Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e4c3e431397affb0b53a175f1d739e123a548290e92aa64fcfafdab4741baa
+oid sha256:d61ee6f50f1b38602e247416c3fbc3f9da4f9ca2da74fcec59debbb84780870d
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c437b4883ae346b7f4da009a3b6066984851ff7b629fd190c3180636fa144ec5
+oid sha256:0ff7198d896f1265c9e1f4343bf134256c22dbb81e0f14a45f4d8971ab2b8779
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330796178c89f0a970539182417e271745b4e562e5f628fb3ab81d04129143f0
+oid sha256:b05333b718c0f42708ebb8ba84e263b80dd3708563071b373694dfee958ff762
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f907450757c510bc85cf5ba3c442a20b76731dbae558c5d4cdc37061b46d99
+oid sha256:9d42e03a0a3d94b2b0007a43190dd2041868878539beefabe7cf790df6d1d4f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.946034550666809,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.6531204644412192,
+  "best_metric": 1.9433879852294922,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.7256894049346879,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 11.817,
       "eval_steps_per_second": 2.975,
       "step": 450
+    },
+    {
+      "epoch": 0.6676342525399129,
+      "grad_norm": 0.895086407661438,
+      "learning_rate": 4.009414470383994e-06,
+      "loss": 1.9791,
+      "step": 460
+    },
+    {
+      "epoch": 0.6821480406386067,
+      "grad_norm": 0.8754801750183105,
+      "learning_rate": 2.261723324051111e-06,
+      "loss": 1.9452,
+      "step": 470
+    },
+    {
+      "epoch": 0.6966618287373004,
+      "grad_norm": 1.139264702796936,
+      "learning_rate": 1.0072548852474675e-06,
+      "loss": 1.9159,
+      "step": 480
+    },
+    {
+      "epoch": 0.7111756168359942,
+      "grad_norm": 1.3206005096435547,
+      "learning_rate": 2.5212079810819554e-07,
+      "loss": 1.9687,
+      "step": 490
+    },
+    {
+      "epoch": 0.7256894049346879,
+      "grad_norm": 2.6603949069976807,
+      "learning_rate": 0.0,
+      "loss": 1.8801,
+      "step": 500
+    },
+    {
+      "epoch": 0.7256894049346879,
+      "eval_loss": 1.9433879852294922,
+      "eval_runtime": 24.5489,
+      "eval_samples_per_second": 11.813,
+      "eval_steps_per_second": 2.974,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1634410976077414e+17,
+  "total_flos": 1.2944932147612877e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null