Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056a46bcbac60d6e917614c2d1e9fa915417f221af7f0bde6710d3e21f3375d2
+oid sha256:a545c1d8325b400e0f6194e0932b200249520d1a93191c363664b433b5f22831
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842c6a1ca707825f2688bee9c61cc4f4a449babc9073e3e23b01a794328ead09
+oid sha256:ba8f69ee562a7a1e9a099873d1f2cd9eb9f2049ff60756dd419ff3c4dd3edab6
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95bb917618d6b3dbc089cac4c9f61c14ca385d595854a7db3eaaf658076ad01
+oid sha256:6c204243aef9fde9d455c10bcc4067d85b4437c2b5d01b5fbf1c115992271e08
 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": 0.5206258296966553,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006397952655150352,
+  "best_metric": 0.5165967345237732,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00799744081893794,
   "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": 5.35,
       "eval_steps_per_second": 2.677,
       "step": 20
+    },
+    {
+      "epoch": 0.0067178502879078695,
+      "grad_norm": 1.0390733480453491,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.6656,
+      "step": 21
+    },
+    {
+      "epoch": 0.007037747920665387,
+      "grad_norm": 1.3606775999069214,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.2844,
+      "step": 22
+    },
+    {
+      "epoch": 0.007357645553422905,
+      "grad_norm": 0.9153907299041748,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.0168,
+      "step": 23
+    },
+    {
+      "epoch": 0.007677543186180422,
+      "grad_norm": 1.013383150100708,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.3948,
+      "step": 24
+    },
+    {
+      "epoch": 0.00799744081893794,
+      "grad_norm": 1.1324673891067505,
+      "learning_rate": 0.0,
+      "loss": 2.0969,
+      "step": 25
+    },
+    {
+      "epoch": 0.00799744081893794,
+      "eval_loss": 0.5165967345237732,
+      "eval_runtime": 246.1203,
+      "eval_samples_per_second": 5.351,
+      "eval_steps_per_second": 2.678,
+      "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": 8578352598220800.0,
+  "total_flos": 1.07866413858816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null