Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c013cdfb8d2f8ca20c0080fd8cf52f64d97360e2cd22aee0990bfc82319272
+oid sha256:155245912af85216c438ea0cb3cce8c998291371412e7ed33cd29683a01135e7
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344a9e081cdcbfa4ffb3b46c15cfb8b7ee652b4aa935ab6f9ac75bee1010ded6
+oid sha256:66a8e1d075405962c641f1762acb4b600abc0aae028e41a7339ed3c8da160195
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb4b705b0599bd124de3315089e766e78a4efe2be4f993feb71580630a17b20
+oid sha256:6a0f4afd20ed7ebb9f94982eede3ad3f384b4d57f80967073377fe88ae5cbe5a
 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": 3.1601524353027344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.055865921787709494,
+  "best_metric": 3.1504673957824707,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.06983240223463687,
   "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": 32.237,
       "eval_steps_per_second": 16.225,
       "step": 20
+    },
+    {
+      "epoch": 0.05865921787709497,
+      "grad_norm": 1758.541748046875,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 13.4797,
+      "step": 21
+    },
+    {
+      "epoch": 0.061452513966480445,
+      "grad_norm": 1436.4757080078125,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 13.0247,
+      "step": 22
+    },
+    {
+      "epoch": 0.06424581005586592,
+      "grad_norm": 4008.150634765625,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 12.935,
+      "step": 23
+    },
+    {
+      "epoch": 0.0670391061452514,
+      "grad_norm": 1392.25927734375,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.7266,
+      "step": 24
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "grad_norm": 1336.1402587890625,
+      "learning_rate": 0.0,
+      "loss": 13.1131,
+      "step": 25
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "eval_loss": 3.1504673957824707,
+      "eval_runtime": 4.7717,
+      "eval_samples_per_second": 31.645,
+      "eval_steps_per_second": 15.927,
+      "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": 61375669862400.0,
+  "total_flos": 76719587328000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null