Training in progress, step 33, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87514ed48e3e5763ff5d20d973c6ade8f3b4a9e288960a10ffc6e1a1e65d0adb
+oid sha256:a8e740fb0bce7f60d959518299493cc77095fd634792c8dcca967f9f078b21e0
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fda3a833a8c8b15763a20525426723616688470896e1b329db00d3545e60c67
+oid sha256:b91a7c74f33f650fe7077815de9d509e59da0c71779caf0abebf0a45e45c4c08
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f2f0c0b26cbfeb862ca4e60a6350174c6a3f94d1046d9d3d8f144291f69c2c
+oid sha256:5f00ee03e681244e21b740589da178f6b40513c538b140a109eab1d1d1985a87
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1222ab2a09b96fa69e3c65aa6fcf2f73dc3488dc6278f6dda868a8736ecf5460
+oid sha256:ab23334051182127d40dcfaaddb1906631b17b5a81d4e26920994d04a6ea09c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e610af5d010b52329979c7e0b80f764e5a040ad687def1dddb9d181988a4c75a
+oid sha256:45421302d8c65d5b9128fd13601b411f72298a9e9d3b8666e951efb7c0bd6311
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27883ba3b2f56f90e1d0a58dd7b64bc769f9c63621a2c6b541514a5a500904d1
+oid sha256:9ec08220af7b23a04e65d2af83011debe79b64fff03327e74879ecd7e72d4edc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23f0477a4f52d73a0d5b42bcbbd59be121e3f32646b13d269cf4b1a335f645d7
+oid sha256:3cd3f6e9267a2b7ffad41dddfa33b74e45aa7c480b8283eebbe1a013b2da49f9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5904276967048645,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2727272727272725,
+  "epoch": 3.0,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,62 @@
       "eval_samples_per_second": 101.523,
       "eval_steps_per_second": 13.719,
       "step": 25
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 1.1513195037841797,
+      "learning_rate": 1.2062093865360458e-05,
+      "loss": 0.6313,
+      "step": 26
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 1.2628175020217896,
+      "learning_rate": 8.961827939636196e-06,
+      "loss": 0.6297,
+      "step": 27
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 1.271503210067749,
+      "learning_rate": 6.282669192770896e-06,
+      "loss": 0.6808,
+      "step": 28
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 1.3215694427490234,
+      "learning_rate": 4.05210941898847e-06,
+      "loss": 0.734,
+      "step": 29
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 1.12972891330719,
+      "learning_rate": 2.2930371799975594e-06,
+      "loss": 0.5775,
+      "step": 30
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 1.0475295782089233,
+      "learning_rate": 1.0235029373752758e-06,
+      "loss": 0.5434,
+      "step": 31
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 1.3993170261383057,
+      "learning_rate": 2.5653383040524227e-07,
+      "loss": 0.6718,
+      "step": 32
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1576110124588013,
+      "learning_rate": 0.0,
+      "loss": 0.5754,
+      "step": 33
     }
   ],
   "logging_steps": 1,
@@ -221,12 +277,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 5.500548187737293e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null