Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ebf5062fb46c7d7c1c89a56dc5fb2b68e86fb67bf133333a8f5018c4bb9b690
+oid sha256:faf718e34af6a2398cda7508f10aeea94a4aea20d020e3f0a5ac60dfc24e1bcd
 size 119975656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffdb65ab723ca1200484217cb00a01860c723198486491d1e25bf0025edfcea1
+oid sha256:d8b32bdcd9d4fafaaafd5acba7225b0c30e9bb18e67e5ed828b0a0d9a9da50d2
 size 240145026

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bc4e7beb1022a92470b21f9014f069343ad498e6241ad135c1012281b29af9
+oid sha256:72269765e4e2b060aa098177173e63a7b137cff6df6e71b56f1db858c555f555
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6729626c2941ce2f46ad869e09cdc2713f8b4c7aa316bec65384f5a43f3d7e3
+oid sha256:a17a9d3d70888903a001e8f0df8a0370c6ed4b4747389d9c28f947d41c1b773f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bddf773cf55af387a35e33e77647fdee488cb843ccf5d0f20b63961624e9389
+oid sha256:709766974ace611e681b901fa1854ca42ffc881ad38bf72da685c1ea5e98991e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049713b44b0b4b6a8b6cc2d978769a9c3d5020ff7261bcecef0dbefd6f274edc
+oid sha256:b9fe0333dd05401f805d49f229c256c9256a5c976b3fb27a1f4f52f71fb6bb5a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6350988149642944,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16260162601626016,
+  "best_metric": 1.5799205303192139,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3252032520325203,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 26.996,
       "eval_steps_per_second": 3.388,
       "step": 25
+    },
+    {
+      "epoch": 0.16910569105691056,
+      "grad_norm": 0.28785306215286255,
+      "learning_rate": 5e-05,
+      "loss": 1.37,
+      "step": 26
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 0.26578181982040405,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3331,
+      "step": 27
+    },
+    {
+      "epoch": 0.1821138211382114,
+      "grad_norm": 0.26452162861824036,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3761,
+      "step": 28
+    },
+    {
+      "epoch": 0.1886178861788618,
+      "grad_norm": 0.20922784507274628,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3182,
+      "step": 29
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.18566425144672394,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2673,
+      "step": 30
+    },
+    {
+      "epoch": 0.2016260162601626,
+      "grad_norm": 0.18694765865802765,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2826,
+      "step": 31
+    },
+    {
+      "epoch": 0.208130081300813,
+      "grad_norm": 0.181863933801651,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2765,
+      "step": 32
+    },
+    {
+      "epoch": 0.2146341463414634,
+      "grad_norm": 0.1935238540172577,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.295,
+      "step": 33
+    },
+    {
+      "epoch": 0.22113821138211381,
+      "grad_norm": 0.21044613420963287,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3621,
+      "step": 34
+    },
+    {
+      "epoch": 0.22764227642276422,
+      "grad_norm": 0.2689436972141266,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4391,
+      "step": 35
+    },
+    {
+      "epoch": 0.23414634146341465,
+      "grad_norm": 0.376651793718338,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8876,
+      "step": 36
+    },
+    {
+      "epoch": 0.24065040650406505,
+      "grad_norm": 1.4348276853561401,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.0286,
+      "step": 37
+    },
+    {
+      "epoch": 0.24715447154471545,
+      "grad_norm": 0.2289065718650818,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3651,
+      "step": 38
+    },
+    {
+      "epoch": 0.25365853658536586,
+      "grad_norm": 0.19455616176128387,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2948,
+      "step": 39
+    },
+    {
+      "epoch": 0.2601626016260163,
+      "grad_norm": 0.2245715707540512,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3066,
+      "step": 40
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.20435915887355804,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3163,
+      "step": 41
+    },
+    {
+      "epoch": 0.2731707317073171,
+      "grad_norm": 0.17328569293022156,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2732,
+      "step": 42
+    },
+    {
+      "epoch": 0.27967479674796747,
+      "grad_norm": 0.1736893206834793,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2619,
+      "step": 43
+    },
+    {
+      "epoch": 0.2861788617886179,
+      "grad_norm": 0.1751582771539688,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2683,
+      "step": 44
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.17826324701309204,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2849,
+      "step": 45
+    },
+    {
+      "epoch": 0.2991869918699187,
+      "grad_norm": 0.18487432599067688,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3155,
+      "step": 46
+    },
+    {
+      "epoch": 0.3056910569105691,
+      "grad_norm": 0.22769266366958618,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3759,
+      "step": 47
+    },
+    {
+      "epoch": 0.3121951219512195,
+      "grad_norm": 0.2902439534664154,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5236,
+      "step": 48
+    },
+    {
+      "epoch": 0.31869918699186994,
+      "grad_norm": 1.0033760070800781,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.0646,
+      "step": 49
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 1.7348500490188599,
+      "learning_rate": 0.0,
+      "loss": 2.9307,
+      "step": 50
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "eval_loss": 1.5799205303192139,
+      "eval_runtime": 38.3497,
+      "eval_samples_per_second": 27.015,
+      "eval_steps_per_second": 3.39,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.670051300501094e+16,
+  "total_flos": 1.3307911230560666e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null