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:ec4edec1d31d4d3b2e6f85e1c08921fc14070f491a661be34f1783f6a0c26c54
+oid sha256:498c50b4cc520feda8ed9232e9b148c491e703b5a516a2bd9e445adb28fb1fa6
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bef635eb48d9584516f999c203ecba9097220e490279e5bd5bf60b60de7d45c
+oid sha256:10bbea4812de78cf60afaff521693fa917c0d447e2e1f0bdeaf3c86a99640fa6
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b5f447fdf5275d96a8aa3fd1a386234c8c0b0a0ddf0d4ee97f8353919167c5
+oid sha256:15591282530628074d1abaa01e0c13f007c06cb685f2583adb40d1a3d629d0e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8762316703796387,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.000255424579507286,
+  "best_metric": 2.846574068069458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00031928072438410746,
   "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": 19.323,
       "eval_steps_per_second": 9.662,
       "step": 20
+    },
+    {
+      "epoch": 0.0002681958084826503,
+      "grad_norm": 1.3929669857025146,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.8727,
+      "step": 21
+    },
+    {
+      "epoch": 0.0002809670374580146,
+      "grad_norm": 1.3348205089569092,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.8768,
+      "step": 22
+    },
+    {
+      "epoch": 0.00029373826643337887,
+      "grad_norm": 1.1417149305343628,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.9845,
+      "step": 23
+    },
+    {
+      "epoch": 0.00030650949540874317,
+      "grad_norm": 1.084378719329834,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.7393,
+      "step": 24
+    },
+    {
+      "epoch": 0.00031928072438410746,
+      "grad_norm": 1.1352297067642212,
+      "learning_rate": 0.0,
+      "loss": 2.7416,
+      "step": 25
+    },
+    {
+      "epoch": 0.00031928072438410746,
+      "eval_loss": 2.846574068069458,
+      "eval_runtime": 1715.0978,
+      "eval_samples_per_second": 19.223,
+      "eval_steps_per_second": 9.612,
+      "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": 68585300951040.0,
+  "total_flos": 85731626188800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null