Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69fee2e3151b208f0428e64da587da6c664ae0f90ed3d4a5fa23d54c44708a0b
+oid sha256:f4841b27772aa0c11b1ec3e88dad82c40c5986b6acf7280b0af6b5365d5dff11
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab875c9ea2eba406ddb487cbc40910cd3c06a07ea8185bf961546bc06b908e2
+oid sha256:c63d1405dc23a1e329a44ee42eea2b62b8fab4e0204d19d2fb6176f16a0396fa
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e127c5735f592030883226bb7e6212829e90bdab82288e432cba0360369d53
+oid sha256:d0440de5c28f7345a289f11a1ee4f9a711729a2e754168fc19025144bbdcc9c9
 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": 0.9566317796707153,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017191361340926185,
+  "best_metric": 0.8958336114883423,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.002148920167615773,
   "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": 5.364,
       "eval_steps_per_second": 2.682,
       "step": 20
+    },
+    {
+      "epoch": 0.0018050929407972495,
+      "grad_norm": 12.677580833435059,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.2249,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018910497475018804,
+      "grad_norm": 12.029895782470703,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.49,
+      "step": 22
+    },
+    {
+      "epoch": 0.0019770065542065113,
+      "grad_norm": 10.942070007324219,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.2089,
+      "step": 23
+    },
+    {
+      "epoch": 0.0020629633609111422,
+      "grad_norm": 10.995729446411133,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 4.444,
+      "step": 24
+    },
+    {
+      "epoch": 0.002148920167615773,
+      "grad_norm": 17.779237747192383,
+      "learning_rate": 0.0,
+      "loss": 3.7744,
+      "step": 25
+    },
+    {
+      "epoch": 0.002148920167615773,
+      "eval_loss": 0.8958336114883423,
+      "eval_runtime": 915.4296,
+      "eval_samples_per_second": 5.352,
+      "eval_steps_per_second": 2.676,
+      "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": 597531285258240.0,
+  "total_flos": 746914106572800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null