Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384eabeee676669feddb82a96865399e8817769b590021d063e3193f4d08c5a9
+oid sha256:e850ee4fe59e12eac1d7851606d44127600c6931e5bc199a9c058ca56da96af0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515220f66945f685d25f7c6cc6b47df12225a37216d3c20aca4528d7e895c964
+oid sha256:53a408074c2434cb23b7f1a11f744a5dac1b44cbbc11fb900d5f58b2aa2f416e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702ed72ea3950fc1f8b63fb6694dc8b514e3b1aa425124a22238be312563d76c
+oid sha256:d80d95a487a02fb9c8ae968d0aaaa0ea45f5e07904c5dd0e3c54637fd3184623
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dfe0cd94301e1acf153fc56b362ba5219fd26309b5c59185f05af251451cc09
+oid sha256:ed0d0ca98ec676c9c941556be6af69f6074ac6e4ebfe34758827d2ec9dbf2f48
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.390733003616333,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.8785046728971961,
+  "epoch": 2.0373831775700935,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,34 @@
       "eval_samples_per_second": 11.919,
       "eval_steps_per_second": 1.669,
       "step": 50
+    },
+    {
+      "epoch": 1.9158878504672896,
+      "grad_norm": 3.5007739067077637,
+      "learning_rate": 3.4279701043260886e-06,
+      "loss": 2.5603,
+      "step": 51
+    },
+    {
+      "epoch": 1.953271028037383,
+      "grad_norm": 3.4901020526885986,
+      "learning_rate": 1.5267837178600972e-06,
+      "loss": 2.6862,
+      "step": 52
+    },
+    {
+      "epoch": 1.9906542056074765,
+      "grad_norm": 5.5853047370910645,
+      "learning_rate": 3.821828084619727e-07,
+      "loss": 3.6647,
+      "step": 53
+    },
+    {
+      "epoch": 2.0373831775700935,
+      "grad_norm": 2.95920729637146,
+      "learning_rate": 0.0,
+      "loss": 2.2325,
+      "step": 54
     }
   ],
   "logging_steps": 1,
@@ -404,12 +432,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.88255238782976e+16,
+  "total_flos": 8.51315657885614e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null