Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbe5cadd994ed6761f1d1a85796c0dd8441a52e940ea9c94ef8e1eac6d95c4a
+oid sha256:efce2e850478b2e48f94163cc2f14cd887446514a01f77769e158a5d95199032
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8bb340171829c266facc192b4ed0154ace8ea134f65785f003f4037a9d107f
+oid sha256:b05dc9c30f71c67e6f75f6548146ef552c0f96ec1e01fd3ed8b8c3cebc192af9
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365b308e21e40965cc43c734700c842d1fd9fc8ab6e508c7d2d7e988a7c96896
+oid sha256:0d23cfbadd8ed1ffad8e8f415952692ed2ac3d423a4e8c593ec375be06b2f38b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9916974902153015,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 0.9879741072654724,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.615,
       "eval_steps_per_second": 2.808,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 5.642496109008789,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 4.0999,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 132.07199096679688,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.3195,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 0.9875946044921875,
+      "eval_runtime": 87.1705,
+      "eval_samples_per_second": 5.621,
+      "eval_steps_per_second": 2.811,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 22.84010124206543,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.4951,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 13.633731842041016,
+      "learning_rate": 0.0,
+      "loss": 4.3465,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 0.9879741072654724,
+      "eval_runtime": 87.1769,
+      "eval_samples_per_second": 5.621,
+      "eval_steps_per_second": 2.81,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7222245734400000.0,
+  "total_flos": 1.0400033857536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null