Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abd2394bff0d5e0616490f53057db386a685e20efe8926ec587b5254a7069df
+oid sha256:379334a52a2727f79f2069d480bebdfe4a8cbfcdaf82034e65b3151ace1d4f1a
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7578dca2bdcf0edb5113f6c91fe537bb8201d93a35c843ef88c65f039995d65
+oid sha256:e331b9c2ee57bb34fdfb1baf1ec585e44a24f4d515914af987cc5cec15533fc8
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb04d53c32f2d5bd67ab5c0e66af36987277bd0439697b05fa91b0129cac6e9
+oid sha256:88e41831d1aedc623c12b273cf0ff1924d2ca85edf91d84637c9febd4f6c5666
 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": 0.5574434995651245,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009461856889414548,
+  "best_metric": 0.5506227016448975,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.011827321111768185,
   "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": 2.816,
       "eval_steps_per_second": 1.408,
       "step": 20
+    },
+    {
+      "epoch": 0.009934949733885276,
+      "grad_norm": 0.6496264338493347,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.6153,
+      "step": 21
+    },
+    {
+      "epoch": 0.010408042578356003,
+      "grad_norm": 0.8121730089187622,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5568,
+      "step": 22
+    },
+    {
+      "epoch": 0.01088113542282673,
+      "grad_norm": 0.6858046650886536,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5282,
+      "step": 23
+    },
+    {
+      "epoch": 0.011354228267297458,
+      "grad_norm": 0.5924935340881348,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5527,
+      "step": 24
+    },
+    {
+      "epoch": 0.011827321111768185,
+      "grad_norm": 0.5828019976615906,
+      "learning_rate": 0.0,
+      "loss": 0.5005,
+      "step": 25
+    },
+    {
+      "epoch": 0.011827321111768185,
+      "eval_loss": 0.5506227016448975,
+      "eval_runtime": 315.5321,
+      "eval_samples_per_second": 2.821,
+      "eval_steps_per_second": 1.41,
+      "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": 7071038240194560.0,
+  "total_flos": 8886575085649920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null