Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6a7d2d6f241d7b191ceba7da340ce6f73393738536ce9a3bcbc2b9c10e60b3
+oid sha256:c8c65489a5ac3e7792d33d5db54a2843eebb5da3b2b3cfc8f0376019932489aa
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbf897d2ababa82d1821ae33dcf01997684697f95c347319ca00bf1d8c94a7b8
+oid sha256:29745285941fe15e4c3f3b6865ea23d1308a4a54f875192b6a23a6be2f07cbd0
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
+oid sha256:705deedf796b313cb76cd6c14cb7b94da899d809f9d9c1109db82fbb592f3b6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.88244366645813,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0003900517306107723,
+  "best_metric": 3.839513063430786,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0005850775959161584,
   "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": 29.335,
       "eval_steps_per_second": 14.667,
       "step": 20
+    },
+    {
+      "epoch": 0.00040955431714131084,
+      "grad_norm": 22.563886642456055,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 15.521,
+      "step": 21
+    },
+    {
+      "epoch": 0.0004680620767329267,
+      "grad_norm": 8.729718208312988,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 15.695,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004875646632634653,
+      "eval_loss": 3.8451759815216064,
+      "eval_runtime": 737.0999,
+      "eval_samples_per_second": 29.29,
+      "eval_steps_per_second": 14.645,
+      "step": 25
+    },
+    {
+      "epoch": 0.0005265698363245426,
+      "grad_norm": 10.4032564163208,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 15.0216,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005850775959161584,
+      "grad_norm": 8.15900993347168,
+      "learning_rate": 0.0,
+      "loss": 15.2282,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005850775959161584,
+      "eval_loss": 3.839513063430786,
+      "eval_runtime": 735.1733,
+      "eval_samples_per_second": 29.367,
+      "eval_steps_per_second": 14.684,
+      "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": 303370988421120.0,
+  "total_flos": 455056482631680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null