Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af04d18e4134b46a9a0895ab542b9c3456027e09170b7329e6eca48611aeffa
+oid sha256:6c4ef8094296d02a7107c055737ef3e663f3c4cae7d56d4ce0571856ef58d387
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa09760f408923f94fd1029a2eb68494cebe8d18e1abc6d9040da33552ab1de
+oid sha256:db2b5b9b6e41b92f2ef0a416b9d305a4a8a9cb2a8f52defde72c7d5739a69304
 size 203622650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e1816ae3370f89ccd7ca21572840bb755ebc45ccbed715a8dd0c0de6a21ed9
+oid sha256:0a485d484494d123d6b5dd3e1ede69a483d74a1255d08e10e8d67f3e0f00277d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.027435064315796,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017236550104496584,
+  "best_metric": 1.9577324390411377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0025854825156744875,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 6.725,
       "eval_steps_per_second": 3.363,
       "step": 20
+    },
+    {
+      "epoch": 0.0018098377609721413,
+      "grad_norm": 0.6979389190673828,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.098,
+      "step": 21
+    },
+    {
+      "epoch": 0.00206838601253959,
+      "grad_norm": 0.6137436032295227,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.9768,
+      "step": 24
+    },
+    {
+      "epoch": 0.002154568763062073,
+      "eval_loss": 1.970348596572876,
+      "eval_runtime": 727.1195,
+      "eval_samples_per_second": 6.72,
+      "eval_steps_per_second": 3.36,
+      "step": 25
+    },
+    {
+      "epoch": 0.002326934264107039,
+      "grad_norm": 0.5752513408660889,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.9468,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025854825156744875,
+      "grad_norm": 0.9238215088844299,
+      "learning_rate": 0.0,
+      "loss": 2.0248,
+      "step": 30
+    },
+    {
+      "epoch": 0.0025854825156744875,
+      "eval_loss": 1.9577324390411377,
+      "eval_runtime": 727.8641,
+      "eval_samples_per_second": 6.713,
+      "eval_steps_per_second": 3.356,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3745437159260160.0,
+  "total_flos": 5597576413839360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null