Training in progress, step 153, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4838fa2c8bb43fc8201d1fb5d3b79356e330dd7d016f30e17495277bee58f9
+oid sha256:64b54e751050e80854ff9419effe47e5890f5f86384afb67d69816a41b0d1517
 size 34456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5262e88bd3557a17fa6687be71d9898baee97572a4e4f2054ac7eb2862f226a
+oid sha256:cc6db7f670b15b691c0655eea939ae3628247d303b0a8f38d5e35bde373660a9
 size 73222

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4739ef310ab20c951c534d2705b5492dee6f6f2c4201d2f19772a6795c9bc0f0
+oid sha256:ca1a1663768d62f1559fe99f656a48bbb3525db71d9ba579f3f102b3da5d7ba0
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515b01c20d47c4235a61caa45929f2334dd50e09d667c62b3ea73c75730c43ef
+oid sha256:9a4de154a926d3c130752f0b696004fd23a2c3782f06c6d5d084d7d057c7c726
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4adef96e5ec76c71f47f268873caeee77e3216feab5eca738bb9805d374d739
+oid sha256:99588fffc4e37fdae4656064d2bb7ab19b1255bf6a381663a1d4621e091549d2
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3155846846fa58c87f68d96256f4bc61df6abba308f69477b804614075f5e495
+oid sha256:70d84988daf27712df8f9f2a6b494e94d37df6ed1e9dee90b179fae4f05a8d90
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c057076cf2084724735dc32f41dfda26c172f674f9dccde9ac983266354d03
+oid sha256:c85847e60015ac028665cea14f4bbda3c46ee3f0a2a648ef8305d4760c4ceffb
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a009d96aafa20eefe57b2fe7a1860ec304b152a12480df82f2454c641964e95
+oid sha256:3c1796eb6215b32bcb067098575b2859a70f92074bfb2a46ef02399c23b4a004
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e32fe7dfd7bc3da0fb5496daadb63ed69841ce068b5ed17509d922bf461bb74
+oid sha256:3a8809fac98cf7c959687a09cb7bbd1cd35dcfae3c1792041ff884876fdc80cd
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8628e0674db96292ef8de772b7c476428c09427022ddce2a3875d28de96525
+oid sha256:2f45e2f1c39e337be125769ba44a0bd5d1a0da9ee116e87e54c4df23afa999e0
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e618c561766e531a3b508498a52b6a60ed26e61c8d989456e9bc321d17c91c51
+oid sha256:3e80c77d0f985cdc2ae889979d6f64528d8acd1c039d2a4379d31400b142f489
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.9411764705882355,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 153,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,27 @@
       "eval_samples_per_second": 634.42,
       "eval_steps_per_second": 20.287,
       "step": 150
+    },
+    {
+      "epoch": 2.9607843137254903,
+      "grad_norm": 0.00048230637912638485,
+      "learning_rate": 1.4125874125874126e-06,
+      "loss": 46.0,
+      "step": 151
+    },
+    {
+      "epoch": 2.980392156862745,
+      "grad_norm": 0.0005095683154650033,
+      "learning_rate": 7.062937062937063e-07,
+      "loss": 46.0,
+      "step": 152
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.00042812549509108067,
+      "learning_rate": 0.0,
+      "loss": 46.0,
+      "step": 153
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1133,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 192950776627200.0,
+  "total_flos": 196809792159744.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null