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:d2ba6709880916f77a34eed6d1c2c2a558cd4bb13317b0ec2bb7d324d02ae4cc
+oid sha256:14ff1bbaacac174b9efb1bfdac4380ca5beb762a0a83c9577afe6278e18f6bb9
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d3a238cf1a07566a6378e9e6ffd3244d8ab8824f039c2f0fd952c1f6c92a49
+oid sha256:d7f3ea77881f6c7da4f5c99b31810be55d3733b815ba68e8cef725e484ce50e6
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 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": 2.7909083366394043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0003900517306107723,
+  "best_metric": 2.7604312896728516,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0004875646632634653,
   "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": 12.034,
       "eval_steps_per_second": 6.017,
       "step": 20
+    },
+    {
+      "epoch": 0.00040955431714131084,
+      "grad_norm": 13.265759468078613,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 11.5817,
+      "step": 21
+    },
+    {
+      "epoch": 0.00042905690367184946,
+      "grad_norm": 13.504497528076172,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 12.1199,
+      "step": 22
+    },
+    {
+      "epoch": 0.0004485594902023881,
+      "grad_norm": 11.75288200378418,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 10.8835,
+      "step": 23
+    },
+    {
+      "epoch": 0.0004680620767329267,
+      "grad_norm": 13.522823333740234,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.2051,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004875646632634653,
+      "grad_norm": 12.743696212768555,
+      "learning_rate": 0.0,
+      "loss": 10.4655,
+      "step": 25
+    },
+    {
+      "epoch": 0.0004875646632634653,
+      "eval_loss": 2.7604312896728516,
+      "eval_runtime": 1790.5951,
+      "eval_samples_per_second": 12.057,
+      "eval_steps_per_second": 6.029,
+      "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": 150139305984000.0,
+  "total_flos": 187674132480000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null