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:db5560bd82cc0e72e4d5e42b7ae61eaad5b872ff504260352ce51651adc64fd4
+oid sha256:90f8502fc6d838e8c00ec0b8844c6cf68d95f7fee78c1ddd56c5d471ea387eea
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd86e598712cf8e6fd4ed4e9ad54f6cb04e0c0a4e254e02597f5c85e5e9472b
+oid sha256:13e516cd937403a2324419c981a1a22c9d70138d4cecf7d9fab117173c312cb0
 size 188914170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86582f1b3e0a6e04605301ac1d31dbe586462185e106c2f8a9afd8e5dc66ef98
+oid sha256:3cd94c2602207659c65a88edd8fa5c10dead9661705be03eee5fc92ade03b6bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.756742477416992,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005106600280863015,
+  "best_metric": 2.743968963623047,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.006383250351078769,
   "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": 6.879,
       "eval_steps_per_second": 3.442,
       "step": 20
+    },
+    {
+      "epoch": 0.005361930294906166,
+      "grad_norm": 4.26030158996582,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.4889,
+      "step": 21
+    },
+    {
+      "epoch": 0.005617260308949317,
+      "grad_norm": 6.210017681121826,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.0761,
+      "step": 22
+    },
+    {
+      "epoch": 0.005872590322992467,
+      "grad_norm": 3.9016616344451904,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 9.6805,
+      "step": 23
+    },
+    {
+      "epoch": 0.006127920337035618,
+      "grad_norm": 4.461097717285156,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.136,
+      "step": 24
+    },
+    {
+      "epoch": 0.006383250351078769,
+      "grad_norm": 3.818615674972534,
+      "learning_rate": 0.0,
+      "loss": 11.7023,
+      "step": 25
+    },
+    {
+      "epoch": 0.006383250351078769,
+      "eval_loss": 2.743968963623047,
+      "eval_runtime": 239.0686,
+      "eval_samples_per_second": 6.898,
+      "eval_steps_per_second": 3.451,
+      "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": 5705610716774400.0,
+  "total_flos": 7132013395968000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null