Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875b90734cb8e259fda69e4c5377b4b22d6d582a994ad0efd65920a6d587d7e4
+oid sha256:383e69ecc672b9300db5e92d03369bece75c67e5751b5483bccc1d61c2c0000d
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3edf406ca11fdfc8b9c0a90ded0bbe3244cc7d706570817e05264a3b9e4ca0
+oid sha256:d01bb139baeb53e383004a55b81cfe78e685e3cf5e7c72f6c65398528ee16248
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29fff7474d6d194c011aebcbb61c87fc618c305edb91d68feb3491e2e28e2d74
+oid sha256:5f6e56f39cecdd7b22841df0178e7d8b15f5407240c214b3912362eec7038720
 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": 1.5036325454711914,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004292075755137078,
+  "best_metric": 1.4530510902404785,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.006438113632705618,
   "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": 12.541,
       "eval_steps_per_second": 3.135,
       "step": 20
+    },
+    {
+      "epoch": 0.0045066795428939325,
+      "grad_norm": 6.944516658782959,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.1814,
+      "step": 21
+    },
+    {
+      "epoch": 0.005150490906164494,
+      "grad_norm": 6.075719356536865,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 5.829,
+      "step": 24
+    },
+    {
+      "epoch": 0.005365094693921347,
+      "eval_loss": 1.4611380100250244,
+      "eval_runtime": 312.8644,
+      "eval_samples_per_second": 12.542,
+      "eval_steps_per_second": 3.136,
+      "step": 25
+    },
+    {
+      "epoch": 0.005794302269435055,
+      "grad_norm": 5.367476940155029,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.8356,
+      "step": 27
+    },
+    {
+      "epoch": 0.006438113632705618,
+      "grad_norm": 6.34188985824585,
+      "learning_rate": 0.0,
+      "loss": 5.9808,
+      "step": 30
+    },
+    {
+      "epoch": 0.006438113632705618,
+      "eval_loss": 1.4530510902404785,
+      "eval_runtime": 313.1667,
+      "eval_samples_per_second": 12.53,
+      "eval_steps_per_second": 3.133,
+      "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": 2388578952806400.0,
+  "total_flos": 3582868429209600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null