Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe11a4e28310e3b86a748920d7cc8c9adfd47cd78fcebffb8437e2d97aba821
+oid sha256:717604e5702ea1a9ff7f833413ba255ce9fe914cd229722ec36f4d65345b560d
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6a17c20d773fc37974801390665efeed09f972660bc6919b772f236fc5905c
+oid sha256:bd37dda95add854d49646274ec0c873e6ff4ea5588eaa860a7965dd5b041c22e
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a637fe19d8cbda4eb111f449af880086e2badde14ed5a28cf16047af108bbaf9
+oid sha256:dbd7febb297e7c4156a8f2693467492292870625dc87c4aa7aece1a872061707
 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": 1.146728754043579,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.311284046692607,
+  "best_metric": 1.136946678161621,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.38910505836575876,
   "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": 4.142,
       "eval_steps_per_second": 2.148,
       "step": 20
+    },
+    {
+      "epoch": 0.32684824902723736,
+      "grad_norm": 0.803828775882721,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9064,
+      "step": 21
+    },
+    {
+      "epoch": 0.3424124513618677,
+      "grad_norm": 1.1670228242874146,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9652,
+      "step": 22
+    },
+    {
+      "epoch": 0.35797665369649806,
+      "grad_norm": 1.113417387008667,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.8614,
+      "step": 23
+    },
+    {
+      "epoch": 0.3735408560311284,
+      "grad_norm": 1.2294334173202515,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0798,
+      "step": 24
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "grad_norm": 1.2414882183074951,
+      "learning_rate": 0.0,
+      "loss": 1.1288,
+      "step": 25
+    },
+    {
+      "epoch": 0.38910505836575876,
+      "eval_loss": 1.136946678161621,
+      "eval_runtime": 6.4836,
+      "eval_samples_per_second": 4.164,
+      "eval_steps_per_second": 2.159,
+      "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": 4104787234652160.0,
+  "total_flos": 5130984043315200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null