Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871d8c4a9add6b4fd7bc4a6efa63e199132464aa5612e902b23c8f933e753a51
+oid sha256:3223e393d6c8ffc54c6aaefb03d4a69fe5553741238c82a5ae5290287807e5fc
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:addd9d279958a39de12a67c80b570eaf9a6b3208e808f1f0029c21268a5f81fe
+oid sha256:ddb9efb2dfb7fe3a01c8207c5504a133580266eddd49fab8b59c15026b7a6ec6
 size 201478138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
+oid sha256:d0384a91293efd3ba6280cd22395b5c719e02504ad3e64b7952c1b9f54bd096a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4728478491306305,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008530603540200469,
+  "best_metric": 0.4652339220046997,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012795905310300703,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 3.759,
       "eval_steps_per_second": 1.88,
       "step": 20
+    },
+    {
+      "epoch": 0.008957133717210493,
+      "grad_norm": 0.5234971046447754,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.8444,
+      "step": 21
+    },
+    {
+      "epoch": 0.010236724248240563,
+      "grad_norm": 0.5886001586914062,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.0016,
+      "step": 24
+    },
+    {
+      "epoch": 0.010663254425250587,
+      "eval_loss": 0.46638426184654236,
+      "eval_runtime": 263.2899,
+      "eval_samples_per_second": 3.753,
+      "eval_steps_per_second": 1.876,
+      "step": 25
+    },
+    {
+      "epoch": 0.011516314779270634,
+      "grad_norm": 0.45593273639678955,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.7822,
+      "step": 27
+    },
+    {
+      "epoch": 0.012795905310300703,
+      "grad_norm": 0.4886685907840729,
+      "learning_rate": 0.0,
+      "loss": 1.7605,
+      "step": 30
+    },
+    {
+      "epoch": 0.012795905310300703,
+      "eval_loss": 0.4652339220046997,
+      "eval_runtime": 263.4922,
+      "eval_samples_per_second": 3.75,
+      "eval_steps_per_second": 1.875,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7368366033469440.0,
+  "total_flos": 1.105254905020416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null