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:f960f37bd3e2e61759cfa6f023e4bd02341ee05578acfa3dfbac9f447abccfee
+oid sha256:1cab384e5f58cf0f3b4f5875d2d09b47f619d07b9a2807a6821033f74ab880e7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac93e7d328bf8a4eea2e35e667454ea268eeefbd9de2fd11258cc1d9ae2bb0b
+oid sha256:dea5d2239729b2d1e8199dd9e653c06a6e32f5ac7ec176057635696222643fd9
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf65b63797e01914e679f2cb4e3a5f388bdd2739784dd0c0edfa1e2eda6ba1e
+oid sha256:b5213cc0528a2bab1ef3958c8c1e28bbaaba11061b358b7a0484b64510bd1e93
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63340612ba084969257673092e2813ac76804d45806c322e4a66a42e954cd9d4
+oid sha256:036facae037aced6d8fcdab3969d5e0e2492e920c566287ab208879ddd307e1a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd20601b33f3be6880d0f8f02d5446d48be42178607e9368ec3325eb5b2a456d
+oid sha256:006ae55e2739db87e90d68f9dc965fbdf3dfbd3d0b484cd388c906e5df8b1b01
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074461e4b992ad8056b8f5c4d7a1b51e2bff64d370c69f3809b1a1a391a6f3dd
+oid sha256:edafce26b9b6bd8fb71609ce864b6d7f5ab967364e96aedf8cb02756f822bc2d
 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": 0.0668637827038765,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7155635062611807,
+  "best_metric": 0.04139801859855652,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4561717352415027,
   "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": 34.01,
       "eval_steps_per_second": 4.342,
       "step": 25
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 6.980295658111572,
+      "learning_rate": 5e-05,
+      "loss": 0.0684,
+      "step": 26
+    },
+    {
+      "epoch": 0.7728085867620751,
+      "grad_norm": 8.31533145904541,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0578,
+      "step": 27
+    },
+    {
+      "epoch": 0.8014311270125224,
+      "grad_norm": 4.423112869262695,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0607,
+      "step": 28
+    },
+    {
+      "epoch": 0.8300536672629696,
+      "grad_norm": 6.696436405181885,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0686,
+      "step": 29
+    },
+    {
+      "epoch": 0.8586762075134168,
+      "grad_norm": 6.26486873626709,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0516,
+      "step": 30
+    },
+    {
+      "epoch": 0.8872987477638641,
+      "grad_norm": 6.031646251678467,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0539,
+      "step": 31
+    },
+    {
+      "epoch": 0.9159212880143113,
+      "grad_norm": 7.471781253814697,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0529,
+      "step": 32
+    },
+    {
+      "epoch": 0.9445438282647585,
+      "grad_norm": 4.425765514373779,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0518,
+      "step": 33
+    },
+    {
+      "epoch": 0.9731663685152058,
+      "grad_norm": 6.656881332397461,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.052,
+      "step": 34
+    },
+    {
+      "epoch": 1.0268336314847943,
+      "grad_norm": 11.75803279876709,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0384,
+      "step": 35
+    },
+    {
+      "epoch": 1.0554561717352415,
+      "grad_norm": 7.5000786781311035,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0322,
+      "step": 36
+    },
+    {
+      "epoch": 1.0840787119856887,
+      "grad_norm": 12.667994499206543,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0492,
+      "step": 37
+    },
+    {
+      "epoch": 1.112701252236136,
+      "grad_norm": 9.831031799316406,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0388,
+      "step": 38
+    },
+    {
+      "epoch": 1.141323792486583,
+      "grad_norm": 9.961572647094727,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0306,
+      "step": 39
+    },
+    {
+      "epoch": 1.1699463327370303,
+      "grad_norm": 7.772109031677246,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0553,
+      "step": 40
+    },
+    {
+      "epoch": 1.1985688729874777,
+      "grad_norm": 7.32382345199585,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0418,
+      "step": 41
+    },
+    {
+      "epoch": 1.227191413237925,
+      "grad_norm": 16.050722122192383,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0489,
+      "step": 42
+    },
+    {
+      "epoch": 1.255813953488372,
+      "grad_norm": 8.445350646972656,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0344,
+      "step": 43
+    },
+    {
+      "epoch": 1.2844364937388193,
+      "grad_norm": 5.381591320037842,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0279,
+      "step": 44
+    },
+    {
+      "epoch": 1.3130590339892665,
+      "grad_norm": 5.421046733856201,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0472,
+      "step": 45
+    },
+    {
+      "epoch": 1.341681574239714,
+      "grad_norm": 9.946616172790527,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0377,
+      "step": 46
+    },
+    {
+      "epoch": 1.3703041144901609,
+      "grad_norm": 10.54006290435791,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0489,
+      "step": 47
+    },
+    {
+      "epoch": 1.3989266547406083,
+      "grad_norm": 7.798122406005859,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0341,
+      "step": 48
+    },
+    {
+      "epoch": 1.4275491949910555,
+      "grad_norm": 7.607766628265381,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0504,
+      "step": 49
+    },
+    {
+      "epoch": 1.4561717352415027,
+      "grad_norm": 8.484859466552734,
+      "learning_rate": 0.0,
+      "loss": 0.0358,
+      "step": 50
+    },
+    {
+      "epoch": 1.4561717352415027,
+      "eval_loss": 0.04139801859855652,
+      "eval_runtime": 6.9109,
+      "eval_samples_per_second": 34.004,
+      "eval_steps_per_second": 4.341,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null