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:e8bcf46e8273fdd9e6a39d172604b262358ca5acc917132c993e726f06d682d7
+oid sha256:ccb5613f0fd3999f469717653390fb6edaf6001ef93c4717375aeae1d54ed511
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1864e57bcb997745217395bd9f3793e8ad1ebb369000e11b9bd13ef72dce50ad
+oid sha256:a07ec758fbd8596d7e7a3cb2c4fc97be34af16643859820ee14f912e192de394
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbdf3c563e47901060c8a0a1969c7b40974ea2772ee3fd006b4c4488361a030
+oid sha256:aa18bc5b48cb8d63339d694651b38aec275d5543fe73d579ad0cce3a4ca817f3
 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": 2.5436248779296875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 2.538435697555542,
+  "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": 17.962,
       "eval_steps_per_second": 8.981,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 1.9827948808670044,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.1527,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 3.5701653957366943,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.3196,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 2.539433240890503,
+      "eval_runtime": 27.4227,
+      "eval_samples_per_second": 17.868,
+      "eval_steps_per_second": 8.934,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 3.908367395401001,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.589,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 2.505573272705078,
+      "learning_rate": 0.0,
+      "loss": 10.4872,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 2.538435697555542,
+      "eval_runtime": 27.4559,
+      "eval_samples_per_second": 17.847,
+      "eval_steps_per_second": 8.923,
+      "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": 1893182157619200.0,
+  "total_flos": 2839773236428800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null