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:eda9cc0f82f63ca880708633357af0cd601a24fc3a0599aef424ae8a204888b2
+oid sha256:07d362317c83c46e404d30f90e4b98f16c3631f95717db4cad2755bbfce636da
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4992a1eb494490708867ff5aa9087ecdae61cb9dd818a06effff9d61bebee94
+oid sha256:deab9b1fa01fbf0b9abd847e17e3634356e0ea9538ca9efbed0f6b02b679a5f5
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a21d97c7b4f852e699ec9396cc6f321dd7d7c9e8ccf2defda70289bbb6f8e3
+oid sha256:5da01e5353e10c9040c0d4081c58dc100921ea8bfa74ee690c7eb6036e8ada92
 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": 3.401686906814575,
   "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": 11.863,
       "eval_steps_per_second": 1.661,
       "step": 50
+    },
+    {
+      "epoch": 1.9158878504672896,
+      "grad_norm": 3.5044848918914795,
+      "learning_rate": 3.4279701043260886e-06,
+      "loss": 2.5647,
+      "step": 51
+    },
+    {
+      "epoch": 1.953271028037383,
+      "grad_norm": 3.4336962699890137,
+      "learning_rate": 1.5267837178600972e-06,
+      "loss": 2.6922,
+      "step": 52
+    },
+    {
+      "epoch": 1.9906542056074765,
+      "grad_norm": 5.213560104370117,
+      "learning_rate": 3.821828084619727e-07,
+      "loss": 3.6647,
+      "step": 53
+    },
+    {
+      "epoch": 2.0373831775700935,
+      "grad_norm": 2.9050323963165283,
+      "learning_rate": 0.0,
+      "loss": 2.2642,
+      "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