+      "epoch": 0.053966540744738264,
+      "grad_norm": 0.590212881565094,
+      "learning_rate": 0.0,
+      "loss": 2.4887,
+      "step": 25
+    },
+    {
+      "epoch": 0.053966540744738264,
+      "eval_loss": 2.4719741344451904,
+      "eval_runtime": 33.3118,
+      "eval_samples_per_second": 5.854,
+      "eval_steps_per_second": 2.942,
+      "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": 6332408345395200.0,
+  "total_flos": 7915510431744000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null