Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6f41c29119a72864dfed9bda11c11ddd48e89bdfe90c9bda3f0e97968550e3
+oid sha256:d2d097a8953713c5011da1ecfb0239d4478db483e4230dd193b63935a7acfea9
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0259ee54ab3e9b9b11f839dd15fc8a03931cba121c0e16179b38c65cbc9cc9b
+oid sha256:5a9083d0ffaa6d50a401dd9b4f8668abd8efc4f73f83df82b0bca86150a4defc
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41031c00e47b0114a7ae8d3c565162e5e1acbf339d8aa4d6393528e9d3b5a79
+oid sha256:ecee6b35af54beb50ef2d84cfb1fb2466f0bf8a158658256e8c91da4a2c15516
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.33818519115448,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0021861507350931847,
+  "best_metric": 1.272352933883667,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.003279226102639777,
   "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": 14.403,
       "eval_steps_per_second": 3.601,
       "step": 20
+    },
+    {
+      "epoch": 0.002295458271847844,
+      "grad_norm": 2.25827956199646,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.1886,
+      "step": 21
+    },
+    {
+      "epoch": 0.0026233808821118218,
+      "grad_norm": 1.7416315078735352,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.4143,
+      "step": 24
+    },
+    {
+      "epoch": 0.002732688418866481,
+      "eval_loss": 1.2895269393920898,
+      "eval_runtime": 534.2014,
+      "eval_samples_per_second": 14.422,
+      "eval_steps_per_second": 3.605,
+      "step": 25
+    },
+    {
+      "epoch": 0.002951303492375799,
+      "grad_norm": 2.217322826385498,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 4.8088,
+      "step": 27
+    },
+    {
+      "epoch": 0.003279226102639777,
+      "grad_norm": 2.894871234893799,
+      "learning_rate": 0.0,
+      "loss": 4.8256,
+      "step": 30
+    },
+    {
+      "epoch": 0.003279226102639777,
+      "eval_loss": 1.272352933883667,
+      "eval_runtime": 535.3969,
+      "eval_samples_per_second": 14.389,
+      "eval_steps_per_second": 3.597,
+      "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": 4801896917237760.0,
+  "total_flos": 6512572694003712.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null