Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45886af6b34dfc006b17f45d1ed7e1c0acba277611618b556f981ce32187e95c
+oid sha256:8ee59f9b2b727087207c4735fe1a34d37596b39949d22d64eb9d79c329ca6c3a
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50dfd3e6b14f85402fc6a98dfdf59243f2c28f9282273c526b4fb7e919152db
+oid sha256:d186585616b637b5c5d988e36dc98f85e85adb90025b440364f407e5fe09a85e
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.732574224472046,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03368421052631579,
+  "best_metric": 2.7208340167999268,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.042105263157894736,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 17.188,
       "eval_steps_per_second": 8.594,
       "step": 20
+    },
+    {
+      "epoch": 0.03536842105263158,
+      "grad_norm": 40.93978500366211,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 9.9624,
+      "step": 21
+    },
+    {
+      "epoch": 0.03705263157894737,
+      "grad_norm": 41.63092041015625,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.9608,
+      "step": 22
+    },
+    {
+      "epoch": 0.03873684210526316,
+      "grad_norm": 34.82494354248047,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 11.4685,
+      "step": 23
+    },
+    {
+      "epoch": 0.04042105263157895,
+      "grad_norm": 41.74858474731445,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 12.6479,
+      "step": 24
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 42.13344192504883,
+      "learning_rate": 0.0,
+      "loss": 10.1041,
+      "step": 25
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 2.7208340167999268,
+      "eval_runtime": 14.6308,
+      "eval_samples_per_second": 17.087,
+      "eval_steps_per_second": 8.544,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 175457131560960.0,
+  "total_flos": 219321414451200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null