Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a84583b673e1892ba37ae41ddc12d5b07f0a655b326896ae79835d214030c82
+oid sha256:09d82f9c269f44c47652bbab7252e6cbc396c53819d8560217b591f5803b3679
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d355524bc6f9e20d64238de11810f9eb5e5fb5d52b4d13afe6ac27d4ad84870
+oid sha256:37d68d1db55eb8d018d3b1b15b325ddae129ee2ab5ecb174cfacde7b23799411
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc5bcebaccae49f5dc921912b09ddedf4c46d38bf32792de6f1d34325668c4ea
+oid sha256:47573c7f44c553df5bbbb304a1f30b6d4d53e7e9e2d7579a8ac6b92477e95e63
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.608821153640747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0009215740484747949,
+  "best_metric": 1.6042733192443848,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0011519675605934938,
   "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": 2.762,
       "eval_steps_per_second": 1.381,
       "step": 20
+    },
+    {
+      "epoch": 0.0009676527508985347,
+      "grad_norm": 1.247157096862793,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 5.8863,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010137314533222744,
+      "grad_norm": 1.7679110765457153,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 5.8775,
+      "step": 22
+    },
+    {
+      "epoch": 0.0010598101557460142,
+      "grad_norm": 1.592766284942627,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 5.9673,
+      "step": 23
+    },
+    {
+      "epoch": 0.001105888858169754,
+      "grad_norm": 1.4257538318634033,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 6.3244,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011519675605934938,
+      "grad_norm": 1.1082109212875366,
+      "learning_rate": 0.0,
+      "loss": 5.128,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011519675605934938,
+      "eval_loss": 1.6042733192443848,
+      "eval_runtime": 1312.2555,
+      "eval_samples_per_second": 6.964,
+      "eval_steps_per_second": 3.482,
+      "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": 9815295346606080.0,
+  "total_flos": 1.211080796798976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null