Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945fc7eece7cc22e8ef95aed85d8dbf3a10057831eb21355b1f223d8c267c3fb
+oid sha256:3beb57f93171a5793680a9181e4e7305ef7c5da9168648fac2cb1c7645e2265b
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931f2ae219ced8c9a837e938eabdcdc2e3325b89bac538566f7944c38980d852
+oid sha256:6fe9da49fbfa321a3c5acc6ffbf80cdf51f7dd77a334ccafd26f90febe5ebd15
 size 102009558

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9d1ebf09b505f76dee426288bfee7734b789b5ffb4a889d3987eebbc6d9d6ae
+oid sha256:e9a0d0d36a7ef0b460d4a0320ee966a859fe34dffbb66a56fda32233acec2517
 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": 2.433856248855591,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0015338893682293165,
+  "best_metric": 2.425968647003174,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0019173617102866455,
   "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": 13.16,
       "eval_steps_per_second": 6.58,
       "step": 20
+    },
+    {
+      "epoch": 0.0016105838366407823,
+      "grad_norm": 0.5742405652999878,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 2.3185,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016872783050522482,
+      "grad_norm": 0.7196751236915588,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 2.5311,
+      "step": 22
+    },
+    {
+      "epoch": 0.001763972773463714,
+      "grad_norm": 0.8010265231132507,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 2.3778,
+      "step": 23
+    },
+    {
+      "epoch": 0.0018406672418751796,
+      "grad_norm": 0.5996159315109253,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 2.4828,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019173617102866455,
+      "grad_norm": 0.6843820810317993,
+      "learning_rate": 0.0,
+      "loss": 2.3326,
+      "step": 25
+    },
+    {
+      "epoch": 0.0019173617102866455,
+      "eval_loss": 2.425968647003174,
+      "eval_runtime": 417.4573,
+      "eval_samples_per_second": 13.151,
+      "eval_steps_per_second": 6.576,
+      "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": 2562652078080000.0,
+  "total_flos": 3177688576819200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null